summaryrefslogtreecommitdiff
path: root/arch/s390/kvm/vsie.c
blob: fef42e2a80a2ae5bc47eae89f2b4e38293a2586b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * kvm nested virtualization support for s390x
 *
 * Copyright IBM Corp. 2016, 2018
 *
 *    Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
 */
#include <linux/vmalloc.h>
#include <linux/kvm_host.h>
#include <linux/bug.h>
#include <linux/list.h>
#include <linux/bitmap.h>
#include <linux/sched/signal.h>

#include <asm/gmap.h>
#include <asm/mmu_context.h>
#include <asm/sclp.h>
#include <asm/nmi.h>
#include <asm/dis.h>
#include <asm/fpu/api.h>
#include <asm/facility.h>
#include "kvm-s390.h"
#include "gaccess.h"

struct vsie_page {
	struct kvm_s390_sie_block scb_s;	/* 0x0000 */
	/*
	 * the backup info for machine check. ensure it's at
	 * the same offset as that in struct sie_page!
	 */
	struct mcck_volatile_info mcck_info;    /* 0x0200 */
	/*
	 * The pinned original scb. Be aware that other VCPUs can modify
	 * it while we read from it. Values that are used for conditions or
	 * are reused conditionally, should be accessed via READ_ONCE.
	 */
	struct kvm_s390_sie_block *scb_o;	/* 0x0218 */
	/* the shadow gmap in use by the vsie_page */
	struct gmap *gmap;			/* 0x0220 */
	/* address of the last reported fault to guest2 */
	unsigned long fault_addr;		/* 0x0228 */
	/* calculated guest addresses of satellite control blocks */
	gpa_t sca_gpa;				/* 0x0230 */
	gpa_t itdba_gpa;			/* 0x0238 */
	gpa_t gvrd_gpa;				/* 0x0240 */
	gpa_t riccbd_gpa;			/* 0x0248 */
	gpa_t sdnx_gpa;				/* 0x0250 */
	__u8 reserved[0x0700 - 0x0258];		/* 0x0258 */
	struct kvm_s390_crypto_cb crycb;	/* 0x0700 */
	__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE];	/* 0x0800 */
};

/* trigger a validity icpt for the given scb */
static int set_validity_icpt(struct kvm_s390_sie_block *scb,
			     __u16 reason_code)
{
	scb->ipa = 0x1000;
	scb->ipb = ((__u32) reason_code) << 16;
	scb->icptcode = ICPT_VALIDITY;
	return 1;
}

/* mark the prefix as unmapped, this will block the VSIE */
static void prefix_unmapped(struct vsie_page *vsie_page)
{
	atomic_or(PROG_REQUEST, &vsie_page->scb_s.prog20);
}

/* mark the prefix as unmapped and wait until the VSIE has been left */
static void prefix_unmapped_sync(struct vsie_page *vsie_page)
{
	prefix_unmapped(vsie_page);
	if (vsie_page->scb_s.prog0c & PROG_IN_SIE)
		atomic_or(CPUSTAT_STOP_INT, &vsie_page->scb_s.cpuflags);
	while (vsie_page->scb_s.prog0c & PROG_IN_SIE)
		cpu_relax();
}

/* mark the prefix as mapped, this will allow the VSIE to run */
static void prefix_mapped(struct vsie_page *vsie_page)
{
	atomic_andnot(PROG_REQUEST, &vsie_page->scb_s.prog20);
}

/* test if the prefix is mapped into the gmap shadow */
static int prefix_is_mapped(struct vsie_page *vsie_page)
{
	return !(atomic_read(&vsie_page->scb_s.prog20) & PROG_REQUEST);
}

/* copy the updated intervention request bits into the shadow scb */
static void update_intervention_requests(struct vsie_page *vsie_page)
{
	const int bits = CPUSTAT_STOP_INT | CPUSTAT_IO_INT | CPUSTAT_EXT_INT;
	int cpuflags;

	cpuflags = atomic_read(&vsie_page->scb_o->cpuflags);
	atomic_andnot(bits, &vsie_page->scb_s.cpuflags);
	atomic_or(cpuflags & bits, &vsie_page->scb_s.cpuflags);
}

/* shadow (filter and validate) the cpuflags  */
static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	int newflags, cpuflags = atomic_read(&scb_o->cpuflags);

	/* we don't allow ESA/390 guests */
	if (!(cpuflags & CPUSTAT_ZARCH))
		return set_validity_icpt(scb_s, 0x0001U);

	if (cpuflags & (CPUSTAT_RRF | CPUSTAT_MCDS))
		return set_validity_icpt(scb_s, 0x0001U);
	else if (cpuflags & (CPUSTAT_SLSV | CPUSTAT_SLSR))
		return set_validity_icpt(scb_s, 0x0007U);

	/* intervention requests will be set later */
	newflags = CPUSTAT_ZARCH;
	if (cpuflags & CPUSTAT_GED && test_kvm_facility(vcpu->kvm, 8))
		newflags |= CPUSTAT_GED;
	if (cpuflags & CPUSTAT_GED2 && test_kvm_facility(vcpu->kvm, 78)) {
		if (cpuflags & CPUSTAT_GED)
			return set_validity_icpt(scb_s, 0x0001U);
		newflags |= CPUSTAT_GED2;
	}
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_GPERE))
		newflags |= cpuflags & CPUSTAT_P;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_GSLS))
		newflags |= cpuflags & CPUSTAT_SM;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IBS))
		newflags |= cpuflags & CPUSTAT_IBS;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_KSS))
		newflags |= cpuflags & CPUSTAT_KSS;

	atomic_set(&scb_s->cpuflags, newflags);
	return 0;
}
/* Copy to APCB FORMAT1 from APCB FORMAT0 */
static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
			unsigned long crycb_gpa, struct kvm_s390_apcb1 *apcb_h)
{
	struct kvm_s390_apcb0 tmp;
	unsigned long apcb_gpa;

	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);

	if (read_guest_real(vcpu, apcb_gpa, &tmp,
			    sizeof(struct kvm_s390_apcb0)))
		return -EFAULT;

	apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
	apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL;
	apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL;

	return 0;

