summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s.c
blob: 686d8d9eda3e537c4442628bb10df7278c710a03 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * 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>.
 */

#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/miscdevice.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>

#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
#include <asm/xive.h>

#include "book3s.h"
#include "trace.h"

/* #define EXIT_DEBUG */

const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
	KVM_GENERIC_VM_STATS(),
	STATS_DESC_ICOUNTER(VM, num_2M_pages),
	STATS_DESC_ICOUNTER(VM, num_1G_pages)
};

const struct kvm_stats_header kvm_vm_stats_header = {
	.name_size = KVM_STATS_NAME_SIZE,
	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
	.id_offset = sizeof(struct kvm_stats_header),
	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
		       sizeof(kvm_vm_stats_desc),
};

const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
	KVM_GENERIC_VCPU_STATS(),
	STATS_DESC_COUNTER(VCPU, sum_exits),
	STATS_DESC_COUNTER(VCPU, mmio_exits),
	STATS_DESC_COUNTER(VCPU, signal_exits),
	STATS_DESC_COUNTER(VCPU, light_exits),
	STATS_DESC_COUNTER(VCPU, itlb_real_miss_exits),
	STATS_DESC_COUNTER(VCPU, itlb_virt_miss_exits),
	STATS_DESC_COUNTER(VCPU, dtlb_real_miss_exits),
	STATS_DESC_COUNTER(VCPU, dtlb_virt_miss_exits),
	STATS_DESC_COUNTER(VCPU, syscall_exits),
	STATS_DESC_COUNTER(VCPU, isi_exits),
	STATS_DESC_COUNTER(VCPU, dsi_exits),
	STATS_DESC_COUNTER(VCPU, emulated_inst_exits),
	STATS_DESC_COUNTER(VCPU, dec_exits),
	STATS_DESC_COUNTER(VCPU, ext_intr_exits),
	STATS_DESC_COUNTER(VCPU, halt_successful_wait),
	STATS_DESC_COUNTER(VCPU, dbell_exits),
	STATS_DESC_COUNTER(VCPU, gdbell_exits),
	STATS_DESC_COUNTER(VCPU, ld),
	STATS_DESC_COUNTER(VCPU, st),
	STATS_DESC_COUNTER(VCPU, pf_storage),
	STATS_DESC_COUNTER(VCPU, pf_instruc),
	STATS_DESC_COUNTER(VCPU, sp_storage),
	STATS_DESC_COUNTER(VCPU, sp_instruc),
	STATS_DESC_COUNTER(VCPU, queue_intr),
	STATS_DESC_COUNTER(VCPU, ld_slow),
	STATS_DESC_COUNTER(VCPU, st_slow),
	STATS_DESC_COUNTER(VCPU, pthru_all),
	STATS_DESC_COUNTER(VCPU, pthru_host),
	STATS_DESC_COUNTER(VCPU, pthru_bad_aff)
};

const struct kvm_stats_header kvm_vcpu_stats_header = {
	.name_size = KVM_STATS_NAME_SIZE,
	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
	.id_offset = sizeof(struct kvm_stats_header),
	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
		       sizeof(kvm_vcpu_stats_desc),
};

static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
			unsigned long pending_now, unsigned long old_pending)
{
	if (is_kvmppc_hv_enabled(vcpu->kvm))
		return;
	if (pending_now)
		kvmppc_set_int_pending(vcpu, 1);
	else if (old_pending)
		kvmppc_set_int_pending(vcpu, 0);
}

static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
{
	ulong crit_raw;
	ulong crit_r1;
	bool crit;

	if (is_kvmppc_hv_enabled(vcpu->kvm))
		return false;

	crit_raw = kvmppc_get_critical(vcpu);
	crit_r1 = kvmppc_get_gpr(vcpu, 1);

	/* Truncate crit indicators in 32 bit mode */
	if (!(kvmppc_get_msr(vcpu) & 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 && !(kvmppc_get_msr(vcpu) & MSR_PR);

	return crit;
}

void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
{
	vcpu->kvm->arch.kvm_ops->inject_interrupt(vcpu, vec, flags);
}

