summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu/paging_tmpl.h
blob: a1811f51eda925b9eacdc5255b20e68a490247ee (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * 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.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 */

/*
 * We need the mmu code to access both 32-bit and 64-bit guest ptes,
 * so the code in this file is compiled twice, once per pte size.
 */

#if PTTYPE == 64
	#define pt_element_t u64
	#define guest_walker guest_walker64
	#define FNAME(name) paging##64_##name
	#define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
	#define PT_LEVEL_BITS PT64_LEVEL_BITS
	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
	#ifdef CONFIG_X86_64
	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
	#define CMPXCHG "cmpxchgq"
	#else
	#define PT_MAX_FULL_LEVELS 2
	#endif
#elif PTTYPE == 32
	#define pt_element_t u32
	#define guest_walker guest_walker32
	#define FNAME(name) paging##32_##name
	#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
	#define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
	#define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
	#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
	#define PT_LEVEL_BITS PT32_LEVEL_BITS
	#define PT_MAX_FULL_LEVELS 2
	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
	#define CMPXCHG "cmpxchgl"
#elif PTTYPE == PTTYPE_EPT
	#define pt_element_t u64
	#define guest_walker guest_walkerEPT
	#define FNAME(name) ept_##name
	#define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
	#define PT_LEVEL_BITS PT64_LEVEL_BITS
	#define PT_GUEST_DIRTY_SHIFT 9
	#define PT_GUEST_ACCESSED_SHIFT 8
	#define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad)
	#ifdef CONFIG_X86_64
	#define CMPXCHG "cmpxchgq"
	#endif
	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
#else
	#error Invalid PTTYPE value
#endif

#define PT_GUEST_DIRTY_MASK    (1 << PT_GUEST_DIRTY_SHIFT)
#define PT_GUEST_ACCESSED_MASK (1 << PT_GUEST_ACCESSED_SHIFT)

#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PG_LEVEL_4K)

/*
 * The guest_walker structure emulates the behavior of the hardware page
 * table walker.
 */
struct guest_walker {
	int level;
	unsigned max_level;
	gfn_t table_gfn[PT_MAX_FULL_LEVELS];
	pt_element_t ptes[PT_MAX_FULL_LEVELS];
	pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
	gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
	pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
	bool pte_writable[PT_MAX_FULL_LEVELS];
	unsigned int pt_access[PT_MAX_FULL_LEVELS];
	unsigned int pte_access;
	gfn_t gfn;
	struct x86_exception fault;
};

static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
{
	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
}

static inline void FNAME(protect_clean_gpte)(struct kvm_mmu *mmu, unsigned *access,
					     unsigned gpte)
{
	unsigned mask;

	/* dirty bit is not supported, so no need to track it */
	if (!PT_HAVE_ACCESSED_DIRTY(mmu))
		return;

	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);

	mask = (unsigned)~ACC_WRITE_MASK;
	/* Allow write access to dirty gptes */
	mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
		PT_WRITABLE_MASK;
	*access &= mask;
}

static inline int FNAME(is_present_gpte)(unsigned long pte)
{
#if PTTYPE != PTTYPE_EPT
	return pte & PT_PRESENT_MASK;
#else
	return pte & 7;
#endif
}

static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte)
{
#if PTTYPE != PTTYPE_EPT
	return false;
#else
	return __is_bad_mt_xwr(rsvd_check, gpte);
#endif
}

static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
{
	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
	       FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
}

static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
			       pt_element_t __user *ptep_user, unsigned index,
			       pt_element_t orig_pte, pt_element_t new_pte)
{
	int r = -EFAULT;

	if (!user_access_begin(ptep_user, sizeof(pt_element_t)))
		return -EFAULT;

