summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/paging_tmpl.h
blob: 2ce4f05e81d3804cef4ded542a105a5a917b8bed (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
/*
 * 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>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

/*
 * 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.
 */

/*
 * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro
 * uses for EPT without A/D paging type.
 */
extern u64 __pure __using_nonexistent_pte_bit(void)
	       __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT");

#if PTTYPE == 64
	#define pt_element_t u64
	#define guest_walker guest_walker64
	#define FNAME(name) paging##64_##name
	#define PT_BASE_ADDR_MASK 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_ACCESSED_MASK PT_ACCESSED_MASK
	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
	#ifdef CONFIG_X86_64
	#define PT_MAX_FULL_LEVELS 4
	#define CMPXCHG cmpxchg
	#else
	#define CMPXCHG cmpxchg64
	#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_ACCESSED_MASK PT_ACCESSED_MASK
	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
	#define CMPXCHG cmpxchg
#elif PTTYPE == PTTYPE_EPT
	#define pt_element_t u64
	#define guest_walker guest_walkerEPT
	#define FNAME(name) ept_##name
	#define PT_BASE_ADDR_MASK 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_ACCESSED_MASK 0
	#define PT_GUEST_DIRTY_MASK 0
	#define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit()
	#define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit()
	#define CMPXCHG cmpxchg64
	#define PT_MAX_FULL_LEVELS 4
#else
	#error Invalid PTTYPE value
#endif

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

/*
 * 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 pt_access;
	unsigned 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)(unsigned *access, unsigned gpte)
{
	unsigned mask;

	/* dirty bit is not supported, so no need to track it */
	if (!PT_GUEST_DIRTY_MASK)
		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 is_present_gpte(pte);
#else
	return pte & 7;
#endif
}

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 npages;
	pt_element_t ret;
	pt_element_t *table;
	struct page *page;

	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
	/* Check if the user is doing something meaningless. */
	if (unlikely(npages != 1))
		return -EFAULT;

	table = kmap_atomic(page);
	ret = CMPXCHG(&table[index], orig_pte, new_pte);
	kunmap_atomic(table);

	kvm_release_page_dirty(page);

	return (ret != orig_pte);
}

static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
				  struct kvm_mmu_page *sp, u64 *spte,
				  u64 gpte)
{
	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
		goto no_present;

	if (!FNAME(is_present_gpte)(gpte))
		goto no_present;

	/* if accessed bit is not supported prefetch non accessed gpte */
	if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK))
		goto no_present;

	return false;

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

static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, 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) |
		ACC_USER_MASK;
#else
	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | 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,
					     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_GUEST_DIRTY_MASK)
		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));
			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;
}

/*
 * Fetch a guest pte for a guest virtual address
 */
static int FNAME(walk_addr_generic)(struct guest_walker *walker,
				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
				    gva_t addr, u32 access)
{
	int ret;
	pt_element_t pte;
	pt_element_t __user *uninitialized_var(ptep_user);
	gfn_t table_gfn;
	unsigned index, pt_access, pte_access, accessed_dirty;
	gpa_t pte_gpa;
	int offset;
	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_cr3(vcpu);

#if PTTYPE == 64
	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)));

	accessed_dirty = PT_GUEST_ACCESSED_MASK;
	pt_access = pte_access = ACC_ALL;
	++walker->level;

	do {
		gfn_t real_gfn;
		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;
		walker->table_gfn[walker->level - 1] = table_gfn;
		walker->pte_gpa[walker->level - 1] = pte_gpa;

		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
					      PFERR_USER_MASK|PFERR_WRITE_MASK,
					      &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_gfn == UNMAPPED_GVA))
			return 0;

		real_gfn = gpa_to_gfn(real_gfn);

		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
					    &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(__copy_from_user(&pte, ptep_user, sizeof(pte))))
			goto error;
		walker->ptep_user[walker->level - 1] = ptep_user;

		trace_kvm_mmu_paging_element(pte, walker->level);

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

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

		accessed_dirty &= pte;
		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);

		walker->ptes[walker->level - 1] = pte;
	} while (!is_last_gpte(mmu, walker->level, pte));

	if (unlikely(permission_fault(vcpu, mmu, pte_access, access))) {
		errcode |= PFERR_PRESENT_MASK;
		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 == PT_DIRECTORY_LEVEL && 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)(&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, write_fault);
		if (unlikely(ret < 0))
			goto error;
		else if (ret)
			goto retry_walk;
	}

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

error:
	errcode |= write_fault | user_fault;
	if (fetch_fault && (mmu->nx ||
			    kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)))
		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 [2:0] of real exit_qualification at EPT violation
	 * [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 &= 0x187;
		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
	}
#endif
	walker->fault.address = addr;
	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;

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

static int FNAME(walk_addr)(struct guest_walker *walker,
			    struct kvm_vcpu *vcpu, gva_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)(vcpu, gpte);
	FNAME(protect_clean_gpte)(&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, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn,
		     true, true);

	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 == PT_PAGE_TABLE_LEVEL) {
		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 = page_header(__pa(sptep));

