summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/powerpc.c
blob: 95c91a9de351c4b8b67f23c299279faa283efef7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
/*
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * Copyright IBM Corp. 2007
 *
 * Authors: Hollis Blanchard <hollisb@us.ibm.com>
 *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
 */

#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/vmalloc.h>
#include <linux/hrtimer.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/irqbypass.h>
#include <linux/kvm_irqfd.h>
#include <asm/cputable.h>
#include <linux/uaccess.h>
#include <asm/kvm_ppc.h>
#include <asm/tlbflush.h>
#include <asm/cputhreads.h>
#include <asm/irqflags.h>
#include <asm/iommu.h>
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

struct kvmppc_ops *kvmppc_hv_ops;
EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
struct kvmppc_ops *kvmppc_pr_ops;
EXPORT_SYMBOL_GPL(kvmppc_pr_ops);


int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
	return !!(v->arch.pending_exceptions) ||
	       v->requests;
}

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	return 1;
}

/*
 * Common checks before entering the guest world.  Call with interrupts
 * disabled.
 *
 * returns:
 *
 * == 1 if we're ready to go into guest state
 * <= 0 if we need to go back to the host with return value
 */
int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
{
	int r;

	WARN_ON(irqs_disabled());
	hard_irq_disable();

	while (true) {
		if (need_resched()) {
			local_irq_enable();
			cond_resched();
			hard_irq_disable();
			continue;
		}

		if (signal_pending(current)) {
			kvmppc_account_exit(vcpu, SIGNAL_EXITS);
			vcpu->run->exit_reason = KVM_EXIT_INTR;
			r = -EINTR;
			break;
		}

		vcpu->mode = IN_GUEST_MODE;

		/*
		 * Reading vcpu->requests must happen after setting vcpu->mode,
		 * so we don't miss a request because the requester sees
		 * OUTSIDE_GUEST_MODE and assumes we'll be checking requests
		 * before next entering the guest (and thus doesn't IPI).
		 * This also orders the write to mode from any reads
		 * to the page tables done while the VCPU is running.
		 * Please see the comment in kvm_flush_remote_tlbs.
		 */
		smp_mb();

		if (vcpu->requests) {
			/* Make sure we process requests preemptable */
			local_irq_enable();
			trace_kvm_check_requests(vcpu);
			r = kvmppc_core_check_requests(vcpu);
			hard_irq_disable();
			if (r > 0)
				continue;
			break;
		}

		if (kvmppc_core_prepare_to_enter(vcpu)) {
			/* interrupts got enabled in between, so we
			   are back at square 1 */
			continue;
		}

		guest_enter_irqoff();
		return 1;
	}

	/* return to host */
	local_irq_enable();
	return r;
}
EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);

#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
static void kvmppc_swab_shared(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
	int i;

	shared->sprg0 = swab64(shared->sprg0);
	shared->sprg1 = swab64(shared->sprg1);
	shared->sprg2 = swab64(shared->sprg2);
	shared->sprg3 = swab64(shared->sprg3);
	shared->srr0 = swab64(shared->srr0);
	shared->srr1 = swab64(shared->srr1);
	shared->dar = swab64(shared->dar);
	shared->msr = swab64(shared->msr);
	shared->dsisr = swab32(shared->dsisr);
	shared->int_pending = swab32(shared->int_pending);
	for (i = 0; i < ARRAY_SIZE(shared->sr); i++)
		shared->sr[i] = swab32(shared->sr[i]);
}
#endif

int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
{
	int nr = kvmppc_get_gpr(vcpu, 11);
	int r;
	unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
	unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
	unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
	unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
	unsigned long r2 = 0;

	if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
		/* 32 bit mode */
		param1 &= 0xffffffff;
		param2 &= 0xffffffff;
		param3 &= 0xffffffff;
		param4 &= 0xffffffff;
	}

	switch (nr) {
	case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
	{
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
		/* Book3S can be little endian, find it out here */
		int shared_big_endian = true;
		if (vcpu->arch.intr_msr & MSR_LE)
			shared_big_endian = false;
		if (shared_big_endian != vcpu->arch.shared_big_endian)
			kvmppc_swab_shared(vcpu);
		vcpu->arch.shared_big_endian = shared_big_endian;
#endif

		if (!(param2 & MAGIC_PAGE_FLAG_NOT_MAPPED_NX)) {
			/*
			 * Older versions of the Linux magic page code had
			 * a bug where they would map their trampoline code
			 * NX. If that's the case, remove !PR NX capability.
			 */
			vcpu->arch.disable_kernel_nx = true;
			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
		}

		vcpu->arch.magic_page_pa = param1 & ~0xfffULL;
		vcpu->arch.magic_page_ea = param2 & ~0xfffULL;