}

/**
 * setup_apcb00 - Copy to APCB FORMAT0 from APCB FORMAT0
 * @vcpu: pointer to the virtual CPU
 * @apcb_s: pointer to start of apcb in the shadow crycb
 * @crycb_gpa: guest physical address to start of original guest crycb
 * @apcb_h: pointer to start of apcb in the guest1
 *
 * Returns 0 and -EFAULT on error reading guest apcb
 */
static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
			unsigned long crycb_gpa, unsigned long *apcb_h)
{
	unsigned long apcb_gpa;

	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);

	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
			    sizeof(struct kvm_s390_apcb0)))
		return -EFAULT;

	bitmap_and(apcb_s, apcb_s, apcb_h,
		   BITS_PER_BYTE * sizeof(struct kvm_s390_apcb0));

	return 0;
}

/**
 * setup_apcb11 - Copy the FORMAT1 APCB from the guest to the shadow CRYCB
 * @vcpu: pointer to the virtual CPU
 * @apcb_s: pointer to start of apcb in the shadow crycb
 * @crycb_gpa: guest physical address to start of original guest crycb
 * @apcb_h: pointer to start of apcb in the host
 *
 * Returns 0 and -EFAULT on error reading guest apcb
 */
static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
			unsigned long crycb_gpa,
			unsigned long *apcb_h)
{
	unsigned long apcb_gpa;

	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb1);

	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
			    sizeof(struct kvm_s390_apcb1)))
		return -EFAULT;

	bitmap_and(apcb_s, apcb_s, apcb_h,
		   BITS_PER_BYTE * sizeof(struct kvm_s390_apcb1));

	return 0;
}

/**
 * setup_apcb - Create a shadow copy of the apcb.
 * @vcpu: pointer to the virtual CPU
 * @crycb_s: pointer to shadow crycb
 * @crycb_gpa: guest physical address of original guest crycb
 * @crycb_h: pointer to the host crycb
 * @fmt_o: format of the original guest crycb.
 * @fmt_h: format of the host crycb.
 *
 * Checks the compatibility between the guest and host crycb and calls the
 * appropriate copy function.
 *
 * Return 0 or an error number if the guest and host crycb are incompatible.
 */
static int setup_apcb(struct kvm_vcpu *vcpu, struct kvm_s390_crypto_cb *crycb_s,
	       const u32 crycb_gpa,
	       struct kvm_s390_crypto_cb *crycb_h,
	       int fmt_o, int fmt_h)
{
	switch (fmt_o) {
	case CRYCB_FORMAT2:
		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 256) & PAGE_MASK))
			return -EACCES;
		if (fmt_h != CRYCB_FORMAT2)
			return -EINVAL;
		return setup_apcb11(vcpu, (unsigned long *)&crycb_s->apcb1,
				    crycb_gpa,
				    (unsigned long *)&crycb_h->apcb1);
	case CRYCB_FORMAT1:
		switch (fmt_h) {
		case CRYCB_FORMAT2:
			return setup_apcb10(vcpu, &crycb_s->apcb1,
					    crycb_gpa,
					    &crycb_h->apcb1);
		case CRYCB_FORMAT1:
			return setup_apcb00(vcpu,
					    (unsigned long *) &crycb_s->apcb0,
					    crycb_gpa,
					    (unsigned long *) &crycb_h->apcb0);
		}
		break;
	case CRYCB_FORMAT0:
		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 32) & PAGE_MASK))
			return -EACCES;

		switch (fmt_h) {
		case CRYCB_FORMAT2:
			return setup_apcb10(vcpu, &crycb_s->apcb1,
					    crycb_gpa,
					    &crycb_h->apcb1);
		case CRYCB_FORMAT1:
		case CRYCB_FORMAT0:
			return setup_apcb00(vcpu,
					    (unsigned long *) &crycb_s->apcb0,
					    crycb_gpa,
					    (unsigned long *) &crycb_h->apcb0);
		}
	}
	return -EINVAL;
}

/**
 * shadow_crycb - Create a shadow copy of the crycb block
 * @vcpu: a pointer to the virtual CPU
 * @vsie_page: a pointer to internal date used for the vSIE
 *
 * Create a shadow copy of the crycb block and setup key wrapping, if
 * requested for guest 3 and enabled for guest 2.
 *
 * We accept format-1 or format-2, but we convert format-1 into format-2
 * in the shadow CRYCB.
 * Using format-2 enables the firmware to choose the right format when
 * scheduling the SIE.
 * There is nothing to do for format-0.
 *
 * This function centralize the issuing of set_validity_icpt() for all
 * the subfunctions working on the crycb.
 *
 * Returns: - 0 if shadowed or nothing to do
 *          - > 0 if control has to be given to guest 2
 */
static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd);
	const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
	unsigned long *b1, *b2;
	u8 ecb3_flags;
	u32 ecd_flags;
	int apie_h;
	int apie_s;
	int key_msk = test_kvm_facility(vcpu->kvm, 76);
	int fmt_o = crycbd_o & CRYCB_FORMAT_MASK;
	int fmt_h = vcpu->arch.sie_block->crycbd & CRYCB_FORMAT_MASK;
	int ret = 0;

	scb_s->crycbd = 0;

	apie_h = vcpu->arch.sie_block->eca & ECA_APIE;
	apie_s = apie_h & scb_o->eca;
	if (!apie_s && (!key_msk || (fmt_o == CRYCB_FORMAT0)))
		return 0;

	if (!crycb_addr)
		return set_validity_icpt(scb_s, 0x0039U);

	if (fmt_o == CRYCB_FORMAT1)
		if ((crycb_addr & PAGE_MASK) !=
		    ((crycb_addr + 128) & PAGE_MASK))
			return set_validity_icpt(scb_s, 0x003CU);

	if (apie_s) {
		ret = setup_apcb(vcpu, &vsie_page->crycb, crycb_addr,
				 vcpu->kvm->arch.crypto.crycb,
				 fmt_o, fmt_h);
		if (ret)
			goto end;
		scb_s->eca |= scb_o->eca & ECA_APIE;
	}

	/* we may only allow it if enabled for guest 2 */
	ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
		     (ECB3_AES | ECB3_DEA);
	ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & ECD_ECC;
	if (!ecb3_flags && !ecd_flags)
		goto end;

	/* copy only the wrapping keys */
	if (read_guest_real(vcpu, crycb_addr + 72,
			    vsie_page->crycb.dea_wrapping_key_mask, 56))
		return set_validity_icpt(scb_s, 0x0035U);

	scb_s->ecb3 |= ecb3_flags;
	scb_s->ecd |= ecd_flags;

