summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu/paging_tmpl.h
blob: d3dbcf382ed2d43977e909f9760d2648bf2c745e (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
/* 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>
 */

/*
 * The MMU needs to be able to access/walk 32-bit and 64-bit guest page tables,
 * as well as guest EPT tables, so the code in this file is compiled thrice,
 * once per guest PTE type.  The per-type defines are #undef'd at the end.
 */

#if PTTYPE == 64
	#define pt_element_t u64
	#define guest_walker guest_walker64
	#define FNAME(name) paging##64_##name
	#define PT_LEVEL_BITS 9
	#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
	#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_LEVEL_BITS 10
	#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 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)
#elif PTTYPE == PTTYPE_EPT
	#define pt_element_t u64
	#define guest_walker guest_walkerEPT
	#define FNAME(name) ept_##name
	#define PT_LEVEL_BITS 9
	#define PT_GUEST_DIRTY_SHIFT 9
	#define PT_GUEST_ACCESSED_SHIFT 8
	#define PT_HAVE_ACCESSED_DIRTY(mmu) (!(mmu)->cpu_role.base.ad_disabled)
	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
#else
	#error Invalid PTTYPE value
#endif

/* Common logic, but per-type values.  These also need to be undefined. */
#define PT_BASE_ADDR_MASK	((pt_element_t)__PT_BASE_ADDR_MASK)
#define PT_LVL_ADDR_MASK(lvl)	__PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
#define PT_LVL_OFFSET_MASK(lvl)	__PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
#define PT_INDEX(addr, lvl)	__PT_INDEX(addr, lvl, PT_LEVEL_BITS)

#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;
};

#if PTTYPE == 32
static inline gfn_t pse36_gfn_delta(u32 gpte)
{
	int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;

	return (gpte & PT32_DIR_PSE36_MASK) << shift;
}
#endif

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 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;

	/* Prefetch only accessed entries (unless A/D bits are disabled). */
	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 = __try_cmpxchg_user(ptep_user, &orig_pte, pte, fault);
		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->cpu_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, u64 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;
	u64 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->cpu_role.base.level;
	pte           = kvm_mmu_get_guest_pgd(vcpu, mmu);
	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;

	/*
	 * 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;

	/*
	 * Queue a page fault for injection if this assertion fails, as callers
	 * assume that walker.fault contains sane info on a walk failure.  I.e.
	 * avoid making the situation worse by inducing even worse badness
	 * between when the assertion fails and when KVM kicks the vCPU out to
	 * userspace (because the VM is bugged).
	 */
	if (KVM_BUG_ON(is_long_mode(vcpu) && !is_pae(vcpu), vcpu->kvm))
		goto error;

	++walker->level;

	do {
		struct kvm_memory_slot *slot;
		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 = kvm_translate_gpa(vcpu, mmu, 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 == INVALID_GPA))
			return 0;

		slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(real_gpa));
		if (!kvm_is_visible_memslot(slot))
			goto error;

		host_addr = gfn_to_hva_memslot_prot(slot, 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
	if (walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
		gfn += pse36_gfn_delta(pte);
#endif

	real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault);
	if (real_gpa == INVALID_GPA)
		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;
	}

	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 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)) {
		walker->fault.exit_qualification = 0;

		if (write_fault)
			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
		if (user_fault)
			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ;
		if (fetch_fault)
			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR;

		/*
		 * Note, pte_access holds the raw RWX bits from the EPTE, not
		 * ACC_*_MASK flags!
		 */
		walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
						     EPT_VIOLATION_RWX_SHIFT;
	}
#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, u64 access)
{
	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
					access);
}

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

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

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

	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, pte_access & ACC_WRITE_MASK);
	if (!slot)
		return false;

	pfn = gfn_to_pfn_memslot_atomic(slot, gfn);
	if (is_error_pfn(pfn))
		return false;

	mmu_set_spte(vcpu, slot, spte, pte_access, gfn, pfn, NULL);
	kvm_release_pfn_clean(pfn);
	return true;
}

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_invalidate_in_progress))
		return;

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

	i = spte_index(sptep) & ~(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]))
			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, struct kvm_page_fault *fault,
			 struct guest_walker *gw)
{
	struct kvm_mmu_page *sp = NULL;
	struct kvm_shadow_walk_iterator it;
	unsigned int direct_access, access;
	int top_level, ret;
	gfn_t base_gfn = fault->gfn;

	WARN_ON_ONCE(gw->gfn != base_gfn);
	direct_access = gw->pte_access;

	top_level = vcpu->arch.mmu->cpu_role.base.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_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
		goto out_gpte_changed;

	/*
	 * Load a new root and retry the faulting instruction in the extremely
	 * unlikely scenario that the guest root gfn became visible between
	 * loading a dummy root and handling the resulting page fault, e.g. if
	 * userspace create a memslot in the interim.
	 */
	if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) {
		kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu);
		goto out_gpte_changed;
	}

	for_each_shadow_entry(vcpu, fault->addr, it) {
		gfn_t table_gfn;

		clear_sp_write_flooding_count(it.sptep);
		if (it.level == gw->level)
			break;

		table_gfn = gw->table_gfn[it.level - 2];
		access = gw->pt_access[it.level - 2];
		sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn,
					  false, access);

		if (sp != ERR_PTR(-EEXIST)) {
			/*
			 * 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 != ERR_PTR(-EEXIST))
			link_shadow_page(vcpu, it.sptep, sp);

		if (fault->write && table_gfn == fault->gfn)
			fault->write_fault_to_shadow_pgtable = true;
	}

