aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_hv.c
blob: cc0d7f1b19ab474f62c702192f8fb44ff8ecf216 (plain) (blame)
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
/*
 * 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/fs.h>
#include <linux/anon_inodes.h>
#include <linux/cpumask.h>
#include <linux/spinlock.h>
#include <linux/page-flags.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 <asm/lppaca.h>
#include <asm/processor.h>
#include <asm/cputhreads.h>
#include <asm/page.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>

/*
 * For now, limit memory to 64GB and require it to be large pages.
 * This value is chosen because it makes the ram_pginfo array be
 * 64kB in size, which is about as large as we want to be trying
 * to allocate with kmalloc.
 */
#define MAX_MEM_ORDER		36

#define LARGE_PAGE_ORDER	24	/* 16MB pages */

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

void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	local_paca->kvm_hstate.kvm_vcpu = vcpu;
	local_paca->kvm_hstate.kvm_vcore = vcpu->arch.vcore;
}

void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
}

static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu);
static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu);

void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
{
	u64 now;
	unsigned long dec_nsec;

	now = get_tb();
	if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu))
		kvmppc_core_queue_dec(vcpu);
	if (vcpu->arch.pending_exceptions)
		return;
	if (vcpu->arch.dec_expires != ~(u64)0) {
		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);
	}

	kvmppc_vcpu_blocked(vcpu);

	kvm_vcpu_block(vcpu);
	vcpu->stat.halt_wakeup++;

	if (vcpu->arch.dec_expires != ~(u64)0)
		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);

	kvmppc_vcpu_unblocked(vcpu);
}

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

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

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->kvm->arch.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->shared_proc = 1;
	vpa->yield_count = 1;
}

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 pg_index, ra, len;
	unsigned long pg_offset;
	void *va;
	struct kvm_vcpu *tvcpu;

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

	flags >>= 63 - 18;
	flags &= 7;
	if (flags == 0 || flags == 4)
		return H_PARAMETER;
	if (flags < 4) {
		if (vpa & 0x7f)
			return H_PARAMETER;
		/* registering new area; convert logical addr to real */
		pg_index = vpa >> kvm->arch.ram_porder;
		pg_offset = vpa & (kvm->arch.ram_psize - 1);
		if (pg_index >= kvm->arch.ram_npages)
			return H_PARAMETER;
		if (kvm->arch.ram_pginfo[pg_index].pfn == 0)
			return H_PARAMETER;
		ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT;
		ra |= pg_offset;
		va = __va(ra);
		if (flags <= 1)
			len = *(unsigned short *)(va + 4);
		else
			len = *(unsigned int *)(va + 4);
		if (pg_offset + len > kvm->arch.ram_psize)
			return H_PARAMETER;
		switch (flags) {
		case 1:		/* register VPA */
			if (len < 640)
				return H_PARAMETER;
			tvcpu->arch.vpa = va;
			init_vpa(vcpu, va);
			break;
		case 2:		/* register DTL */
			if (len < 48)
				return H_PARAMETER;
			if (!tvcpu->arch.vpa)
				return H_RESOURCE;
			len -= len % 48;
			tvcpu->arch.dtl = va;
			tvcpu->arch.dtl_end = va + len;
			break;
		case 3:		/* register SLB shadow buffer */
			if (len < 8)
				return H_PARAMETER;
			if (!tvcpu->arch.vpa)
				return H_RESOURCE;
			tvcpu->arch.slb_shadow = va;
			len = (len - 16) / 16;
			tvcpu->arch.slb_shadow = va;
			break;
		}
	} else {
		switch (flags) {
		case 5:		/* unregister VPA */
			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
				return H_RESOURCE;
			tvcpu->arch.vpa = NULL;
			break;
		case 6:		/* unregister DTL */
			tvcpu->arch.dtl = NULL;
			break;
		case 7:		/* unregister SLB shadow buffer */
			tvcpu->arch.slb_shadow = NULL;
			break;
		}
	}
	return H_SUCCESS;
}