#ifdef CONFIG_PPC_64K_PAGES
		/*
		 * Make sure our 4k magic page is in the same window of a 64k
		 * page within the guest and within the host's page.
		 */
		if ((vcpu->arch.magic_page_pa & 0xf000) !=
		    ((ulong)vcpu->arch.shared & 0xf000)) {
			void *old_shared = vcpu->arch.shared;
			ulong shared = (ulong)vcpu->arch.shared;
			void *new_shared;

			shared &= PAGE_MASK;
			shared |= vcpu->arch.magic_page_pa & 0xf000;
			new_shared = (void*)shared;
			memcpy(new_shared, old_shared, 0x1000);
			vcpu->arch.shared = new_shared;
		}
#endif

		r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;

		r = EV_SUCCESS;
		break;
	}
	case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
		r = EV_SUCCESS;
#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
		r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
#endif

		/* Second return value is in r4 */
		break;
	case EV_HCALL_TOKEN(EV_IDLE):
		r = EV_SUCCESS;
		kvm_vcpu_block(vcpu);
		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
		break;
	default:
		r = EV_UNIMPLEMENTED;
		break;
	}

	kvmppc_set_gpr(vcpu, 4, r2);

	return r;
}
EXPORT_SYMBOL_GPL(kvmppc_kvm_pv);

int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
{
	int r = false;

	/* We have to know what CPU to virtualize */
	if (!vcpu->arch.pvr)
		goto out;

	/* PAPR only works with book3s_64 */
	if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
		goto out;

	/* HV KVM can only do PAPR mode for now */
	if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm))
		goto out;

#ifdef CONFIG_KVM_BOOKE_HV
	if (!cpu_has_feature(CPU_FTR_EMB_HV))
		goto out;
#endif

	r = true;

out:
	vcpu->arch.sane = r;
	return r ? 0 : -EINVAL;
}
EXPORT_SYMBOL_GPL(kvmppc_sanity_check);

int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	enum emulation_result er;
	int r;

	er = kvmppc_emulate_loadstore(vcpu);
	switch (er) {
	case EMULATE_DONE:
		/* Future optimization: only reload non-volatiles if they were
		 * actually modified. */
		r = RESUME_GUEST_NV;
		break;
	case EMULATE_AGAIN:
		r = RESUME_GUEST;
		break;
	case EMULATE_DO_MMIO:
		run->exit_reason = KVM_EXIT_MMIO;
		/* We must reload nonvolatiles because "update" load/store
		 * instructions modify register state. */
		/* Future optimization: only reload non-volatiles if they were
		 * actually modified. */
		r = RESUME_HOST_NV;
		break;
	case EMULATE_FAIL:
	{
		u32 last_inst;

		kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
		/* XXX Deliver Program interrupt to guest. */
		pr_emerg("%s: emulation failed (%08x)\n", __func__, last_inst);
		r = RESUME_HOST;
		break;
	}
	default:
		WARN_ON(1);
		r = RESUME_GUEST;
	}

	return r;
}
EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);

int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
	      bool data)
{
	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
	struct kvmppc_pte pte;
	int r;

	vcpu->stat.st++;

	r = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
			 XLATE_WRITE, &pte);
	if (r < 0)
		return r;

	*eaddr = pte.raddr;

	if (!pte.may_write)
		return -EPERM;

	/* Magic page override */
	if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
	    ((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
	    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
		void *magic = vcpu->arch.shared;
		magic += pte.eaddr & 0xfff;
		memcpy(magic, ptr, size);
		return EMULATE_DONE;
	}

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

	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_st);

int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
		      bool data)
{
	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
	struct kvmppc_pte pte;
	int rc;

	vcpu->stat.ld++;

	rc = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
			  XLATE_READ, &pte);
	if (rc)
		return rc;

	*eaddr = pte.raddr;

	if (!pte.may_read)
		return -EPERM;

	if (!data && !pte.may_execute)
		return -ENOEXEC;

	/* Magic page override */
	if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
	    ((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
	    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
		void *magic = vcpu->arch.shared;
		magic += pte.eaddr & 0xfff;
		memcpy(ptr, magic, size);
		return EMULATE_DONE;
	}