	/* xor both blocks in one run */
	b1 = (unsigned long *) vsie_page->crycb.dea_wrapping_key_mask;
	b2 = (unsigned long *)
			    vcpu->kvm->arch.crypto.crycb->dea_wrapping_key_mask;
	/* as 56%8 == 0, bitmap_xor won't overwrite any data */
	bitmap_xor(b1, b1, b2, BITS_PER_BYTE * 56);
end:
	switch (ret) {
	case -EINVAL:
		return set_validity_icpt(scb_s, 0x0022U);
	case -EFAULT:
		return set_validity_icpt(scb_s, 0x0035U);
	case -EACCES:
		return set_validity_icpt(scb_s, 0x003CU);
	}
	scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2;
	return 0;
}

/* shadow (round up/down) the ibc to avoid validity icpt */
static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	/* READ_ONCE does not work on bitfields - use a temporary variable */
	const uint32_t __new_ibc = scb_o->ibc;
	const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU;
	__u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;

	scb_s->ibc = 0;
	/* ibc installed in g2 and requested for g3 */
	if (vcpu->kvm->arch.model.ibc && new_ibc) {
		scb_s->ibc = new_ibc;
		/* takte care of the minimum ibc level of the machine */
		if (scb_s->ibc < min_ibc)
			scb_s->ibc = min_ibc;
		/* take care of the maximum ibc level set for the guest */
		if (scb_s->ibc > vcpu->kvm->arch.model.ibc)
			scb_s->ibc = vcpu->kvm->arch.model.ibc;
	}
}

/* unshadow the scb, copying parameters back to the real scb */
static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;

	/* interception */
	scb_o->icptcode = scb_s->icptcode;
	scb_o->icptstatus = scb_s->icptstatus;
	scb_o->ipa = scb_s->ipa;
	scb_o->ipb = scb_s->ipb;
	scb_o->gbea = scb_s->gbea;

	/* timer */
	scb_o->cputm = scb_s->cputm;
	scb_o->ckc = scb_s->ckc;
	scb_o->todpr = scb_s->todpr;

	/* guest state */
	scb_o->gpsw = scb_s->gpsw;
	scb_o->gg14 = scb_s->gg14;
	scb_o->gg15 = scb_s->gg15;
	memcpy(scb_o->gcr, scb_s->gcr, 128);
	scb_o->pp = scb_s->pp;

	/* branch prediction */
	if (test_kvm_facility(vcpu->kvm, 82)) {
		scb_o->fpf &= ~FPF_BPBC;
		scb_o->fpf |= scb_s->fpf & FPF_BPBC;
	}

	/* interrupt intercept */
	switch (scb_s->icptcode) {
	case ICPT_PROGI:
	case ICPT_INSTPROGI:
	case ICPT_EXTINT:
		memcpy((void *)((u64)scb_o + 0xc0),
		       (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0);
		break;
	}

	if (scb_s->ihcpu != 0xffffU)
		scb_o->ihcpu = scb_s->ihcpu;
}

/*
 * Setup the shadow scb by copying and checking the relevant parts of the g2
 * provided scb.
 *
 * Returns: - 0 if the scb has been shadowed
 *          - > 0 if control has to be given to guest 2
 */
static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	/* READ_ONCE does not work on bitfields - use a temporary variable */
	const uint32_t __new_prefix = scb_o->prefix;
	const uint32_t new_prefix = READ_ONCE(__new_prefix);
	const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE;
	bool had_tx = scb_s->ecb & ECB_TE;
	unsigned long new_mso = 0;
	int rc;

	/* make sure we don't have any leftovers when reusing the scb */
	scb_s->icptcode = 0;
	scb_s->eca = 0;
	scb_s->ecb = 0;
	scb_s->ecb2 = 0;
	scb_s->ecb3 = 0;
	scb_s->ecd = 0;
	scb_s->fac = 0;
	scb_s->fpf = 0;

	rc = prepare_cpuflags(vcpu, vsie_page);
	if (rc)
		goto out;

	/* timer */
	scb_s->cputm = scb_o->cputm;
	scb_s->ckc = scb_o->ckc;
	scb_s->todpr = scb_o->todpr;
	scb_s->epoch = scb_o->epoch;

	/* guest state */
	scb_s->gpsw = scb_o->gpsw;
	scb_s->gg14 = scb_o->gg14;
	scb_s->gg15 = scb_o->gg15;
	memcpy(scb_s->gcr, scb_o->gcr, 128);
	scb_s->pp = scb_o->pp;

	/* interception / execution handling */
	scb_s->gbea = scb_o->gbea;
	scb_s->lctl = scb_o->lctl;
	scb_s->svcc = scb_o->svcc;
	scb_s->ictl = scb_o->ictl;
	/*
	 * SKEY handling functions can't deal with false setting of PTE invalid
	 * bits. Therefore we cannot provide interpretation and would later
	 * have to provide own emulation handlers.
	 */
	if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_KSS))
		scb_s->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;

	scb_s->icpua = scb_o->icpua;

	if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM))
		new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL;
	/* if the hva of the prefix changes, we have to remap the prefix */
	if (scb_s->mso != new_mso || scb_s->prefix != new_prefix)
		prefix_unmapped(vsie_page);
	 /* SIE will do mso/msl validity and exception checks for us */
	scb_s->msl = scb_o->msl & 0xfffffffffff00000UL;
	scb_s->mso = new_mso;
	scb_s->prefix = new_prefix;

	/* We have to definitely flush the tlb if this scb never ran */
	if (scb_s->ihcpu != 0xffffU)
		scb_s->ihcpu = scb_o->ihcpu;