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 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;
	case 0xf60: prio = BOOK3S_IRQPRIO_FAC_UNAVAIL;		break;
	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
	}

	return prio;
}

void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
					  unsigned int vec)
{
	unsigned long old_pending = vcpu->arch.pending_exceptions;

	clear_bit(kvmppc_book3s_vec2irqprio(vec),
		  &vcpu->arch.pending_exceptions);

	kvmppc_update_int_pending(vcpu, vcpu->arch.pending_exceptions,
				  old_pending);
}

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
}
EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);

void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	/* might as well deliver this straight away */
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, srr1_flags);
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check);

void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu)
{
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_SYSCALL, 0);
}
EXPORT_SYMBOL(kvmppc_core_queue_syscall);

void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	/* might as well deliver this straight away */
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, srr1_flags);
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_program);

void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	/* might as well deliver this straight away */
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, srr1_flags);
}

void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	/* might as well deliver this straight away */
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, srr1_flags);
}

void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	/* might as well deliver this straight away */
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, srr1_flags);
}

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

int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
{
	return test_bit(BOOK3S_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
}
EXPORT_SYMBOL_GPL(kvmppc_core_pending_dec);

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

void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                struct kvm_interrupt *irq)
{
	/*
	 * This case (KVM_INTERRUPT_SET) should never actually arise for
	 * a pseries guest (because pseries guests expect their interrupt
	 * controllers to continue asserting an external interrupt request
	 * until it is acknowledged at the interrupt controller), but is
	 * included to avoid ABI breakage and potentially for other
	 * sorts of guest.
	 *
	 * There is a subtlety here: HV KVM does not test the
	 * external_oneshot flag in the code that synthesizes
	 * external interrupts for the guest just before entering
	 * the guest.  That is OK even if userspace did do a
	 * KVM_INTERRUPT_SET on a pseries guest vcpu, because the
	 * caller (kvm_vcpu_ioctl_interrupt) does a kvm_vcpu_kick()
	 * which ends up doing a smp_send_reschedule(), which will
	 * pull the guest all the way out to the host, meaning that
	 * we will call kvmppc_core_prepare_to_enter() before entering
	 * the guest again, and that will handle the external_oneshot
	 * flag correctly.
	 */
	if (irq->irq == KVM_INTERRUPT_SET)
		vcpu->arch.external_oneshot = 1;

	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
}

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

void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong srr1_flags,
				    ulong dar, ulong dsisr)
{
	kvmppc_set_dar(vcpu, dar);
	kvmppc_set_dsisr(vcpu, dsisr);
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, srr1_flags);
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage);

void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong srr1_flags)
{
	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, srr1_flags);
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_inst_storage);

static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
					 unsigned int priority)
{
	int deliver = 1;
	int vec = 0;
	bool crit = kvmppc_critical_section(vcpu);

	switch (priority) {
	case BOOK3S_IRQPRIO_DECREMENTER:
		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
		vec = BOOK3S_INTERRUPT_DECREMENTER;
		break;
	case BOOK3S_IRQPRIO_EXTERNAL:
		deliver = (kvmppc_get_msr(vcpu) & 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;
		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;
	case BOOK3S_IRQPRIO_FAC_UNAVAIL:
		vec = BOOK3S_INTERRUPT_FAC_UNAVAIL;
		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, 0);

	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:
			/*
			 * External interrupts get cleared by userspace
			 * except when set by the KVM_INTERRUPT ioctl with
			 * KVM_INTERRUPT_SET (not KVM_INTERRUPT_SET_LEVEL).
			 */
			if (vcpu->arch.external_oneshot) {
				vcpu->arch.external_oneshot = 0;
				return true;
			}
			return false;
	}

	return true;
}

int kvmppc_core_prepare_to_enter(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 */
	kvmppc_update_int_pending(vcpu, *pending, old_pending);

	return 0;
}
EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter);

kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing,
			bool *writable)
{
	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM;
	gfn_t gfn = gpa >> PAGE_SHIFT;

	if (!(kvmppc_get_msr(vcpu) & MSR_SF))
		mp_pa = (uint32_t)mp_pa;