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

	switch (req) {
	case H_CEDE:
		vcpu->arch.shregs.msr |= MSR_EE;
		vcpu->arch.ceded = 1;
		smp_mb();
		if (!vcpu->arch.prodded)
			kvmppc_vcpu_block(vcpu);
		else
			vcpu->arch.prodded = 0;
		smp_mb();
		vcpu->arch.ceded = 0;
		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:
		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;
	default:
		return RESUME_HOST;
	}
	kvmppc_set_gpr(vcpu, 3, ret);
	vcpu->arch.hcall_needed = 0;
	return RESUME_GUEST;
}

static int kvmppc_handle_exit(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:
		vcpu->stat.ext_intr_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_PERFMON:
		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;

		if (vcpu->arch.shregs.msr & MSR_PR) {
			/* sc 1 from userspace - reflect to guest syscall */
			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL);
			r = RESUME_GUEST;
			break;
		}
		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 does a bad real-mode access,
	 * as we have enabled VRMA (virtualized real mode area) mode in the
	 * LPCR.  We just generate an appropriate DSI/ISI to the guest.
	 */
	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
		vcpu->arch.shregs.dsisr = vcpu->arch.fault_dsisr;
		vcpu->arch.shregs.dar = vcpu->arch.fault_dar;
		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_H_INST_STORAGE:
		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE,
					0x08000000);
		r = RESUME_GUEST;
		break;
	/*
	 * This occurs if the guest executes an illegal instruction.
	 * We just generate a program interrupt to the guest, since
	 * we don't emulate any guest instructions at this stage.
	 */
	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
		kvmppc_core_queue_program(vcpu, 0x80000);
		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);
		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(tsk)) {
			vcpu->stat.signal_exits++;
			run->exit_reason = KVM_EXIT_INTR;
			r = -EINTR;
		} else {
			kvmppc_core_deliver_interrupts(vcpu);
		}
	}

	return r;
}

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

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

	memset(sregs, 0, sizeof(struct kvm_sregs));
	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;
}

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

	kvmppc_set_pvr(vcpu, sregs->pvr);

	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;
}

int kvmppc_core_check_processor_compat(void)
{
	if (cpu_has_feature(CPU_FTR_HVMODE))
		return 0;
	return -EIO;
}

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

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

	err = -ENOMEM;
	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
	if (!vcpu)
		goto out;

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

	vcpu->arch.shared = &vcpu->arch.shregs;
	vcpu->arch.last_cpu = -1;
	vcpu->arch.mmcr[0] = MMCR0_FC;
	vcpu->arch.ctrl = CTRL_RUNLATCH;
	/* default to host PVR, since we can't spoof it */
	vcpu->arch.pvr = mfspr(SPRN_PVR);
	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);

	kvmppc_mmu_book3s_hv_init(vcpu);

	/*
	 * Some vcpus may start out in stopped state.  If we initialize
	 * them to busy-in-host state they will stop other vcpus in the
	 * vcore from running.  Instead we initialize them to blocked
	 * state, effectively considering them to be stopped until we
	 * see the first run ioctl for them.
	 */
	vcpu->arch.state = KVMPPC_VCPU_BLOCKED;

	init_waitqueue_head(&vcpu->arch.cpu_run);

	mutex_lock(&kvm->lock);
	vcore = kvm->arch.vcores[core];
	if (!vcore) {
		vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL);
		if (vcore) {
			INIT_LIST_HEAD(&vcore->runnable_threads);
			spin_lock_init(&vcore->lock);
		}
		kvm->arch.vcores[core] = vcore;
	}
	mutex_unlock(&kvm->lock);

	if (!vcore)
		goto free_vcpu;

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

	return vcpu;

free_vcpu:
	kfree(vcpu);
out:
	return ERR_PTR(err);
}

void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
	kvm_vcpu_uninit(vcpu);
	kfree(vcpu);
}

static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	spin_lock(&vc->lock);
	vcpu->arch.state = KVMPPC_VCPU_BLOCKED;
	++vc->n_blocked;
	if (vc->n_runnable > 0 &&
	    vc->n_runnable + vc->n_blocked == vc->num_threads) {
		vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu,
					arch.run_list);
		wake_up(&vcpu->arch.cpu_run);
	}
	spin_unlock(&vc->lock);
}

static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	spin_lock(&vc->lock);
	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
	--vc->n_blocked;
	spin_unlock(&vc->lock);
}

extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
extern void xics_wake_cpu(int cpu);

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

	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
		return;
	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
	--vc->n_runnable;
	/* decrement the physical thread id of each following vcpu */
	v = vcpu;
	list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list)
		--v->arch.ptid;
	list_del(&vcpu->arch.run_list);
}