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

	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_ld);

int kvm_arch_hardware_enable(void)
{
	return 0;
}

int kvm_arch_hardware_setup(void)
{
	return 0;
}

void kvm_arch_check_processor_compat(void *rtn)
{
	*(int *)rtn = kvmppc_core_check_processor_compat();
}

int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
	struct kvmppc_ops *kvm_ops = NULL;
	/*
	 * if we have both HV and PR enabled, default is HV
	 */
	if (type == 0) {
		if (kvmppc_hv_ops)
			kvm_ops = kvmppc_hv_ops;
		else
			kvm_ops = kvmppc_pr_ops;
		if (!kvm_ops)
			goto err_out;
	} else	if (type == KVM_VM_PPC_HV) {
		if (!kvmppc_hv_ops)
			goto err_out;
		kvm_ops = kvmppc_hv_ops;
	} else if (type == KVM_VM_PPC_PR) {
		if (!kvmppc_pr_ops)
			goto err_out;
		kvm_ops = kvmppc_pr_ops;
	} else
		goto err_out;

	if (kvm_ops->owner && !try_module_get(kvm_ops->owner))
		return -ENOENT;

	kvm->arch.kvm_ops = kvm_ops;
	return kvmppc_core_init_vm(kvm);
err_out:
	return -EINVAL;
}

bool kvm_arch_has_vcpu_debugfs(void)
{
	return false;
}

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

void kvm_arch_destroy_vm(struct kvm *kvm)
{
	unsigned int i;
	struct kvm_vcpu *vcpu;

#ifdef CONFIG_KVM_XICS
	/*
	 * We call kick_all_cpus_sync() to ensure that all
	 * CPUs have executed any pending IPIs before we
	 * continue and free VCPUs structures below.
	 */
	if (is_kvmppc_hv_enabled(kvm))
		kick_all_cpus_sync();
#endif

	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_arch_vcpu_free(vcpu);

	mutex_lock(&kvm->lock);
	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
		kvm->vcpus[i] = NULL;

	atomic_set(&kvm->online_vcpus, 0);

	kvmppc_core_destroy_vm(kvm);

	mutex_unlock(&kvm->lock);

	/* drop the module reference */
	module_put(kvm->arch.kvm_ops->owner);
}

int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
	int r;
	/* Assume we're using HV mode when the HV module is loaded */
	int hv_enabled = kvmppc_hv_ops ? 1 : 0;

	if (kvm) {
		/*
		 * Hooray - we know which VM type we're running on. Depend on
		 * that rather than the guess above.
		 */
		hv_enabled = is_kvmppc_hv_enabled(kvm);
	}

	switch (ext) {
#ifdef CONFIG_BOOKE
	case KVM_CAP_PPC_BOOKE_SREGS:
	case KVM_CAP_PPC_BOOKE_WATCHDOG:
	case KVM_CAP_PPC_EPR:
#else
	case KVM_CAP_PPC_SEGSTATE:
	case KVM_CAP_PPC_HIOR:
	case KVM_CAP_PPC_PAPR:
#endif
	case KVM_CAP_PPC_UNSET_IRQ:
	case KVM_CAP_PPC_IRQ_LEVEL:
	case KVM_CAP_ENABLE_CAP:
	case KVM_CAP_ENABLE_CAP_VM:
	case KVM_CAP_ONE_REG:
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_DEVICE_CTRL:
	case KVM_CAP_IMMEDIATE_EXIT:
		r = 1;
		break;
	case KVM_CAP_PPC_PAIRED_SINGLES:
	case KVM_CAP_PPC_OSI:
	case KVM_CAP_PPC_GET_PVINFO:
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
	case KVM_CAP_SW_TLB:
#endif
		/* We support this only for PR */
		r = !hv_enabled;
		break;
#ifdef CONFIG_KVM_MMIO
	case KVM_CAP_COALESCED_MMIO:
		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
		break;
#endif
#ifdef CONFIG_KVM_MPIC
	case KVM_CAP_IRQ_MPIC:
		r = 1;
		break;
#endif

#ifdef CONFIG_PPC_BOOK3S_64
	case KVM_CAP_SPAPR_TCE:
	case KVM_CAP_SPAPR_TCE_64:
	case KVM_CAP_PPC_RTAS:
	case KVM_CAP_PPC_FIXUP_HCALL:
	case KVM_CAP_PPC_ENABLE_HCALL:
#ifdef CONFIG_KVM_XICS
	case KVM_CAP_IRQ_XICS:
#endif
		r = 1;
		break;

