summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/e500_tlb.c
blob: 6e53e4164de195583a138c7de853f89a94746c97 (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
/*
 * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
 *
 * Author: Yu Liu, yu.liu@freescale.com
 *
 * Description:
 * This file is based on arch/powerpc/kvm/44x_tlb.c,
 * by Hollis Blanchard <hollisb@us.ibm.com>.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/log2.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/rwsem.h>
#include <linux/vmalloc.h>
#include <linux/hugetlb.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_e500.h>

#include "../mm/mmu_decl.h"
#include "e500_tlb.h"
#include "trace.h"
#include "timing.h"

#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)

struct id {
	unsigned long val;
	struct id **pentry;
};

#define NUM_TIDS 256

/*
 * This table provide mappings from:
 * (guestAS,guestTID,guestPR) --> ID of physical cpu
 * guestAS	[0..1]
 * guestTID	[0..255]
 * guestPR	[0..1]
 * ID		[1..255]
 * Each vcpu keeps one vcpu_id_table.
 */
struct vcpu_id_table {
	struct id id[2][NUM_TIDS][2];
};

/*
 * This table provide reversed mappings of vcpu_id_table:
 * ID --> address of vcpu_id_table item.
 * Each physical core has one pcpu_id_table.
 */
struct pcpu_id_table {
	struct id *entry[NUM_TIDS];
};

static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);

/* This variable keeps last used shadow ID on local core.
 * The valid range of shadow ID is [1..255] */
static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);

static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];

static struct kvm_book3e_206_tlb_entry *get_entry(
	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
{
	int offset = vcpu_e500->gtlb_offset[tlbsel];
	return &vcpu_e500->gtlb_arch[offset + entry];
}

/*
 * Allocate a free shadow id and setup a valid sid mapping in given entry.
 * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
 *
 * The caller must have preemption disabled, and keep it that way until
 * it has finished with the returned shadow id (either written into the
 * TLB or arch.shadow_pid, or discarded).
 */
static inline int local_sid_setup_one(struct id *entry)
{
	unsigned long sid;
	int ret = -1;

	sid = ++(__get_cpu_var(pcpu_last_used_sid));
	if (sid < NUM_TIDS) {
		__get_cpu_var(pcpu_sids).entry[sid] = entry;
		entry->val = sid;
		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
		ret = sid;
	}

	/*
	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
	 * the caller will invalidate everything and start over.
	 *
	 * sid > NUM_TIDS indicates a race, which we disable preemption to
	 * avoid.
	 */
	WARN_ON(sid > NUM_TIDS);

	return ret;
}

/*
 * Check if given entry contain a valid shadow id mapping.
 * An ID mapping is considered valid only if
 * both vcpu and pcpu know this mapping.
 *
 * The caller must have preemption disabled, and keep it that way until
 * it has finished with the returned shadow id (either written into the
 * TLB or arch.shadow_pid, or discarded).
 */
static inline int local_sid_lookup(struct id *entry)
{
	if (entry && entry->val != 0 &&
	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
		return entry->val;
	return -1;
}

/* Invalidate all id mappings on local core -- call with preempt disabled */
static inline void local_sid_destroy_all(void)
{
	__get_cpu_var(pcpu_last_used_sid) = 0;
	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
}

static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
	return vcpu_e500->idt;
}

static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	kfree(vcpu_e500->idt);
}

/* Invalidate all mappings on vcpu */
static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));

	/* Update shadow pid when mappings are changed */
	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
}

/* Invalidate one ID mapping on vcpu */
static inline void kvmppc_e500_id_table_reset_one(
			       struct kvmppc_vcpu_e500 *vcpu_e500,
			       int as, int pid, int pr)
{
	struct vcpu_id_table *idt = vcpu_e500->idt;

	BUG_ON(as >= 2);
	BUG_ON(pid >= NUM_TIDS);
	BUG_ON(pr >= 2);

	idt->id[as][pid][pr].val = 0;
	idt->id[as][pid][pr].pentry = NULL;

	/* Update shadow pid when mappings are changed */
	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
}

/*
 * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
 * This function first lookup if a valid mapping exists,
 * if not, then creates a new one.
 *
 * The caller must have preemption disabled, and keep it that way until
 * it has finished with the returned shadow id (either written into the
 * TLB or arch.shadow_pid, or discarded).
 */
static unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
					unsigned int as, unsigned int gid,
					unsigned int pr, int avoid_recursion)
{
	struct vcpu_id_table *idt = vcpu_e500->idt;
	int sid;

