summaryrefslogtreecommitdiffstats
path: root/drivers/kvm/mmu.c
blob: e4a20a45d834414cc904341819e5397b3db1a254 (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
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * MMU support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */
#include <linux/types.h>
#include <linux/string.h>
#include <asm/page.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/module.h>

#include "vmx.h"
#include "kvm.h"

#define pgprintk(x...) do { printk(x); } while (0)
#define rmap_printk(x...) do { printk(x); } while (0)

#define ASSERT(x)							\
	if (!(x)) {							\
		printk(KERN_WARNING "assertion failed %s:%d: %s\n",	\
		       __FILE__, __LINE__, #x);				\
	}

#define PT64_PT_BITS 9
#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
#define PT32_PT_BITS 10
#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)

#define PT_WRITABLE_SHIFT 1

#define PT_PRESENT_MASK (1ULL << 0)
#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
#define PT_USER_MASK (1ULL << 2)
#define PT_PWT_MASK (1ULL << 3)
#define PT_PCD_MASK (1ULL << 4)
#define PT_ACCESSED_MASK (1ULL << 5)
#define PT_DIRTY_MASK (1ULL << 6)
#define PT_PAGE_SIZE_MASK (1ULL << 7)
#define PT_PAT_MASK (1ULL << 7)
#define PT_GLOBAL_MASK (1ULL << 8)
#define PT64_NX_MASK (1ULL << 63)

#define PT_PAT_SHIFT 7
#define PT_DIR_PAT_SHIFT 12
#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)

#define PT32_DIR_PSE36_SIZE 4
#define PT32_DIR_PSE36_SHIFT 13
#define PT32_DIR_PSE36_MASK (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)


#define PT32_PTE_COPY_MASK \
	(PT_PRESENT_MASK | PT_ACCESSED_MASK | PT_DIRTY_MASK | PT_GLOBAL_MASK)

#define PT64_PTE_COPY_MASK (PT64_NX_MASK | PT32_PTE_COPY_MASK)

#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52

#define PT_SHADOW_PS_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)

#define PT_SHADOW_WRITABLE_SHIFT (PT_FIRST_AVAIL_BITS_SHIFT + 1)
#define PT_SHADOW_WRITABLE_MASK (1ULL << PT_SHADOW_WRITABLE_SHIFT)

#define PT_SHADOW_USER_SHIFT (PT_SHADOW_WRITABLE_SHIFT + 1)
#define PT_SHADOW_USER_MASK (1ULL << (PT_SHADOW_USER_SHIFT))

#define PT_SHADOW_BITS_OFFSET (PT_SHADOW_WRITABLE_SHIFT - PT_WRITABLE_SHIFT)

#define VALID_PAGE(x) ((x) != INVALID_PAGE)

#define PT64_LEVEL_BITS 9

#define PT64_LEVEL_SHIFT(level) \
		( PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS )

#define PT64_LEVEL_MASK(level) \
		(((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level))

#define PT64_INDEX(address, level)\
	(((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1))


#define PT32_LEVEL_BITS 10

#define PT32_LEVEL_SHIFT(level) \
		( PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS )

#define PT32_LEVEL_MASK(level) \
		(((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level))

#define PT32_INDEX(address, level)\
	(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))


#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & PAGE_MASK)
#define PT64_DIR_BASE_ADDR_MASK \
	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))

#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
	(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))


#define PFERR_PRESENT_MASK (1U << 0)
#define PFERR_WRITE_MASK (1U << 1)
#define PFERR_USER_MASK (1U << 2)

#define PT64_ROOT_LEVEL 4
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3

#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1

#define RMAP_EXT 4

struct kvm_rmap_desc {
	u64 *shadow_ptes[RMAP_EXT];
	struct kvm_rmap_desc *more;
};

static int is_write_protection(struct kvm_vcpu *vcpu)
{
	return vcpu->cr0 & CR0_WP_MASK;
}

static int is_cpuid_PSE36(void)
{
	return 1;
}

static int is_present_pte(unsigned long pte)
{
	return pte & PT_PRESENT_MASK;
}

static int is_writeble_pte(unsigned long pte)
{
	return pte & PT_WRITABLE_MASK;
}

static int is_io_pte(unsigned long pte)
{
	return pte & PT_SHADOW_IO_MARK;
}

static int is_rmap_pte(u64 pte)
{
	return (pte & (PT_WRITABLE_MASK | PT_PRESENT_MASK))
		== (PT_WRITABLE_MASK | PT_PRESENT_MASK);
}