	case KVM_CAP_PPC_ALLOC_HTAB:
		r = hv_enabled;
		break;
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	case KVM_CAP_PPC_SMT:
		r = 0;
		if (hv_enabled) {
			if (cpu_has_feature(CPU_FTR_ARCH_300))
				r = 1;
			else
				r = threads_per_subcore;
		}
		break;
	case KVM_CAP_PPC_RMA:
		r = 0;
		break;
	case KVM_CAP_PPC_HWRNG:
		r = kvmppc_hwrng_present();
		break;
	case KVM_CAP_PPC_MMU_RADIX:
		r = !!(hv_enabled && radix_enabled());
		break;
	case KVM_CAP_PPC_MMU_HASH_V3:
		r = !!(hv_enabled && !radix_enabled() &&
		       cpu_has_feature(CPU_FTR_ARCH_300));
		break;
#endif
	case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
		r = hv_enabled;
#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
		r = 1;
#else
		r = 0;
#endif
		break;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	case KVM_CAP_PPC_HTAB_FD:
		r = hv_enabled;
		break;
#endif
	case KVM_CAP_NR_VCPUS:
		/*
		 * Recommending a number of CPUs is somewhat arbitrary; we
		 * return the number of present CPUs for -HV (since a host
		 * will have secondary threads "offline"), and for other KVM
		 * implementations just count online CPUs.
		 */
		if (hv_enabled)
			r = num_present_cpus();
		else
			r = num_online_cpus();
		break;
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
#ifdef CONFIG_PPC_BOOK3S_64
	case KVM_CAP_PPC_GET_SMMU_INFO:
		r = 1;
		break;
	case KVM_CAP_SPAPR_MULTITCE:
		r = 1;
		break;
	case KVM_CAP_SPAPR_RESIZE_HPT:
		/* Disable this on POWER9 until code handles new HPTE format */
		r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300);
		break;
#endif
	case KVM_CAP_PPC_HTM:
		r = cpu_has_feature(CPU_FTR_TM_COMP) &&
		    is_kvmppc_hv_enabled(kvm);
		break;
	default:
		r = 0;
		break;
	}
	return r;

}

long kvm_arch_dev_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
{
	return -EINVAL;
}

void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
			   struct kvm_memory_slot *dont)
{
	kvmppc_core_free_memslot(kvm, free, dont);
}

int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
{
	return kvmppc_core_create_memslot(kvm, slot, npages);
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
				   const struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
{
	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   const struct kvm_userspace_memory_region *mem,
				   const struct kvm_memory_slot *old,
				   const struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	kvmppc_core_commit_memory_region(kvm, mem, old, new);
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
	kvmppc_core_flush_memslot(kvm, slot);
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
	struct kvm_vcpu *vcpu;
	vcpu = kvmppc_core_vcpu_create(kvm, id);
	if (!IS_ERR(vcpu)) {
		vcpu->arch.wqp = &vcpu->wq;
		kvmppc_create_vcpu_debugfs(vcpu, id);
	}
	return vcpu;
}

void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
}

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
	/* Make sure we're not using the vcpu anymore */
	hrtimer_cancel(&vcpu->arch.dec_timer);

	kvmppc_remove_vcpu_debugfs(vcpu);

	switch (vcpu->arch.irq_type) {
	case KVMPPC_IRQ_MPIC:
		kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
		break;
	case KVMPPC_IRQ_XICS:
		kvmppc_xics_free_icp(vcpu);
		break;
	}

	kvmppc_core_vcpu_free(vcpu);
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_free(vcpu);
}

int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
	return kvmppc_core_pending_dec(vcpu);
}

static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;

	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
	kvmppc_decrementer_func(vcpu);

	return HRTIMER_NORESTART;
}

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
	int ret;

	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
	vcpu->arch.dec_expires = ~(u64)0;

#ifdef CONFIG_KVM_EXIT_TIMING
	mutex_init(&vcpu->arch.exit_timing_lock);
#endif
	ret = kvmppc_subarch_vcpu_init(vcpu);
	return ret;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	kvmppc_mmu_destroy(vcpu);
	kvmppc_subarch_vcpu_uninit(vcpu);
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
#ifdef CONFIG_BOOKE
	/*
	 * vrsave (formerly usprg0) isn't used by Linux, but may
	 * be used by the guest.
	 *
	 * On non-booke this is associated with Altivec and
	 * is handled by code in book3s.c.
	 */
	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
#endif
	kvmppc_core_vcpu_load(vcpu, cpu);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	kvmppc_core_vcpu_put(vcpu);
#ifdef CONFIG_BOOKE
	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
#endif
}

/*
 * irq_bypass_add_producer and irq_bypass_del_producer are only
 * useful if the architecture supports PCI passthrough.
 * irq_bypass_stop and irq_bypass_start are not needed and so
 * kvm_ops are not defined for them.
 */
bool kvm_arch_has_irq_bypass(void)
{
	return ((kvmppc_hv_ops && kvmppc_hv_ops->irq_bypass_add_producer) ||
		(kvmppc_pr_ops && kvmppc_pr_ops->irq_bypass_add_producer));
}

int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
				     struct irq_bypass_producer *prod)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);
	struct kvm *kvm = irqfd->kvm;

	if (kvm->arch.kvm_ops->irq_bypass_add_producer)
		return kvm->arch.kvm_ops->irq_bypass_add_producer(cons, prod);