	/* MVPG and Protection Exception Interpretation are always available */
	scb_s->eca |= scb_o->eca & (ECA_MVPGI | ECA_PROTEXCI);
	/* Host-protection-interruption introduced with ESOP */
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
		scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
	/*
	 * CPU Topology
	 * This facility only uses the utility field of the SCA and none of
	 * the cpu entries that are problematic with the other interpretation
	 * facilities so we can pass it through
	 */
	if (test_kvm_facility(vcpu->kvm, 11))
		scb_s->ecb |= scb_o->ecb & ECB_PTF;
	/* transactional execution */
	if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
		/* remap the prefix is tx is toggled on */
		if (!had_tx)
			prefix_unmapped(vsie_page);
		scb_s->ecb |= ECB_TE;
	}
	/* specification exception interpretation */
	scb_s->ecb |= scb_o->ecb & ECB_SPECI;
	/* branch prediction */
	if (test_kvm_facility(vcpu->kvm, 82))
		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
	/* SIMD */
	if (test_kvm_facility(vcpu->kvm, 129)) {
		scb_s->eca |= scb_o->eca & ECA_VX;
		scb_s->ecd |= scb_o->ecd & ECD_HOSTREGMGMT;
	}
	/* Run-time-Instrumentation */
	if (test_kvm_facility(vcpu->kvm, 64))
		scb_s->ecb3 |= scb_o->ecb3 & ECB3_RI;
	/* Instruction Execution Prevention */
	if (test_kvm_facility(vcpu->kvm, 130))
		scb_s->ecb2 |= scb_o->ecb2 & ECB2_IEP;
	/* Guarded Storage */
	if (test_kvm_facility(vcpu->kvm, 133)) {
		scb_s->ecb |= scb_o->ecb & ECB_GS;
		scb_s->ecd |= scb_o->ecd & ECD_HOSTREGMGMT;
	}
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIIF))
		scb_s->eca |= scb_o->eca & ECA_SII;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IB))
		scb_s->eca |= scb_o->eca & ECA_IB;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI))
		scb_s->eca |= scb_o->eca & ECA_CEI;
	/* Epoch Extension */
	if (test_kvm_facility(vcpu->kvm, 139)) {
		scb_s->ecd |= scb_o->ecd & ECD_MEF;
		scb_s->epdx = scb_o->epdx;
	}

	/* etoken */
	if (test_kvm_facility(vcpu->kvm, 156))
		scb_s->ecd |= scb_o->ecd & ECD_ETOKENF;

	scb_s->hpid = HPID_VSIE;
	scb_s->cpnc = scb_o->cpnc;

	prepare_ibc(vcpu, vsie_page);
	rc = shadow_crycb(vcpu, vsie_page);
out:
	if (rc)
		unshadow_scb(vcpu, vsie_page);
	return rc;
}

void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
				 unsigned long end)
{
	struct kvm *kvm = gmap->private;
	struct vsie_page *cur;
	unsigned long prefix;
	struct page *page;
	int i;

	if (!gmap_is_shadow(gmap))
		return;
	/*
	 * Only new shadow blocks are added to the list during runtime,
	 * therefore we can safely reference them all the time.
	 */
	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
		page = READ_ONCE(kvm->arch.vsie.pages[i]);
		if (!page)
			continue;
		cur = page_to_virt(page);
		if (READ_ONCE(cur->gmap) != gmap)
			continue;
		prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
		/* with mso/msl, the prefix lies at an offset */
		prefix += cur->scb_s.mso;
		if (prefix <= end && start <= prefix + 2 * PAGE_SIZE - 1)
			prefix_unmapped_sync(cur);
	}
}

/*
 * Map the first prefix page and if tx is enabled also the second prefix page.
 *
 * The prefix will be protected, a gmap notifier will inform about unmaps.
 * The shadow scb must not be executed until the prefix is remapped, this is
 * guaranteed by properly handling PROG_REQUEST.
 *
 * Returns: - 0 on if successfully mapped or already mapped
 *          - > 0 if control has to be given to guest 2
 *          - -EAGAIN if the caller can retry immediately
 *          - -ENOMEM if out of memory
 */
static int map_prefix(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	u64 prefix = scb_s->prefix << GUEST_PREFIX_SHIFT;
	int rc;

	if (prefix_is_mapped(vsie_page))
		return 0;

	/* mark it as mapped so we can catch any concurrent unmappers */
	prefix_mapped(vsie_page);

	/* with mso/msl, the prefix lies at offset *mso* */
	prefix += scb_s->mso;

	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix, NULL);
	if (!rc && (scb_s->ecb & ECB_TE))
		rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
					   prefix + PAGE_SIZE, NULL);
	/*
	 * We don't have to mprotect, we will be called for all unshadows.
	 * SIE will detect if protection applies and trigger a validity.
	 */
	if (rc)
		prefix_unmapped(vsie_page);
	if (rc > 0 || rc == -EFAULT)
		rc = set_validity_icpt(scb_s, 0x0037U);
	return rc;
}

/*
 * Pin the guest page given by gpa and set hpa to the pinned host address.
 * Will always be pinned writable.
 *
 * Returns: - 0 on success
 *          - -EINVAL if the gpa is not valid guest storage
 */
static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa)
{
	struct page *page;

	page = gfn_to_page(kvm, gpa_to_gfn(gpa));
	if (is_error_page(page))
		return -EINVAL;
	*hpa = (hpa_t)page_to_phys(page) + (gpa & ~PAGE_MASK);
	return 0;
}

/* Unpins a page previously pinned via pin_guest_page, marking it as dirty. */
static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
{
	kvm_release_pfn_dirty(hpa >> PAGE_SHIFT);
	/* mark the page always as dirty for migration */
	mark_page_dirty(kvm, gpa_to_gfn(gpa));
}

/* unpin all blocks previously pinned by pin_blocks(), marking them dirty */
static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	hpa_t hpa;

	hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol;
	if (hpa) {
		unpin_guest_page(vcpu->kvm, vsie_page->sca_gpa, hpa);
		vsie_page->sca_gpa = 0;
		scb_s->scaol = 0;
		scb_s->scaoh = 0;
	}

	hpa = scb_s->itdba;
	if (hpa) {
		unpin_guest_page(vcpu->kvm, vsie_page->itdba_gpa, hpa);
		vsie_page->itdba_gpa = 0;
		scb_s->itdba = 0;
	}

	hpa = scb_s->gvrd;
	if (hpa) {
		unpin_guest_page(vcpu->kvm, vsie_page->gvrd_gpa, hpa);
		vsie_page->gvrd_gpa = 0;
		scb_s->gvrd = 0;
	}

	hpa = scb_s->riccbd;
	if (hpa) {
		unpin_guest_page(vcpu->kvm, vsie_page->riccbd_gpa, hpa);
		vsie_page->riccbd_gpa = 0;
		scb_s->riccbd = 0;
	}

	hpa = scb_s->sdnxo;
	if (hpa) {
		unpin_guest_page(vcpu->kvm, vsie_page->sdnx_gpa, hpa);
		vsie_page->sdnx_gpa = 0;
		scb_s->sdnxo = 0;
	}
}

