summaryrefslogtreecommitdiff
path: root/include/linux/kvm_host.h
blob: d1ad38a3f048b15f3501f24bb838f75081efcdd4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef __KVM_HOST_H
#define __KVM_HOST_H


#include <linux/types.h>
#include <linux/hardirq.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/preempt.h>
#include <linux/msi.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/rcupdate.h>
#include <linux/ratelimit.h>
#include <linux/err.h>
#include <linux/irqflags.h>
#include <linux/context_tracking.h>
#include <linux/irqbypass.h>
#include <linux/swait.h>
#include <linux/refcount.h>
#include <linux/nospec.h>
#include <asm/signal.h>

#include <linux/kvm.h>
#include <linux/kvm_para.h>

#include <linux/kvm_types.h>

#include <asm/kvm_host.h>

#ifndef KVM_MAX_VCPU_ID
#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
#endif

/*
 * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
 * in kvm, other bits are visible for userspace which are defined in
 * include/linux/kvm_h.
 */
#define KVM_MEMSLOT_INVALID	(1UL << 16)

/*
 * Bit 63 of the memslot generation number is an "update in-progress flag",
 * e.g. is temporarily set for the duration of install_new_memslots().
 * This flag effectively creates a unique generation number that is used to
 * mark cached memslot data, e.g. MMIO accesses, as potentially being stale,
 * i.e. may (or may not) have come from the previous memslots generation.
 *
 * This is necessary because the actual memslots update is not atomic with
 * respect to the generation number update.  Updating the generation number
 * first would allow a vCPU to cache a spte from the old memslots using the
 * new generation number, and updating the generation number after switching
 * to the new memslots would allow cache hits using the old generation number
 * to reference the defunct memslots.
 *
 * This mechanism is used to prevent getting hits in KVM's caches while a
 * memslot update is in-progress, and to prevent cache hits *after* updating
 * the actual generation number against accesses that were inserted into the
 * cache *before* the memslots were updated.
 */
#define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS	BIT_ULL(63)

/* Two fragments for cross MMIO pages. */
#define KVM_MAX_MMIO_FRAGMENTS	2

#ifndef KVM_ADDRESS_SPACE_NUM
#define KVM_ADDRESS_SPACE_NUM	1
#endif

/*
 * For the normal pfn, the highest 12 bits should be zero,
 * so we can mask bit 62 ~ bit 52  to indicate the error pfn,
 * mask bit 63 to indicate the noslot pfn.
 */
#define KVM_PFN_ERR_MASK	(0x7ffULL << 52)
#define KVM_PFN_ERR_NOSLOT_MASK	(0xfffULL << 52)
#define KVM_PFN_NOSLOT		(0x1ULL << 63)

#define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
#define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)

/*
 * error pfns indicate that the gfn is in slot but faild to
 * translate it to pfn on host.
 */
static inline bool is_error_pfn(kvm_pfn_t pfn)
{
	return !!(pfn & KVM_PFN_ERR_MASK);
}

/*
 * error_noslot pfns indicate that the gfn can not be
 * translated to pfn - it is not in slot or failed to
 * translate it to pfn.
 */
static inline bool is_error_noslot_pfn(kvm_pfn_t pfn)
{
	return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
}

/* noslot pfn indicates that the gfn is not in slot. */
static inline bool is_noslot_pfn(kvm_pfn_t pfn)
{
	return pfn == KVM_PFN_NOSLOT;
}

/*
 * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390)
 * provide own defines and kvm_is_error_hva
 */
#ifndef KVM_HVA_ERR_BAD

#define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
#define KVM_HVA_ERR_RO_BAD	(PAGE_OFFSET + PAGE_SIZE)

static inline bool kvm_is_error_hva(unsigned long addr)
{
	return addr >= PAGE_OFFSET;
}