	return 0;
}

void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
				      struct irq_bypass_producer *prod)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(cons, struct kvm_kernel_irqfd, consumer);
	struct kvm *kvm = irqfd->kvm;

	if (kvm->arch.kvm_ops->irq_bypass_del_producer)
		kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod);
}

static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
                                      struct kvm_run *run)
{
	u64 uninitialized_var(gpr);

	if (run->mmio.len > sizeof(gpr)) {
		printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
		return;
	}

	if (!vcpu->arch.mmio_host_swabbed) {
		switch (run->mmio.len) {
		case 8: gpr = *(u64 *)run->mmio.data; break;
		case 4: gpr = *(u32 *)run->mmio.data; break;
		case 2: gpr = *(u16 *)run->mmio.data; break;
		case 1: gpr = *(u8 *)run->mmio.data; break;
		}
	} else {
		switch (run->mmio.len) {
		case 8: gpr = swab64(*(u64 *)run->mmio.data); break;
		case 4: gpr = swab32(*(u32 *)run->mmio.data); break;
		case 2: gpr = swab16(*(u16 *)run->mmio.data); break;
		case 1: gpr = *(u8 *)run->mmio.data; break;
		}
	}

	if (vcpu->arch.mmio_sign_extend) {
		switch (run->mmio.len) {
#ifdef CONFIG_PPC64
		case 4:
			gpr = (s64)(s32)gpr;
			break;
#endif
		case 2:
			gpr = (s64)(s16)gpr;
			break;
		case 1:
			gpr = (s64)(s8)gpr;
			break;
		}
	}

	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);

	switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) {
	case KVM_MMIO_REG_GPR:
		kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
		break;
	case KVM_MMIO_REG_FPR:
		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
		break;
#ifdef CONFIG_PPC_BOOK3S
	case KVM_MMIO_REG_QPR:
		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
		break;
	case KVM_MMIO_REG_FQPR:
		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
		break;
#endif
	default:
		BUG();
	}
}

static int __kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
				unsigned int rt, unsigned int bytes,
				int is_default_endian, int sign_extend)
{
	int idx, ret;
	bool host_swabbed;

	/* Pity C doesn't have a logical XOR operator */
	if (kvmppc_need_byteswap(vcpu)) {
		host_swabbed = is_default_endian;
	} else {
		host_swabbed = !is_default_endian;
	}

	if (bytes > sizeof(run->mmio.data)) {
		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
		       run->mmio.len);
	}

	run->mmio.phys_addr = vcpu->arch.paddr_accessed;
	run->mmio.len = bytes;
	run->mmio.is_write = 0;

	vcpu->arch.io_gpr = rt;
	vcpu->arch.mmio_host_swabbed = host_swabbed;
	vcpu->mmio_needed = 1;
	vcpu->mmio_is_write = 0;
	vcpu->arch.mmio_sign_extend = sign_extend;

	idx = srcu_read_lock(&vcpu->kvm->srcu);

	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr,
			      bytes, &run->mmio.data);

	srcu_read_unlock(&vcpu->kvm->srcu, idx);

	if (!ret) {
		kvmppc_complete_mmio_load(vcpu, run);
		vcpu->mmio_needed = 0;
		return EMULATE_DONE;
	}

	return EMULATE_DO_MMIO;
}

int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
		       unsigned int rt, unsigned int bytes,
		       int is_default_endian)
{
	return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 0);
}
EXPORT_SYMBOL_GPL(kvmppc_handle_load);

/* Same as above, but sign extends */
int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
			unsigned int rt, unsigned int bytes,
			int is_default_endian)
{
	return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 1);
}

int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
			u64 val, unsigned int bytes, int is_default_endian)
{
	void *data = run->mmio.data;
	int idx, ret;
	bool host_swabbed;

	/* Pity C doesn't have a logical XOR operator */
	if (kvmppc_need_byteswap(vcpu)) {
		host_swabbed = is_default_endian;
	} else {
		host_swabbed = !is_default_endian;
	}

	if (bytes > sizeof(run->mmio.data)) {
		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
		       run->mmio.len);
	}

	run->mmio.phys_addr = vcpu->arch.paddr_accessed;
	run->mmio.len = bytes;
	run->mmio.is_write = 1;
	vcpu->mmio_needed = 1;
	vcpu->mmio_is_write = 1;

	/* Store the value at the lowest bytes in 'data'. */
	if (!host_swabbed) {
		switch (bytes) {
		case 8: *(u64 *)data = val; break;
		case 4: *(u32 *)data = val; break;
		case 2: *(u16 *)data = val; break;
		case 1: *(u8  *)data = val; break;
		}
	} else {
		switch (bytes) {
		case 8: *(u64 *)data = swab64(val); break;
		case 4: *(u32 *)data = swab32(val); break;
		case 2: *(u16 *)data = swab16(val); break;
		case 1: *(u8  *)data = val; break;
		}
	}

	idx = srcu_read_lock(&vcpu->kvm->srcu);