/*
 * Instead of shadowing some blocks, we can simply forward them because the
 * addresses in the scb are 64 bit long.
 *
 * This works as long as the data lies in one page. If blocks ever exceed one
 * page, we have to fall back to shadowing.
 *
 * As we reuse the sca, the vcpu pointers contained in it are invalid. We must
 * therefore not enable any facilities that access these pointers (e.g. SIGPIF).
 *
 * Returns: - 0 if all blocks were pinned.
 *          - > 0 if control has to be given to guest 2
 *          - -ENOMEM if out of memory
 */
static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	hpa_t hpa;
	gpa_t gpa;
	int rc = 0;

	gpa = READ_ONCE(scb_o->scaol) & ~0xfUL;
	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
		gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32;
	if (gpa) {
		if (gpa < 2 * PAGE_SIZE)
			rc = set_validity_icpt(scb_s, 0x0038U);
		else if ((gpa & ~0x1fffUL) == kvm_s390_get_prefix(vcpu))
			rc = set_validity_icpt(scb_s, 0x0011U);
		else if ((gpa & PAGE_MASK) !=
			 ((gpa + sizeof(struct bsca_block) - 1) & PAGE_MASK))
			rc = set_validity_icpt(scb_s, 0x003bU);
		if (!rc) {
			rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
			if (rc)
				rc = set_validity_icpt(scb_s, 0x0034U);
		}
		if (rc)
			goto unpin;
		vsie_page->sca_gpa = gpa;
		scb_s->scaoh = (u32)((u64)hpa >> 32);
		scb_s->scaol = (u32)(u64)hpa;
	}

	gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
	if (gpa && (scb_s->ecb & ECB_TE)) {
		if (gpa < 2 * PAGE_SIZE) {
			rc = set_validity_icpt(scb_s, 0x0080U);
			goto unpin;
		}
		/* 256 bytes cannot cross page boundaries */
		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
		if (rc) {
			rc = set_validity_icpt(scb_s, 0x0080U);
			goto unpin;
		}
		vsie_page->itdba_gpa = gpa;
		scb_s->itdba = hpa;
	}

	gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL;
	if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
		if (gpa < 2 * PAGE_SIZE) {
			rc = set_validity_icpt(scb_s, 0x1310U);
			goto unpin;
		}
		/*
		 * 512 bytes vector registers cannot cross page boundaries
		 * if this block gets bigger, we have to shadow it.
		 */
		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
		if (rc) {
			rc = set_validity_icpt(scb_s, 0x1310U);
			goto unpin;
		}
		vsie_page->gvrd_gpa = gpa;
		scb_s->gvrd = hpa;
	}

	gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL;
	if (gpa && (scb_s->ecb3 & ECB3_RI)) {
		if (gpa < 2 * PAGE_SIZE) {
			rc = set_validity_icpt(scb_s, 0x0043U);
			goto unpin;
		}
		/* 64 bytes cannot cross page boundaries */
		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
		if (rc) {
			rc = set_validity_icpt(scb_s, 0x0043U);
			goto unpin;
		}
		/* Validity 0x0044 will be checked by SIE */
		vsie_page->riccbd_gpa = gpa;
		scb_s->riccbd = hpa;
	}
	if (((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) ||
	    (scb_s->ecd & ECD_ETOKENF)) {
		unsigned long sdnxc;

		gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL;
		sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL;
		if (!gpa || gpa < 2 * PAGE_SIZE) {
			rc = set_validity_icpt(scb_s, 0x10b0U);
			goto unpin;
		}
		if (sdnxc < 6 || sdnxc > 12) {
			rc = set_validity_icpt(scb_s, 0x10b1U);
			goto unpin;
		}
		if (gpa & ((1 << sdnxc) - 1)) {
			rc = set_validity_icpt(scb_s, 0x10b2U);
			goto unpin;
		}
		/* Due to alignment rules (checked above) this cannot
		 * cross page boundaries
		 */
		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
		if (rc) {
			rc = set_validity_icpt(scb_s, 0x10b0U);
			goto unpin;
		}
		vsie_page->sdnx_gpa = gpa;
		scb_s->sdnxo = hpa | sdnxc;
	}
	return 0;
unpin:
	unpin_blocks(vcpu, vsie_page);
	return rc;
}

/* unpin the scb provided by guest 2, marking it as dirty */
static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
		      gpa_t gpa)
{
	hpa_t hpa = (hpa_t) vsie_page->scb_o;

	if (hpa)
		unpin_guest_page(vcpu->kvm, gpa, hpa);
	vsie_page->scb_o = NULL;
}

/*
 * Pin the scb at gpa provided by guest 2 at vsie_page->scb_o.
 *
 * Returns: - 0 if the scb was pinned.
 *          - > 0 if control has to be given to guest 2
 */
static int pin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
		   gpa_t gpa)
{
	hpa_t hpa;
	int rc;

	rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
	if (rc) {
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
		WARN_ON_ONCE(rc);
		return 1;
	}
	vsie_page->scb_o = phys_to_virt(hpa);
	return 0;
}

/*
 * Inject a fault into guest 2.
 *
 * Returns: - > 0 if control has to be given to guest 2
 *            < 0 if an error occurred during injection.
 */
static int inject_fault(struct kvm_vcpu *vcpu, __u16 code, __u64 vaddr,
			bool write_flag)
{
	struct kvm_s390_pgm_info pgm = {
		.code = code,
		.trans_exc_code =
			/* 0-51: virtual address */
			(vaddr & 0xfffffffffffff000UL) |
			/* 52-53: store / fetch */
			(((unsigned int) !write_flag) + 1) << 10,
			/* 62-63: asce id (always primary == 0) */
		.exc_access_id = 0, /* always primary */
		.op_access_id = 0, /* not MVPG */
	};
	int rc;

	if (code == PGM_PROTECTION)
		pgm.trans_exc_code |= 0x4UL;

	rc = kvm_s390_inject_prog_irq(vcpu, &pgm);
	return rc ? rc : 1;
}

/*
 * Handle a fault during vsie execution on a gmap shadow.
 *
 * Returns: - 0 if the fault was resolved
 *          - > 0 if control has to be given to guest 2
 *          - < 0 if an error occurred
 */
static int handle_fault(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	int rc;

	if (current->thread.gmap_int_code == PGM_PROTECTION)
		/* we can directly forward all protection exceptions */
		return inject_fault(vcpu, PGM_PROTECTION,
				    current->thread.gmap_addr, 1);