	BUG_ON(as >= 2);
	BUG_ON(gid >= NUM_TIDS);
	BUG_ON(pr >= 2);

	sid = local_sid_lookup(&idt->id[as][gid][pr]);

	while (sid <= 0) {
		/* No mapping yet */
		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
		if (sid <= 0) {
			_tlbil_all();
			local_sid_destroy_all();
		}

		/* Update shadow pid when mappings are changed */
		if (!avoid_recursion)
			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
	}

	return sid;
}

/* Map guest pid to shadow.
 * We use PID to keep shadow of current guest non-zero PID,
 * and use PID1 to keep shadow of guest zero PID.
 * So that guest tlbe with TID=0 can be accessed at any time */
void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	preempt_disable();
	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
			get_cur_as(&vcpu_e500->vcpu),
			get_cur_pid(&vcpu_e500->vcpu),
			get_cur_pr(&vcpu_e500->vcpu), 1);
	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
			get_cur_as(&vcpu_e500->vcpu), 0,
			get_cur_pr(&vcpu_e500->vcpu), 1);
	preempt_enable();
}

static inline unsigned int gtlb0_get_next_victim(
		struct kvmppc_vcpu_e500 *vcpu_e500)
{
	unsigned int victim;

	victim = vcpu_e500->gtlb_nv[0]++;
	if (unlikely(vcpu_e500->gtlb_nv[0] >= vcpu_e500->gtlb_params[0].ways))
		vcpu_e500->gtlb_nv[0] = 0;

	return victim;
}

static inline unsigned int tlb1_max_shadow_size(void)
{
	/* reserve one entry for magic page */
	return host_tlb_params[1].entries - tlbcam_index - 1;
}

static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
{
	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
}

static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
{
	/* Mask off reserved bits. */
	mas3 &= MAS3_ATTRIB_MASK;

	if (!usermode) {
		/* Guest is in supervisor mode,
		 * so we need to translate guest
		 * supervisor permissions into user permissions. */
		mas3 &= ~E500_TLB_USER_PERM_MASK;
		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
	}

	return mas3 | E500_TLB_SUPER_PERM_MASK;
}

static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
{
#ifdef CONFIG_SMP
	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
#else
	return mas2 & MAS2_ATTRIB_MASK;
#endif
}

/*
 * writing shadow tlb entry to host TLB
 */
static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
				     uint32_t mas0)
{
	unsigned long flags;

	local_irq_save(flags);
	mtspr(SPRN_MAS0, mas0);
	mtspr(SPRN_MAS1, stlbe->mas1);
	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
	asm volatile("isync; tlbwe" : : : "memory");
	local_irq_restore(flags);

	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
	                              stlbe->mas2, stlbe->mas7_3);
}

/*
 * Acquire a mas0 with victim hint, as if we just took a TLB miss.
 *
 * We don't care about the address we're searching for, other than that it's
 * in the right set and is not present in the TLB.  Using a zero PID and a
 * userspace address means we don't have to set and then restore MAS5, or
 * calculate a proper MAS6 value.
 */
static u32 get_host_mas0(unsigned long eaddr)
{
	unsigned long flags;
	u32 mas0;

	local_irq_save(flags);
	mtspr(SPRN_MAS6, 0);
	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
	mas0 = mfspr(SPRN_MAS0);
	local_irq_restore(flags);

	return mas0;
}

/* sesel is for tlb1 only */
static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
{
	u32 mas0;

	if (tlbsel == 0) {
		mas0 = get_host_mas0(stlbe->mas2);
		__write_host_tlbe(stlbe, mas0);
	} else {
		__write_host_tlbe(stlbe,
				  MAS0_TLBSEL(1) |
				  MAS0_ESEL(to_htlb1_esel(sesel)));
	}
}

void kvmppc_map_magic(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct kvm_book3e_206_tlb_entry magic;
	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
	unsigned int stid;
	pfn_t pfn;

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

	preempt_disable();
	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);

	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
	magic.mas8 = 0;

	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
	preempt_enable();
}

void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);