	/* Magic page override */
	gpa &= ~0xFFFULL;
	if (unlikely(mp_pa) && unlikely((gpa & KVM_PAM) == mp_pa)) {
		ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
		kvm_pfn_t pfn;

		pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
		get_page(pfn_to_page(pfn));
		if (writable)
			*writable = true;
		return pfn;
	}

	return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
}
EXPORT_SYMBOL_GPL(kvmppc_gpa_to_pfn);

int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, enum xlate_instdata xlid,
		 enum xlate_readwrite xlrw, struct kvmppc_pte *pte)
{
	bool data = (xlid == XLATE_DATA);
	bool iswrite = (xlrw == XLATE_WRITE);
	int relocated = (kvmppc_get_msr(vcpu) & (data ? MSR_DR : MSR_IR));
	int r;

	if (relocated) {
		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data, iswrite);
	} 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;

		if ((kvmppc_get_msr(vcpu) & (MSR_IR | MSR_DR)) == MSR_DR &&
		    !data) {
			if ((vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) &&
			    ((eaddr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS))
			pte->raddr &= ~SPLIT_HACK_MASK;
		}
	}

	return r;
}

/*
 * Returns prefixed instructions with the prefix in the high 32 bits
 * of *inst and suffix in the low 32 bits.  This is the same convention
 * as used in HEIR, vcpu->arch.last_inst and vcpu->arch.emul_inst.
 * Like vcpu->arch.last_inst but unlike vcpu->arch.emul_inst, each
 * half of the value needs byte-swapping if the guest endianness is
 * different from the host endianness.
 */
int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
		enum instruction_fetch_type type, unsigned long *inst)
{
	ulong pc = kvmppc_get_pc(vcpu);
	int r;
	u32 iw;

	if (type == INST_SC)
		pc -= 4;

	r = kvmppc_ld(vcpu, &pc, sizeof(u32), &iw, false);
	if (r != EMULATE_DONE)
		return EMULATE_AGAIN;
	/*
	 * If [H]SRR1 indicates that the instruction that caused the
	 * current interrupt is a prefixed instruction, get the suffix.
	 */
	if (kvmppc_get_msr(vcpu) & SRR1_PREFIXED) {
		u32 suffix;
		pc += 4;
		r = kvmppc_ld(vcpu, &pc, sizeof(u32), &suffix, false);
		if (r != EMULATE_DONE)
			return EMULATE_AGAIN;
		*inst = ((u64)iw << 32) | suffix;
	} else {
		*inst = iw;
	}
	return r;
}
EXPORT_SYMBOL_GPL(kvmppc_load_last_inst);

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

void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
}

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

	vcpu_load(vcpu);
	ret = vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
	vcpu_put(vcpu);

	return ret;
}

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

	vcpu_load(vcpu);
	ret = vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
	vcpu_put(vcpu);

	return ret;
}

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 = kvmppc_get_msr(vcpu);
	regs->srr0 = kvmppc_get_srr0(vcpu);
	regs->srr1 = kvmppc_get_srr1(vcpu);
	regs->pid = vcpu->arch.pid;
	regs->sprg0 = kvmppc_get_sprg0(vcpu);
	regs->sprg1 = kvmppc_get_sprg1(vcpu);
	regs->sprg2 = kvmppc_get_sprg2(vcpu);
	regs->sprg3 = kvmppc_get_sprg3(vcpu);
	regs->sprg4 = kvmppc_get_sprg4(vcpu);
	regs->sprg5 = kvmppc_get_sprg5(vcpu);
	regs->sprg6 = kvmppc_get_sprg6(vcpu);
	regs->sprg7 = kvmppc_get_sprg7(vcpu);