	/*
	 * Adjust the hugepage size _after_ resolving indirect shadow pages.
	 * KVM doesn't support mapping hugepages into the guest for gfns that
	 * are being shadowed by KVM, i.e. allocating a new shadow page may
	 * affect the allowed hugepage size.
	 */
	kvm_mmu_hugepage_adjust(vcpu, fault);

	trace_kvm_mmu_spte_requested(fault);

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

		base_gfn = gfn_round_for_level(fault->gfn, it.level);
		if (it.level == fault->goal_level)
			break;

		validate_direct_spte(vcpu, it.sptep, direct_access);

		sp = kvm_mmu_get_child_sp(vcpu, it.sptep, base_gfn,
					  true, direct_access);
		if (sp == ERR_PTR(-EEXIST))
			continue;

		link_shadow_page(vcpu, it.sptep, sp);
		if (fault->huge_page_disallowed)
			account_nx_huge_page(vcpu->kvm, sp,
					     fault->req_level >= it.level);
	}

	if (WARN_ON_ONCE(it.level != fault->goal_level))
		return -EFAULT;

	ret = mmu_set_spte(vcpu, fault->slot, it.sptep, gw->pte_access,
			   base_gfn, fault->pfn, fault);
	if (ret == RET_PF_SPURIOUS)
		return ret;

	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
	return ret;

out_gpte_changed:
	return RET_PF_RETRY;
}

/*
 * 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, struct kvm_page_fault *fault)
{
	struct guest_walker walker;
	int r;

	WARN_ON_ONCE(fault->is_tdp);

	/*
	 * Look up the guest pte for the faulting address.
	 * If PFEC.RSVD is set, this is a shadow page fault.
	 * The bit needs to be cleared before walking guest page tables.
	 */
	r = FNAME(walk_addr)(&walker, vcpu, fault->addr,
			     fault->error_code & ~PFERR_RSVD_MASK);

	/*
	 * The page is not mapped by the guest.  Let the guest handle it.
	 */
	if (!r) {
		if (!fault->prefetch)
			kvm_inject_emulated_page_fault(vcpu, &walker.fault);

		return RET_PF_RETRY;
	}

	fault->gfn = walker.gfn;
	fault->max_level = walker.level;
	fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn);

	if (page_fault_handle_page_track(vcpu, fault)) {
		shadow_page_table_clear_flood(vcpu, fault->addr);
		return RET_PF_EMULATE;
	}

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

	r = kvm_faultin_pfn(vcpu, fault, walker.pte_access);
	if (r != RET_PF_CONTINUE)
		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 (fault->write && !(walker.pte_access & ACC_WRITE_MASK) &&
	    !is_cr0_wp(vcpu->arch.mmu) && !fault->user && fault->slot) {
		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_page_fault_stale(vcpu, fault))
		goto out_unlock;

	r = make_mmu_pages_available(vcpu);
	if (r)
		goto out_unlock;
	r = FNAME(fetch)(vcpu, fault, &walker);

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

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

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

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

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

/* 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, struct kvm_mmu *mmu,
			       gpa_t addr, u64 access,
			       struct x86_exception *exception)
{
	struct guest_walker walker;
	gpa_t gpa = INVALID_GPA;
	int r;

#ifndef CONFIG_X86_64
	/* A 64-bit GVA should be impossible on 32-bit KVM. */
	WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu);
#endif

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

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

	return gpa;
}

/*
 * Using the information in sp->shadowed_translation (kvm_mmu_page_get_gfn()) 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.
 *
 * Returns
 * < 0: failed to sync spte
 *   0: the spte is synced and no tlb flushing is required
 * > 0: the spte is synced and tlb flushing is required
 */
static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i)
{
	bool host_writable;
	gpa_t first_pte_gpa;
	u64 *sptep, spte;
	struct kvm_memory_slot *slot;
	unsigned pte_access;
	pt_element_t gpte;
	gpa_t pte_gpa;
	gfn_t gfn;

	if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
		return 0;

	first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
	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 -1;

	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte))
		return 1;

	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))
		return 0;

	/*
	 * Drop the SPTE if the new protections result in no effective
	 * "present" bit or if the gfn is changing.  The former case
	 * only affects EPT with execute-only support with pte_access==0;
	 * all other paging modes will create a read-only SPTE if
	 * pte_access is zero.
	 */
	if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE ||
	    gfn != kvm_mmu_page_get_gfn(sp, i)) {
		drop_spte(vcpu->kvm, &sp->spt[i]);
		return 1;
	}
	/*
	 * Do nothing if the permissions are unchanged.  The existing SPTE is
	 * still, and prefetch_invalid_gpte() has verified that the A/D bits
	 * are set in the "new" gPTE, i.e. there is no danger of missing an A/D
	 * update due to A/D bits being set in the SPTE but not the gPTE.
	 */
	if (kvm_mmu_page_get_access(sp, i) == pte_access)
		return 0;

	/* Update the shadowed access bits in case they changed. */
	kvm_mmu_page_set_access(sp, i, pte_access);

	sptep = &sp->spt[i];
	spte = *sptep;
	host_writable = spte & shadow_host_writable_mask;
	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	make_spte(vcpu, sp, slot, pte_access, gfn,
		  spte_to_pfn(spte), spte, true, false,
		  host_writable, &spte);

	return mmu_spte_update(sptep, spte);
}

#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 PT_GUEST_ACCESSED_MASK
#undef PT_GUEST_DIRTY_MASK
#undef PT_GUEST_DIRTY_SHIFT
#undef PT_GUEST_ACCESSED_SHIFT
#undef PT_HAVE_ACCESSED_DIRTY