	/* Shadow PID may be expired on local core */
	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
}

void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
{
}

static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
				int tlbsel, int esel)
{
	struct kvm_book3e_206_tlb_entry *gtlbe =
		get_entry(vcpu_e500, tlbsel, esel);
	struct vcpu_id_table *idt = vcpu_e500->idt;
	unsigned int pr, tid, ts, pid;
	u32 val, eaddr;
	unsigned long flags;

	ts = get_tlb_ts(gtlbe);
	tid = get_tlb_tid(gtlbe);

	preempt_disable();

	/* One guest ID may be mapped to two shadow IDs */
	for (pr = 0; pr < 2; pr++) {
		/*
		 * The shadow PID can have a valid mapping on at most one
		 * host CPU.  In the common case, it will be valid on this
		 * CPU, in which case (for TLB0) we do a local invalidation
		 * of the specific address.
		 *
		 * If the shadow PID is not valid on the current host CPU, or
		 * if we're invalidating a TLB1 entry, we invalidate the
		 * entire shadow PID.
		 */
		if (tlbsel == 1 ||
		    (pid = local_sid_lookup(&idt->id[ts][tid][pr])) <= 0) {
			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
			continue;
		}

		/*
		 * The guest is invalidating a TLB0 entry which is in a PID
		 * that has a valid shadow mapping on this host CPU.  We
		 * search host TLB0 to invalidate it's shadow TLB entry,
		 * similar to __tlbil_va except that we need to look in AS1.
		 */
		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
		eaddr = get_tlb_eaddr(gtlbe);

		local_irq_save(flags);

		mtspr(SPRN_MAS6, val);
		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
		val = mfspr(SPRN_MAS1);
		if (val & MAS1_VALID) {
			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
			asm volatile("tlbwe");
		}

		local_irq_restore(flags);
	}

	preempt_enable();
}

static int tlb0_set_base(gva_t addr, int sets, int ways)
{
	int set_base;

	set_base = (addr >> PAGE_SHIFT) & (sets - 1);
	set_base *= ways;

	return set_base;
}

static int gtlb0_set_base(struct kvmppc_vcpu_e500 *vcpu_e500, gva_t addr)
{
	return tlb0_set_base(addr, vcpu_e500->gtlb_params[0].sets,
			     vcpu_e500->gtlb_params[0].ways);
}

static unsigned int get_tlb_esel(struct kvm_vcpu *vcpu, int tlbsel)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	int esel = get_tlb_esel_bit(vcpu);

	if (tlbsel == 0) {
		esel &= vcpu_e500->gtlb_params[0].ways - 1;
		esel += gtlb0_set_base(vcpu_e500, vcpu->arch.shared->mas2);
	} else {
		esel &= vcpu_e500->gtlb_params[tlbsel].entries - 1;
	}

	return esel;
}

/* Search the guest TLB for a matching entry. */
static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
		gva_t eaddr, int tlbsel, unsigned int pid, int as)
{
	int size = vcpu_e500->gtlb_params[tlbsel].entries;
	unsigned int set_base, offset;
	int i;

	if (tlbsel == 0) {
		set_base = gtlb0_set_base(vcpu_e500, eaddr);
		size = vcpu_e500->gtlb_params[0].ways;
	} else {
		set_base = 0;
	}

	offset = vcpu_e500->gtlb_offset[tlbsel];

	for (i = 0; i < size; i++) {
		struct kvm_book3e_206_tlb_entry *tlbe =
			&vcpu_e500->gtlb_arch[offset + set_base + i];
		unsigned int tid;

		if (eaddr < get_tlb_eaddr(tlbe))
			continue;

		if (eaddr > get_tlb_end(tlbe))
			continue;

		tid = get_tlb_tid(tlbe);
		if (tid && (tid != pid))
			continue;

		if (!get_tlb_v(tlbe))
			continue;

		if (get_tlb_ts(tlbe) != as && as != -1)
			continue;

		return set_base + i;
	}

	return -1;
}

static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
					 struct kvm_book3e_206_tlb_entry *gtlbe,
					 pfn_t pfn)
{
	ref->pfn = pfn;
	ref->flags = E500_TLB_VALID;

	if (tlbe_is_writable(gtlbe))
		ref->flags |= E500_TLB_DIRTY;
}

static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
{
	if (ref->flags & E500_TLB_VALID) {
		if (ref->flags & E500_TLB_DIRTY)
			kvm_release_pfn_dirty(ref->pfn);
		else
			kvm_release_pfn_clean(ref->pfn);

		ref->flags = 0;
	}
}

static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	int tlbsel = 0;
	int i;

	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
		struct tlbe_ref *ref =
			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
		kvmppc_e500_ref_release(ref);
	}
}

static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	int stlbsel = 1;
	int i;

	kvmppc_e500_id_table_reset_all(vcpu_e500);

	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
		struct tlbe_ref *ref =
			&vcpu_e500->tlb_refs[stlbsel][i];
		kvmppc_e500_ref_release(ref);
	}

	clear_tlb_privs(vcpu_e500);
}

static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
		unsigned int eaddr, int as)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	unsigned int victim, pidsel, tsized;
	int tlbsel;

	/* since we only have two TLBs, only lower bit is used. */
	tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
	victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
	pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
	tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;

	vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
		| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
	vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
		| MAS1_TID(vcpu_e500->pid[pidsel])
		| MAS1_TSIZE(tsized);
	vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
		| (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
	vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
	vcpu->arch.shared->mas6 = (vcpu->arch.shared->mas6 & MAS6_SPID1)
		| (get_cur_pid(vcpu) << 16)
		| (as ? MAS6_SAS : 0);
}

/* TID must be supplied by the caller */
static inline void kvmppc_e500_setup_stlbe(
	struct kvmppc_vcpu_e500 *vcpu_e500,
	struct kvm_book3e_206_tlb_entry *gtlbe,
	int tsize, struct tlbe_ref *ref, u64 gvaddr,
	struct kvm_book3e_206_tlb_entry *stlbe)
{
	pfn_t pfn = ref->pfn;

	BUG_ON(!(ref->flags & E500_TLB_VALID));

	/* Force TS=1 IPROT=0 for all guest mappings. */
	stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
	stlbe->mas2 = (gvaddr & MAS2_EPN)
		| e500_shadow_mas2_attrib(gtlbe->mas2,
				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
		| e500_shadow_mas3_attrib(gtlbe->mas7_3,
				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
}

static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
	struct tlbe_ref *ref)
{
	struct kvm_memory_slot *slot;
	unsigned long pfn, hva;
	int pfnmap = 0;
	int tsize = BOOK3E_PAGESZ_4K;

	/*
	 * Translate guest physical to true physical, acquiring
	 * a page reference if it is normal, non-reserved memory.
	 *
	 * gfn_to_memslot() must succeed because otherwise we wouldn't
	 * have gotten this far.  Eventually we should just pass the slot
	 * pointer through from the first lookup.
	 */
	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
	hva = gfn_to_hva_memslot(slot, gfn);

	if (tlbsel == 1) {
		struct vm_area_struct *vma;
		down_read(&current->mm->mmap_sem);

		vma = find_vma(current->mm, hva);
		if (vma && hva >= vma->vm_start &&
		    (vma->vm_flags & VM_PFNMAP)) {
			/*
			 * This VMA is a physically contiguous region (e.g.
			 * /dev/mem) that bypasses normal Linux page
			 * management.  Find the overlap between the
			 * vma and the memslot.
			 */

			unsigned long start, end;
			unsigned long slot_start, slot_end;

			pfnmap = 1;

			start = vma->vm_pgoff;
			end = start +
			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);

			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);

			slot_start = pfn - (gfn - slot->base_gfn);
			slot_end = slot_start + slot->npages;

			if (start < slot_start)
				start = slot_start;
			if (end > slot_end)
				end = slot_end;

			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
				MAS1_TSIZE_SHIFT;

			/*
			 * e500 doesn't implement the lowest tsize bit,
			 * or 1K pages.
			 */
			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);

			/*
			 * Now find the largest tsize (up to what the guest
			 * requested) that will cover gfn, stay within the
			 * range, and for which gfn and pfn are mutually
			 * aligned.
			 */

			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
				unsigned long gfn_start, gfn_end, tsize_pages;
				tsize_pages = 1 << (tsize - 2);

				gfn_start = gfn & ~(tsize_pages - 1);
				gfn_end = gfn_start + tsize_pages;

				if (gfn_start + pfn - gfn < start)
					continue;
				if (gfn_end + pfn - gfn > end)
					continue;
				if ((gfn & (tsize_pages - 1)) !=
				    (pfn & (tsize_pages - 1)))
					continue;

				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
				pfn &= ~(tsize_pages - 1);
				break;
			}
		} else if (vma && hva >= vma->vm_start &&
			   (vma->vm_flags & VM_HUGETLB)) {
			unsigned long psize = vma_kernel_pagesize(vma);

			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
				MAS1_TSIZE_SHIFT;

			/*
			 * Take the largest page size that satisfies both host
			 * and guest mapping
			 */
			tsize = min(__ilog2(psize) - 10, tsize);

			/*
			 * e500 doesn't implement the lowest tsize bit,
			 * or 1K pages.
			 */
			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
		}

		up_read(&current->mm->mmap_sem);
	}

	if (likely(!pfnmap)) {
		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
		pfn = gfn_to_pfn_memslot(vcpu_e500->vcpu.kvm, slot, gfn);
		if (is_error_pfn(pfn)) {
			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
					(long)gfn);
			kvm_release_pfn_clean(pfn);
			return;
		}

		/* Align guest and physical address to page map boundaries */
		pfn &= ~(tsize_pages - 1);
		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
	}

	/* Drop old ref and setup new one. */
	kvmppc_e500_ref_release(ref);
	kvmppc_e500_ref_setup(ref, gtlbe, pfn);

	kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
}

/* XXX only map the one-one case, for now use TLB0 */
static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
				 int esel,
				 struct kvm_book3e_206_tlb_entry *stlbe)
{
	struct kvm_book3e_206_tlb_entry *gtlbe;
	struct tlbe_ref *ref;

	gtlbe = get_entry(vcpu_e500, 0, esel);
	ref = &vcpu_e500->gtlb_priv[0][esel].ref;

	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
			gtlbe, 0, stlbe, ref);
}

/* Caller must ensure that the specified guest TLB entry is safe to insert into
 * the shadow TLB. */
/* XXX for both one-one and one-to-many , for now use TLB1 */
static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
		struct kvm_book3e_206_tlb_entry *stlbe)
{
	struct tlbe_ref *ref;
	unsigned int victim;

	victim = vcpu_e500->host_tlb1_nv++;

	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
		vcpu_e500->host_tlb1_nv = 0;

	ref = &vcpu_e500->tlb_refs[1][victim];
	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);

	return victim;
}

void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);

	/* Recalc shadow pid since MSR changes */
	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
}

static inline int kvmppc_e500_gtlbe_invalidate(
				struct kvmppc_vcpu_e500 *vcpu_e500,
				int tlbsel, int esel)
{
	struct kvm_book3e_206_tlb_entry *gtlbe =
		get_entry(vcpu_e500, tlbsel, esel);

	if (unlikely(get_tlb_iprot(gtlbe)))
		return -1;

	gtlbe->mas1 = 0;

	return 0;
}

int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
{
	int esel;

	if (value & MMUCSR0_TLB0FI)
		for (esel = 0; esel < vcpu_e500->gtlb_params[0].entries; esel++)
			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 0, esel);
	if (value & MMUCSR0_TLB1FI)
		for (esel = 0; esel < vcpu_e500->gtlb_params[1].entries; esel++)
			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);

	/* Invalidate all vcpu id mappings */
	kvmppc_e500_id_table_reset_all(vcpu_e500);

	return EMULATE_DONE;
}

int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	unsigned int ia;
	int esel, tlbsel;
	gva_t ea;

	ea = ((ra) ? kvmppc_get_gpr(vcpu, ra) : 0) + kvmppc_get_gpr(vcpu, rb);

	ia = (ea >> 2) & 0x1;

	/* since we only have two TLBs, only lower bit is used. */
	tlbsel = (ea >> 3) & 0x1;

	if (ia) {
		/* invalidate all entries */
		for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries;
		     esel++)
			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
	} else {
		ea &= 0xfffff000;
		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel,
				get_cur_pid(vcpu), -1);
		if (esel >= 0)
			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
	}

	/* Invalidate all vcpu id mappings */
	kvmppc_e500_id_table_reset_all(vcpu_e500);

	return EMULATE_DONE;
}

int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	int tlbsel, esel;
	struct kvm_book3e_206_tlb_entry *gtlbe;

	tlbsel = get_tlb_tlbsel(vcpu);
	esel = get_tlb_esel(vcpu, tlbsel);