	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);
	kvmppc_set_srr0(vcpu, regs->srr0);
	kvmppc_set_srr1(vcpu, regs->srr1);
	kvmppc_set_sprg0(vcpu, regs->sprg0);
	kvmppc_set_sprg1(vcpu, regs->sprg1);
	kvmppc_set_sprg2(vcpu, regs->sprg2);
	kvmppc_set_sprg3(vcpu, regs->sprg3);
	kvmppc_set_sprg4(vcpu, regs->sprg4);
	kvmppc_set_sprg5(vcpu, regs->sprg5);
	kvmppc_set_sprg6(vcpu, regs->sprg6);
	kvmppc_set_sprg7(vcpu, regs->sprg7);

	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_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -EOPNOTSUPP;
}

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

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

	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, id, val);
	if (r == -EINVAL) {
		r = 0;
		switch (id) {
		case KVM_REG_PPC_DAR:
			*val = get_reg_val(id, kvmppc_get_dar(vcpu));
			break;
		case KVM_REG_PPC_DSISR:
			*val = get_reg_val(id, kvmppc_get_dsisr(vcpu));
			break;
		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
			i = id - KVM_REG_PPC_FPR0;
			*val = get_reg_val(id, VCPU_FPR(vcpu, i));
			break;
		case KVM_REG_PPC_FPSCR:
			*val = get_reg_val(id, vcpu->arch.fp.fpscr);
			break;
#ifdef CONFIG_VSX
		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
			if (cpu_has_feature(CPU_FTR_VSX)) {
				i = id - KVM_REG_PPC_VSR0;
				val->vsxval[0] = vcpu->arch.fp.fpr[i][0];
				val->vsxval[1] = vcpu->arch.fp.fpr[i][1];
			} else {
				r = -ENXIO;
			}
			break;
#endif /* CONFIG_VSX */
		case KVM_REG_PPC_DEBUG_INST:
			*val = get_reg_val(id, INS_TW);
			break;
#ifdef CONFIG_KVM_XICS
		case KVM_REG_PPC_ICP_STATE:
			if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
				r = -ENXIO;
				break;
			}
			if (xics_on_xive())
				*val = get_reg_val(id, kvmppc_xive_get_icp(vcpu));
			else
				*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
			break;
#endif /* CONFIG_KVM_XICS */
#ifdef CONFIG_KVM_XIVE
		case KVM_REG_PPC_VP_STATE:
			if (!vcpu->arch.xive_vcpu) {
				r = -ENXIO;
				break;
			}
			if (xive_enabled())
				r = kvmppc_xive_native_get_vp(vcpu, val);
			else
				r = -ENXIO;
			break;
#endif /* CONFIG_KVM_XIVE */
		case KVM_REG_PPC_FSCR:
			*val = get_reg_val(id, vcpu->arch.fscr);
			break;
		case KVM_REG_PPC_TAR:
			*val = get_reg_val(id, vcpu->arch.tar);
			break;
		case KVM_REG_PPC_EBBHR:
			*val = get_reg_val(id, vcpu->arch.ebbhr);
			break;
		case KVM_REG_PPC_EBBRR:
			*val = get_reg_val(id, vcpu->arch.ebbrr);
			break;
		case KVM_REG_PPC_BESCR:
			*val = get_reg_val(id, vcpu->arch.bescr);
			break;
		case KVM_REG_PPC_IC:
			*val = get_reg_val(id, vcpu->arch.ic);
			break;
		default:
			r = -EINVAL;
			break;
		}
	}