/*
 * Reverse mapping data structures:
 *
 * If page->private bit zero is zero, then page->private points to the
 * shadow page table entry that points to page_address(page).
 *
 * If page->private bit zero is one, (then page->private & ~1) points
 * to a struct kvm_rmap_desc containing more mappings.
 */
static void rmap_add(struct kvm *kvm, u64 *spte)
{
	struct page *page;
	struct kvm_rmap_desc *desc;
	int i;

	if (!is_rmap_pte(*spte))
		return;
	page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
	if (!page->private) {
		rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
		page->private = (unsigned long)spte;
	} else if (!(page->private & 1)) {
		rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
		desc = kzalloc(sizeof *desc, GFP_NOWAIT);
		if (!desc)
			BUG(); /* FIXME: return error */
		desc->shadow_ptes[0] = (u64 *)page->private;
		desc->shadow_ptes[1] = spte;
		page->private = (unsigned long)desc | 1;
	} else {
		rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
		desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
		while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
			desc = desc->more;
		if (desc->shadow_ptes[RMAP_EXT-1]) {
			desc->more = kzalloc(sizeof *desc->more, GFP_NOWAIT);
			if (!desc->more)
				BUG(); /* FIXME: return error */
			desc = desc->more;
		}
		for (i = 0; desc->shadow_ptes[i]; ++i)
			;
		desc->shadow_ptes[i] = spte;
	}
}

static void rmap_desc_remove_entry(struct page *page,
				   struct kvm_rmap_desc *desc,
				   int i,
				   struct kvm_rmap_desc *prev_desc)
{
	int j;

	for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j)
		;
	desc->shadow_ptes[i] = desc->shadow_ptes[j];
	desc->shadow_ptes[j] = 0;
	if (j != 0)
		return;
	if (!prev_desc && !desc->more)
		page->private = (unsigned long)desc->shadow_ptes[0];
	else
		if (prev_desc)
			prev_desc->more = desc->more;
		else
			page->private = (unsigned long)desc->more | 1;
	kfree(desc);
}

static void rmap_remove(struct kvm *kvm, u64 *spte)
{
	struct page *page;
	struct kvm_rmap_desc *desc;
	struct kvm_rmap_desc *prev_desc;
	int i;

	if (!is_rmap_pte(*spte))
		return;
	page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
	if (!page->private) {
		printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
		BUG();
	} else if (!(page->private & 1)) {
		rmap_printk("rmap_remove:  %p %llx 1->0\n", spte, *spte);
		if ((u64 *)page->private != spte) {
			printk(KERN_ERR "rmap_remove:  %p %llx 1->BUG\n",
			       spte, *spte);
			BUG();
		}
		page->private = 0;
	} else {
		rmap_printk("rmap_remove:  %p %llx many->many\n", spte, *spte);
		desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
		prev_desc = NULL;
		while (desc) {
			for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
				if (desc->shadow_ptes[i] == spte) {
					rmap_desc_remove_entry(page, desc, i,
							       prev_desc);
					return;
				}
			prev_desc = desc;
			desc = desc->more;
		}
		BUG();
	}
}

static void rmap_write_protect(struct kvm *kvm, u64 gfn)
{
	struct page *page;
	struct kvm_memory_slot *slot;
	struct kvm_rmap_desc *desc;
	u64 *spte;

	slot = gfn_to_memslot(kvm, gfn);
	BUG_ON(!slot);
	page = gfn_to_page(slot, gfn);

	while (page->private) {
		if (!(page->private & 1))
			spte = (u64 *)page->private;
		else {
			desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
			spte = desc->shadow_ptes[0];
		}
		BUG_ON(!spte);
		BUG_ON((*spte & PT64_BASE_ADDR_MASK) !=
		       page_to_pfn(page) << PAGE_SHIFT);
		BUG_ON(!(*spte & PT_PRESENT_MASK));
		BUG_ON(!(*spte & PT_WRITABLE_MASK));
		rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
		rmap_remove(kvm, spte);
		*spte &= ~(u64)PT_WRITABLE_MASK;
	}
}