	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr,
			       bytes, &run->mmio.data);

	srcu_read_unlock(&vcpu->kvm->srcu, idx);

	if (!ret) {
		vcpu->mmio_needed = 0;
		return EMULATE_DONE;
	}

	return EMULATE_DO_MMIO;
}
EXPORT_SYMBOL_GPL(kvmppc_handle_store);

int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
	int r = 0;
	union kvmppc_one_reg val;
	int size;

	size = one_reg_size(reg->id);
	if (size > sizeof(val))
		return -EINVAL;

	r = kvmppc_get_one_reg(vcpu, reg->id, &val);
	if (r == -EINVAL) {
		r = 0;
		switch (reg->id) {
#ifdef CONFIG_ALTIVEC
		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
				r = -ENXIO;
				break;
			}
			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
			break;
		case KVM_REG_PPC_VSCR:
			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
				r = -ENXIO;
				break;
			}
			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
			break;
		case KVM_REG_PPC_VRSAVE:
			val = get_reg_val(reg->id, vcpu->arch.vrsave);
			break;
#endif /* CONFIG_ALTIVEC */
		default:
			r = -EINVAL;
			break;
		}
	}

	if (r)
		return r;

	if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
		r = -EFAULT;

	return r;
}

int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
	int r;
	union kvmppc_one_reg val;
	int size;

	size = one_reg_size(reg->id);
	if (size > sizeof(val))
		return -EINVAL;

	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
		return -EFAULT;

	r = kvmppc_set_one_reg(vcpu, reg->id, &val);
	if (r == -EINVAL) {
		r = 0;
		switch (reg->id) {
#ifdef CONFIG_ALTIVEC
		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
				r = -ENXIO;
				break;
			}
			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
			break;
		case KVM_REG_PPC_VSCR:
			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
				r = -ENXIO;
				break;
			}
			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
			break;
		case KVM_REG_PPC_VRSAVE:
			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
				r = -ENXIO;
				break;
			}
			vcpu->arch.vrsave = set_reg_val(reg->id, val);
			break;
#endif /* CONFIG_ALTIVEC */
		default:
			r = -EINVAL;
			break;
		}
	}

	return r;
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	int r;
	sigset_t sigsaved;

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

	if (vcpu->mmio_needed) {
		if (!vcpu->mmio_is_write)
			kvmppc_complete_mmio_load(vcpu, run);
		vcpu->mmio_needed = 0;
	} else if (vcpu->arch.osi_needed) {
		u64 *gprs = run->osi.gprs;
		int i;

		for (i = 0; i < 32; i++)
			kvmppc_set_gpr(vcpu, i, gprs[i]);
		vcpu->arch.osi_needed = 0;
	} else if (vcpu->arch.hcall_needed) {
		int i;

		kvmppc_set_gpr(vcpu, 3, run->papr_hcall.ret);
		for (i = 0; i < 9; ++i)
			kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
		vcpu->arch.hcall_needed = 0;
#ifdef CONFIG_BOOKE
	} else if (vcpu->arch.epr_needed) {
		kvmppc_set_epr(vcpu, run->epr.epr);
		vcpu->arch.epr_needed = 0;
#endif
	}

	if (run->immediate_exit)
		r = -EINTR;
	else
		r = kvmppc_vcpu_run(run, vcpu);

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	return r;
}

int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
{
	if (irq->irq == KVM_INTERRUPT_UNSET) {
		kvmppc_core_dequeue_external(vcpu);
		return 0;
	}

	kvmppc_core_queue_external(vcpu, irq);

	kvm_vcpu_kick(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
				     struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
	case KVM_CAP_PPC_OSI:
		r = 0;
		vcpu->arch.osi_enabled = true;
		break;
	case KVM_CAP_PPC_PAPR:
		r = 0;
		vcpu->arch.papr_enabled = true;
		break;
	case KVM_CAP_PPC_EPR:
		r = 0;
		if (cap->args[0])
			vcpu->arch.epr_flags |= KVMPPC_EPR_USER;
		else
			vcpu->arch.epr_flags &= ~KVMPPC_EPR_USER;
		break;
#ifdef CONFIG_BOOKE
	case KVM_CAP_PPC_BOOKE_WATCHDOG:
		r = 0;
		vcpu->arch.watchdog_enabled = true;
		break;
#endif
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
	case KVM_CAP_SW_TLB: {
		struct kvm_config_tlb cfg;
		void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];