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

	cpu = vc->pcpu + vcpu->arch.ptid;
	tpaca = &paca[cpu];
	tpaca->kvm_hstate.kvm_vcpu = vcpu;
	tpaca->kvm_hstate.kvm_vcore = vc;
	smp_wmb();
#ifdef CONFIG_PPC_ICP_NATIVE
	if (vcpu->arch.ptid) {
		tpaca->cpu_start = 0x80;
		tpaca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST;
		wmb();
		xics_wake_cpu(cpu);
		++vc->n_woken;
	}
#endif
}

static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
{
	int i;

	HMT_low();
	i = 0;
	while (vc->nap_count < vc->n_woken) {
		if (++i >= 1000000) {
			pr_err("kvmppc_wait_for_nap timeout %d %d\n",
			       vc->nap_count, vc->n_woken);
			break;
		}
		cpu_relax();
	}
	HMT_medium();
}

/*
 * Check that we are on thread 0 and that any other threads in
 * this core are off-line.
 */
static int on_primary_thread(void)
{
	int cpu = smp_processor_id();
	int thr = cpu_thread_in_core(cpu);

	if (thr)
		return 0;
	while (++thr < threads_per_core)
		if (cpu_online(cpu + thr))
			return 0;
	return 1;
}

/*
 * Run a set of guest threads on a physical core.
 * Called with vc->lock held.
 */
static int kvmppc_run_core(struct kvmppc_vcore *vc)
{
	struct kvm_vcpu *vcpu, *vnext;
	long ret;
	u64 now;

	/* don't start if any threads have a signal pending */
	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
		if (signal_pending(vcpu->arch.run_task))
			return 0;

	/*
	 * Make sure we are running on thread 0, and that
	 * secondary threads are offline.
	 * XXX we should also block attempts to bring any
	 * secondary threads online.
	 */
	if (threads_per_core > 1 && !on_primary_thread()) {
		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
			vcpu->arch.ret = -EBUSY;
		goto out;
	}

	vc->n_woken = 0;
	vc->nap_count = 0;
	vc->entry_exit_count = 0;
	vc->vcore_running = 1;
	vc->in_guest = 0;
	vc->pcpu = smp_processor_id();
	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
		kvmppc_start_thread(vcpu);
	vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu,
				arch.run_list);

	spin_unlock(&vc->lock);

	preempt_disable();
	kvm_guest_enter();
	__kvmppc_vcore_entry(NULL, vcpu);

	/* wait for secondary threads to finish writing their state to memory */
	spin_lock(&vc->lock);
	if (vc->nap_count < vc->n_woken)
		kvmppc_wait_for_nap(vc);
	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
	vc->vcore_running = 2;
	spin_unlock(&vc->lock);

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

	preempt_enable();
	kvm_resched(vcpu);

	now = get_tb();
	list_for_each_entry(vcpu, &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);
		if (!vcpu->arch.trap) {
			if (signal_pending(vcpu->arch.run_task)) {
				vcpu->arch.kvm_run->exit_reason = KVM_EXIT_INTR;
				vcpu->arch.ret = -EINTR;
			}
			continue;		/* didn't get to run */
		}
		ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
					 vcpu->arch.run_task);
		vcpu->arch.ret = ret;
		vcpu->arch.trap = 0;
	}

	spin_lock(&vc->lock);
 out:
	vc->vcore_running = 0;
	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
				 arch.run_list) {
		if (vcpu->arch.ret != RESUME_GUEST) {
			kvmppc_remove_runnable(vc, vcpu);
			wake_up(&vcpu->arch.cpu_run);
		}
	}

	return 1;
}

static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	int ptid;
	int wait_state;
	struct kvmppc_vcore *vc;
	DEFINE_WAIT(wait);

	/* 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;
	}

	/* On PPC970, check that we have an RMA region */
	if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201))
		return -EPERM;

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

	flush_fp_to_thread(current);
	flush_altivec_to_thread(current);
	flush_vsx_to_thread(current);