#ifdef CMPXCHG
	asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n"
		     "mov $0, %[r]\n"
		     "setnz %b[r]\n"
		     "2:"
		     _ASM_EXTABLE_UA(1b, 2b)
		     : [ptr] "+m" (*ptep_user),
		       [old] "+a" (orig_pte),
		       [r] "+q" (r)
		     : [new] "r" (new_pte)
		     : "memory");
#else
	asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n"
		     "movl $0, %[r]\n"
		     "jz 2f\n"
		     "incl %[r]\n"
		     "2:"
		     _ASM_EXTABLE_UA(1b, 2b)
		     : [ptr] "+m" (*ptep_user),
		       [old] "+A" (orig_pte),
		       [r] "+rm" (r)
		     : [new_lo] "b" ((u32)new_pte),
		       [new_hi] "c" ((u32)(new_pte >> 32))
		     : "memory");
#endif

	user_access_end();
	return r;
}

static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
				  struct kvm_mmu_page *sp, u64 *spte,
				  u64 gpte)
{
	if (!FNAME(is_present_gpte)(gpte))
		goto no_present;

	/* if accessed bit is not supported prefetch non accessed gpte */
	if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
	    !(gpte & PT_GUEST_ACCESSED_MASK))
		goto no_present;

	if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PG_LEVEL_4K))
		goto no_present;

	return false;

no_present:
	drop_spte(vcpu->kvm, spte);
	return true;
}

/*
 * For PTTYPE_EPT, a page table can be executable but not readable
 * on supported processors. Therefore, set_spte does not automatically
 * set bit 0 if execute only is supported. Here, we repurpose ACC_USER_MASK
 * to signify readability since it isn't used in the EPT case
 */
static inline unsigned FNAME(gpte_access)(u64 gpte)
{
	unsigned access;
#if PTTYPE == PTTYPE_EPT
	access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
		((gpte & VMX_EPT_READABLE_MASK) ? ACC_USER_MASK : 0);
#else
	BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK);
	BUILD_BUG_ON(ACC_EXEC_MASK != 1);
	access = gpte & (PT_WRITABLE_MASK | PT_USER_MASK | PT_PRESENT_MASK);
	/* Combine NX with P (which is set here) to get ACC_EXEC_MASK.  */
	access ^= (gpte >> PT64_NX_SHIFT);
#endif

	return access;
}

static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
					     struct kvm_mmu *mmu,
					     struct guest_walker *walker,
					     gpa_t addr, int write_fault)
{
	unsigned level, index;
	pt_element_t pte, orig_pte;
	pt_element_t __user *ptep_user;
	gfn_t table_gfn;
	int ret;

	/* dirty/accessed bits are not supported, so no need to update them */
	if (!PT_HAVE_ACCESSED_DIRTY(mmu))
		return 0;

	for (level = walker->max_level; level >= walker->level; --level) {
		pte = orig_pte = walker->ptes[level - 1];
		table_gfn = walker->table_gfn[level - 1];
		ptep_user = walker->ptep_user[level - 1];
		index = offset_in_page(ptep_user) / sizeof(pt_element_t);
		if (!(pte & PT_GUEST_ACCESSED_MASK)) {
			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
			pte |= PT_GUEST_ACCESSED_MASK;
		}
		if (level == walker->level && write_fault &&
				!(pte & PT_GUEST_DIRTY_MASK)) {
			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
#if PTTYPE == PTTYPE_EPT
			if (kvm_x86_ops.nested_ops->write_log_dirty(vcpu, addr))
				return -EINVAL;
#endif
			pte |= PT_GUEST_DIRTY_MASK;
		}
		if (pte == orig_pte)
			continue;

		/*
		 * If the slot is read-only, simply do not process the accessed
		 * and dirty bits.  This is the correct thing to do if the slot
		 * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
		 * are only supported if the accessed and dirty bits are already
		 * set in the ROM (so that MMIO writes are never needed).
		 *
		 * Note that NPT does not allow this at all and faults, since
		 * it always wants nested page table entries for the guest
		 * page tables to be writable.  And EPT works but will simply
		 * overwrite the read-only memory to set the accessed and dirty
		 * bits.
		 */
		if (unlikely(!walker->pte_writable[level - 1]))
			continue;

		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
		if (ret)
			return ret;