	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
				   current->thread.gmap_addr, NULL);
	if (rc > 0) {
		rc = inject_fault(vcpu, rc,
				  current->thread.gmap_addr,
				  current->thread.gmap_write_flag);
		if (rc >= 0)
			vsie_page->fault_addr = current->thread.gmap_addr;
	}
	return rc;
}

/*
 * Retry the previous fault that required guest 2 intervention. This avoids
 * one superfluous SIE re-entry and direct exit.
 *
 * Will ignore any errors. The next SIE fault will do proper fault handling.
 */
static void handle_last_fault(struct kvm_vcpu *vcpu,
			      struct vsie_page *vsie_page)
{
	if (vsie_page->fault_addr)
		kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
				      vsie_page->fault_addr, NULL);
	vsie_page->fault_addr = 0;
}

static inline void clear_vsie_icpt(struct vsie_page *vsie_page)
{
	vsie_page->scb_s.icptcode = 0;
}

/* rewind the psw and clear the vsie icpt, so we can retry execution */
static void retry_vsie_icpt(struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	int ilen = insn_length(scb_s->ipa >> 8);

	/* take care of EXECUTE instructions */
	if (scb_s->icptstatus & 1) {
		ilen = (scb_s->icptstatus >> 4) & 0x6;
		if (!ilen)
			ilen = 4;
	}
	scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, ilen);
	clear_vsie_icpt(vsie_page);
}

/*
 * Try to shadow + enable the guest 2 provided facility list.
 * Retry instruction execution if enabled for and provided by guest 2.
 *
 * Returns: - 0 if handled (retry or guest 2 icpt)
 *          - > 0 if control has to be given to guest 2
 */
static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	__u32 fac = READ_ONCE(vsie_page->scb_o->fac);

	/*
	 * Alternate-STFLE-Interpretive-Execution facilities are not supported
	 * -> format-0 flcb
	 */
	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
		retry_vsie_icpt(vsie_page);
		/*
		 * The facility list origin (FLO) is in bits 1 - 28 of the FLD
		 * so we need to mask here before reading.
		 */
		fac = fac & 0x7ffffff8U;
		/*
		 * format-0 -> size of nested guest's facility list == guest's size
		 * guest's size == host's size, since STFLE is interpretatively executed
		 * using a format-0 for the guest, too.
		 */
		if (read_guest_real(vcpu, fac, &vsie_page->fac,
				    stfle_size() * sizeof(u64)))
			return set_validity_icpt(scb_s, 0x1090U);
		scb_s->fac = (__u32)(__u64) &vsie_page->fac;
	}
	return 0;
}

/*
 * Get a register for a nested guest.
 * @vcpu the vcpu of the guest
 * @vsie_page the vsie_page for the nested guest
 * @reg the register number, the upper 4 bits are ignored.
 * returns: the value of the register.
 */
static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, u8 reg)
{
	/* no need to validate the parameter and/or perform error handling */
	reg &= 0xf;
	switch (reg) {
	case 15:
		return vsie_page->scb_s.gg15;
	case 14:
		return vsie_page->scb_s.gg14;
	default:
		return vcpu->run->s.regs.gprs[reg];
	}
}

static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	unsigned long pei_dest, pei_src, src, dest, mask, prefix;
	u64 *pei_block = &vsie_page->scb_o->mcic;
	int edat, rc_dest, rc_src;
	union ctlreg0 cr0;

	cr0.val = vcpu->arch.sie_block->gcr[0];
	edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8);
	mask = _kvm_s390_logical_to_effective(&scb_s->gpsw, PAGE_MASK);
	prefix = scb_s->prefix << GUEST_PREFIX_SHIFT;

	dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & mask;
	dest = _kvm_s390_real_to_abs(prefix, dest) + scb_s->mso;
	src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) & mask;
	src = _kvm_s390_real_to_abs(prefix, src) + scb_s->mso;

	rc_dest = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, &pei_dest);
	rc_src = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, &pei_src);
	/*
	 * Either everything went well, or something non-critical went wrong
	 * e.g. because of a race. In either case, simply retry.
	 */
	if (rc_dest == -EAGAIN || rc_src == -EAGAIN || (!rc_dest && !rc_src)) {
		retry_vsie_icpt(vsie_page);
		return -EAGAIN;
	}
	/* Something more serious went wrong, propagate the error */
	if (rc_dest < 0)
		return rc_dest;
	if (rc_src < 0)
		return rc_src;

	/* The only possible suppressing exception: just deliver it */
	if (rc_dest == PGM_TRANSLATION_SPEC || rc_src == PGM_TRANSLATION_SPEC) {
		clear_vsie_icpt(vsie_page);
		rc_dest = kvm_s390_inject_program_int(vcpu, PGM_TRANSLATION_SPEC);
		WARN_ON_ONCE(rc_dest);
		return 1;
	}

	/*
	 * Forward the PEI intercept to the guest if it was a page fault, or
	 * also for segment and region table faults if EDAT applies.
	 */
	if (edat) {
		rc_dest = rc_dest == PGM_ASCE_TYPE ? rc_dest : 0;
		rc_src = rc_src == PGM_ASCE_TYPE ? rc_src : 0;
	} else {
		rc_dest = rc_dest != PGM_PAGE_TRANSLATION ? rc_dest : 0;
		rc_src = rc_src != PGM_PAGE_TRANSLATION ? rc_src : 0;
	}
	if (!rc_dest && !rc_src) {
		pei_block[0] = pei_dest;
		pei_block[1] = pei_src;
		return 1;
	}

	retry_vsie_icpt(vsie_page);

	/*
	 * The host has edat, and the guest does not, or it was an ASCE type
	 * exception. The host needs to inject the appropriate DAT interrupts
	 * into the guest.
	 */
	if (rc_dest)
		return inject_fault(vcpu, rc_dest, dest, 1);
	return inject_fault(vcpu, rc_src, src, 0);
}