		r = -EFAULT;
		if (copy_from_user(&cfg, user_ptr, sizeof(cfg)))
			break;

		r = kvm_vcpu_ioctl_config_tlb(vcpu, &cfg);
		break;
	}
#endif
#ifdef CONFIG_KVM_MPIC
	case KVM_CAP_IRQ_MPIC: {
		struct fd f;
		struct kvm_device *dev;

		r = -EBADF;
		f = fdget(cap->args[0]);
		if (!f.file)
			break;

		r = -EPERM;
		dev = kvm_device_from_filp(f.file);
		if (dev)
			r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);

		fdput(f);
		break;
	}
#endif
#ifdef CONFIG_KVM_XICS
	case KVM_CAP_IRQ_XICS: {
		struct fd f;
		struct kvm_device *dev;

		r = -EBADF;
		f = fdget(cap->args[0]);
		if (!f.file)
			break;

		r = -EPERM;
		dev = kvm_device_from_filp(f.file);
		if (dev)
			r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);

		fdput(f);
		break;
	}
#endif /* CONFIG_KVM_XICS */
	default:
		r = -EINVAL;
		break;
	}

	if (!r)
		r = kvmppc_sanity_check(vcpu);

	return r;
}

bool kvm_arch_intc_initialized(struct kvm *kvm)
{
#ifdef CONFIG_KVM_MPIC
	if (kvm->arch.mpic)
		return true;
#endif
#ifdef CONFIG_KVM_XICS
	if (kvm->arch.xics)
		return true;
#endif
	return false;
}

int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
                                    struct kvm_mp_state *mp_state)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
                                    struct kvm_mp_state *mp_state)
{
	return -EINVAL;
}

long kvm_arch_vcpu_ioctl(struct file *filp,
                         unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	long r;

	switch (ioctl) {
	case KVM_INTERRUPT: {
		struct kvm_interrupt irq;
		r = -EFAULT;
		if (copy_from_user(&irq, argp, sizeof(irq)))
			goto out;
		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
		goto out;
	}

	case KVM_ENABLE_CAP:
	{
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			goto out;
		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
		break;
	}

	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG:
	{
		struct kvm_one_reg reg;
		r = -EFAULT;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			goto out;
		if (ioctl == KVM_SET_ONE_REG)
			r = kvm_vcpu_ioctl_set_one_reg(vcpu, &reg);
		else
			r = kvm_vcpu_ioctl_get_one_reg(vcpu, &reg);
		break;
	}

#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
	case KVM_DIRTY_TLB: {
		struct kvm_dirty_tlb dirty;
		r = -EFAULT;
		if (copy_from_user(&dirty, argp, sizeof(dirty)))
			goto out;
		r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
		break;
	}
#endif
	default:
		r = -EINVAL;
	}

out:
	return r;
}

int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
	return VM_FAULT_SIGBUS;
}

static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
{
	u32 inst_nop = 0x60000000;
#ifdef CONFIG_KVM_BOOKE_HV
	u32 inst_sc1 = 0x44000022;
	pvinfo->hcall[0] = cpu_to_be32(inst_sc1);
	pvinfo->hcall[1] = cpu_to_be32(inst_nop);
	pvinfo->hcall[2] = cpu_to_be32(inst_nop);
	pvinfo->hcall[3] = cpu_to_be32(inst_nop);
#else
	u32 inst_lis = 0x3c000000;
	u32 inst_ori = 0x60000000;
	u32 inst_sc = 0x44000002;
	u32 inst_imm_mask = 0xffff;

	/*
	 * The hypercall to get into KVM from within guest context is as
	 * follows:
	 *
	 *    lis r0, r0, KVM_SC_MAGIC_R0@h
	 *    ori r0, KVM_SC_MAGIC_R0@l
	 *    sc
	 *    nop
	 */
	pvinfo->hcall[0] = cpu_to_be32(inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask));
	pvinfo->hcall[1] = cpu_to_be32(inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask));
	pvinfo->hcall[2] = cpu_to_be32(inst_sc);
	pvinfo->hcall[3] = cpu_to_be32(inst_nop);
#endif

	pvinfo->flags = KVM_PPC_PVINFO_FLAGS_EV_IDLE;

	return 0;
}

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
			  bool line_status)
{
	if (!irqchip_in_kernel(kvm))
		return -ENXIO;