static void kvm_mmu_free_page(struct kvm_vcpu *vcpu, hpa_t page_hpa)
{
	struct kvm_mmu_page *page_head = page_header(page_hpa);

	list_del(&page_head->link);
	page_head->page_hpa = page_hpa;
	list_add(&page_head->link, &vcpu->free_pages);
	++vcpu->kvm->n_free_mmu_pages;
}

static int is_empty_shadow_page(hpa_t page_hpa)
{
	u32 *pos;
	u32 *end;
	for (pos = __va(page_hpa), end = pos + PAGE_SIZE / sizeof(u32);
		      pos != end; pos++)
		if (*pos != 0)
			return 0;
	return 1;
}

static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
	return gfn;
}

static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
					       u64 *parent_pte)
{
	struct kvm_mmu_page *page;

	if (list_empty(&vcpu->free_pages))
		return NULL;

	page = list_entry(vcpu->free_pages.next, struct kvm_mmu_page, link);
	list_del(&page->link);
	list_add(&page->link, &vcpu->kvm->active_mmu_pages);
	ASSERT(is_empty_shadow_page(page->page_hpa));
	page->slot_bitmap = 0;
	page->global = 1;
	page->multimapped = 0;
	page->parent_pte = parent_pte;
	--vcpu->kvm->n_free_mmu_pages;
	return page;
}

static void mmu_page_add_parent_pte(struct kvm_mmu_page *page, u64 *parent_pte)
{
	struct kvm_pte_chain *pte_chain;
	struct hlist_node *node;
	int i;

	if (!parent_pte)
		return;
	if (!page->multimapped) {
		u64 *old = page->parent_pte;

		if (!old) {
			page->parent_pte = parent_pte;
			return;
		}
		page->multimapped = 1;
		pte_chain = kzalloc(sizeof(struct kvm_pte_chain), GFP_NOWAIT);
		BUG_ON(!pte_chain);
		INIT_HLIST_HEAD(&page->parent_ptes);
		hlist_add_head(&pte_chain->link, &page->parent_ptes);
		pte_chain->parent_ptes[0] = old;
	}
	hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link) {
		if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1])
			continue;
		for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i)
			if (!pte_chain->parent_ptes[i]) {
				pte_chain->parent_ptes[i] = parent_pte;
				return;
			}
	}
	pte_chain = kzalloc(sizeof(struct kvm_pte_chain), GFP_NOWAIT);
	BUG_ON(!pte_chain);
	hlist_add_head(&pte_chain->link, &page->parent_ptes);
	pte_chain->parent_ptes[0] = parent_pte;
}

static void mmu_page_remove_parent_pte(struct kvm_mmu_page *page,
				       u64 *parent_pte)
{
	struct kvm_pte_chain *pte_chain;
	struct hlist_node *node;
	int i;

	if (!page->multimapped) {
		BUG_ON(page->parent_pte != parent_pte);
		page->parent_pte = NULL;
		return;
	}
	hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link)
		for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
			if (!pte_chain->parent_ptes[i])
				break;
			if (pte_chain->parent_ptes[i] != parent_pte)
				continue;
			while (i + 1 < NR_PTE_CHAIN_ENTRIES
				&& pte_chain->parent_ptes[i + 1]) {
				pte_chain->parent_ptes[i]
					= pte_chain->parent_ptes[i + 1];
				++i;
			}
			pte_chain->parent_ptes[i] = NULL;
			if (i == 0) {
				hlist_del(&pte_chain->link);
				kfree(pte_chain);
				if (hlist_empty(&page->parent_ptes)) {
					page->multimapped = 0;
					page->parent_pte = NULL;
				}
			}
			return;
		}
	BUG();
}

static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm_vcpu *vcpu,
						gfn_t gfn)
{
	unsigned index;
	struct hlist_head *bucket;
	struct kvm_mmu_page *page;
	struct hlist_node *node;