	return r;
}

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

	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, id, val);
	if (r == -EINVAL) {
		r = 0;
		switch (id) {
		case KVM_REG_PPC_DAR:
			kvmppc_set_dar(vcpu, set_reg_val(id, *val));
			break;
		case KVM_REG_PPC_DSISR:
			kvmppc_set_dsisr(vcpu, set_reg_val(id, *val));
			break;
		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
			i = id - KVM_REG_PPC_FPR0;
			VCPU_FPR(vcpu, i) = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_FPSCR:
			vcpu->arch.fp.fpscr = set_reg_val(id, *val);
			break;
#ifdef CONFIG_VSX
		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
			if (cpu_has_feature(CPU_FTR_VSX)) {
				i = id - KVM_REG_PPC_VSR0;
				vcpu->arch.fp.fpr[i][0] = val->vsxval[0];
				vcpu->arch.fp.fpr[i][1] = val->vsxval[1];
			} else {
				r = -ENXIO;
			}
			break;
#endif /* CONFIG_VSX */
#ifdef CONFIG_KVM_XICS
		case KVM_REG_PPC_ICP_STATE:
			if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
				r = -ENXIO;
				break;
			}
			if (xics_on_xive())
				r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val));
			else
				r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
			break;
#endif /* CONFIG_KVM_XICS */
#ifdef CONFIG_KVM_XIVE
		case KVM_REG_PPC_VP_STATE:
			if (!vcpu->arch.xive_vcpu) {
				r = -ENXIO;
				break;
			}
			if (xive_enabled())
				r = kvmppc_xive_native_set_vp(vcpu, val);
			else
				r = -ENXIO;
			break;
#endif /* CONFIG_KVM_XIVE */
		case KVM_REG_PPC_FSCR:
			vcpu->arch.fscr = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_TAR:
			vcpu->arch.tar = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_EBBHR:
			vcpu->arch.ebbhr = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_EBBRR:
			vcpu->arch.ebbrr = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_BESCR:
			vcpu->arch.bescr = set_reg_val(id, *val);
			break;
		case KVM_REG_PPC_IC:
			vcpu->arch.ic = set_reg_val(id, *val);
			break;
		default:
			r = -EINVAL;
			break;
		}
	}

	return r;
}

void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
}

void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
}

void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
{
	vcpu->kvm->arch.kvm_ops->set_msr(vcpu, msr);
}
EXPORT_SYMBOL_GPL(kvmppc_set_msr);

int kvmppc_vcpu_run(struct kvm_vcpu *vcpu)
{
	return vcpu->kvm->arch.kvm_ops->vcpu_run(vcpu);
}

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

int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
{
	vcpu_load(vcpu);
	vcpu->guest_debug = dbg->control;
	vcpu_put(vcpu);
	return 0;
}

void kvmppc_decrementer_func(struct kvm_vcpu *vcpu)
{
	kvmppc_core_queue_dec(vcpu);
	kvm_vcpu_kick(vcpu);
}

int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu)
{
	return vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu);
}

void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
}

int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
{
	return vcpu->kvm->arch.kvm_ops->check_requests(vcpu);
}

void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{

}

int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
	return kvm->arch.kvm_ops->get_dirty_log(kvm, log);
}

void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
	kvm->arch.kvm_ops->free_memslot(slot);
}

void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
	kvm->arch.kvm_ops->flush_memslot(kvm, memslot);
}

int kvmppc_core_prepare_memory_region(struct kvm *kvm,
				      const struct kvm_memory_slot *old,
				      struct kvm_memory_slot *new,
				      enum kvm_mr_change change)
{
	return kvm->arch.kvm_ops->prepare_memory_region(kvm, old, new, change);
}

void kvmppc_core_commit_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *old,
				const struct kvm_memory_slot *new,
				enum kvm_mr_change change)
{
	kvm->arch.kvm_ops->commit_memory_region(kvm, old, new, change);
}

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	return kvm->arch.kvm_ops->unmap_gfn_range(kvm, range);
}

bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	return kvm->arch.kvm_ops->age_gfn(kvm, range);
}

bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	return kvm->arch.kvm_ops->test_age_gfn(kvm, range);
}

bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	return kvm->arch.kvm_ops->set_spte_gfn(kvm, range);
}

int kvmppc_core_init_vm(struct kvm *kvm)
{

#ifdef CONFIG_PPC64
	INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables);
	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
	mutex_init(&kvm->arch.rtas_token_lock);
#endif

	return kvm->arch.kvm_ops->init_vm(kvm);
}

void kvmppc_core_destroy_vm(struct kvm *kvm)
{
	kvm->arch.kvm_ops->destroy_vm(kvm);

#ifdef CONFIG_PPC64
	kvmppc_rtas_tokens_free(kvm);
	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
#endif