	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
	vcpu->arch.shared->mas0 &= ~MAS0_NV(~0);
	vcpu->arch.shared->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
	vcpu->arch.shared->mas1 = gtlbe->mas1;
	vcpu->arch.shared->mas2 = gtlbe->mas2;
	vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;

	return EMULATE_DONE;
}

int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	int as = !!get_cur_sas(vcpu);
	unsigned int pid = get_cur_spid(vcpu);
	int esel, tlbsel;
	struct kvm_book3e_206_tlb_entry *gtlbe = NULL;
	gva_t ea;

	ea = kvmppc_get_gpr(vcpu, rb);

	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
		if (esel >= 0) {
			gtlbe = get_entry(vcpu_e500, tlbsel, esel);
			break;
		}
	}

	if (gtlbe) {
		esel &= vcpu_e500->gtlb_params[tlbsel].ways - 1;

		vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
			| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
		vcpu->arch.shared->mas1 = gtlbe->mas1;
		vcpu->arch.shared->mas2 = gtlbe->mas2;
		vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;
	} else {
		int victim;

		/* since we only have two TLBs, only lower bit is used. */
		tlbsel = vcpu->arch.shared->mas4 >> 28 & 0x1;
		victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;

		vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel)
			| MAS0_ESEL(victim)
			| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
		vcpu->arch.shared->mas1 =
			  (vcpu->arch.shared->mas6 & MAS6_SPID0)
			| (vcpu->arch.shared->mas6 & (MAS6_SAS ? MAS1_TS : 0))
			| (vcpu->arch.shared->mas4 & MAS4_TSIZED(~0));
		vcpu->arch.shared->mas2 &= MAS2_EPN;
		vcpu->arch.shared->mas2 |= vcpu->arch.shared->mas4 &
					   MAS2_ATTRIB_MASK;
		vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 |
					     MAS3_U2 | MAS3_U3;
	}

	kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
	return EMULATE_DONE;
}

/* sesel is for tlb1 only */
static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
			struct kvm_book3e_206_tlb_entry *gtlbe,
			struct kvm_book3e_206_tlb_entry *stlbe,
			int stlbsel, int sesel)
{
	int stid;

	preempt_disable();
	stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
				   get_tlb_tid(gtlbe),
				   get_cur_pr(&vcpu_e500->vcpu), 0);

	stlbe->mas1 |= MAS1_TID(stid);
	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
	preempt_enable();
}

int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct kvm_book3e_206_tlb_entry *gtlbe;
	int tlbsel, esel;

	tlbsel = get_tlb_tlbsel(vcpu);
	esel = get_tlb_esel(vcpu, tlbsel);

	gtlbe = get_entry(vcpu_e500, tlbsel, esel);

	if (get_tlb_v(gtlbe))
		inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);

	gtlbe->mas1 = vcpu->arch.shared->mas1;
	gtlbe->mas2 = vcpu->arch.shared->mas2;
	gtlbe->mas7_3 = vcpu->arch.shared->mas7_3;

	trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,
	                              gtlbe->mas2, gtlbe->mas7_3);

	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
	if (tlbe_is_host_safe(vcpu, gtlbe)) {
		struct kvm_book3e_206_tlb_entry stlbe;
		int stlbsel, sesel;
		u64 eaddr;
		u64 raddr;

		switch (tlbsel) {
		case 0:
			/* TLB0 */
			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);

			stlbsel = 0;
			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
			sesel = 0; /* unused */

			break;

		case 1:
			/* TLB1 */
			eaddr = get_tlb_eaddr(gtlbe);
			raddr = get_tlb_raddr(gtlbe);

			/* Create a 4KB mapping on the host.
			 * If the guest wanted a large page,
			 * only the first 4KB is mapped here and the rest
			 * are mapped on the fly. */
			stlbsel = 1;
			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
					raddr >> PAGE_SHIFT, gtlbe, &stlbe);
			break;

		default:
			BUG();
		}

		write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
	}

	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
	return EMULATE_DONE;
}

int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);

	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}

int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
	unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);

	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}

void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
{
	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);

	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
}

void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
{
	unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);

	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
}

gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
			gva_t eaddr)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct kvm_book3e_206_tlb_entry *gtlbe;
	u64 pgmask;

	gtlbe = get_entry(vcpu_e500, tlbsel_of(index), esel_of(index));
	pgmask = get_tlb_bytes(gtlbe) - 1;