	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
	bucket = &vcpu->kvm->mmu_page_hash[index];
	hlist_for_each_entry(page, node, bucket, hash_link)
		if (page->gfn == gfn && !page->role.metaphysical) {
			pgprintk("%s: found role %x\n",
				 __FUNCTION__, page->role.word);
			return page;
		}
	return NULL;
}

static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
					     gfn_t gfn,
					     gva_t gaddr,
					     unsigned level,
					     int metaphysical,
					     u64 *parent_pte)
{
	union kvm_mmu_page_role role;
	unsigned index;
	unsigned quadrant;
	struct hlist_head *bucket;
	struct kvm_mmu_page *page;
	struct hlist_node *node;

	role.word = 0;
	role.glevels = vcpu->mmu.root_level;
	role.level = level;
	role.metaphysical = metaphysical;
	if (vcpu->mmu.root_level <= PT32_ROOT_LEVEL) {
		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
		role.quadrant = quadrant;
	}
	pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
		 gfn, role.word);
	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
	bucket = &vcpu->kvm->mmu_page_hash[index];
	hlist_for_each_entry(page, node, bucket, hash_link)
		if (page->gfn == gfn && page->role.word == role.word) {
			mmu_page_add_parent_pte(page, parent_pte);
			pgprintk("%s: found\n", __FUNCTION__);
			return page;
		}
	page = kvm_mmu_alloc_page(vcpu, parent_pte);
	if (!page)
		return page;
	pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word);
	page->gfn = gfn;
	page->role = role;
	hlist_add_head(&page->hash_link, bucket);
	if (!metaphysical)
		rmap_write_protect(vcpu->kvm, gfn);
	return page;
}

static void kvm_mmu_page_unlink_children(struct kvm_vcpu *vcpu,
					 struct kvm_mmu_page *page)
{
	unsigned i;
	u64 *pt;
	u64 ent;

	pt = __va(page->page_hpa);

	if (page->role.level == PT_PAGE_TABLE_LEVEL) {
		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
			if (pt[i] & PT_PRESENT_MASK)
				rmap_remove(vcpu->kvm, &pt[i]);
			pt[i] = 0;
		}
		return;
	}

	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
		ent = pt[i];

		pt[i] = 0;
		if (!(ent & PT_PRESENT_MASK))
			continue;
		ent &= PT64_BASE_ADDR_MASK;
		mmu_page_remove_parent_pte(page_header(ent), &pt[i]);
	}
}

static void kvm_mmu_put_page(struct kvm_vcpu *vcpu,
			     struct kvm_mmu_page *page,
			     u64 *parent_pte)
{
	mmu_page_remove_parent_pte(page, parent_pte);
}

static void kvm_mmu_zap_page(struct kvm_vcpu *vcpu,
			     struct kvm_mmu_page *page)
{
	u64 *parent_pte;

	while (page->multimapped || page->parent_pte) {
		if (!page->multimapped)
			parent_pte = page->parent_pte;
		else {
			struct kvm_pte_chain *chain;

			chain = container_of(page->parent_ptes.first,
					     struct kvm_pte_chain, link);
			parent_pte = chain->parent_ptes[0];
		}
		BUG_ON(!parent_pte);
		kvm_mmu_put_page(vcpu, page, parent_pte);
		*parent_pte = 0;
	}
	kvm_mmu_page_unlink_children(vcpu, page);
	hlist_del(&page->hash_link);
	kvm_mmu_free_page(vcpu, page->page_hpa);
}

static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	unsigned index;
	struct hlist_head *bucket;
	struct kvm_mmu_page *page;
	struct hlist_node *node, *n;
	int r;

	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
	r = 0;
	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
	bucket = &vcpu->kvm->mmu_page_hash[index];
	hlist_for_each_entry_safe(page, node, n, bucket, hash_link)
		if (page->gfn == gfn && !page->role.metaphysical) {
			pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
				 page->role.word);
			kvm_mmu_zap_page(vcpu, page);
			r = 1;
		}
	return r;
}

static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa)
{
	int slot = memslot_id(kvm, gfn_to_memslot(kvm, gpa >> PAGE_SHIFT));
	struct kvm_mmu_page *page_head = page_header(__pa(pte));