#endif

#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))

static inline bool is_error_page(struct page *page)
{
	return IS_ERR(page);
}

#define KVM_REQUEST_MASK           GENMASK(7,0)
#define KVM_REQUEST_NO_WAKEUP      BIT(8)
#define KVM_REQUEST_WAIT           BIT(9)
/*
 * Architecture-independent vcpu->requests bit members
 * Bits 4-7 are reserved for more arch-independent bits.
 */
#define KVM_REQ_TLB_FLUSH         (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_MMU_RELOAD        (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_PENDING_TIMER     2
#define KVM_REQ_UNHALT            3
#define KVM_REQUEST_ARCH_BASE     8

#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
	BUILD_BUG_ON((unsigned)(nr) >= (FIELD_SIZEOF(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \
	(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
})
#define KVM_ARCH_REQ(nr)           KVM_ARCH_REQ_FLAGS(nr, 0)

#define KVM_USERSPACE_IRQ_SOURCE_ID		0
#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1

extern struct kmem_cache *kvm_vcpu_cache;

extern spinlock_t kvm_lock;
extern struct list_head vm_list;

struct kvm_io_range {
	gpa_t addr;
	int len;
	struct kvm_io_device *dev;
};

#define NR_IOBUS_DEVS 1000

struct kvm_io_bus {
	int dev_count;
	int ioeventfd_count;
	struct kvm_io_range range[];
};

enum kvm_bus {
	KVM_MMIO_BUS,
	KVM_PIO_BUS,
	KVM_VIRTIO_CCW_NOTIFY_BUS,
	KVM_FAST_MMIO_BUS,
	KVM_NR_BUSES
};

int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
		     int len, const void *val);
int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
			    gpa_t addr, int len, const void *val, long cookie);
int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
		    int len, void *val);
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
			    int len, struct kvm_io_device *dev);
void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
			       struct kvm_io_device *dev);
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
					 gpa_t addr);

#ifdef CONFIG_KVM_ASYNC_PF
struct kvm_async_pf {
	struct work_struct work;
	struct list_head link;
	struct list_head queue;
	struct kvm_vcpu *vcpu;
	struct mm_struct *mm;
	gva_t gva;
	unsigned long addr;
	struct kvm_arch_async_pf arch;
	bool   wakeup_all;
};

void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
		       struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif

enum {
	OUTSIDE_GUEST_MODE,
	IN_GUEST_MODE,
	EXITING_GUEST_MODE,
	READING_SHADOW_PAGE_TABLES,
};

#define KVM_UNMAPPED_PAGE	((void *) 0x500 + POISON_POINTER_DELTA)

struct kvm_host_map {
	/*
	 * Only valid if the 'pfn' is managed by the host kernel (i.e. There is
	 * a 'struct page' for it. When using mem= kernel parameter some memory
	 * can be used as guest memory but they are not managed by host
	 * kernel).
	 * If 'pfn' is not managed by the host kernel, this field is
	 * initialized to KVM_UNMAPPED_PAGE.
	 */
	struct page *page;
	void *hva;
	kvm_pfn_t pfn;
	kvm_pfn_t gfn;
};

/*
 * Used to check if the mapping is valid or not. Never use 'kvm_host_map'
 * directly to check for that.
 */
static inline bool kvm_vcpu_mapped(struct kvm_host_map *map)
{
	return !!map->hva;
}

/*
 * Sometimes a large or cross-page mmio needs to be broken up into separate
 * exits for userspace servicing.
 */
struct kvm_mmio_fragment {
	gpa_t gpa;
	void *data;
	unsigned len;
};

struct kvm_vcpu {
	struct kvm *kvm;
#ifdef CONFIG_PREEMPT_NOTIFIERS
	struct preempt_notifier preempt_notifier;
#endif
	int cpu;
	int vcpu_id;
	int srcu_idx;
	int mode;
	u64 requests;
	unsigned long guest_debug;

	int pre_pcpu;
	struct list_head blocked_vcpu_list;

	struct mutex mutex;
	struct kvm_run *run;

	int guest_xcr0_loaded;
	struct swait_queue_head wq;
	struct pid __rcu *pid;
	int sigset_active;
	sigset_t sigset;
	struct kvm_vcpu_stat stat;
	unsigned int halt_poll_ns;
	bool valid_wakeup;