		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
		walker->ptes[level - 1] = pte;
	}
	return 0;
}

static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
{
	unsigned pkeys = 0;
#if PTTYPE == 64
	pte_t pte = {.pte = gpte};

	pkeys = pte_flags_pkey(pte_flags(pte));
#endif
	return pkeys;
}

static inline bool FNAME(is_last_gpte)(struct kvm_mmu *mmu,
				       unsigned int level, unsigned int gpte)
{
	/*
	 * For EPT and PAE paging (both variants), bit 7 is either reserved at
	 * all level or indicates a huge page (ignoring CR3/EPTP).  In either
	 * case, bit 7 being set terminates the walk.
	 */
#if PTTYPE == 32
	/*
	 * 32-bit paging requires special handling because bit 7 is ignored if
	 * CR4.PSE=0, not reserved.  Clear bit 7 in the gpte if the level is
	 * greater than the last level for which bit 7 is the PAGE_SIZE bit.
	 *
	 * The RHS has bit 7 set iff level < (2 + PSE).  If it is clear, bit 7
	 * is not reserved and does not indicate a large page at this level,
	 * so clear PT_PAGE_SIZE_MASK in gpte if that is the case.
	 */
	gpte &= level - (PT32_ROOT_LEVEL + mmu->mmu_role.ext.cr4_pse);
#endif
	/*
	 * PG_LEVEL_4K always terminates.  The RHS has bit 7 set
	 * iff level <= PG_LEVEL_4K, which for our purpose means
	 * level == PG_LEVEL_4K; set PT_PAGE_SIZE_MASK in gpte then.
	 */
	gpte |= level - PG_LEVEL_4K - 1;

	return gpte & PT_PAGE_SIZE_MASK;
}
/*
 * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
 */
static int FNAME(walk_addr_generic)(struct guest_walker *walker,
				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
				    gpa_t addr, u32 access)
{
	int ret;
	pt_element_t pte;
	pt_element_t __user *ptep_user;
	gfn_t table_gfn;
	u64 pt_access, pte_access;
	unsigned index, accessed_dirty, pte_pkey;
	unsigned nested_access;
	gpa_t pte_gpa;
	bool have_ad;
	int offset;
	u64 walk_nx_mask = 0;
	const int write_fault = access & PFERR_WRITE_MASK;
	const int user_fault  = access & PFERR_USER_MASK;
	const int fetch_fault = access & PFERR_FETCH_MASK;
	u16 errcode = 0;
	gpa_t real_gpa;
	gfn_t gfn;

	trace_kvm_mmu_pagetable_walk(addr, access);
retry_walk:
	walker->level = mmu->root_level;
	pte           = mmu->get_guest_pgd(vcpu);
	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);

#if PTTYPE == 64
	walk_nx_mask = 1ULL << PT64_NX_SHIFT;
	if (walker->level == PT32E_ROOT_LEVEL) {
		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
		trace_kvm_mmu_paging_element(pte, walker->level);
		if (!FNAME(is_present_gpte)(pte))
			goto error;
		--walker->level;
	}
#endif
	walker->max_level = walker->level;
	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));

	/*
	 * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
	 * by the MOV to CR instruction are treated as reads and do not cause the
	 * processor to set the dirty flag in any EPT paging-structure entry.
	 */
	nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;

	pte_access = ~0;
	++walker->level;

	do {
		unsigned long host_addr;

		pt_access = pte_access;
		--walker->level;

		index = PT_INDEX(addr, walker->level);
		table_gfn = gpte_to_gfn(pte);
		offset    = index * sizeof(pt_element_t);
		pte_gpa   = gfn_to_gpa(table_gfn) + offset;

		BUG_ON(walker->level < 1);
		walker->table_gfn[walker->level - 1] = table_gfn;
		walker->pte_gpa[walker->level - 1] = pte_gpa;

		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
					      nested_access,
					      &walker->fault);

		/*
		 * FIXME: This can happen if emulation (for of an INS/OUTS
		 * instruction) triggers a nested page fault.  The exit
		 * qualification / exit info field will incorrectly have
		 * "guest page access" as the nested page fault's cause,
		 * instead of "guest page structure access".  To fix this,
		 * the x86_exception struct should be augmented with enough
		 * information to fix the exit_qualification or exit_info_1
		 * fields.
		 */
		if (unlikely(real_gpa == UNMAPPED_GVA))
			return 0;