	/*
	 * Synchronize with other threads in this virtual core
	 */
	vc = vcpu->arch.vcore;
	spin_lock(&vc->lock);
	/* This happens the first time this is called for a vcpu */
	if (vcpu->arch.state == KVMPPC_VCPU_BLOCKED)
		--vc->n_blocked;
	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
	ptid = vc->n_runnable;
	vcpu->arch.run_task = current;
	vcpu->arch.kvm_run = kvm_run;
	vcpu->arch.ptid = ptid;
	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
	++vc->n_runnable;

	wait_state = TASK_INTERRUPTIBLE;
	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
		if (signal_pending(current)) {
			if (!vc->vcore_running) {
				kvm_run->exit_reason = KVM_EXIT_INTR;
				vcpu->arch.ret = -EINTR;
				break;
			}
			/* have to wait for vcore to stop executing guest */
			wait_state = TASK_UNINTERRUPTIBLE;
			smp_send_reschedule(vc->pcpu);
		}

		if (!vc->vcore_running &&
		    vc->n_runnable + vc->n_blocked == vc->num_threads) {
			/* we can run now */
			if (kvmppc_run_core(vc))
				continue;
		}

		if (vc->vcore_running == 1 && VCORE_EXIT_COUNT(vc) == 0)
			kvmppc_start_thread(vcpu);

		/* wait for other threads to come in, or wait for vcore */
		prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
		spin_unlock(&vc->lock);
		schedule();
		finish_wait(&vcpu->arch.cpu_run, &wait);
		spin_lock(&vc->lock);
	}

	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE)
		kvmppc_remove_runnable(vc, vcpu);
	spin_unlock(&vc->lock);

	return vcpu->arch.ret;
}

int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	int r;

	do {
		r = kvmppc_run_vcpu(run, vcpu);

		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
		    !(vcpu->arch.shregs.msr & MSR_PR)) {
			r = kvmppc_pseries_do_hcall(vcpu);
			kvmppc_core_deliver_interrupts(vcpu);
		}
	} while (r == RESUME_GUEST);
	return r;
}

static long kvmppc_stt_npages(unsigned long window_size)
{
	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
}

static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
{
	struct kvm *kvm = stt->kvm;
	int i;

	mutex_lock(&kvm->lock);
	list_del(&stt->list);
	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
		__free_page(stt->pages[i]);
	kfree(stt);
	mutex_unlock(&kvm->lock);

	kvm_put_kvm(kvm);
}

static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
	struct page *page;

	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
		return VM_FAULT_SIGBUS;

	page = stt->pages[vmf->pgoff];
	get_page(page);
	vmf->page = page;
	return 0;
}

static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
	.fault = kvm_spapr_tce_fault,
};

static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
{
	vma->vm_ops = &kvm_spapr_tce_vm_ops;
	return 0;
}

static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
{
	struct kvmppc_spapr_tce_table *stt = filp->private_data;

	release_spapr_tce_table(stt);
	return 0;
}

static struct file_operations kvm_spapr_tce_fops = {
	.mmap           = kvm_spapr_tce_mmap,
	.release	= kvm_spapr_tce_release,
};

long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
				   struct kvm_create_spapr_tce *args)
{
	struct kvmppc_spapr_tce_table *stt = NULL;
	long npages;
	int ret = -ENOMEM;
	int i;

	/* Check this LIOBN hasn't been previously allocated */
	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
		if (stt->liobn == args->liobn)
			return -EBUSY;
	}

	npages = kvmppc_stt_npages(args->window_size);

	stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *),
		      GFP_KERNEL);
	if (!stt)
		goto fail;

	stt->liobn = args->liobn;
	stt->window_size = args->window_size;
	stt->kvm = kvm;

	for (i = 0; i < npages; i++) {
		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
		if (!stt->pages[i])
			goto fail;
	}

	kvm_get_kvm(kvm);

	mutex_lock(&kvm->lock);
	list_add(&stt->list, &kvm->arch.spapr_tce_tables);

	mutex_unlock(&kvm->lock);

	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
				stt, O_RDWR);

fail:
	if (stt) {
		for (i = 0; i < npages; i++)
			if (stt->pages[i])
				__free_page(stt->pages[i]);

		kfree(stt);
	}
	return ret;
}

/* Work out RMLS (real mode limit selector) field value for a given RMA size.
   Assumes POWER7 or PPC970. */
static inline int lpcr_rmls(unsigned long rma_size)
{
	switch (rma_size) {
	case 32ul << 20:	/* 32 MB */
		if (cpu_has_feature(CPU_FTR_ARCH_206))
			return 8;	/* only supported on POWER7 */
		return -1;
	case 64ul << 20:	/* 64 MB */
		return 3;
	case 128ul << 20:	/* 128 MB */
		return 7;
	case 256ul << 20:	/* 256 MB */
		return 4;
	case 1ul << 30:		/* 1 GB */
		return 2;
	case 16ul << 30:	/* 16 GB */
		return 1;
	case 256ul << 30:	/* 256 GB */
		return 0;
	default:
		return -1;
	}
}