#ifdef CONFIG_HAS_IOMEM
	int mmio_needed;
	int mmio_read_completed;
	int mmio_is_write;
	int mmio_cur_fragment;
	int mmio_nr_fragments;
	struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
#endif

#ifdef CONFIG_KVM_ASYNC_PF
	struct {
		u32 queued;
		struct list_head queue;
		struct list_head done;
		spinlock_t lock;
	} async_pf;
#endif

#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
	/*
	 * Cpu relax intercept or pause loop exit optimization
	 * in_spin_loop: set when a vcpu does a pause loop exit
	 *  or cpu relax intercepted.
	 * dy_eligible: indicates whether vcpu is eligible for directed yield.
	 */
	struct {
		bool in_spin_loop;
		bool dy_eligible;
	} spin_loop;
#endif
	bool preempted;
	struct kvm_vcpu_arch arch;
	struct dentry *debugfs_dentry;
};

static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
	/*
	 * The memory barrier ensures a previous write to vcpu->requests cannot
	 * be reordered with the read of vcpu->mode.  It pairs with the general
	 * memory barrier following the write of vcpu->mode in VCPU RUN.
	 */
	smp_mb__before_atomic();
	return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
}

/*
 * Some of the bitops functions do not support too long bitmaps.
 * This number must be determined not to exceed such limits.
 */
#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)

struct kvm_memory_slot {
	gfn_t base_gfn;
	unsigned long npages;
	unsigned long *dirty_bitmap;
	struct kvm_arch_memory_slot arch;
	unsigned long userspace_addr;
	u32 flags;
	short id;
};

static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
{
	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
}

static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot)
{
	unsigned long len = kvm_dirty_bitmap_bytes(memslot);

	return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap);
}

struct kvm_s390_adapter_int {
	u64 ind_addr;
	u64 summary_addr;
	u64 ind_offset;
	u32 summary_offset;
	u32 adapter_id;
};

struct kvm_hv_sint {
	u32 vcpu;
	u32 sint;
};

struct kvm_kernel_irq_routing_entry {
	u32 gsi;
	u32 type;
	int (*set)(struct kvm_kernel_irq_routing_entry *e,
		   struct kvm *kvm, int irq_source_id, int level,
		   bool line_status);
	union {
		struct {
			unsigned irqchip;
			unsigned pin;
		} irqchip;
		struct {
			u32 address_lo;
			u32 address_hi;
			u32 data;
			u32 flags;
			u32 devid;
		} msi;
		struct kvm_s390_adapter_int adapter;
		struct kvm_hv_sint hv_sint;
	};
	struct hlist_node link;
};

#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
struct kvm_irq_routing_table {
	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
	u32 nr_rt_entries;
	/*
	 * Array indexed by gsi. Each entry contains list of irq chips
	 * the gsi is connected to.
	 */
	struct hlist_head map[0];
};
#endif

#ifndef KVM_PRIVATE_MEM_SLOTS
#define KVM_PRIVATE_MEM_SLOTS 0
#endif

#ifndef KVM_MEM_SLOTS_NUM
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
#endif

#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
{
	return 0;
}
#endif

/*
 * Note:
 * memslots are not sorted by id anymore, please use id_to_memslot()
 * to get the memslot by its id.
 */
struct kvm_memslots {
	u64 generation;
	struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM];
	/* The mapping table from slot id to the index in memslots[]. */
	short id_to_index[KVM_MEM_SLOTS_NUM];
	atomic_t lru_slot;
	int used_slots;
};

struct kvm {
	spinlock_t mmu_lock;
	struct mutex slots_lock;
	struct mm_struct *mm; /* userspace tied to this vm */
	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];