		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
					    &walker->pte_writable[walker->level - 1]);
		if (unlikely(kvm_is_error_hva(host_addr)))
			goto error;

		ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
		if (unlikely(__get_user(pte, ptep_user)))
			goto error;
		walker->ptep_user[walker->level - 1] = ptep_user;

		trace_kvm_mmu_paging_element(pte, walker->level);

		/*
		 * Inverting the NX it lets us AND it like other
		 * permission bits.
		 */
		pte_access = pt_access & (pte ^ walk_nx_mask);

		if (unlikely(!FNAME(is_present_gpte)(pte)))
			goto error;

		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) {
			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
			goto error;
		}

		walker->ptes[walker->level - 1] = pte;

		/* Convert to ACC_*_MASK flags for struct guest_walker.  */
		walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
	} while (!FNAME(is_last_gpte)(mmu, walker->level, pte));

	pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
	accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;

	/* Convert to ACC_*_MASK flags for struct guest_walker.  */
	walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask);
	errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
	if (unlikely(errcode))
		goto error;

	gfn = gpte_to_gfn_lvl(pte, walker->level);
	gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;

	if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
		gfn += pse36_gfn_delta(pte);

	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
	if (real_gpa == UNMAPPED_GVA)
		return 0;

	walker->gfn = real_gpa >> PAGE_SHIFT;

	if (!write_fault)
		FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
	else
		/*
		 * On a write fault, fold the dirty bit into accessed_dirty.
		 * For modes without A/D bits support accessed_dirty will be
		 * always clear.
		 */
		accessed_dirty &= pte >>
			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);

	if (unlikely(!accessed_dirty)) {
		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
							addr, write_fault);
		if (unlikely(ret < 0))
			goto error;
		else if (ret)
			goto retry_walk;
	}

	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
		 __func__, (u64)pte, walker->pte_access,
		 walker->pt_access[walker->level - 1]);
	return 1;

error:
	errcode |= write_fault | user_fault;
	if (fetch_fault && (is_efer_nx(mmu) || is_cr4_smep(mmu)))
		errcode |= PFERR_FETCH_MASK;

	walker->fault.vector = PF_VECTOR;
	walker->fault.error_code_valid = true;
	walker->fault.error_code = errcode;

#if PTTYPE == PTTYPE_EPT
	/*
	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
	 * misconfiguration requires to be injected. The detection is
	 * done by is_rsvd_bits_set() above.
	 *
	 * We set up the value of exit_qualification to inject:
	 * [2:0] - Derive from the access bits. The exit_qualification might be
	 *         out of date if it is serving an EPT misconfiguration.
	 * [5:3] - Calculated by the page walk of the guest EPT page tables
	 * [7:8] - Derived from [7:8] of real exit_qualification
	 *
	 * The other bits are set to 0.
	 */
	if (!(errcode & PFERR_RSVD_MASK)) {
		vcpu->arch.exit_qualification &= 0x180;
		if (write_fault)
			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
		if (user_fault)
			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ;
		if (fetch_fault)
			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
		vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
	}
#endif
	walker->fault.address = addr;
	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
	walker->fault.async_page_fault = false;

	trace_kvm_mmu_walker_error(walker->fault.error_code);
	return 0;
}

static int FNAME(walk_addr)(struct guest_walker *walker,
			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
{
	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
					access);
}

#if PTTYPE != PTTYPE_EPT
static int FNAME(walk_addr_nested)(struct guest_walker *walker,
				   struct kvm_vcpu *vcpu, gva_t addr,
				   u32 access)
{
	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
					addr, access);
}
#endif

static bool
FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
		     u64 *spte, pt_element_t gpte, bool no_dirty_log)
{
	unsigned pte_access;
	gfn_t gfn;
	kvm_pfn_t pfn;

	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
		return false;

	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);

	gfn = gpte_to_gfn(gpte);
	pte_access = sp->role.access & FNAME(gpte_access)(gpte);
	FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
			no_dirty_log && (pte_access & ACC_WRITE_MASK));
	if (is_error_pfn(pfn))
		return false;