	__set_bit(slot, &page_head->slot_bitmap);
}

hpa_t safe_gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
	hpa_t hpa = gpa_to_hpa(vcpu, gpa);

	return is_error_hpa(hpa) ? bad_page_address | (gpa & ~PAGE_MASK): hpa;
}

hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
	struct kvm_memory_slot *slot;
	struct page *page;

	ASSERT((gpa & HPA_ERR_MASK) == 0);
	slot = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT);
	if (!slot)
		return gpa | HPA_ERR_MASK;
	page = gfn_to_page(slot, gpa >> PAGE_SHIFT);
	return ((hpa_t)page_to_pfn(page) << PAGE_SHIFT)
		| (gpa & (PAGE_SIZE-1));
}

hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva)
{
	gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);

	if (gpa == UNMAPPED_GVA)
		return UNMAPPED_GVA;
	return gpa_to_hpa(vcpu, gpa);
}


static void release_pt_page_64(struct kvm_vcpu *vcpu, hpa_t page_hpa,
			       int level)
{
	u64 *pos;
	u64 *end;

	ASSERT(vcpu);
	ASSERT(VALID_PAGE(page_hpa));
	ASSERT(level <= PT64_ROOT_LEVEL && level > 0);

	for (pos = __va(page_hpa), end = pos + PT64_ENT_PER_PAGE;
	     pos != end; pos++) {
		u64 current_ent = *pos;

		if (is_present_pte(current_ent)) {
			if (level != 1)
				release_pt_page_64(vcpu,
						  current_ent &
						  PT64_BASE_ADDR_MASK,
						  level - 1);
			else
				rmap_remove(vcpu->kvm, pos);
		}
		*pos = 0;
	}
	kvm_mmu_free_page(vcpu, page_hpa);
}

static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
{
}

static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, hpa_t p)
{
	int level = PT32E_ROOT_LEVEL;
	hpa_t table_addr = vcpu->mmu.root_hpa;

	for (; ; level--) {
		u32 index = PT64_INDEX(v, level);
		u64 *table;
		u64 pte;

		ASSERT(VALID_PAGE(table_addr));
		table = __va(table_addr);

		if (level == 1) {
			pte = table[index];
			if (is_present_pte(pte) && is_writeble_pte(pte))
				return 0;
			mark_page_dirty(vcpu->kvm, v >> PAGE_SHIFT);
			page_header_update_slot(vcpu->kvm, table, v);
			table[index] = p | PT_PRESENT_MASK | PT_WRITABLE_MASK |
								PT_USER_MASK;
			rmap_add(vcpu->kvm, &table[index]);
			return 0;
		}

		if (table[index] == 0) {
			struct kvm_mmu_page *new_table;
			gfn_t pseudo_gfn;

			pseudo_gfn = (v & PT64_DIR_BASE_ADDR_MASK)
				>> PAGE_SHIFT;
			new_table = kvm_mmu_get_page(vcpu, pseudo_gfn,
						     v, level - 1,
						     1, &table[index]);
			if (!new_table) {
				pgprintk("nonpaging_map: ENOMEM\n");
				return -ENOMEM;
			}

			table[index] = new_table->page_hpa | PT_PRESENT_MASK
				| PT_WRITABLE_MASK | PT_USER_MASK;
		}
		table_addr = table[index] & PT64_BASE_ADDR_MASK;
	}
}

static void mmu_free_roots(struct kvm_vcpu *vcpu)
{
	int i;

#ifdef CONFIG_X86_64
	if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) {
		hpa_t root = vcpu->mmu.root_hpa;

		ASSERT(VALID_PAGE(root));
		vcpu->mmu.root_hpa = INVALID_PAGE;
		return;
	}
#endif
	for (i = 0; i < 4; ++i) {
		hpa_t root = vcpu->mmu.pae_root[i];

		ASSERT(VALID_PAGE(root));
		root &= PT64_BASE_ADDR_MASK;
		vcpu->mmu.pae_root[i] = INVALID_PAGE;
	}
	vcpu->mmu.root_hpa = INVALID_PAGE;
}

static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
	int i;
	gfn_t root_gfn;
	root_gfn = vcpu->cr3 >> PAGE_SHIFT;

#ifdef CONFIG_X86_64
	if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) {
		hpa_t root = vcpu->mmu.root_hpa;