	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
		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, gva_t addr,
			 struct guest_walker *gw,
			 int write_fault, int hlevel,
			 kvm_pfn_t pfn, bool map_writable, bool prefault)
{
	struct kvm_mmu_page *sp = NULL;
	struct kvm_shadow_walk_iterator it;
	unsigned direct_access, access = gw->pt_access;
	int top_level, emulate;

	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 (!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];
			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
					      false, access);
		}

		/*
		 * 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);
	}

	for (;
	     shadow_walk_okay(&it) && it.level > hlevel;
	     shadow_walk_next(&it)) {
		gfn_t direct_gfn;

		clear_sp_write_flooding_count(it.sptep);
		validate_direct_spte(vcpu, it.sptep, direct_access);

		drop_large_spte(vcpu, it.sptep);

		if (is_shadow_present_pte(*it.sptep))
			continue;

		direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);

		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
				      true, direct_access);
		link_shadow_page(vcpu, it.sptep, sp);
	}

	clear_sp_write_flooding_count(it.sptep);
	emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
			       it.level, gw->gfn, pfn, prefault, map_writable);
	FNAME(pte_prefetch)(vcpu, gw, it.sptep);

	return emulate;

out_gpte_changed:
	kvm_release_pfn_clean(pfn);
	return 0;
}

 /*
 * 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, int 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_write_protection(vcpu) && !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, gva_t addr, u32 error_code,
			     bool prefault)
{
	int write_fault = error_code & PFERR_WRITE_MASK;
	int user_fault = error_code & PFERR_USER_MASK;
	struct guest_walker walker;
	int r;
	kvm_pfn_t pfn;
	int level = PT_PAGE_TABLE_LEVEL;
	bool force_pt_level = false;
	unsigned long mmu_seq;
	bool map_writable, is_self_change_mapping;

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

	if (unlikely(error_code & PFERR_RSVD_MASK)) {
		r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu));
		if (likely(r != RET_MMIO_PF_INVALID))
			return r;

		/*
		 * page fault with PFEC.RSVD  = 1 is caused by shadow
		 * page fault, should not be used to walk guest page
		 * table.
		 */
		error_code &= ~PFERR_RSVD_MASK;
	};

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

	/*
	 * 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)
			inject_page_fault(vcpu, &walker.fault);

		return 0;
	}

	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 (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) {
		level = mapping_level(vcpu, walker.gfn, &force_pt_level);
		if (likely(!force_pt_level)) {
			level = min(walker.level, level);
			walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
		}
	} else
		force_pt_level = true;

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

	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
			 &map_writable))
		return 0;

	if (handle_abnormal_pfn(vcpu, mmu_is_nested(vcpu) ? 0 : 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_write_protection(vcpu) && !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 (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
			walker.pte_access &= ~ACC_EXEC_MASK;
	}

	spin_lock(&vcpu->kvm->mmu_lock);
	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
		goto out_unlock;

	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
	make_mmu_pages_available(vcpu);
	if (!force_pt_level)
		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
			 level, pfn, map_writable, prefault);
	++vcpu->stat.pf_fixed;
	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
	spin_unlock(&vcpu->kvm->mmu_lock);

	return r;

out_unlock:
	spin_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return 0;
}

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

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

	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)
{
	struct kvm_shadow_walk_iterator iterator;
	struct kvm_mmu_page *sp;
	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);

	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) {
		WARN_ON(1);
		return;
	}

	spin_lock(&vcpu->kvm->mmu_lock);
	for_each_shadow_entry(vcpu, gva, iterator) {
		level = iterator.level;
		sptep = iterator.sptep;

		sp = page_header(__pa(sptep));
		if (is_last_spte(*sptep, 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);

			if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
				kvm_flush_remote_tlbs(vcpu->kvm);

			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;
	}
	spin_unlock(&vcpu->kvm->mmu_lock);
}

static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
			       struct x86_exception *exception)
{
	struct guest_walker walker;
	gpa_t gpa = UNMAPPED_GVA;
	int r;

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

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

	return gpa;
}

#if PTTYPE != PTTYPE_EPT
static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
				      u32 access,
				      struct x86_exception *exception)
{
	struct guest_walker walker;
	gpa_t gpa = UNMAPPED_GVA;
	int r;

	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.
 *
 * Note:
 *   We should flush all tlbs if spte is dropped even though guest is
 *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
 *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
 *   used by guest then tlbs are not flushed, so guest is allowed to access the
 *   freed pages.
 *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
 */
static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
	int i, nr_present = 0;
	bool host_writable;
	gpa_t first_pte_gpa;

	/* direct kvm_mmu_page can not be unsync. */
	BUG_ON(sp->role.direct);

	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 -EINVAL;

		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
			vcpu->kvm->tlbs_dirty++;
			continue;
		}

		gfn = gpte_to_gfn(gpte);
		pte_access = sp->role.access;
		pte_access &= FNAME(gpte_access)(vcpu, gpte);
		FNAME(protect_clean_gpte)(&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]);
			vcpu->kvm->tlbs_dirty++;
			continue;
		}

		nr_present++;

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

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

	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