	/*
	 * created_vcpus is protected by kvm->lock, and is incremented
	 * at the beginning of KVM_CREATE_VCPU.  online_vcpus is only
	 * incremented after storing the kvm_vcpu pointer in vcpus,
	 * and is accessed atomically.
	 */
	atomic_t online_vcpus;
	int created_vcpus;
	int last_boosted_vcpu;
	struct list_head vm_list;
	struct mutex lock;
	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
#ifdef CONFIG_HAVE_KVM_EVENTFD
	struct {
		spinlock_t        lock;
		struct list_head  items;
		struct list_head  resampler_list;
		struct mutex      resampler_lock;
	} irqfds;
	struct list_head ioeventfds;
#endif
	struct kvm_vm_stat stat;
	struct kvm_arch arch;
	refcount_t users_count;
#ifdef CONFIG_KVM_MMIO
	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
	spinlock_t ring_lock;
	struct list_head coalesced_zones;
#endif

	struct mutex irq_lock;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
	/*
	 * Update side is protected by irq_lock.
	 */
	struct kvm_irq_routing_table __rcu *irq_routing;
#endif
#ifdef CONFIG_HAVE_KVM_IRQFD
	struct hlist_head irq_ack_notifier_list;
#endif

#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
	struct mmu_notifier mmu_notifier;
	unsigned long mmu_notifier_seq;
	long mmu_notifier_count;
#endif
	long tlbs_dirty;
	struct list_head devices;
	bool manual_dirty_log_protect;
	struct dentry *debugfs_dentry;
	struct kvm_stat_data **debugfs_stat_data;
	struct srcu_struct srcu;
	struct srcu_struct irq_srcu;
	pid_t userspace_pid;
};

#define kvm_err(fmt, ...) \
	pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_info(fmt, ...) \
	pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug(fmt, ...) \
	pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug_ratelimited(fmt, ...) \
	pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \
			     ## __VA_ARGS__)
#define kvm_pr_unimpl(fmt, ...) \
	pr_err_ratelimited("kvm [%i]: " fmt, \
			   task_tgid_nr(current), ## __VA_ARGS__)

/* The guest did something we don't support. */
#define vcpu_unimpl(vcpu, fmt, ...)					\
	kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt,			\
			(vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__)

#define vcpu_debug(vcpu, fmt, ...)					\
	kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
#define vcpu_debug_ratelimited(vcpu, fmt, ...)				\
	kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id,           \
			      ## __VA_ARGS__)
#define vcpu_err(vcpu, fmt, ...)					\
	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)

static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
{
	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
				      lockdep_is_held(&kvm->slots_lock) ||
				      !refcount_read(&kvm->users_count));
}

static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
	int num_vcpus = atomic_read(&kvm->online_vcpus);
	i = array_index_nospec(i, num_vcpus);

	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu.  */
	smp_rmb();
	return kvm->vcpus[i];
}

#define kvm_for_each_vcpu(idx, vcpup, kvm) \
	for (idx = 0; \
	     idx < atomic_read(&kvm->online_vcpus) && \
	     (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
	     idx++)

static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
{
	struct kvm_vcpu *vcpu = NULL;
	int i;

	if (id < 0)
		return NULL;
	if (id < KVM_MAX_VCPUS)
		vcpu = kvm_get_vcpu(kvm, id);
	if (vcpu && vcpu->vcpu_id == id)
		return vcpu;
	kvm_for_each_vcpu(i, vcpu, kvm)
		if (vcpu->vcpu_id == id)
			return vcpu;
	return NULL;
}

static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu *tmp;
	int idx;

	kvm_for_each_vcpu(idx, tmp, vcpu->kvm)
		if (tmp == vcpu)
			return idx;
	BUG();
}

#define kvm_for_each_memslot(memslot, slots)	\
	for (memslot = &slots->memslots[0];	\
	      memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
		memslot++)

int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);

void vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);