		ASSERT(!VALID_PAGE(root));
		root = kvm_mmu_get_page(vcpu, root_gfn, 0,
					PT64_ROOT_LEVEL, 0, NULL)->page_hpa;
		vcpu->mmu.root_hpa = root;
		return;
	}
#endif
	for (i = 0; i < 4; ++i) {
		hpa_t root = vcpu->mmu.pae_root[i];

		ASSERT(!VALID_PAGE(root));
		if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL)
			root_gfn = vcpu->pdptrs[i] >> PAGE_SHIFT;
		else if (vcpu->mmu.root_level == 0)
			root_gfn = 0;
		root = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
					PT32_ROOT_LEVEL, !is_paging(vcpu),
					NULL)->page_hpa;
		vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK;
	}
	vcpu->mmu.root_hpa = __pa(vcpu->mmu.pae_root);
}

static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
{
	return vaddr;
}

static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
			       u32 error_code)
{
	gpa_t addr = gva;
	hpa_t paddr;

	ASSERT(vcpu);
	ASSERT(VALID_PAGE(vcpu->mmu.root_hpa));


	paddr = gpa_to_hpa(vcpu , addr & PT64_BASE_ADDR_MASK);

	if (is_error_hpa(paddr))
		return 1;

	return nonpaging_map(vcpu, addr & PAGE_MASK, paddr);
}

static void nonpaging_inval_page(struct kvm_vcpu *vcpu, gva_t addr)
{
}

static void nonpaging_free(struct kvm_vcpu *vcpu)
{
	mmu_free_roots(vcpu);
}

static int nonpaging_init_context(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = &vcpu->mmu;

	context->new_cr3 = nonpaging_new_cr3;
	context->page_fault = nonpaging_page_fault;
	context->inval_page = nonpaging_inval_page;
	context->gva_to_gpa = nonpaging_gva_to_gpa;
	context->free = nonpaging_free;
	context->root_level = 0;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	mmu_alloc_roots(vcpu);
	ASSERT(VALID_PAGE(context->root_hpa));
	kvm_arch_ops->set_cr3(vcpu, context->root_hpa);
	return 0;
}

static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
	++kvm_stat.tlb_flush;
	kvm_arch_ops->tlb_flush(vcpu);
}

static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
	pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3);
	mmu_free_roots(vcpu);
	mmu_alloc_roots(vcpu);
	kvm_mmu_flush_tlb(vcpu);
	kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
}

static void mark_pagetable_nonglobal(void *shadow_pte)
{
	page_header(__pa(shadow_pte))->global = 0;
}

static inline void set_pte_common(struct kvm_vcpu *vcpu,
			     u64 *shadow_pte,
			     gpa_t gaddr,
			     int dirty,
			     u64 access_bits,
			     gfn_t gfn)
{
	hpa_t paddr;

	*shadow_pte |= access_bits << PT_SHADOW_BITS_OFFSET;
	if (!dirty)
		access_bits &= ~PT_WRITABLE_MASK;

	paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);

	*shadow_pte |= access_bits;

	if (!(*shadow_pte & PT_GLOBAL_MASK))
		mark_pagetable_nonglobal(shadow_pte);

	if (is_error_hpa(paddr)) {
		*shadow_pte |= gaddr;
		*shadow_pte |= PT_SHADOW_IO_MARK;
		*shadow_pte &= ~PT_PRESENT_MASK;
		return;
	}

	*shadow_pte |= paddr;

	if (access_bits & PT_WRITABLE_MASK) {
		struct kvm_mmu_page *shadow;

		shadow = kvm_mmu_lookup_page(vcpu, gfn);
		if (shadow) {
			pgprintk("%s: found shadow page for %lx, marking ro\n",
				 __FUNCTION__, gfn);
			access_bits &= ~PT_WRITABLE_MASK;
			*shadow_pte &= ~PT_WRITABLE_MASK;
		}
	}

	if (access_bits & PT_WRITABLE_MASK)
		mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);

	page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
	rmap_add(vcpu->kvm, shadow_pte);
}

static void inject_page_fault(struct kvm_vcpu *vcpu,
			      u64 addr,
			      u32 err_code)
{
	kvm_arch_ops->inject_page_fault(vcpu, addr, err_code);
}

static inline int fix_read_pf(u64 *shadow_ent)
{
	if ((*shadow_ent & PT_SHADOW_USER_MASK) &&
	    !(*shadow_ent & PT_USER_MASK)) {
		/*
		 * If supervisor write protect is disabled, we shadow kernel
		 * pages as user pages so we can trap the write access.
		 */
		*shadow_ent |= PT_USER_MASK;
		*shadow_ent &= ~PT_WRITABLE_MASK;

		return 1;