#ifdef CONFIG_KVM_XICS
	/*
	 * Free the XIVE and XICS devices which are not directly freed by the
	 * device 'release' method
	 */
	kfree(kvm->arch.xive_devices.native);
	kvm->arch.xive_devices.native = NULL;
	kfree(kvm->arch.xive_devices.xics_on_xive);
	kvm->arch.xive_devices.xics_on_xive = NULL;
	kfree(kvm->arch.xics_device);
	kvm->arch.xics_device = NULL;
#endif /* CONFIG_KVM_XICS */
}

int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
{
	unsigned long size = kvmppc_get_gpr(vcpu, 4);
	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
	u64 buf;
	int srcu_idx;
	int ret;

	if (!is_power_of_2(size) || (size > sizeof(buf)))
		return H_TOO_HARD;

	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf);
	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
	if (ret != 0)
		return H_TOO_HARD;

	switch (size) {
	case 1:
		kvmppc_set_gpr(vcpu, 4, *(u8 *)&buf);
		break;

	case 2:
		kvmppc_set_gpr(vcpu, 4, be16_to_cpu(*(__be16 *)&buf));
		break;

	case 4:
		kvmppc_set_gpr(vcpu, 4, be32_to_cpu(*(__be32 *)&buf));
		break;

	case 8:
		kvmppc_set_gpr(vcpu, 4, be64_to_cpu(*(__be64 *)&buf));
		break;

	default:
		BUG();
	}

	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_load);

int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
{
	unsigned long size = kvmppc_get_gpr(vcpu, 4);
	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
	unsigned long val = kvmppc_get_gpr(vcpu, 6);
	u64 buf;
	int srcu_idx;
	int ret;

	switch (size) {
	case 1:
		*(u8 *)&buf = val;
		break;

	case 2:
		*(__be16 *)&buf = cpu_to_be16(val);
		break;

	case 4:
		*(__be32 *)&buf = cpu_to_be32(val);
		break;

	case 8:
		*(__be64 *)&buf = cpu_to_be64(val);
		break;

	default:
		return H_TOO_HARD;
	}

	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf);
	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
	if (ret != 0)
		return H_TOO_HARD;

	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_store);

int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall)
{
	return kvm->arch.kvm_ops->hcall_implemented(hcall);
}

#ifdef CONFIG_KVM_XICS
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
		bool line_status)
{
	if (xics_on_xive())
		return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level,
					   line_status);
	else
		return kvmppc_xics_set_irq(kvm, irq_source_id, irq, level,
					   line_status);
}

int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
			      struct kvm *kvm, int irq_source_id,
			      int level, bool line_status)
{
	return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
			   level, line_status);
}
static int kvmppc_book3s_set_irq(struct kvm_kernel_irq_routing_entry *e,
				 struct kvm *kvm, int irq_source_id, int level,
				 bool line_status)
{
	return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
}

int kvm_irq_map_gsi(struct kvm *kvm,
		    struct kvm_kernel_irq_routing_entry *entries, int gsi)
{
	entries->gsi = gsi;
	entries->type = KVM_IRQ_ROUTING_IRQCHIP;
	entries->set = kvmppc_book3s_set_irq;
	entries->irqchip.irqchip = 0;
	entries->irqchip.pin = gsi;
	return 1;
}

int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
	return pin;
}

#endif /* CONFIG_KVM_XICS */

static int kvmppc_book3s_init(void)
{
	int r;

	r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
	if (r)
		return r;
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
	r = kvmppc_book3s_init_pr();
#endif

#ifdef CONFIG_KVM_XICS
#ifdef CONFIG_KVM_XIVE
	if (xics_on_xive()) {
		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
		if (kvmppc_xive_native_supported())
			kvm_register_device_ops(&kvm_xive_native_ops,
						KVM_DEV_TYPE_XIVE);
	} else
#endif
		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
#endif
	return r;
}

static void kvmppc_book3s_exit(void)
{
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
	kvmppc_book3s_exit_pr();
#endif
	kvm_exit();
}

module_init(kvmppc_book3s_init);
module_exit(kvmppc_book3s_exit);

/* On 32bit this is our one and only kernel module */
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
#endif