	/*
	 * we call mmu_set_spte() with host_writable = true because
	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
	 */
	mmu_set_spte(vcpu, spte, pte_access, false, PG_LEVEL_4K, gfn, pfn,
		     true, true);

	kvm_release_pfn_clean(pfn);
	return true;
}

static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			      u64 *spte, const void *pte)
{
	pt_element_t gpte = *(const pt_element_t *)pte;

	FNAME(prefetch_gpte)(vcpu, sp, spte, gpte, false);
}

static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
				struct guest_walker *gw, int level)
{
	pt_element_t curr_pte;
	gpa_t base_gpa, pte_gpa = gw->pte_gpa[level - 1];
	u64 mask;
	int r, index;

	if (level == PG_LEVEL_4K) {
		mask = PTE_PREFETCH_NUM * sizeof(pt_element_t) - 1;
		base_gpa = pte_gpa & ~mask;
		index = (pte_gpa - base_gpa) / sizeof(pt_element_t);

		r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa,
				gw->prefetch_ptes, sizeof(gw->prefetch_ptes));
		curr_pte = gw->prefetch_ptes[index];
	} else
		r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa,
				  &curr_pte, sizeof(curr_pte));

	return r || curr_pte != gw->ptes[level - 1];
}

static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
				u64 *sptep)
{
	struct kvm_mmu_page *sp;
	pt_element_t *gptep = gw->prefetch_ptes;
	u64 *spte;
	int i;

	sp = sptep_to_sp(sptep);

	if (sp->role.level > PG_LEVEL_4K)
		return;

	/*
	 * If addresses are being invalidated, skip prefetching to avoid
	 * accidentally prefetching those addresses.
	 */
	if (unlikely(vcpu->kvm->mmu_notifier_count))
		return;

	if (sp->role.direct)
		return __direct_pte_prefetch(vcpu, sp, sptep);

	i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1);
	spte = sp->spt + i;

	for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
		if (spte == sptep)
			continue;

		if (is_shadow_present_pte(*spte))
			continue;

		if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true))
			break;
	}
}

/*
 * Fetch a shadow pte for a specific level in the paging hierarchy.
 * If the guest tries to write a write-protected page, we need to
 * emulate this operation, return 1 to indicate this case.
 */
static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
			 struct guest_walker *gw, u32 error_code,
			 int max_level, kvm_pfn_t pfn, bool map_writable,
			 bool prefault)
{
	bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
	bool write_fault = error_code & PFERR_WRITE_MASK;
	bool exec = error_code & PFERR_FETCH_MASK;
	bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
	struct kvm_mmu_page *sp = NULL;
	struct kvm_shadow_walk_iterator it;
	unsigned int direct_access, access;
	int top_level, level, req_level, ret;
	gfn_t base_gfn = gw->gfn;

	direct_access = gw->pte_access;

	top_level = vcpu->arch.mmu->root_level;
	if (top_level == PT32E_ROOT_LEVEL)
		top_level = PT32_ROOT_LEVEL;
	/*
	 * Verify that the top-level gpte is still there.  Since the page
	 * is a root page, it is either write protected (and cannot be
	 * changed from now on) or it is invalid (in which case, we don't
	 * really care if it changes underneath us after this point).
	 */
	if (FNAME(gpte_changed)(vcpu, gw, top_level))
		goto out_gpte_changed;

	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
		goto out_gpte_changed;

	for (shadow_walk_init(&it, vcpu, addr);
	     shadow_walk_okay(&it) && it.level > gw->level;
	     shadow_walk_next(&it)) {
		gfn_t table_gfn;

		clear_sp_write_flooding_count(it.sptep);
		drop_large_spte(vcpu, it.sptep);

		sp = NULL;
		if (!is_shadow_present_pte(*it.sptep)) {
			table_gfn = gw->table_gfn[it.level - 2];
			access = gw->pt_access[it.level - 2];
			sp = kvm_mmu_get_page(vcpu, table_gfn, addr,
					      it.level-1, false, access);
			/*
			 * We must synchronize the pagetable before linking it
			 * because the guest doesn't need to flush tlb when
			 * the gpte is changed from non-present to present.
			 * Otherwise, the guest may use the wrong mapping.
			 *
			 * For PG_LEVEL_4K, kvm_mmu_get_page() has already
			 * synchronized it transiently via kvm_sync_page().
			 *
			 * For higher level pagetable, we synchronize it via
			 * the slower mmu_sync_children().  If it needs to
			 * break, some progress has been made; return
			 * RET_PF_RETRY and retry on the next #PF.
			 * KVM_REQ_MMU_SYNC is not necessary but it
			 * expedites the process.
			 */
			if (sp->unsync_children &&
			    mmu_sync_children(vcpu, sp, false))
				return RET_PF_RETRY;
		}