	}
	return 0;
}

static int may_access(u64 pte, int write, int user)
{

	if (user && !(pte & PT_USER_MASK))
		return 0;
	if (write && !(pte & PT_WRITABLE_MASK))
		return 0;
	return 1;
}

/*
 * Remove a shadow pte.
 */
static void paging_inval_page(struct kvm_vcpu *vcpu, gva_t addr)
{
	hpa_t page_addr = vcpu->mmu.root_hpa;
	int level = vcpu->mmu.shadow_root_level;

	++kvm_stat.invlpg;

	for (; ; level--) {
		u32 index = PT64_INDEX(addr, level);
		u64 *table = __va(page_addr);

		if (level == PT_PAGE_TABLE_LEVEL ) {
			rmap_remove(vcpu->kvm, &table[index]);
			table[index] = 0;
			return;
		}

		if (!is_present_pte(table[index]))
			return;

		page_addr = table[index] & PT64_BASE_ADDR_MASK;

		if (level == PT_DIRECTORY_LEVEL &&
			  (table[index] & PT_SHADOW_PS_MARK)) {
			table[index] = 0;
			release_pt_page_64(vcpu, page_addr, PT_PAGE_TABLE_LEVEL);

			kvm_arch_ops->tlb_flush(vcpu);
			return;
		}
	}
}

static void paging_free(struct kvm_vcpu *vcpu)
{
	nonpaging_free(vcpu);
}

#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE

#define PTTYPE 32
#include "paging_tmpl.h"
#undef PTTYPE

static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
{
	struct kvm_mmu *context = &vcpu->mmu;

	ASSERT(is_pae(vcpu));
	context->new_cr3 = paging_new_cr3;
	context->page_fault = paging64_page_fault;
	context->inval_page = paging_inval_page;
	context->gva_to_gpa = paging64_gva_to_gpa;
	context->free = paging_free;
	context->root_level = level;
	context->shadow_root_level = level;
	mmu_alloc_roots(vcpu);
	ASSERT(VALID_PAGE(context->root_hpa));
	kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
		    (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
	return 0;
}

static int paging64_init_context(struct kvm_vcpu *vcpu)
{
	return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
}

static int paging32_init_context(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = &vcpu->mmu;

	context->new_cr3 = paging_new_cr3;
	context->page_fault = paging32_page_fault;
	context->inval_page = paging_inval_page;
	context->gva_to_gpa = paging32_gva_to_gpa;
	context->free = paging_free;
	context->root_level = PT32_ROOT_LEVEL;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	mmu_alloc_roots(vcpu);
	ASSERT(VALID_PAGE(context->root_hpa));
	kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
		    (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
	return 0;
}

static int paging32E_init_context(struct kvm_vcpu *vcpu)
{
	return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
}

static int init_kvm_mmu(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));

	if (!is_paging(vcpu))
		return nonpaging_init_context(vcpu);
	else if (is_long_mode(vcpu))
		return paging64_init_context(vcpu);
	else if (is_pae(vcpu))
		return paging32E_init_context(vcpu);
	else
		return paging32_init_context(vcpu);
}

static void destroy_kvm_mmu(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	if (VALID_PAGE(vcpu->mmu.root_hpa)) {
		vcpu->mmu.free(vcpu);
		vcpu->mmu.root_hpa = INVALID_PAGE;
	}
}

int kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
{
	destroy_kvm_mmu(vcpu);
	return init_kvm_mmu(vcpu);
}

void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	struct kvm_mmu_page *page;
	struct kvm_mmu_page *child;
	struct hlist_node *node;
	struct hlist_head *bucket;
	unsigned index;
	u64 *spte;
	u64 pte;
	unsigned offset = offset_in_page(gpa);
	unsigned page_offset;
	int level;

	pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
	bucket = &vcpu->kvm->mmu_page_hash[index];
	hlist_for_each_entry(page, node, bucket, hash_link) {
		if (page->gfn != gfn || page->role.metaphysical)
			continue;
		page_offset = offset;
		level = page->role.level;
		if (page->role.glevels == PT32_ROOT_LEVEL) {
			page_offset <<= 1;          /* 32->64 */
			page_offset &= ~PAGE_MASK;
		}
		spte = __va(page->page_hpa);
		spte += page_offset / sizeof(*spte);
		pte = *spte;
		if (is_present_pte(pte)) {
			if (level == PT_PAGE_TABLE_LEVEL)
				rmap_remove(vcpu->kvm, spte);
			else {
				child = page_header(pte & PT64_BASE_ADDR_MASK);
				mmu_page_remove_parent_pte(child, spte);
			}
		}
		*spte = 0;
	}
}

void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
{
}

int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
{
	gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);

	return kvm_mmu_unprotect_page(vcpu, gpa >> PAGE_SHIFT);
}

void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
	while (vcpu->kvm->n_free_mmu_pages < KVM_REFILL_PAGES) {
		struct kvm_mmu_page *page;

		page = container_of(vcpu->kvm->active_mmu_pages.prev,
				    struct kvm_mmu_page, link);
		kvm_mmu_zap_page(vcpu, page);
	}
}
EXPORT_SYMBOL_GPL(kvm_mmu_free_some_pages);

static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
	while (!list_empty(&vcpu->free_pages)) {
		struct kvm_mmu_page *page;

		page = list_entry(vcpu->free_pages.next,
				  struct kvm_mmu_page, link);
		list_del(&page->link);
		__free_page(pfn_to_page(page->page_hpa >> PAGE_SHIFT));
		page->page_hpa = INVALID_PAGE;
	}
	free_page((unsigned long)vcpu->mmu.pae_root);
}

static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
{
	struct page *page;
	int i;

	ASSERT(vcpu);

	for (i = 0; i < KVM_NUM_MMU_PAGES; i++) {
		struct kvm_mmu_page *page_header = &vcpu->page_header_buf[i];

		INIT_LIST_HEAD(&page_header->link);
		if ((page = alloc_page(GFP_KERNEL)) == NULL)
			goto error_1;
		page->private = (unsigned long)page_header;
		page_header->page_hpa = (hpa_t)page_to_pfn(page) << PAGE_SHIFT;
		memset(__va(page_header->page_hpa), 0, PAGE_SIZE);
		list_add(&page_header->link, &vcpu->free_pages);
		++vcpu->kvm->n_free_mmu_pages;
	}

	/*
	 * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
	 * Therefore we need to allocate shadow page tables in the first
	 * 4GB of memory, which happens to fit the DMA32 zone.
	 */
	page = alloc_page(GFP_KERNEL | __GFP_DMA32);
	if (!page)
		goto error_1;
	vcpu->mmu.pae_root = page_address(page);
	for (i = 0; i < 4; ++i)
		vcpu->mmu.pae_root[i] = INVALID_PAGE;

	return 0;

error_1:
	free_mmu_pages(vcpu);
	return -ENOMEM;
}

int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
	ASSERT(list_empty(&vcpu->free_pages));

	return alloc_mmu_pages(vcpu);
}

int kvm_mmu_setup(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
	ASSERT(!list_empty(&vcpu->free_pages));

	return init_kvm_mmu(vcpu);
}

void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);

	destroy_kvm_mmu(vcpu);
	free_mmu_pages(vcpu);
}

void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
{
	struct kvm_mmu_page *page;

	list_for_each_entry(page, &kvm->active_mmu_pages, link) {
		int i;
		u64 *pt;

		if (!test_bit(slot, &page->slot_bitmap))
			continue;

		pt = __va(page->page_hpa);
		for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
			/* avoid RMW */
			if (pt[i] & PT_WRITABLE_MASK) {
				rmap_remove(kvm, &pt[i]);
				pt[i] &= ~PT_WRITABLE_MASK;
			}
	}
}