#ifdef __KVM_HAVE_IOAPIC
void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
void kvm_arch_post_irq_routing_update(struct kvm *kvm);
#else
static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
{
}
static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
{
}
#endif

#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd_init(void);
void kvm_irqfd_exit(void);
#else
static inline int kvm_irqfd_init(void)
{
	return 0;
}

static inline void kvm_irqfd_exit(void)
{
}
#endif
int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
		  struct module *module);
void kvm_exit(void);

void kvm_get_kvm(struct kvm *kvm);
void kvm_put_kvm(struct kvm *kvm);

static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
			lockdep_is_held(&kvm->slots_lock) ||
			!refcount_read(&kvm->users_count));
}

static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
{
	return __kvm_memslots(kvm, 0);
}

static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu)
{
	int as_id = kvm_arch_vcpu_memslots_id(vcpu);

	return __kvm_memslots(vcpu->kvm, as_id);
}

static inline struct kvm_memory_slot *
id_to_memslot(struct kvm_memslots *slots, int id)
{
	int index = slots->id_to_index[id];
	struct kvm_memory_slot *slot;

	slot = &slots->memslots[index];

	WARN_ON(slot->id != id);
	return slot;
}

/*
 * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
 * - create a new memory slot
 * - delete an existing memory slot
 * - modify an existing memory slot
 *   -- move it in the guest physical memory space
 *   -- just change its flags
 *
 * Since flags can be changed by some of these operations, the following
 * differentiation is the best we can do for __kvm_set_memory_region():
 */
enum kvm_mr_change {
	KVM_MR_CREATE,
	KVM_MR_DELETE,
	KVM_MR_MOVE,
	KVM_MR_FLAGS_ONLY,
};

int kvm_set_memory_region(struct kvm *kvm,
			  const struct kvm_userspace_memory_region *mem);
int __kvm_set_memory_region(struct kvm *kvm,
			    const struct kvm_userspace_memory_region *mem);
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
			   struct kvm_memory_slot *dont);
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages);
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *memslot,
				const struct kvm_userspace_memory_region *mem,
				enum kvm_mr_change change);
void kvm_arch_commit_memory_region(struct kvm *kvm,
				const struct kvm_userspace_memory_region *mem,
				const struct kvm_memory_slot *old,
				const struct kvm_memory_slot *new,
				enum kvm_mr_change change);
bool kvm_largepages_enabled(void);
void kvm_disable_largepages(void);
/* flush all memory translations */
void kvm_arch_flush_shadow_all(struct kvm *kvm);
/* flush memory translations pointing to 'slot' */
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot);

int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
			    struct page **pages, int nr_pages);

struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
				      bool *writable);
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
void kvm_set_page_accessed(struct page *page);

kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
		      bool *writable);
kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
			       bool atomic, bool *async, bool write_fault,
			       bool *writable);

void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_accessed(kvm_pfn_t pfn);
void kvm_get_pfn(kvm_pfn_t pfn);

int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
			int len);
int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
			  unsigned long len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
			   void *data, unsigned long len);
int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
			 int offset, int len);
int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
		    unsigned long len);
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
			   void *data, unsigned long len);
int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
				  void *data, unsigned int offset,
				  unsigned long len);
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
			      gpa_t gpa, unsigned long len);
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);

struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
			     int len);
int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
			       unsigned long len);
int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
			unsigned long len);
int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data,
			      int offset, int len);
int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
			 unsigned long len);
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);

void kvm_sigset_activate(struct kvm_vcpu *vcpu);
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);

void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
int kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);

void kvm_flush_remote_tlbs(struct kvm *kvm);
void kvm_reload_remote_mmus(struct kvm *kvm);

bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
				 unsigned long *vcpu_bitmap, cpumask_var_t tmp);
bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg);
long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg);
vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);

int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);

int kvm_get_dirty_log(struct kvm *kvm,
			struct kvm_dirty_log *log, int *is_dirty);

int kvm_get_dirty_log_protect(struct kvm *kvm,
			      struct kvm_dirty_log *log, bool *flush);
int kvm_clear_dirty_log_protect(struct kvm *kvm,
				struct kvm_clear_dirty_log *log, bool *flush);

void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
					struct kvm_memory_slot *slot,
					gfn_t gfn_offset,
					unsigned long mask);

int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				struct kvm_dirty_log *log);
int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
				  struct kvm_clear_dirty_log *log);