static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct kvmppc_rma_info *ri = vma->vm_file->private_data;
	struct page *page;

	if (vmf->pgoff >= ri->npages)
		return VM_FAULT_SIGBUS;

	page = pfn_to_page(ri->base_pfn + vmf->pgoff);
	get_page(page);
	vmf->page = page;
	return 0;
}

static const struct vm_operations_struct kvm_rma_vm_ops = {
	.fault = kvm_rma_fault,
};

static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
{
	vma->vm_flags |= VM_RESERVED;
	vma->vm_ops = &kvm_rma_vm_ops;
	return 0;
}

static int kvm_rma_release(struct inode *inode, struct file *filp)
{
	struct kvmppc_rma_info *ri = filp->private_data;

	kvm_release_rma(ri);
	return 0;
}

static struct file_operations kvm_rma_fops = {
	.mmap           = kvm_rma_mmap,
	.release	= kvm_rma_release,
};

long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
{
	struct kvmppc_rma_info *ri;
	long fd;

	ri = kvm_alloc_rma();
	if (!ri)
		return -ENOMEM;

	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR);
	if (fd < 0)
		kvm_release_rma(ri);

	ret->rma_size = ri->npages << PAGE_SHIFT;
	return fd;
}

static struct page *hva_to_page(unsigned long addr)
{
	struct page *page[1];
	int npages;

	might_sleep();

	npages = get_user_pages_fast(addr, 1, 1, page);

	if (unlikely(npages != 1))
		return 0;

	return page[0];
}

int kvmppc_core_prepare_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem)
{
	unsigned long psize, porder;
	unsigned long i, npages, totalpages;
	unsigned long pg_ix;
	struct kvmppc_pginfo *pginfo;
	unsigned long hva;
	struct kvmppc_rma_info *ri = NULL;
	struct page *page;

	/* For now, only allow 16MB pages */
	porder = LARGE_PAGE_ORDER;
	psize = 1ul << porder;
	if ((mem->memory_size & (psize - 1)) ||
	    (mem->guest_phys_addr & (psize - 1))) {
		pr_err("bad memory_size=%llx @ %llx\n",
		       mem->memory_size, mem->guest_phys_addr);
		return -EINVAL;
	}

	npages = mem->memory_size >> porder;
	totalpages = (mem->guest_phys_addr + mem->memory_size) >> porder;

	/* More memory than we have space to track? */
	if (totalpages > (1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER)))
		return -EINVAL;

	/* Do we already have an RMA registered? */
	if (mem->guest_phys_addr == 0 && kvm->arch.rma)
		return -EINVAL;

	if (totalpages > kvm->arch.ram_npages)
		kvm->arch.ram_npages = totalpages;

	/* Is this one of our preallocated RMAs? */
	if (mem->guest_phys_addr == 0) {
		struct vm_area_struct *vma;

		down_read(&current->mm->mmap_sem);
		vma = find_vma(current->mm, mem->userspace_addr);
		if (vma && vma->vm_file &&
		    vma->vm_file->f_op == &kvm_rma_fops &&
		    mem->userspace_addr == vma->vm_start)
			ri = vma->vm_file->private_data;
		up_read(&current->mm->mmap_sem);
		if (!ri && cpu_has_feature(CPU_FTR_ARCH_201)) {
			pr_err("CPU requires an RMO\n");
			return -EINVAL;
		}
	}

	if (ri) {
		unsigned long rma_size;
		unsigned long lpcr;
		long rmls;

		rma_size = ri->npages << PAGE_SHIFT;
		if (rma_size > mem->memory_size)
			rma_size = mem->memory_size;
		rmls = lpcr_rmls(rma_size);
		if (rmls < 0) {
			pr_err("Can't use RMA of 0x%lx bytes\n", rma_size);
			return -EINVAL;
		}
		atomic_inc(&ri->use_count);
		kvm->arch.rma = ri;
		kvm->arch.n_rma_pages = rma_size >> porder;