/*
 * Run the vsie on a shadow scb and a shadow gmap, without any further
 * sanity checks, handling SIE faults.
 *
 * Returns: - 0 everything went fine
 *          - > 0 if control has to be given to guest 2
 *          - < 0 if an error occurred
 */
static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
	__releases(vcpu->kvm->srcu)
	__acquires(vcpu->kvm->srcu)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
	int guest_bp_isolation;
	int rc = 0;

	handle_last_fault(vcpu, vsie_page);

	kvm_vcpu_srcu_read_unlock(vcpu);

	/* save current guest state of bp isolation override */
	guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST);

	/*
	 * The guest is running with BPBC, so we have to force it on for our
	 * nested guest. This is done by enabling BPBC globally, so the BPBC
	 * control in the SCB (which the nested guest can modify) is simply
	 * ignored.
	 */
	if (test_kvm_facility(vcpu->kvm, 82) &&
	    vcpu->arch.sie_block->fpf & FPF_BPBC)
		set_thread_flag(TIF_ISOLATE_BP_GUEST);

	local_irq_disable();
	guest_enter_irqoff();
	local_irq_enable();

	/*
	 * Simulate a SIE entry of the VCPU (see sie64a), so VCPU blocking
	 * and VCPU requests also hinder the vSIE from running and lead
	 * to an immediate exit. kvm_s390_vsie_kick() has to be used to
	 * also kick the vSIE.
	 */
	vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
	barrier();
	if (test_cpu_flag(CIF_FPU))
		load_fpu_regs();
	if (!kvm_s390_vcpu_sie_inhibited(vcpu))
		rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
	barrier();
	vcpu->arch.sie_block->prog0c &= ~PROG_IN_SIE;

	local_irq_disable();
	guest_exit_irqoff();
	local_irq_enable();

	/* restore guest state for bp isolation override */
	if (!guest_bp_isolation)
		clear_thread_flag(TIF_ISOLATE_BP_GUEST);

	kvm_vcpu_srcu_read_lock(vcpu);

	if (rc == -EINTR) {
		VCPU_EVENT(vcpu, 3, "%s", "machine check");
		kvm_s390_reinject_machine_check(vcpu, &vsie_page->mcck_info);
		return 0;
	}

	if (rc > 0)
		rc = 0; /* we could still have an icpt */
	else if (rc == -EFAULT)
		return handle_fault(vcpu, vsie_page);

	switch (scb_s->icptcode) {
	case ICPT_INST:
		if (scb_s->ipa == 0xb2b0)
			rc = handle_stfle(vcpu, vsie_page);
		break;
	case ICPT_STOP:
		/* stop not requested by g2 - must have been a kick */
		if (!(atomic_read(&scb_o->cpuflags) & CPUSTAT_STOP_INT))
			clear_vsie_icpt(vsie_page);
		break;
	case ICPT_VALIDITY:
		if ((scb_s->ipa & 0xf000) != 0xf000)
			scb_s->ipa += 0x1000;
		break;
	case ICPT_PARTEXEC:
		if (scb_s->ipa == 0xb254)
			rc = vsie_handle_mvpg(vcpu, vsie_page);
		break;
	}
	return rc;
}

static void release_gmap_shadow(struct vsie_page *vsie_page)
{
	if (vsie_page->gmap)
		gmap_put(vsie_page->gmap);
	WRITE_ONCE(vsie_page->gmap, NULL);
	prefix_unmapped(vsie_page);
}

static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
			       struct vsie_page *vsie_page)
{
	unsigned long asce;
	union ctlreg0 cr0;
	struct gmap *gmap;
	int edat;

	asce = vcpu->arch.sie_block->gcr[1];
	cr0.val = vcpu->arch.sie_block->gcr[0];
	edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8);
	edat += edat && test_kvm_facility(vcpu->kvm, 78);

	/*
	 * ASCE or EDAT could have changed since last icpt, or the gmap
	 * we're holding has been unshadowed. If the gmap is still valid,
	 * we can safely reuse it.
	 */
	if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) {
		vcpu->kvm->stat.gmap_shadow_reuse++;
		return 0;
	}

	/* release the old shadow - if any, and mark the prefix as unmapped */
	release_gmap_shadow(vsie_page);
	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
	if (IS_ERR(gmap))
		return PTR_ERR(gmap);
	gmap->private = vcpu->kvm;
	vcpu->kvm->stat.gmap_shadow_create++;
	WRITE_ONCE(vsie_page->gmap, gmap);
	return 0;
}

/*
 * Register the shadow scb at the VCPU, e.g. for kicking out of vsie.
 */
static void register_shadow_scb(struct kvm_vcpu *vcpu,
				struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;

	WRITE_ONCE(vcpu->arch.vsie_block, &vsie_page->scb_s);
	/*
	 * External calls have to lead to a kick of the vcpu and
	 * therefore the vsie -> Simulate Wait state.
	 */
	kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
	/*
	 * We have to adjust the g3 epoch by the g2 epoch. The epoch will
	 * automatically be adjusted on tod clock changes via kvm_sync_clock.
	 */
	preempt_disable();
	scb_s->epoch += vcpu->kvm->arch.epoch;

	if (scb_s->ecd & ECD_MEF) {
		scb_s->epdx += vcpu->kvm->arch.epdx;
		if (scb_s->epoch < vcpu->kvm->arch.epoch)
			scb_s->epdx += 1;
	}

	preempt_enable();
}

/*
 * Unregister a shadow scb from a VCPU.
 */
static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
{
	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
	WRITE_ONCE(vcpu->arch.vsie_block, NULL);
}