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
			bool line_status);
int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
			    struct kvm_enable_cap *cap);
long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg);

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				    struct kvm_translation *tr);

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);

int kvm_arch_init(void *opaque);
void kvm_arch_exit(void);

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);

void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);

bool kvm_arch_has_vcpu_debugfs(void);
int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu);

int kvm_arch_hardware_enable(void);
void kvm_arch_hardware_disable(void);
int kvm_arch_hardware_setup(void);
void kvm_arch_hardware_unsetup(void);
void kvm_arch_check_processor_compat(void *rtn);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);

#ifndef __KVM_HAVE_ARCH_VM_ALLOC
/*
 * All architectures that want to use vzalloc currently also
 * need their own kvm_arch_alloc_vm implementation.
 */
static inline struct kvm *kvm_arch_alloc_vm(void)
{
	return kzalloc(sizeof(struct kvm), GFP_KERNEL);
}

static inline void kvm_arch_free_vm(struct kvm *kvm)
{
	kfree(kvm);
}
#endif

#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
{
	return -ENOTSUPP;
}
#endif

#ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
bool kvm_arch_has_noncoherent_dma(struct kvm *kvm);
#else
static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
{
}

static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
{
}

static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
{
	return false;
}
#endif
#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
void kvm_arch_start_assignment(struct kvm *kvm);
void kvm_arch_end_assignment(struct kvm *kvm);
bool kvm_arch_has_assigned_device(struct kvm *kvm);
#else
static inline void kvm_arch_start_assignment(struct kvm *kvm)
{
}

static inline void kvm_arch_end_assignment(struct kvm *kvm)
{
}

static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
{
	return false;
}
#endif

static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_WQP
	return vcpu->arch.wqp;
#else
	return &vcpu->wq;
#endif
}

#ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED
/*
 * returns true if the virtual interrupt controller is initialized and
 * ready to accept virtual IRQ. On some architectures the virtual interrupt
 * controller is dynamically instantiated and this is not always true.
 */
bool kvm_arch_intc_initialized(struct kvm *kvm);
#else
static inline bool kvm_arch_intc_initialized(struct kvm *kvm)
{
	return true;
}
#endif

int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
void kvm_arch_sync_events(struct kvm *kvm);

int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);

bool kvm_is_reserved_pfn(kvm_pfn_t pfn);

struct kvm_irq_ack_notifier {
	struct hlist_node link;
	unsigned gsi;
	void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
};

int kvm_irq_map_gsi(struct kvm *kvm,
		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);

int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
		bool line_status);
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
		int irq_source_id, int level, bool line_status);
int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
			       struct kvm *kvm, int irq_source_id,
			       int level, bool line_status);
bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_notify_acked_gsi(struct kvm *kvm, int gsi);
void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_register_irq_ack_notifier(struct kvm *kvm,
				   struct kvm_irq_ack_notifier *kian);
void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
				   struct kvm_irq_ack_notifier *kian);
int kvm_request_irq_source_id(struct kvm *kvm);
void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);