		/* Update LPCR and RMOR */
		lpcr = kvm->arch.lpcr;
		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
			/* PPC970; insert RMLS value (split field) in HID4 */
			lpcr &= ~((1ul << HID4_RMLS0_SH) |
				  (3ul << HID4_RMLS2_SH));
			lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
				((rmls & 3) << HID4_RMLS2_SH);
			/* RMOR is also in HID4 */
			lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
				<< HID4_RMOR_SH;
		} else {
			/* POWER7 */
			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
			lpcr |= rmls << LPCR_RMLS_SH;
			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
		}
		kvm->arch.lpcr = lpcr;
		pr_info("Using RMO at %lx size %lx (LPCR = %lx)\n",
			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
	}

	pg_ix = mem->guest_phys_addr >> porder;
	pginfo = kvm->arch.ram_pginfo + pg_ix;
	for (i = 0; i < npages; ++i, ++pg_ix) {
		if (ri && pg_ix < kvm->arch.n_rma_pages) {
			pginfo[i].pfn = ri->base_pfn +
				(pg_ix << (porder - PAGE_SHIFT));
			continue;
		}
		hva = mem->userspace_addr + (i << porder);
		page = hva_to_page(hva);
		if (!page) {
			pr_err("oops, no pfn for hva %lx\n", hva);
			goto err;
		}
		/* Check it's a 16MB page */
		if (!PageHead(page) ||
		    compound_order(page) != (LARGE_PAGE_ORDER - PAGE_SHIFT)) {
			pr_err("page at %lx isn't 16MB (o=%d)\n",
			       hva, compound_order(page));
			goto err;
		}
		pginfo[i].pfn = page_to_pfn(page);
	}

	return 0;

 err:
	return -EINVAL;
}

void kvmppc_core_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem)
{
	if (mem->guest_phys_addr == 0 && mem->memory_size != 0 &&
	    !kvm->arch.rma)
		kvmppc_map_vrma(kvm, mem);
}

int kvmppc_core_init_vm(struct kvm *kvm)
{
	long r;
	unsigned long npages = 1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER);
	long err = -ENOMEM;
	unsigned long lpcr;

	/* Allocate hashed page table */
	r = kvmppc_alloc_hpt(kvm);
	if (r)
		return r;

	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);

	kvm->arch.ram_pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo),
				       GFP_KERNEL);
	if (!kvm->arch.ram_pginfo) {
		pr_err("kvmppc_core_init_vm: couldn't alloc %lu bytes\n",
		       npages * sizeof(struct kvmppc_pginfo));
		goto out_free;
	}

	kvm->arch.ram_npages = 0;
	kvm->arch.ram_psize = 1ul << LARGE_PAGE_ORDER;
	kvm->arch.ram_porder = LARGE_PAGE_ORDER;
	kvm->arch.rma = NULL;
	kvm->arch.n_rma_pages = 0;

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

	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
		/* PPC970; HID4 is effectively the LPCR */
		unsigned long lpid = kvm->arch.lpid;
		kvm->arch.host_lpid = 0;
		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
		lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
		lpcr |= ((lpid >> 4) << HID4_LPID1_SH) |
			((lpid & 0xf) << HID4_LPID5_SH);
	} else {
		/* POWER7; 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_VRMA_L;
	}
	kvm->arch.lpcr = lpcr;

	return 0;

 out_free:
	kvmppc_free_hpt(kvm);
	return err;
}

void kvmppc_core_destroy_vm(struct kvm *kvm)
{
	struct kvmppc_pginfo *pginfo;
	unsigned long i;

	if (kvm->arch.ram_pginfo) {
		pginfo = kvm->arch.ram_pginfo;
		kvm->arch.ram_pginfo = NULL;
		for (i = kvm->arch.n_rma_pages; i < kvm->arch.ram_npages; ++i)
			if (pginfo[i].pfn)
				put_page(pfn_to_page(pginfo[i].pfn));
		kfree(pginfo);
	}
	if (kvm->arch.rma) {
		kvm_release_rma(kvm->arch.rma);
		kvm->arch.rma = NULL;
	}

	kvmppc_free_hpt(kvm);
	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
}

/* These are stubs for now */
void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
{
}

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

int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
{
	return EMULATE_FAIL;
}

int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
{
	return EMULATE_FAIL;
}

static int kvmppc_book3s_hv_init(void)
{
	int r;

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

	if (r)
		return r;

	r = kvmppc_mmu_hv_init();

	return r;
}

static void kvmppc_book3s_hv_exit(void)
{
	kvm_exit();
}

module_init(kvmppc_book3s_hv_init);
module_exit(kvmppc_book3s_hv_exit);