	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
					irq_event->irq, irq_event->level,
					line_status);
	return 0;
}


static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
				   struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
	case KVM_CAP_PPC_ENABLE_HCALL: {
		unsigned long hcall = cap->args[0];

		r = -EINVAL;
		if (hcall > MAX_HCALL_OPCODE || (hcall & 3) ||
		    cap->args[1] > 1)
			break;
		if (!kvmppc_book3s_hcall_implemented(kvm, hcall))
			break;
		if (cap->args[1])
			set_bit(hcall / 4, kvm->arch.enabled_hcalls);
		else
			clear_bit(hcall / 4, kvm->arch.enabled_hcalls);
		r = 0;
		break;
	}
#endif
	default:
		r = -EINVAL;
		break;
	}

	return r;
}

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

	switch (ioctl) {
	case KVM_PPC_GET_PVINFO: {
		struct kvm_ppc_pvinfo pvinfo;
		memset(&pvinfo, 0, sizeof(pvinfo));
		r = kvm_vm_ioctl_get_pvinfo(&pvinfo);
		if (copy_to_user(argp, &pvinfo, sizeof(pvinfo))) {
			r = -EFAULT;
			goto out;
		}

		break;
	}
	case KVM_ENABLE_CAP:
	{
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			goto out;
		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
		break;
	}
#ifdef CONFIG_PPC_BOOK3S_64
	case KVM_CREATE_SPAPR_TCE_64: {
		struct kvm_create_spapr_tce_64 create_tce_64;

		r = -EFAULT;
		if (copy_from_user(&create_tce_64, argp, sizeof(create_tce_64)))
			goto out;
		if (create_tce_64.flags) {
			r = -EINVAL;
			goto out;
		}
		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
		goto out;
	}
	case KVM_CREATE_SPAPR_TCE: {
		struct kvm_create_spapr_tce create_tce;
		struct kvm_create_spapr_tce_64 create_tce_64;

		r = -EFAULT;
		if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
			goto out;

		create_tce_64.liobn = create_tce.liobn;
		create_tce_64.page_shift = IOMMU_PAGE_SHIFT_4K;
		create_tce_64.offset = 0;
		create_tce_64.size = create_tce.window_size >>
				IOMMU_PAGE_SHIFT_4K;
		create_tce_64.flags = 0;
		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
		goto out;
	}
	case KVM_PPC_GET_SMMU_INFO: {
		struct kvm_ppc_smmu_info info;
		struct kvm *kvm = filp->private_data;

		memset(&info, 0, sizeof(info));
		r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info);
		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
			r = -EFAULT;
		break;
	}
	case KVM_PPC_RTAS_DEFINE_TOKEN: {
		struct kvm *kvm = filp->private_data;

		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
		break;
	}
	case KVM_PPC_CONFIGURE_V3_MMU: {
		struct kvm *kvm = filp->private_data;
		struct kvm_ppc_mmuv3_cfg cfg;

		r = -EINVAL;
		if (!kvm->arch.kvm_ops->configure_mmu)
			goto out;
		r = -EFAULT;
		if (copy_from_user(&cfg, argp, sizeof(cfg)))
			goto out;
		r = kvm->arch.kvm_ops->configure_mmu(kvm, &cfg);
		break;
	}
	case KVM_PPC_GET_RMMU_INFO: {
		struct kvm *kvm = filp->private_data;
		struct kvm_ppc_rmmu_info info;

		r = -EINVAL;
		if (!kvm->arch.kvm_ops->get_rmmu_info)
			goto out;
		r = kvm->arch.kvm_ops->get_rmmu_info(kvm, &info);
		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
			r = -EFAULT;
		break;
	}
	default: {
		struct kvm *kvm = filp->private_data;
		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
	}
#else /* CONFIG_PPC_BOOK3S_64 */
	default:
		r = -ENOTTY;
#endif
	}
out:
	return r;
}

static unsigned long lpid_inuse[BITS_TO_LONGS(KVMPPC_NR_LPIDS)];
static unsigned long nr_lpids;

long kvmppc_alloc_lpid(void)
{
	long lpid;

	do {
		lpid = find_first_zero_bit(lpid_inuse, KVMPPC_NR_LPIDS);
		if (lpid >= nr_lpids) {
			pr_err("%s: No LPIDs free\n", __func__);
			return -ENOMEM;
		}
	} while (test_and_set_bit(lpid, lpid_inuse));

	return lpid;
}
EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid);

void kvmppc_claim_lpid(long lpid)
{
	set_bit(lpid, lpid_inuse);
}
EXPORT_SYMBOL_GPL(kvmppc_claim_lpid);

void kvmppc_free_lpid(long lpid)
{
	clear_bit(lpid, lpid_inuse);
}
EXPORT_SYMBOL_GPL(kvmppc_free_lpid);

void kvmppc_init_lpid(unsigned long nr_lpids_param)
{
	nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
	memset(lpid_inuse, 0, sizeof(lpid_inuse));
}
EXPORT_SYMBOL_GPL(kvmppc_init_lpid);

int kvm_arch_init(void *opaque)
{
	return 0;
}

EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr);