summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_hv_rm_mmu.c
blob: 220305454c23c9e8e8a2b3d975682de53615c93f (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright 2010-2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 */

#include <linux/types.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/hugetlb.h>
#include <linux/module.h>
#include <linux/log2.h>
#include <linux/sizes.h>

#include <asm/trace.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/pte-walk.h>

/* Translate address of a vmalloc'd thing to a linear map address */
static void *real_vmalloc_addr(void *x)
{
	unsigned long addr = (unsigned long) x;
	pte_t *p;
	/*
	 * assume we don't have huge pages in vmalloc space...
	 * So don't worry about THP collapse/split. Called
	 * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
	 */
	p = find_init_mm_pte(addr, NULL);
	if (!p || !pte_present(*p))
		return NULL;
	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
	return __va(addr);
}

/* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */
static int global_invalidates(struct kvm *kvm)
{
	int global;
	int cpu;

	/*
	 * If there is only one vcore, and it's currently running,
	 * as indicated by local_paca->kvm_hstate.kvm_vcpu being set,
	 * we can use tlbiel as long as we mark all other physical
	 * cores as potentially having stale TLB entries for this lpid.
	 * Otherwise, don't use tlbiel.
	 */
	if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcpu)
		global = 0;
	else
		global = 1;

	if (!global) {
		/* any other core might now have stale TLB entries... */
		smp_wmb();
		cpumask_setall(&kvm->arch.need_tlb_flush);
		cpu = local_paca->kvm_hstate.kvm_vcore->pcpu;
		/*
		 * On POWER9, threads are independent but the TLB is shared,
		 * so use the bit for the first thread to represent the core.
		 */
		if (cpu_has_feature(CPU_FTR_ARCH_300))
			cpu = cpu_first_thread_sibling(cpu);
		cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
	}

	return global;
}

/*
 * Add this HPTE into the chain for the real page.
 * Must be called with the chain locked; it unlocks the chain.
 */
void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
			     unsigned long *rmap, long pte_index, int realmode)
{
	struct revmap_entry *head, *tail;
	unsigned long i;

	if (*rmap & KVMPPC_RMAP_PRESENT) {
		i = *rmap & KVMPPC_RMAP_INDEX;
		head = &kvm->arch.hpt.rev[i];
		if (realmode)
			head = real_vmalloc_addr(head);
		tail = &kvm->arch.hpt.rev[head->back];
		if (realmode)
			tail = real_vmalloc_addr(tail);
		rev->forw = i;
		rev->back = head->back;
		tail->forw = pte_index;
		head->back = pte_index;
	} else {
		rev->forw = rev->back = pte_index;
		*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) |
			pte_index | KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_HPT;
	}
	unlock_rmap(rmap);
}
EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);

/* Update the dirty bitmap of a memslot */
void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
			     unsigned long gfn, unsigned long psize)
{
	unsigned long npages;

	if (!psize || !memslot->dirty_bitmap)
		return;
	npages = (psize + PAGE_SIZE - 1) / PAGE_SIZE;
	gfn -= memslot->base_gfn;
	set_dirty_bits_atomic(memslot->dirty_bitmap, gfn, npages);
}
EXPORT_SYMBOL_GPL(kvmppc_update_dirty_map);

static void kvmppc_set_dirty_from_hpte(struct kvm *kvm,
				unsigned long hpte_v, unsigned long hpte_gr)
{
	struct kvm_memory_slot *memslot;
	unsigned long gfn;
	unsigned long psize;

	psize = kvmppc_actual_pgsz(hpte_v, hpte_gr);
	gfn = hpte_rpn(hpte_gr, psize);
	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
	if (memslot && memslot->dirty_bitmap)
		kvmppc_update_dirty_map(memslot, gfn, psize);
}

/* Returns a pointer to the revmap entry for the page mapped by a HPTE */
static unsigned long *revmap_for_hpte(struct kvm *kvm, unsigned long hpte_v,
				      unsigned long hpte_gr,
				      struct kvm_memory_slot **memslotp,
				      unsigned long *gfnp)
{
	struct kvm_memory_slot *memslot;
	unsigned long *rmap;
	unsigned long gfn;

	gfn = hpte_rpn(hpte_gr, kvmppc_actual_pgsz(hpte_v, hpte_gr));
	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
	if (memslotp)
		*memslotp = memslot;
	if (gfnp)
		*gfnp = gfn;
	if (!memslot)
		return NULL;

	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
	return rmap;
}

/* Remove this HPTE from the chain for a real page */
static void remove_revmap_chain(struct kvm *kvm, long pte_index,
				struct revmap_entry *rev,
				unsigned long hpte_v, unsigned long hpte_r)
{
	struct revmap_entry *next, *prev;
	unsigned long ptel, head;
	unsigned long *rmap;
	unsigned long rcbits;
	struct kvm_memory_slot *memslot;
	unsigned long gfn;

	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
	ptel = rev->guest_rpte |= rcbits;
	rmap = revmap_for_hpte(kvm, hpte_v, ptel, &memslot, &gfn);
	if (!rmap)
		return;
	lock_rmap(rmap);

	head = *rmap & KVMPPC_RMAP_INDEX;
	next = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->forw]);
	prev = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->back]);
	next->back = rev->back;
	prev->forw = rev->forw;
	if (head == pte_index) {
		head = rev->forw;
		if (head == pte_index)
			*rmap &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
		else
			*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) | head;
	}
	*rmap |= rcbits << KVMPPC_RMAP_RC_SHIFT;
	if (rcbits & HPTE_R_C)
		kvmppc_update_dirty_map(memslot, gfn,
					kvmppc_actual_pgsz(hpte_v, hpte_r));
	unlock_rmap(rmap);
}

long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
		       long pte_index, unsigned long pteh, unsigned long ptel,
		       pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret)
{
	unsigned long i, pa, gpa, gfn, psize;
	unsigned long slot_fn, hva;
	__be64 *hpte;
	struct revmap_entry *rev;
	unsigned long g_ptel;
	struct kvm_memory_slot *memslot;
	unsigned hpage_shift;
	bool is_ci;
	unsigned long *rmap;
	pte_t *ptep;
	unsigned int writing;
	unsigned long mmu_seq;
	unsigned long rcbits, irq_flags = 0;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	psize = kvmppc_actual_pgsz(pteh, ptel);
	if (!psize)
		return H_PARAMETER;
	writing = hpte_is_writable(ptel);
	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
	ptel &= ~HPTE_GR_RESERVED;
	g_ptel = ptel;

	/* used later to detect if we might have been invalidated */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	/* Find the memslot (if any) for this address */
	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
	gfn = gpa >> PAGE_SHIFT;
	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
	pa = 0;
	is_ci = false;
	rmap = NULL;
	if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
		/* Emulated MMIO - mark this with key=31 */
		pteh |= HPTE_V_ABSENT;
		ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
		goto do_insert;
	}

	/* Check if the requested page fits entirely in the memslot. */
	if (!slot_is_aligned(memslot, psize))
		return H_PARAMETER;
	slot_fn = gfn - memslot->base_gfn;
	rmap = &memslot->arch.rmap[slot_fn];

	/* Translate to host virtual address */
	hva = __gfn_to_hva_memslot(memslot, gfn);
	/*
	 * If we had a page table table change after lookup, we would
	 * retry via mmu_notifier_retry.
	 */
	if (!realmode)
		local_irq_save(irq_flags);
	/*
	 * If called in real mode we have MSR_EE = 0. Otherwise
	 * we disable irq above.
	 */
	ptep = __find_linux_pte(pgdir, hva, NULL, &hpage_shift);
	if (ptep) {
		pte_t pte;
		unsigned int host_pte_size;

		if (hpage_shift)
			host_pte_size = 1ul << hpage_shift;
		else
			host_pte_size = PAGE_SIZE;
		/*
		 * We should always find the guest page size
		 * to <= host page size, if host is using hugepage
		 */
		if (host_pte_size < psize) {
			if (!realmode)
				local_irq_restore(flags);
			return H_PARAMETER;
		}
		pte = kvmppc_read_update_linux_pte(ptep, writing);
		if (pte_present(pte) && !pte_protnone(pte)) {
			if (writing && !__pte_write(pte))
				/* make the actual HPTE be read-only */
				ptel = hpte_make_readonly(ptel);
			is_ci = pte_ci(pte);
			pa = pte_pfn(pte) << PAGE_SHIFT;
			pa |= hva & (host_pte_size - 1);
			pa |= gpa & ~PAGE_MASK;
		}
	}
	if (!realmode)
		local_irq_restore(irq_flags);

	ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1);
	ptel |= pa;

	if (pa)
		pteh |= HPTE_V_VALID;
	else {
		pteh |= HPTE_V_ABSENT;
		ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
	}

	/*If we had host pte mapping then  Check WIMG */
	if (ptep && !hpte_cache_flags_ok(ptel, is_ci)) {
		if (is_ci)
			return H_PARAMETER;
		/*
		 * Allow guest to map emulated device memory as
		 * uncacheable, but actually make it cacheable.
		 */
		ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G);
		ptel |= HPTE_R_M;
	}

	/* Find and lock the HPTEG slot to use */
 do_insert:
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;
	if (likely((flags & H_EXACT) == 0)) {
		pte_index &= ~7UL;
		hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
		for (i = 0; i < 8; ++i) {
			if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0 &&
			    try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
					  HPTE_V_ABSENT))
				break;
			hpte += 2;
		}
		if (i == 8) {
			/*
			 * Since try_lock_hpte doesn't retry (not even stdcx.
			 * failures), it could be that there is a free slot
			 * but we transiently failed to lock it.  Try again,
			 * actually locking each slot and checking it.
			 */
			hpte -= 16;
			for (i = 0; i < 8; ++i) {
				u64 pte;
				while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
					cpu_relax();
				pte = be64_to_cpu(hpte[0]);
				if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT)))
					break;
				__unlock_hpte(hpte, pte);
				hpte += 2;
			}
			if (i == 8)
				return H_PTEG_FULL;
		}
		pte_index += i;
	} else {
		hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
		if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
				   HPTE_V_ABSENT)) {
			/* Lock the slot and check again */
			u64 pte;

			while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
				cpu_relax();
			pte = be64_to_cpu(hpte[0]);
			if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
				__unlock_hpte(hpte, pte);
				return H_PTEG_FULL;
			}
		}
	}

	/* Save away the guest's idea of the second HPTE dword */
	rev = &kvm->arch.hpt.rev[pte_index];
	if (realmode)
		rev = real_vmalloc_addr(rev);
	if (rev) {
		rev->guest_rpte = g_ptel;
		note_hpte_modification(kvm, rev);
	}

	/* Link HPTE into reverse-map chain */
	if (pteh & HPTE_V_VALID) {
		if (realmode)
			rmap = real_vmalloc_addr(rmap);
		lock_rmap(rmap);
		/* Check for pending invalidations under the rmap chain lock */
		if (mmu_notifier_retry(kvm, mmu_seq)) {
			/* inval in progress, write a non-present HPTE */
			pteh |= HPTE_V_ABSENT;
			pteh &= ~HPTE_V_VALID;
			ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
			unlock_rmap(rmap);
		} else {
			kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
						realmode);
			/* Only set R/C in real HPTE if already set in *rmap */
			rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
			ptel &= rcbits | ~(HPTE_R_R | HPTE_R_C);
		}
	}

	/* Convert to new format on P9 */
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		ptel = hpte_old_to_new_r(pteh, ptel);
		pteh = hpte_old_to_new_v(pteh);
	}
	hpte[1] = cpu_to_be64(ptel);

	/* Write the first HPTE dword, unlocking the HPTE and making it valid */
	eieio();
	__unlock_hpte(hpte, pteh);
	asm volatile("ptesync" : : : "memory");

	*pte_idx_ret = pte_index;
	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_do_h_enter);

long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
		    long pte_index, unsigned long pteh, unsigned long ptel)
{
	return kvmppc_do_h_enter(vcpu->kvm, flags, pte_index, pteh, ptel,
				 vcpu->arch.pgdir, true,
				 &vcpu->arch.regs.gpr[4]);
}

#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
#else
#define LOCK_TOKEN	(*(u32 *)(&get_paca()->paca_index))
#endif

static inline int is_mmio_hpte(unsigned long v, unsigned long r)
{
	return ((v & HPTE_V_ABSENT) &&
		(r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
		(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
}

static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid)
{

	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
		/* Radix flush for a hash guest */

		unsigned long rb,rs,prs,r,ric;

		rb = PPC_BIT(52); /* IS = 2 */
		rs = 0;  /* lpid = 0 */
		prs = 0; /* partition scoped */
		r = 1;   /* radix format */
		ric = 0; /* RIC_FLSUH_TLB */

		/*
		 * Need the extra ptesync to make sure we don't
		 * re-order the tlbie
		 */
		asm volatile("ptesync": : :"memory");
		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
			     : : "r"(rb), "i"(r), "i"(prs),
			       "i"(ric), "r"(rs) : "memory");
	}

	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
		asm volatile("ptesync": : :"memory");
		asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
			     "r" (rb_value), "r" (lpid));
	}
}

static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
		      long npages, int global, bool need_sync)
{
	long i;

	/*
	 * We use the POWER9 5-operand versions of tlbie and tlbiel here.
	 * Since we are using RIC=0 PRS=0 R=0, and P7/P8 tlbiel ignores
	 * the RS field, this is backwards-compatible with P7 and P8.
	 */
	if (global) {
		if (need_sync)
			asm volatile("ptesync" : : : "memory");
		for (i = 0; i < npages; ++i) {
			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
		}

		fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid);
		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
	} else {
		if (need_sync)
			asm volatile("ptesync" : : : "memory");
		for (i = 0; i < npages; ++i) {
			asm volatile(PPC_TLBIEL(%0,%1,0,0,0) : :
				     "r" (rbvalues[i]), "r" (0));
		}
		asm volatile("ptesync" : : : "memory");
	}
}

long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
			unsigned long pte_index, unsigned long avpn,
			unsigned long *hpret)
{
	__be64 *hpte;
	unsigned long v, r, rb;
	struct revmap_entry *rev;
	u64 pte, orig_pte, pte_r;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;
	hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
		cpu_relax();
	pte = orig_pte = be64_to_cpu(hpte[0]);
	pte_r = be64_to_cpu(hpte[1]);
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		pte = hpte_new_to_old_v(pte, pte_r);
		pte_r = hpte_new_to_old_r(pte_r);
	}
	if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
	    ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
	    ((flags & H_ANDCOND) && (pte & avpn) != 0)) {
		__unlock_hpte(hpte, orig_pte);
		return H_NOT_FOUND;
	}

	rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
	v = pte & ~HPTE_V_HVLOCK;
	if (v & HPTE_V_VALID) {
		hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
		rb = compute_tlbie_rb(v, pte_r, pte_index);
		do_tlbies(kvm, &rb, 1, global_invalidates(kvm), true);
		/*
		 * The reference (R) and change (C) bits in a HPT
		 * entry can be set by hardware at any time up until
		 * the HPTE is invalidated and the TLB invalidation
		 * sequence has completed.  This means that when
		 * removing a HPTE, we need to re-read the HPTE after
		 * the invalidation sequence has completed in order to
		 * obtain reliable values of R and C.
		 */
		remove_revmap_chain(kvm, pte_index, rev, v,
				    be64_to_cpu(hpte[1]));
	}
	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
	note_hpte_modification(kvm, rev);
	unlock_hpte(hpte, 0);

	if (is_mmio_hpte(v, pte_r))
		atomic64_inc(&kvm->arch.mmio_update);

	if (v & HPTE_V_ABSENT)
		v = (v & ~HPTE_V_ABSENT) | HPTE_V_VALID;
	hpret[0] = v;
	hpret[1] = r;
	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_do_h_remove);

long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
		     unsigned long pte_index, unsigned long avpn)
{
	return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
				  &vcpu->arch.regs.gpr[4]);
}

long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long *args = &vcpu->arch.regs.gpr[4];
	__be64 *hp, *hptes[4];
	unsigned long tlbrb[4];
	long int i, j, k, n, found, indexes[4];
	unsigned long flags, req, pte_index, rcbits;
	int global;
	long int ret = H_SUCCESS;
	struct revmap_entry *rev, *revs[4];
	u64 hp0, hp1;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	global = global_invalidates(kvm);
	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
		n = 0;
		for (; i < 4; ++i) {
			j = i * 2;
			pte_index = args[j];
			flags = pte_index >> 56;
			pte_index &= ((1ul << 56) - 1);
			req = flags >> 6;
			flags &= 3;
			if (req == 3) {		/* no more requests */
				i = 4;
				break;
			}
			if (req != 1 || flags == 3 ||
			    pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) {
				/* parameter error */
				args[j] = ((0xa0 | flags) << 56) + pte_index;
				ret = H_PARAMETER;
				break;
			}
			hp = (__be64 *) (kvm->arch.hpt.virt + (pte_index << 4));
			/* to avoid deadlock, don't spin except for first */
			if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) {
				if (n)
					break;
				while (!try_lock_hpte(hp, HPTE_V_HVLOCK))
					cpu_relax();
			}
			found = 0;
			hp0 = be64_to_cpu(hp[0]);
			hp1 = be64_to_cpu(hp[1]);
			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
				hp0 = hpte_new_to_old_v(hp0, hp1);
				hp1 = hpte_new_to_old_r(hp1);
			}
			if (hp0 & (HPTE_V_ABSENT | HPTE_V_VALID)) {
				switch (flags & 3) {
				case 0:		/* absolute */
					found = 1;
					break;
				case 1:		/* andcond */
					if (!(hp0 & args[j + 1]))
						found = 1;
					break;
				case 2:		/* AVPN */
					if ((hp0 & ~0x7fUL) == args[j + 1])
						found = 1;
					break;
				}
			}
			if (!found) {
				hp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
				args[j] = ((0x90 | flags) << 56) + pte_index;
				continue;
			}

			args[j] = ((0x80 | flags) << 56) + pte_index;
			rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
			note_hpte_modification(kvm, rev);

			if (!(hp0 & HPTE_V_VALID)) {
				/* insert R and C bits from PTE */
				rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
				args[j] |= rcbits << (56 - 5);
				hp[0] = 0;
				if (is_mmio_hpte(hp0, hp1))
					atomic64_inc(&kvm->arch.mmio_update);
				continue;
			}

			/* leave it locked */
			hp[0] &= ~cpu_to_be64(HPTE_V_VALID);
			tlbrb[n] = compute_tlbie_rb(hp0, hp1, pte_index);
			indexes[n] = j;
			hptes[n] = hp;
			revs[n] = rev;
			++n;
		}

		if (!n)
			break;

		/* Now that we've collected a batch, do the tlbies */
		do_tlbies(kvm, tlbrb, n, global, true);

		/* Read PTE low words after tlbie to get final R/C values */
		for (k = 0; k < n; ++k) {
			j = indexes[k];
			pte_index = args[j] & ((1ul << 56) - 1);
			hp = hptes[k];
			rev = revs[k];
			remove_revmap_chain(kvm, pte_index, rev,
				be64_to_cpu(hp[0]), be64_to_cpu(hp[1]));
			rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
			args[j] |= rcbits << (56 - 5);
			__unlock_hpte(hp, 0);
		}
	}

	return ret;
}

long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
		      unsigned long pte_index, unsigned long avpn,
		      unsigned long va)
{
	struct kvm *kvm = vcpu->kvm;
	__be64 *hpte;
	struct revmap_entry *rev;
	unsigned long v, r, rb, mask, bits;
	u64 pte_v, pte_r;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;

	hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
		cpu_relax();
	v = pte_v = be64_to_cpu(hpte[0]);
	if (cpu_has_feature(CPU_FTR_ARCH_300))
		v = hpte_new_to_old_v(v, be64_to_cpu(hpte[1]));
	if ((v & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
	    ((flags & H_AVPN) && (v & ~0x7fUL) != avpn)) {
		__unlock_hpte(hpte, pte_v);
		return H_NOT_FOUND;
	}

	pte_r = be64_to_cpu(hpte[1]);
	bits = (flags << 55) & HPTE_R_PP0;
	bits |= (flags << 48) & HPTE_R_KEY_HI;
	bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);

	/* Update guest view of 2nd HPTE dword */
	mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
		HPTE_R_KEY_HI | HPTE_R_KEY_LO;
	rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
	if (rev) {
		r = (rev->guest_rpte & ~mask) | bits;
		rev->guest_rpte = r;
		note_hpte_modification(kvm, rev);
	}

	/* Update HPTE */
	if (v & HPTE_V_VALID) {
		/*
		 * If the page is valid, don't let it transition from
		 * readonly to writable.  If it should be writable, we'll
		 * take a trap and let the page fault code sort it out.
		 */
		r = (pte_r & ~mask) | bits;
		if (hpte_is_writable(r) && !hpte_is_writable(pte_r))
			r = hpte_make_readonly(r);
		/* If the PTE is changing, invalidate it first */
		if (r != pte_r) {
			rb = compute_tlbie_rb(v, r, pte_index);
			hpte[0] = cpu_to_be64((pte_v & ~HPTE_V_VALID) |
					      HPTE_V_ABSENT);
			do_tlbies(kvm, &rb, 1, global_invalidates(kvm), true);
			/* Don't lose R/C bit updates done by hardware */
			r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C);
			hpte[1] = cpu_to_be64(r);
		}
	}
	unlock_hpte(hpte, pte_v & ~HPTE_V_HVLOCK);
	asm volatile("ptesync" : : : "memory");
	if (is_mmio_hpte(v, pte_r))
		atomic64_inc(&kvm->arch.mmio_update);

	return H_SUCCESS;
}

long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
		   unsigned long pte_index)
{
	struct kvm *kvm = vcpu->kvm;
	__be64 *hpte;
	unsigned long v, r;
	int i, n = 1;
	struct revmap_entry *rev = NULL;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;
	if (flags & H_READ_4) {
		pte_index &= ~3;
		n = 4;
	}
	rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
	for (i = 0; i < n; ++i, ++pte_index) {
		hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
		v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
		r = be64_to_cpu(hpte[1]);
		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
			v = hpte_new_to_old_v(v, r);
			r = hpte_new_to_old_r(r);
		}
		if (v & HPTE_V_ABSENT) {
			v &= ~HPTE_V_ABSENT;
			v |= HPTE_V_VALID;
		}
		if (v & HPTE_V_VALID) {
			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
			r &= ~HPTE_GR_RESERVED;
		}
		vcpu->arch.regs.gpr[4 + i * 2] = v;
		vcpu->arch.regs.gpr[5 + i * 2] = r;
	}
	return H_SUCCESS;
}

long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
			unsigned long pte_index)
{
	struct kvm *kvm = vcpu->kvm;
	__be64 *hpte;
	unsigned long v, r, gr;
	struct revmap_entry *rev;
	unsigned long *rmap;
	long ret = H_NOT_FOUND;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;

	rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
	hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
		cpu_relax();
	v = be64_to_cpu(hpte[0]);
	r = be64_to_cpu(hpte[1]);
	if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
		goto out;

	gr = rev->guest_rpte;
	if (rev->guest_rpte & HPTE_R_R) {
		rev->guest_rpte &= ~HPTE_R_R;
		note_hpte_modification(kvm, rev);
	}
	if (v & HPTE_V_VALID) {
		gr |= r & (HPTE_R_R | HPTE_R_C);
		if (r & HPTE_R_R) {
			kvmppc_clear_ref_hpte(kvm, hpte, pte_index);
			rmap = revmap_for_hpte(kvm, v, gr, NULL, NULL);
			if (rmap) {
				lock_rmap(rmap);
				*rmap |= KVMPPC_RMAP_REFERENCED;
				unlock_rmap(rmap);
			}
		}
	}
	vcpu->arch.regs.gpr[4] = gr;
	ret = H_SUCCESS;
 out:
	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
	return ret;
}

long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
			unsigned long pte_index)
{
	struct kvm *kvm = vcpu->kvm;
	__be64 *hpte;
	unsigned long v, r, gr;
	struct revmap_entry *rev;
	long ret = H_NOT_FOUND;

	if (kvm_is_radix(kvm))
		return H_FUNCTION;
	if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
		return H_PARAMETER;

	rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]);
	hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
		cpu_relax();
	v = be64_to_cpu(hpte[0]);
	r = be64_to_cpu(hpte[1]);
	if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
		goto out;

	gr = rev->guest_rpte;
	if (gr & HPTE_R_C) {
		rev->guest_rpte &= ~HPTE_R_C;
		note_hpte_modification(kvm, rev);
	}
	if (v & HPTE_V_VALID) {
		/* need to make it temporarily absent so C is stable */
		hpte[0] |= cpu_to_be64(HPTE_V_ABSENT);
		kvmppc_invalidate_hpte(kvm, hpte, pte_index);
		r = be64_to_cpu(hpte[1]);
		gr |= r & (HPTE_R_R | HPTE_R_C);
		if (r & HPTE_R_C) {
			hpte[1] = cpu_to_be64(r & ~HPTE_R_C);
			eieio();
			kvmppc_set_dirty_from_hpte(kvm, v, gr);
		}
	}
	vcpu->arch.regs.gpr[4] = gr;
	ret = H_SUCCESS;
 out:
	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
	return ret;
}

static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa,
			  int writing, unsigned long *hpa,
			  struct kvm_memory_slot **memslot_p)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_memory_slot *memslot;
	unsigned long gfn, hva, pa, psize = PAGE_SHIFT;
	unsigned int shift;
	pte_t *ptep, pte;

	/* Find the memslot for this address */
	gfn = gpa >> PAGE_SHIFT;
	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
		return H_PARAMETER;

	/* Translate to host virtual address */
	hva = __gfn_to_hva_memslot(memslot, gfn);

	/* Try to find the host pte for that virtual address */
	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
	if (!ptep)
		return H_TOO_HARD;
	pte = kvmppc_read_update_linux_pte(ptep, writing);
	if (!pte_present(pte))
		return H_TOO_HARD;

	/* Convert to a physical address */
	if (shift)
		psize = 1UL << shift;
	pa = pte_pfn(pte) << PAGE_SHIFT;
	pa |= hva & (psize - 1);
	pa |= gpa & ~PAGE_MASK;

	if (hpa)
		*hpa = pa;
	if (memslot_p)
		*memslot_p = memslot;

	return H_SUCCESS;
}

static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
				       unsigned long dest)
{
	struct kvm_memory_slot *memslot;
	struct kvm *kvm = vcpu->kvm;
	unsigned long pa, mmu_seq;
	long ret = H_SUCCESS;
	int i;

	/* Used later to detect if we might have been invalidated */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	ret = kvmppc_get_hpa(vcpu, dest, 1, &pa, &memslot);
	if (ret != H_SUCCESS)
		return ret;

	/* Check if we've been invalidated */
	raw_spin_lock(&kvm->mmu_lock.rlock);
	if (mmu_notifier_retry(kvm, mmu_seq)) {
		ret = H_TOO_HARD;
		goto out_unlock;
	}

	/* Zero the page */
	for (i = 0; i < SZ_4K; i += L1_CACHE_BYTES, pa += L1_CACHE_BYTES)
		dcbz((void *)pa);
	kvmppc_update_dirty_map(memslot, dest >> PAGE_SHIFT, PAGE_SIZE);

out_unlock:
	raw_spin_unlock(&kvm->mmu_lock.rlock);
	return ret;
}

static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
				       unsigned long dest, unsigned long src)
{
	unsigned long dest_pa, src_pa, mmu_seq;
	struct kvm_memory_slot *dest_memslot;
	struct kvm *kvm = vcpu->kvm;
	long ret = H_SUCCESS;

	/* Used later to detect if we might have been invalidated */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	ret = kvmppc_get_hpa(vcpu, dest, 1, &dest_pa, &dest_memslot);
	if (ret != H_SUCCESS)
		return ret;
	ret = kvmppc_get_hpa(vcpu, src, 0, &src_pa, NULL);
	if (ret != H_SUCCESS)
		return ret;

	/* Check if we've been invalidated */
	raw_spin_lock(&kvm->mmu_lock.rlock);
	if (mmu_notifier_retry(kvm, mmu_seq)) {
		ret = H_TOO_HARD;
		goto out_unlock;
	}

	/* Copy the page */
	memcpy((void *)dest_pa, (void *)src_pa, SZ_4K);

	kvmppc_update_dirty_map(dest_memslot, dest >> PAGE_SHIFT, PAGE_SIZE);

out_unlock:
	raw_spin_unlock(&kvm->mmu_lock.rlock);
	return ret;
}

long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
			   unsigned long dest, unsigned long src)
{
	struct kvm *kvm = vcpu->kvm;
	u64 pg_mask = SZ_4K - 1;	/* 4K page size */
	long ret = H_SUCCESS;

	/* Don't handle radix mode here, go up to the virtual mode handler */
	if (kvm_is_radix(kvm))
		return H_TOO_HARD;

	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
		return H_PARAMETER;

	/* dest (and src if copy_page flag set) must be page aligned */
	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
		return H_PARAMETER;

	/* zero and/or copy the page as determined by the flags */
	if (flags & H_COPY_PAGE)
		ret = kvmppc_do_h_page_init_copy(vcpu, dest, src);
	else if (flags & H_ZERO_PAGE)
		ret = kvmppc_do_h_page_init_zero(vcpu, dest);

	/* We can ignore the other flags */

	return ret;
}

void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
			unsigned long pte_index)
{
	unsigned long rb;
	u64 hp0, hp1;

	hptep[0] &= ~cpu_to_be64(HPTE_V_VALID);
	hp0 = be64_to_cpu(hptep[0]);
	hp1 = be64_to_cpu(hptep[1]);
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		hp0 = hpte_new_to_old_v(hp0, hp1);
		hp1 = hpte_new_to_old_r(hp1);
	}
	rb = compute_tlbie_rb(hp0, hp1, pte_index);
	do_tlbies(kvm, &rb, 1, 1, true);
}
EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);

void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep,
			   unsigned long pte_index)
{
	unsigned long rb;
	unsigned char rbyte;
	u64 hp0, hp1;

	hp0 = be64_to_cpu(hptep[0]);
	hp1 = be64_to_cpu(hptep[1]);
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		hp0 = hpte_new_to_old_v(hp0, hp1);
		hp1 = hpte_new_to_old_r(hp1);
	}
	rb = compute_tlbie_rb(hp0, hp1, pte_index);
	rbyte = (be64_to_cpu(hptep[1]) & ~HPTE_R_R) >> 8;
	/* modify only the second-last byte, which contains the ref bit */
	*((char *)hptep + 14) = rbyte;
	do_tlbies(kvm, &rb, 1, 1, false);
}
EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);

static int slb_base_page_shift[4] = {
	24,	/* 16M */
	16,	/* 64k */
	34,	/* 16G */
	20,	/* 1M, unsupported */
};

static struct mmio_hpte_cache_entry *mmio_cache_search(struct kvm_vcpu *vcpu,
		unsigned long eaddr, unsigned long slb_v, long mmio_update)
{
	struct mmio_hpte_cache_entry *entry = NULL;
	unsigned int pshift;
	unsigned int i;

	for (i = 0; i < MMIO_HPTE_CACHE_SIZE; i++) {
		entry = &vcpu->arch.mmio_cache.entry[i];
		if (entry->mmio_update == mmio_update) {
			pshift = entry->slb_base_pshift;
			if ((entry->eaddr >> pshift) == (eaddr >> pshift) &&
			    entry->slb_v == slb_v)
				return entry;
		}
	}
	return NULL;
}

static struct mmio_hpte_cache_entry *
			next_mmio_cache_entry(struct kvm_vcpu *vcpu)
{
	unsigned int index = vcpu->arch.mmio_cache.index;

	vcpu->arch.mmio_cache.index++;
	if (vcpu->arch.mmio_cache.index == MMIO_HPTE_CACHE_SIZE)
		vcpu->arch.mmio_cache.index = 0;

	return &vcpu->arch.mmio_cache.entry[index];
}

/* When called from virtmode, this func should be protected by
 * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
 * can trigger deadlock issue.
 */
long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
			      unsigned long valid)
{
	unsigned int i;
	unsigned int pshift;
	unsigned long somask;
	unsigned long vsid, hash;
	unsigned long avpn;
	__be64 *hpte;
	unsigned long mask, val;
	unsigned long v, r, orig_v;

	/* Get page shift, work out hash and AVPN etc. */
	mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
	val = 0;
	pshift = 12;
	if (slb_v & SLB_VSID_L) {
		mask |= HPTE_V_LARGE;
		val |= HPTE_V_LARGE;
		pshift = slb_base_page_shift[(slb_v & SLB_VSID_LP) >> 4];
	}
	if (slb_v & SLB_VSID_B_1T) {
		somask = (1UL << 40) - 1;
		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T;
		vsid ^= vsid << 25;
	} else {
		somask = (1UL << 28) - 1;
		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
	}
	hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvmppc_hpt_mask(&kvm->arch.hpt);
	avpn = slb_v & ~(somask >> 16);	/* also includes B */
	avpn |= (eaddr & somask) >> 16;

	if (pshift >= 24)
		avpn &= ~((1UL << (pshift - 16)) - 1);
	else
		avpn &= ~0x7fUL;
	val |= avpn;

	for (;;) {
		hpte = (__be64 *)(kvm->arch.hpt.virt + (hash << 7));

		for (i = 0; i < 16; i += 2) {
			/* Read the PTE racily */
			v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
			if (cpu_has_feature(CPU_FTR_ARCH_300))
				v = hpte_new_to_old_v(v, be64_to_cpu(hpte[i+1]));

			/* Check valid/absent, hash, segment size and AVPN */
			if (!(v & valid) || (v & mask) != val)
				continue;

			/* Lock the PTE and read it under the lock */
			while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
				cpu_relax();
			v = orig_v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
			r = be64_to_cpu(hpte[i+1]);
			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
				v = hpte_new_to_old_v(v, r);
				r = hpte_new_to_old_r(r);
			}

			/*
			 * Check the HPTE again, including base page size
			 */
			if ((v & valid) && (v & mask) == val &&
			    kvmppc_hpte_base_page_shift(v, r) == pshift)
				/* Return with the HPTE still locked */
				return (hash << 3) + (i >> 1);

			__unlock_hpte(&hpte[i], orig_v);
		}

		if (val & HPTE_V_SECONDARY)
			break;
		val |= HPTE_V_SECONDARY;
		hash = hash ^ kvmppc_hpt_mask(&kvm->arch.hpt);
	}
	return -1;
}
EXPORT_SYMBOL(kvmppc_hv_find_lock_hpte);

/*
 * Called in real mode to check whether an HPTE not found fault
 * is due to accessing a paged-out page or an emulated MMIO page,
 * or if a protection fault is due to accessing a page that the
 * guest wanted read/write access to but which we made read-only.
 * Returns a possibly modified status (DSISR) value if not
 * (i.e. pass the interrupt to the guest),
 * -1 to pass the fault up to host kernel mode code, -2 to do that
 * and also load the instruction word (for MMIO emulation),
 * or 0 if we should make the guest retry the access.
 */
long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
			  unsigned long slb_v, unsigned int status, bool data)
{
	struct kvm *kvm = vcpu->kvm;
	long int index;
	unsigned long v, r, gr, orig_v;
	__be64 *hpte;
	unsigned long valid;
	struct revmap_entry *rev;
	unsigned long pp, key;
	struct mmio_hpte_cache_entry *cache_entry = NULL;
	long mmio_update = 0;

	/* For protection fault, expect to find a valid HPTE */
	valid = HPTE_V_VALID;
	if (status & DSISR_NOHPTE) {
		valid |= HPTE_V_ABSENT;
		mmio_update = atomic64_read(&kvm->arch.mmio_update);
		cache_entry = mmio_cache_search(vcpu, addr, slb_v, mmio_update);
	}
	if (cache_entry) {
		index = cache_entry->pte_index;
		v = cache_entry->hpte_v;
		r = cache_entry->hpte_r;
		gr = cache_entry->rpte;
	} else {
		index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
		if (index < 0) {
			if (status & DSISR_NOHPTE)
				return status;	/* there really was no HPTE */
			return 0;	/* for prot fault, HPTE disappeared */
		}
		hpte = (__be64 *)(kvm->arch.hpt.virt + (index << 4));
		v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
		r = be64_to_cpu(hpte[1]);
		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
			v = hpte_new_to_old_v(v, r);
			r = hpte_new_to_old_r(r);
		}
		rev = real_vmalloc_addr(&kvm->arch.hpt.rev[index]);
		gr = rev->guest_rpte;

		unlock_hpte(hpte, orig_v);
	}

	/* For not found, if the HPTE is valid by now, retry the instruction */
	if ((status & DSISR_NOHPTE) && (v & HPTE_V_VALID))
		return 0;

	/* Check access permissions to the page */
	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
	status &= ~DSISR_NOHPTE;	/* DSISR_NOHPTE == SRR1_ISI_NOPT */
	if (!data) {
		if (gr & (HPTE_R_N | HPTE_R_G))
			return status | SRR1_ISI_N_OR_G;
		if (!hpte_read_permission(pp, slb_v & key))
			return status | SRR1_ISI_PROT;
	} else if (status & DSISR_ISSTORE) {
		/* check write permission */
		if (!hpte_write_permission(pp, slb_v & key))
			return status | DSISR_PROTFAULT;
	} else {
		if (!hpte_read_permission(pp, slb_v & key))
			return status | DSISR_PROTFAULT;
	}

	/* Check storage key, if applicable */
	if (data && (vcpu->arch.shregs.msr & MSR_DR)) {
		unsigned int perm = hpte_get_skey_perm(gr, vcpu->arch.amr);
		if (status & DSISR_ISSTORE)
			perm >>= 1;
		if (perm & 1)
			return status | DSISR_KEYFAULT;
	}

	/* Save HPTE info for virtual-mode handler */
	vcpu->arch.pgfault_addr = addr;
	vcpu->arch.pgfault_index = index;
	vcpu->arch.pgfault_hpte[0] = v;
	vcpu->arch.pgfault_hpte[1] = r;
	vcpu->arch.pgfault_cache = cache_entry;

	/* Check the storage key to see if it is possibly emulated MMIO */
	if ((r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
	    (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) {
		if (!cache_entry) {
			unsigned int pshift = 12;
			unsigned int pshift_index;

			if (slb_v & SLB_VSID_L) {
				pshift_index = ((slb_v & SLB_VSID_LP) >> 4);
				pshift = slb_base_page_shift[pshift_index];
			}
			cache_entry = next_mmio_cache_entry(vcpu);
			cache_entry->eaddr = addr;
			cache_entry->slb_base_pshift = pshift;
			cache_entry->pte_index = index;
			cache_entry->hpte_v = v;
			cache_entry->hpte_r = r;
			cache_entry->rpte = gr;
			cache_entry->slb_v = slb_v;
			cache_entry->mmio_update = mmio_update;
		}
		if (data && (vcpu->arch.shregs.msr & MSR_IR))
			return -2;	/* MMIO emulation - load instr word */
	}

	return -1;		/* send fault up to host kernel mode */
}