/*
 * search_memslots() and __gfn_to_memslot() are here because they are
 * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
 * gfn_to_memslot() itself isn't here as an inline because that would
 * bloat other code too much.
 */
static inline struct kvm_memory_slot *
search_memslots(struct kvm_memslots *slots, gfn_t gfn)
{
	int start = 0, end = slots->used_slots;
	int slot = atomic_read(&slots->lru_slot);
	struct kvm_memory_slot *memslots = slots->memslots;

	if (gfn >= memslots[slot].base_gfn &&
	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
		return &memslots[slot];

	while (start < end) {
		slot = start + (end - start) / 2;

		if (gfn >= memslots[slot].base_gfn)
			end = slot;
		else
			start = slot + 1;
	}

	if (gfn >= memslots[start].base_gfn &&
	    gfn < memslots[start].base_gfn + memslots[start].npages) {
		atomic_set(&slots->lru_slot, start);
		return &memslots[start];
	}

	return NULL;
}

static inline struct kvm_memory_slot *
__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
{
	return search_memslots(slots, gfn);
}

static inline unsigned long
__gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
{
	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
}

static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
{
	return gfn_to_memslot(kvm, gfn)->id;
}

static inline gfn_t
hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
{
	gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;

	return slot->base_gfn + gfn_offset;
}

static inline gpa_t gfn_to_gpa(gfn_t gfn)
{
	return (gpa_t)gfn << PAGE_SHIFT;
}

static inline gfn_t gpa_to_gfn(gpa_t gpa)
{
	return (gfn_t)(gpa >> PAGE_SHIFT);
}

static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn)
{
	return (hpa_t)pfn << PAGE_SHIFT;
}

static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu,
						gpa_t gpa)
{
	return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa));
}

static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
{
	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));

	return kvm_is_error_hva(hva);
}

enum kvm_stat_kind {
	KVM_STAT_VM,
	KVM_STAT_VCPU,
};

struct kvm_stat_data {
	int offset;
	struct kvm *kvm;
};

struct kvm_stats_debugfs_item {
	const char *name;
	int offset;
	enum kvm_stat_kind kind;
};
extern struct kvm_stats_debugfs_item debugfs_entries[];
extern struct dentry *kvm_debugfs_dir;

#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
{
	if (unlikely(kvm->mmu_notifier_count))
		return 1;
	/*
	 * Ensure the read of mmu_notifier_count happens before the read
	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
	 * mmu_notifier_invalidate_range_end to make sure that the caller
	 * either sees the old (non-zero) value of mmu_notifier_count or
	 * the new (incremented) value of mmu_notifier_seq.
	 * PowerPC Book3s HV KVM calls this under a per-page lock
	 * rather than under kvm->mmu_lock, for scalability, so
	 * can't rely on kvm->mmu_lock to keep things ordered.
	 */
	smp_rmb();
	if (kvm->mmu_notifier_seq != mmu_seq)
		return 1;
	return 0;
}
#endif

#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING

#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */

bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
			const struct kvm_irq_routing_entry *entries,
			unsigned nr,
			unsigned flags);
int kvm_set_routing_entry(struct kvm *kvm,
			  struct kvm_kernel_irq_routing_entry *e,
			  const struct kvm_irq_routing_entry *ue);
void kvm_free_irq_routing(struct kvm *kvm);

#else

static inline void kvm_free_irq_routing(struct kvm *kvm) {}

#endif

int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);

#ifdef CONFIG_HAVE_KVM_EVENTFD

void kvm_eventfd_init(struct kvm *kvm);
int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);

#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
void kvm_irq_routing_update(struct kvm *);
#else
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
	return -EINVAL;
}

static inline void kvm_irqfd_release(struct kvm *kvm) {}
#endif

#else

static inline void kvm_eventfd_init(struct kvm *kvm) {}

static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
	return -EINVAL;
}

static inline void kvm_irqfd_release(struct kvm *kvm) {}

#ifdef CONFIG_HAVE_KVM_IRQCHIP
static inline void kvm_irq_routing_update(struct kvm *kvm)
{
}
#endif

static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
{
	return -ENOSYS;
}

#endif /* CONFIG_HAVE_KVM_EVENTFD */

void kvm_arch_irq_routing_update(struct kvm *kvm);

static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
	/*
	 * Ensure the rest of the request is published to kvm_check_request's
	 * caller.  Paired with the smp_mb__after_atomic in kvm_check_request.
	 */
	smp_wmb();
	set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}

static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
{
	return READ_ONCE(vcpu->requests);
}

static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
{
	return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}

static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
{
	clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}

static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
{
	if (kvm_test_request(req, vcpu)) {
		kvm_clear_request(req, vcpu);

		/*
		 * Ensure the rest of the request is visible to kvm_check_request's
		 * caller.  Paired with the smp_wmb in kvm_make_request.
		 */
		smp_mb__after_atomic();
		return true;
	} else {
		return false;
	}
}

extern bool kvm_rebooting;

extern unsigned int halt_poll_ns;
extern unsigned int halt_poll_ns_grow;
extern unsigned int halt_poll_ns_grow_start;
extern unsigned int halt_poll_ns_shrink;

struct kvm_device {
	struct kvm_device_ops *ops;
	struct kvm *kvm;
	void *private;
	struct list_head vm_node;
};

/* create, destroy, and name are mandatory */
struct kvm_device_ops {
	const char *name;

	/*
	 * create is called holding kvm->lock and any operations not suitable
	 * to do while holding the lock should be deferred to init (see
	 * below).
	 */
	int (*create)(struct kvm_device *dev, u32 type);

	/*
	 * init is called after create if create is successful and is called
	 * outside of holding kvm->lock.
	 */
	void (*init)(struct kvm_device *dev);

	/*
	 * Destroy is responsible for freeing dev.
	 *
	 * Destroy may be called before or after destructors are called
	 * on emulated I/O regions, depending on whether a reference is
	 * held by a vcpu or other kvm component that gets destroyed
	 * after the emulated I/O.
	 */
	void (*destroy)(struct kvm_device *dev);

	/*
	 * Release is an alternative method to free the device. It is
	 * called when the device file descriptor is closed. Once
	 * release is called, the destroy method will not be called
	 * anymore as the device is removed from the device list of
	 * the VM. kvm->lock is held.
	 */
	void (*release)(struct kvm_device *dev);

	int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
	int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
	int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
	long (*ioctl)(struct kvm_device *dev, unsigned int ioctl,
		      unsigned long arg);
	int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
};

void kvm_device_get(struct kvm_device *dev);
void kvm_device_put(struct kvm_device *dev);
struct kvm_device *kvm_device_from_filp(struct file *filp);
int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
void kvm_unregister_device_ops(u32 type);

extern struct kvm_device_ops kvm_mpic_ops;
extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
extern struct kvm_device_ops kvm_arm_vgic_v3_ops;

#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT

static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
	vcpu->spin_loop.in_spin_loop = val;
}
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
	vcpu->spin_loop.dy_eligible = val;
}

#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */

static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
}

static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
}
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */

#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
bool kvm_arch_has_irq_bypass(void);
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
			   struct irq_bypass_producer *);
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
			   struct irq_bypass_producer *);
void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
				  uint32_t guest_irq, bool set);
#endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */

#ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS
/* If we wakeup during the poll time, was it a sucessful poll? */
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
	return vcpu->valid_wakeup;
}

#else
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
	return true;
}
#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */

#ifdef CONFIG_HAVE_KVM_NO_POLL
/* Callback that tells if we must not poll */
bool kvm_arch_no_poll(struct kvm_vcpu *vcpu);
#else
static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
{
	return false;
}
#endif /* CONFIG_HAVE_KVM_NO_POLL */

#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
long kvm_arch_vcpu_async_ioctl(struct file *filp,
			       unsigned int ioctl, unsigned long arg);
#else
static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
					     unsigned int ioctl,
					     unsigned long arg)
{
	return -ENOIOCTLCMD;
}
#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */

int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
		unsigned long start, unsigned long end, bool blockable);

#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
#else
static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
{
	return 0;
}
#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */

#endif