		/*
		 * Verify that the gpte in the page we've just write
		 * protected is still there.
		 */
		if (FNAME(gpte_changed)(vcpu, gw, it.level - 1))
			goto out_gpte_changed;

		if (sp)
			link_shadow_page(vcpu, it.sptep, sp);
	}

	level = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn,
					huge_page_disallowed, &req_level);

	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);

	for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
		clear_sp_write_flooding_count(it.sptep);

		/*
		 * We cannot overwrite existing page tables with an NX
		 * large page, as the leaf could be executable.
		 */
		if (nx_huge_page_workaround_enabled)
			disallowed_hugepage_adjust(*it.sptep, gw->gfn, it.level,
						   &pfn, &level);

		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
		if (it.level == level)
			break;

		validate_direct_spte(vcpu, it.sptep, direct_access);

		drop_large_spte(vcpu, it.sptep);

		if (!is_shadow_present_pte(*it.sptep)) {
			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
					      it.level - 1, true, direct_access);
			link_shadow_page(vcpu, it.sptep, sp);
			if (huge_page_disallowed && req_level >= it.level)
				account_huge_nx_page(vcpu->kvm, sp);
		}
	}

	ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
			   it.level, base_gfn, pfn, prefault, map_writable);
	if (ret == RET_PF_SPURIOUS)
		return ret;

	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
	++vcpu->stat.pf_fixed;
	return ret;

out_gpte_changed:
	return RET_PF_RETRY;
}

 /*
 * To see whether the mapped gfn can write its page table in the current
 * mapping.
 *
 * It is the helper function of FNAME(page_fault). When guest uses large page
 * size to map the writable gfn which is used as current page table, we should
 * force kvm to use small page size to map it because new shadow page will be
 * created when kvm establishes shadow page table that stop kvm using large
 * page size. Do it early can avoid unnecessary #PF and emulation.
 *
 * @write_fault_to_shadow_pgtable will return true if the fault gfn is
 * currently used as its page table.
 *
 * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok
 * since the PDPT is always shadowed, that means, we can not use large page
 * size to map the gfn which is used as PDPT.
 */
static bool
FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
			      struct guest_walker *walker, bool user_fault,
			      bool *write_fault_to_shadow_pgtable)
{
	int level;
	gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1);
	bool self_changed = false;

	if (!(walker->pte_access & ACC_WRITE_MASK ||
	    (!is_cr0_wp(vcpu->arch.mmu) && !user_fault)))
		return false;

	for (level = walker->level; level <= walker->max_level; level++) {
		gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1];

		self_changed |= !(gfn & mask);
		*write_fault_to_shadow_pgtable |= !gfn;
	}

	return self_changed;
}

/*
 * Page fault handler.  There are several causes for a page fault:
 *   - there is no shadow pte for the guest pte
 *   - write access through a shadow pte marked read only so that we can set
 *     the dirty bit
 *   - write access to a shadow pte marked read only so we can update the page
 *     dirty bitmap, when userspace requests it
 *   - mmio access; in this case we will never install a present shadow pte
 *   - normal guest page fault due to the guest pte marked not present, not
 *     writable, or not executable
 *
 *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
 *           a negative value on error.
 */
static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
			     bool prefault)
{
	bool write_fault = error_code & PFERR_WRITE_MASK;
	bool user_fault = error_code & PFERR_USER_MASK;
	struct guest_walker walker;
	int r;
	kvm_pfn_t pfn;
	hva_t hva;
	unsigned long mmu_seq;
	bool map_writable, is_self_change_mapping;
	int max_level;

	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);

	/*
	 * If PFEC.RSVD is set, this is a shadow page fault.
	 * The bit needs to be cleared before walking guest page tables.
	 */
	error_code &= ~PFERR_RSVD_MASK;

	/*
	 * Look up the guest pte for the faulting address.
	 */
	r = FNAME(walk_addr)(&walker, vcpu, addr, error_code);

	/*
	 * The page is not mapped by the guest.  Let the guest handle it.
	 */
	if (!r) {
		pgprintk("%s: guest page fault\n", __func__);
		if (!prefault)
			kvm_inject_emulated_page_fault(vcpu, &walker.fault);

		return RET_PF_RETRY;
	}

	if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
		shadow_page_table_clear_flood(vcpu, addr);
		return RET_PF_EMULATE;
	}

	r = mmu_topup_memory_caches(vcpu, true);
	if (r)
		return r;

	vcpu->arch.write_fault_to_shadow_pgtable = false;

	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);

	if (is_self_change_mapping)
		max_level = PG_LEVEL_4K;
	else
		max_level = walker.level;

	mmu_seq = vcpu->kvm->mmu_notifier_seq;
	smp_rmb();

	if (kvm_faultin_pfn(vcpu, prefault, walker.gfn, addr, &pfn, &hva,
			 write_fault, &map_writable, &r))
		return r;

	if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
		return r;

	/*
	 * Do not change pte_access if the pfn is a mmio page, otherwise
	 * we will cache the incorrect access into mmio spte.
	 */
	if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) &&
	    !is_cr0_wp(vcpu->arch.mmu) && !user_fault && !is_noslot_pfn(pfn)) {
		walker.pte_access |= ACC_WRITE_MASK;
		walker.pte_access &= ~ACC_USER_MASK;

		/*
		 * If we converted a user page to a kernel page,
		 * so that the kernel can write to it when cr0.wp=0,
		 * then we should prevent the kernel from executing it
		 * if SMEP is enabled.
		 */
		if (is_cr4_smep(vcpu->arch.mmu))
			walker.pte_access &= ~ACC_EXEC_MASK;
	}

	r = RET_PF_RETRY;
	write_lock(&vcpu->kvm->mmu_lock);
	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
		goto out_unlock;

	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
	r = make_mmu_pages_available(vcpu);
	if (r)
		goto out_unlock;
	r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn,
			 map_writable, prefault);
	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);

out_unlock:
	write_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return r;
}

static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
{
	int offset = 0;

	WARN_ON(sp->role.level != PG_LEVEL_4K);

	if (PTTYPE == 32)
		offset = sp->role.quadrant << PT64_LEVEL_BITS;

	return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
}

static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
{
	struct kvm_shadow_walk_iterator iterator;
	struct kvm_mmu_page *sp;
	u64 old_spte;
	int level;
	u64 *sptep;

	vcpu_clear_mmio_info(vcpu, gva);

	/*
	 * No need to check return value here, rmap_can_add() can
	 * help us to skip pte prefetch later.
	 */
	mmu_topup_memory_caches(vcpu, true);

	if (!VALID_PAGE(root_hpa)) {
		WARN_ON(1);
		return;
	}

	write_lock(&vcpu->kvm->mmu_lock);
	for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) {
		level = iterator.level;
		sptep = iterator.sptep;

		sp = sptep_to_sp(sptep);
		old_spte = *sptep;
		if (is_last_spte(old_spte, level)) {
			pt_element_t gpte;
			gpa_t pte_gpa;

			if (!sp->unsync)
				break;

			pte_gpa = FNAME(get_level1_sp_gpa)(sp);
			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);

			mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
			if (is_shadow_present_pte(old_spte))
				kvm_flush_remote_tlbs_with_address(vcpu->kvm,
					sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));

			if (!rmap_can_add(vcpu))
				break;

			if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
						       sizeof(pt_element_t)))
				break;

			FNAME(update_pte)(vcpu, sp, sptep, &gpte);
		}

		if (!is_shadow_present_pte(*sptep) || !sp->unsync_children)
			break;
	}
	write_unlock(&vcpu->kvm->mmu_lock);
}