	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
}

void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
}

void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
			unsigned int index)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct tlbe_priv *priv;
	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
	int tlbsel = tlbsel_of(index);
	int esel = esel_of(index);
	int stlbsel, sesel;

	gtlbe = get_entry(vcpu_e500, tlbsel, esel);

	switch (tlbsel) {
	case 0:
		stlbsel = 0;
		sesel = 0; /* unused */
		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];

		kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
					&priv->ref, eaddr, &stlbe);
		break;

	case 1: {
		gfn_t gfn = gpaddr >> PAGE_SHIFT;

		stlbsel = 1;
		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn,
					     gtlbe, &stlbe);
		break;
	}

	default:
		BUG();
		break;
	}

	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
}

int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
				gva_t eaddr, unsigned int pid, int as)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	int esel, tlbsel;

	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
		if (esel >= 0)
			return index_of(tlbsel, esel);
	}

	return -1;
}

void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);

	if (vcpu->arch.pid != pid) {
		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
	}
}

void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	struct kvm_book3e_206_tlb_entry *tlbe;

	/* Insert large initial mapping for guest. */
	tlbe = get_entry(vcpu_e500, 1, 0);
	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
	tlbe->mas2 = 0;
	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;

	/* 4K map for serial output. Used by kernel wrapper. */
	tlbe = get_entry(vcpu_e500, 1, 1);
	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
}

static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	int i;

	clear_tlb_refs(vcpu_e500);
	kfree(vcpu_e500->gtlb_priv[0]);
	kfree(vcpu_e500->gtlb_priv[1]);

	if (vcpu_e500->shared_tlb_pages) {
		vfree((void *)(round_down((uintptr_t)vcpu_e500->gtlb_arch,
					  PAGE_SIZE)));

		for (i = 0; i < vcpu_e500->num_shared_tlb_pages; i++) {
			set_page_dirty_lock(vcpu_e500->shared_tlb_pages[i]);
			put_page(vcpu_e500->shared_tlb_pages[i]);
		}

		vcpu_e500->num_shared_tlb_pages = 0;
		vcpu_e500->shared_tlb_pages = NULL;
	} else {
		kfree(vcpu_e500->gtlb_arch);
	}

	vcpu_e500->gtlb_arch = NULL;
}

int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
			      struct kvm_config_tlb *cfg)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct kvm_book3e_206_tlb_params params;
	char *virt;
	struct page **pages;
	struct tlbe_priv *privs[2] = {};
	size_t array_len;
	u32 sets;
	int num_pages, ret, i;

	if (cfg->mmu_type != KVM_MMU_FSL_BOOKE_NOHV)
		return -EINVAL;

	if (copy_from_user(&params, (void __user *)(uintptr_t)cfg->params,
			   sizeof(params)))
		return -EFAULT;

	if (params.tlb_sizes[1] > 64)
		return -EINVAL;
	if (params.tlb_ways[1] != params.tlb_sizes[1])
		return -EINVAL;
	if (params.tlb_sizes[2] != 0 || params.tlb_sizes[3] != 0)
		return -EINVAL;
	if (params.tlb_ways[2] != 0 || params.tlb_ways[3] != 0)
		return -EINVAL;

	if (!is_power_of_2(params.tlb_ways[0]))
		return -EINVAL;

	sets = params.tlb_sizes[0] >> ilog2(params.tlb_ways[0]);
	if (!is_power_of_2(sets))
		return -EINVAL;

	array_len = params.tlb_sizes[0] + params.tlb_sizes[1];
	array_len *= sizeof(struct kvm_book3e_206_tlb_entry);

	if (cfg->array_len < array_len)
		return -EINVAL;

	num_pages = DIV_ROUND_UP(cfg->array + array_len - 1, PAGE_SIZE) -
		    cfg->array / PAGE_SIZE;
	pages = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
	if (!pages)
		return -ENOMEM;

	ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
	if (ret < 0)
		goto err_pages;

	if (ret != num_pages) {
		num_pages = ret;
		ret = -EFAULT;
		goto err_put_page;
	}

	virt = vmap(pages, num_pages, VM_MAP, PAGE_KERNEL);
	if (!virt)
		goto err_put_page;

	privs[0] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[0],
			   GFP_KERNEL);
	privs[1] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[1],
			   GFP_KERNEL);

	if (!privs[0] || !privs[1])
		goto err_put_page;

	free_gtlb(vcpu_e500);

	vcpu_e500->gtlb_priv[0] = privs[0];
	vcpu_e500->gtlb_priv[1] = privs[1];

	vcpu_e500->gtlb_arch = (struct kvm_book3e_206_tlb_entry *)
		(virt + (cfg->array & (PAGE_SIZE - 1)));

	vcpu_e500->gtlb_params[0].entries = params.tlb_sizes[0];
	vcpu_e500->gtlb_params[1].entries = params.tlb_sizes[1];

	vcpu_e500->gtlb_offset[0] = 0;
	vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];

	vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
	if (params.tlb_sizes[0] <= 2048)
		vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
	vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;

	vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
	vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
	vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;

	vcpu_e500->shared_tlb_pages = pages;
	vcpu_e500->num_shared_tlb_pages = num_pages;

	vcpu_e500->gtlb_params[0].ways = params.tlb_ways[0];
	vcpu_e500->gtlb_params[0].sets = sets;

	vcpu_e500->gtlb_params[1].ways = params.tlb_sizes[1];
	vcpu_e500->gtlb_params[1].sets = 1;

	return 0;

err_put_page:
	kfree(privs[0]);
	kfree(privs[1]);

	for (i = 0; i < num_pages; i++)
		put_page(pages[i]);

err_pages:
	kfree(pages);
	return ret;
}

int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
			     struct kvm_dirty_tlb *dirty)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);

	clear_tlb_refs(vcpu_e500);
	return 0;
}

int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;

	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;

	/*
	 * This should never happen on real e500 hardware, but is
	 * architecturally possible -- e.g. in some weird nested
	 * virtualization case.
	 */
	if (host_tlb_params[0].entries == 0 ||
	    host_tlb_params[1].entries == 0) {
		pr_err("%s: need to know host tlb size\n", __func__);
		return -ENODEV;
	}

	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
				  TLBnCFG_ASSOC_SHIFT;
	host_tlb_params[1].ways = host_tlb_params[1].entries;

	if (!is_power_of_2(host_tlb_params[0].entries) ||
	    !is_power_of_2(host_tlb_params[0].ways) ||
	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
	    host_tlb_params[0].ways == 0) {
		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
		       __func__, host_tlb_params[0].entries,
		       host_tlb_params[0].ways);
		return -ENODEV;
	}

	host_tlb_params[0].sets =
		host_tlb_params[0].entries / host_tlb_params[0].ways;
	host_tlb_params[1].sets = 1;

	vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE;
	vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE;

	vcpu_e500->gtlb_params[0].ways = KVM_E500_TLB0_WAY_NUM;
	vcpu_e500->gtlb_params[0].sets =
		KVM_E500_TLB0_SIZE / KVM_E500_TLB0_WAY_NUM;

	vcpu_e500->gtlb_params[1].ways = KVM_E500_TLB1_SIZE;
	vcpu_e500->gtlb_params[1].sets = 1;

	vcpu_e500->gtlb_arch = kmalloc(entries * entry_size, GFP_KERNEL);
	if (!vcpu_e500->gtlb_arch)
		return -ENOMEM;

	vcpu_e500->gtlb_offset[0] = 0;
	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;

	vcpu_e500->tlb_refs[0] =
		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
			GFP_KERNEL);
	if (!vcpu_e500->tlb_refs[0])
		goto err;

	vcpu_e500->tlb_refs[1] =
		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
			GFP_KERNEL);
	if (!vcpu_e500->tlb_refs[1])
		goto err;

	vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) *
					  vcpu_e500->gtlb_params[0].entries,
					  GFP_KERNEL);
	if (!vcpu_e500->gtlb_priv[0])
		goto err;

	vcpu_e500->gtlb_priv[1] = kzalloc(sizeof(struct tlbe_ref) *
					  vcpu_e500->gtlb_params[1].entries,
					  GFP_KERNEL);
	if (!vcpu_e500->gtlb_priv[1])
		goto err;

	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
		goto err;

	/* Init TLB configuration register */
	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
	vcpu_e500->tlb0cfg |=
		vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;

	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
	vcpu_e500->tlb0cfg |=
		vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;

	return 0;

err:
	free_gtlb(vcpu_e500);
	kfree(vcpu_e500->tlb_refs[0]);
	kfree(vcpu_e500->tlb_refs[1]);
	return -1;
}

void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	free_gtlb(vcpu_e500);
	kvmppc_e500_id_table_free(vcpu_e500);

	kfree(vcpu_e500->tlb_refs[0]);
	kfree(vcpu_e500->tlb_refs[1]);
}