/*
 * Run the vsie on a shadowed scb, managing the gmap shadow, handling
 * prefix pages and faults.
 *
 * Returns: - 0 if no errors occurred
 *          - > 0 if control has to be given to guest 2
 *          - -ENOMEM if out of memory
 */
static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
	int rc = 0;

	while (1) {
		rc = acquire_gmap_shadow(vcpu, vsie_page);
		if (!rc)
			rc = map_prefix(vcpu, vsie_page);
		if (!rc) {
			gmap_enable(vsie_page->gmap);
			update_intervention_requests(vsie_page);
			rc = do_vsie_run(vcpu, vsie_page);
			gmap_enable(vcpu->arch.gmap);
		}
		atomic_andnot(PROG_BLOCK_SIE, &scb_s->prog20);

		if (rc == -EAGAIN)
			rc = 0;
		if (rc || scb_s->icptcode || signal_pending(current) ||
		    kvm_s390_vcpu_has_irq(vcpu, 0) ||
		    kvm_s390_vcpu_sie_inhibited(vcpu))
			break;
		cond_resched();
	}

	if (rc == -EFAULT) {
		/*
		 * Addressing exceptions are always presentes as intercepts.
		 * As addressing exceptions are suppressing and our guest 3 PSW
		 * points at the responsible instruction, we have to
		 * forward the PSW and set the ilc. If we can't read guest 3
		 * instruction, we can use an arbitrary ilc. Let's always use
		 * ilen = 4 for now, so we can avoid reading in guest 3 virtual
		 * memory. (we could also fake the shadow so the hardware
		 * handles it).
		 */
		scb_s->icptcode = ICPT_PROGI;
		scb_s->iprcc = PGM_ADDRESSING;
		scb_s->pgmilc = 4;
		scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
		rc = 1;
	}
	return rc;
}

/*
 * Get or create a vsie page for a scb address.
 *
 * Returns: - address of a vsie page (cached or new one)
 *          - NULL if the same scb address is already used by another VCPU
 *          - ERR_PTR(-ENOMEM) if out of memory
 */
static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
{
	struct vsie_page *vsie_page;
	struct page *page;
	int nr_vcpus;

	rcu_read_lock();
	page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
	rcu_read_unlock();
	if (page) {
		if (page_ref_inc_return(page) == 2)
			return page_to_virt(page);
		page_ref_dec(page);
	}

	/*
	 * We want at least #online_vcpus shadows, so every VCPU can execute
	 * the VSIE in parallel.
	 */
	nr_vcpus = atomic_read(&kvm->online_vcpus);

	mutex_lock(&kvm->arch.vsie.mutex);
	if (kvm->arch.vsie.page_count < nr_vcpus) {
		page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
		if (!page) {
			mutex_unlock(&kvm->arch.vsie.mutex);
			return ERR_PTR(-ENOMEM);
		}
		page_ref_inc(page);
		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
		kvm->arch.vsie.page_count++;
	} else {
		/* reuse an existing entry that belongs to nobody */
		while (true) {
			page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
			if (page_ref_inc_return(page) == 2)
				break;
			page_ref_dec(page);
			kvm->arch.vsie.next++;
			kvm->arch.vsie.next %= nr_vcpus;
		}
		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
	}
	page->index = addr;
	/* double use of the same address */
	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
		page_ref_dec(page);
		mutex_unlock(&kvm->arch.vsie.mutex);
		return NULL;
	}
	mutex_unlock(&kvm->arch.vsie.mutex);

	vsie_page = page_to_virt(page);
	memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block));
	release_gmap_shadow(vsie_page);
	vsie_page->fault_addr = 0;
	vsie_page->scb_s.ihcpu = 0xffffU;
	return vsie_page;
}

/* put a vsie page acquired via get_vsie_page */
static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page)
{
	struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT);

	page_ref_dec(page);
}

int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
{
	struct vsie_page *vsie_page;
	unsigned long scb_addr;
	int rc;

	vcpu->stat.instruction_sie++;
	if (!test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIEF2))
		return -EOPNOTSUPP;
	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);

	BUILD_BUG_ON(sizeof(struct vsie_page) != PAGE_SIZE);
	scb_addr = kvm_s390_get_base_disp_s(vcpu, NULL);

	/* 512 byte alignment */
	if (unlikely(scb_addr & 0x1ffUL))
		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);

	if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) ||
	    kvm_s390_vcpu_sie_inhibited(vcpu))
		return 0;

	vsie_page = get_vsie_page(vcpu->kvm, scb_addr);
	if (IS_ERR(vsie_page))
		return PTR_ERR(vsie_page);
	else if (!vsie_page)
		/* double use of sie control block - simply do nothing */
		return 0;

	rc = pin_scb(vcpu, vsie_page, scb_addr);
	if (rc)
		goto out_put;
	rc = shadow_scb(vcpu, vsie_page);
	if (rc)
		goto out_unpin_scb;
	rc = pin_blocks(vcpu, vsie_page);
	if (rc)
		goto out_unshadow;
	register_shadow_scb(vcpu, vsie_page);
	rc = vsie_run(vcpu, vsie_page);
	unregister_shadow_scb(vcpu);
	unpin_blocks(vcpu, vsie_page);
out_unshadow:
	unshadow_scb(vcpu, vsie_page);
out_unpin_scb:
	unpin_scb(vcpu, vsie_page, scb_addr);
out_put:
	put_vsie_page(vcpu->kvm, vsie_page);

	return rc < 0 ? rc : 0;
}

/* Init the vsie data structures. To be called when a vm is initialized. */
void kvm_s390_vsie_init(struct kvm *kvm)
{
	mutex_init(&kvm->arch.vsie.mutex);
	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL_ACCOUNT);
}

/* Destroy the vsie data structures. To be called when a vm is destroyed. */
void kvm_s390_vsie_destroy(struct kvm *kvm)
{
	struct vsie_page *vsie_page;
	struct page *page;
	int i;

	mutex_lock(&kvm->arch.vsie.mutex);
	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
		page = kvm->arch.vsie.pages[i];
		kvm->arch.vsie.pages[i] = NULL;
		vsie_page = page_to_virt(page);
		release_gmap_shadow(vsie_page);
		/* free the radix tree entry */
		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
		__free_page(page);
	}
	kvm->arch.vsie.page_count = 0;
	mutex_unlock(&kvm->arch.vsie.mutex);
}

void kvm_s390_vsie_kick(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_sie_block *scb = READ_ONCE(vcpu->arch.vsie_block);

	/*
	 * Even if the VCPU lets go of the shadow sie block reference, it is
	 * still valid in the cache. So we can safely kick it.
	 */
	if (scb) {
		atomic_or(PROG_BLOCK_SIE, &scb->prog20);
		if (scb->prog0c & PROG_IN_SIE)
			atomic_or(CPUSTAT_STOP_INT, &scb->cpuflags);
	}
}