/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
			       struct x86_exception *exception)
{
	struct guest_walker walker;
	gpa_t gpa = UNMAPPED_GVA;
	int r;

	r = FNAME(walk_addr)(&walker, vcpu, addr, access);

	if (r) {
		gpa = gfn_to_gpa(walker.gfn);
		gpa |= addr & ~PAGE_MASK;
	} else if (exception)
		*exception = walker.fault;

	return gpa;
}

#if PTTYPE != PTTYPE_EPT
/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
				      u32 access,
				      struct x86_exception *exception)
{
	struct guest_walker walker;
	gpa_t gpa = UNMAPPED_GVA;
	int r;

#ifndef CONFIG_X86_64
	/* A 64-bit GVA should be impossible on 32-bit KVM. */
	WARN_ON_ONCE(vaddr >> 32);
#endif

	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);

	if (r) {
		gpa = gfn_to_gpa(walker.gfn);
		gpa |= vaddr & ~PAGE_MASK;
	} else if (exception)
		*exception = walker.fault;

	return gpa;
}
#endif

/*
 * Using the cached information from sp->gfns is safe because:
 * - The spte has a reference to the struct page, so the pfn for a given gfn
 *   can't change unless all sptes pointing to it are nuked first.
 */
static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
	union kvm_mmu_page_role mmu_role = vcpu->arch.mmu->mmu_role.base;
	int i, nr_present = 0;
	bool host_writable;
	gpa_t first_pte_gpa;
	int set_spte_ret = 0;

	/*
	 * Ignore various flags when verifying that it's safe to sync a shadow
	 * page using the current MMU context.
	 *
	 *  - level: not part of the overall MMU role and will never match as the MMU's
	 *           level tracks the root level
	 *  - access: updated based on the new guest PTE
	 *  - quadrant: not part of the overall MMU role (similar to level)
	 */
	const union kvm_mmu_page_role sync_role_ign = {
		.level = 0xf,
		.access = 0x7,
		.quadrant = 0x3,
	};

	/*
	 * Direct pages can never be unsync, and KVM should never attempt to
	 * sync a shadow page for a different MMU context, e.g. if the role
	 * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the
	 * reserved bits checks will be wrong, etc...
	 */
	if (WARN_ON_ONCE(sp->role.direct ||
			 (sp->role.word ^ mmu_role.word) & ~sync_role_ign.word))
		return 0;

	first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);

	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
		unsigned pte_access;
		pt_element_t gpte;
		gpa_t pte_gpa;
		gfn_t gfn;

		if (!sp->spt[i])
			continue;

		pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);

		if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
					       sizeof(pt_element_t)))
			return 0;

		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
			continue;
		}

		gfn = gpte_to_gfn(gpte);
		pte_access = sp->role.access;
		pte_access &= FNAME(gpte_access)(gpte);
		FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);

		if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
		      &nr_present))
			continue;

		if (gfn != sp->gfns[i]) {
			drop_spte(vcpu->kvm, &sp->spt[i]);
			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
			continue;
		}

		nr_present++;

		host_writable = sp->spt[i] & shadow_host_writable_mask;

		set_spte_ret |= set_spte(vcpu, &sp->spt[i],
					 pte_access, PG_LEVEL_4K,
					 gfn, spte_to_pfn(sp->spt[i]),
					 true, false, host_writable);
	}

	if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH)
		kvm_flush_remote_tlbs(vcpu->kvm);

	return nr_present;
}

#undef pt_element_t
#undef guest_walker
#undef FNAME
#undef PT_BASE_ADDR_MASK
#undef PT_INDEX
#undef PT_LVL_ADDR_MASK
#undef PT_LVL_OFFSET_MASK
#undef PT_LEVEL_BITS
#undef PT_MAX_FULL_LEVELS
#undef gpte_to_gfn
#undef gpte_to_gfn_lvl
#undef CMPXCHG
#undef PT_GUEST_ACCESSED_MASK
#undef PT_GUEST_DIRTY_MASK
#undef PT_GUEST_DIRTY_SHIFT
#undef PT_GUEST_ACCESSED_SHIFT
#undef PT_HAVE_ACCESSED_DIRTY