Free Electrons

Embedded Linux Experts

   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
#ifndef __KVM_HOST_H
#define __KVM_HOST_H

/*
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 */

#include <linux/types.h>
#include <linux/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/rcupdate.h>
#include <linux/ratelimit.h>
#include <linux/err.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_MMIO_SIZE
#define KVM_MMIO_SIZE 8
#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)

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

/*
 * 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(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(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(pfn_t pfn)
{
	return pfn == KVM_PFN_NOSLOT;
}

#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;
}

#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))

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

/*
 * vcpu->requests bit members
 */
#define KVM_REQ_TLB_FLUSH          0
#define KVM_REQ_MIGRATE_TIMER      1
#define KVM_REQ_REPORT_TPR_ACCESS  2
#define KVM_REQ_MMU_RELOAD         3
#define KVM_REQ_TRIPLE_FAULT       4
#define KVM_REQ_PENDING_TIMER      5
#define KVM_REQ_UNHALT             6
#define KVM_REQ_MMU_SYNC           7
#define KVM_REQ_CLOCK_UPDATE       8
#define KVM_REQ_KICK               9
#define KVM_REQ_DEACTIVATE_FPU    10
#define KVM_REQ_EVENT             11
#define KVM_REQ_APF_HALT          12
#define KVM_REQ_STEAL_UPDATE      13
#define KVM_REQ_NMI               14
#define KVM_REQ_IMMEDIATE_EXIT    15
#define KVM_REQ_PMU               16
#define KVM_REQ_PMI               17
#define KVM_REQ_WATCHDOG          18
#define KVM_REQ_MASTERCLOCK_UPDATE 19
#define KVM_REQ_MCLOCK_INPROGRESS 20

#define KVM_USERSPACE_IRQ_SOURCE_ID		0
#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1

struct kvm;
struct kvm_vcpu;
extern struct kmem_cache *kvm_vcpu_cache;

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;
	struct kvm_io_range range[];
};

enum kvm_bus {
	KVM_MMIO_BUS,
	KVM_PIO_BUS,
	KVM_NR_BUSES
};

int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
		     int len, const void *val);
int kvm_io_bus_read(struct kvm *kvm, 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);
int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
			      struct kvm_io_device *dev);

#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;
	struct page *page;
	bool done;
};

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, gfn_t gfn,
		       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,
};

/*
 * 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;
	unsigned long requests;
	unsigned long guest_debug;

	struct mutex mutex;
	struct kvm_run *run;

	int fpu_active;
	int guest_fpu_loaded, guest_xcr0_loaded;
	wait_queue_head_t wq;
	struct pid *pid;
	int sigset_active;
	sigset_t sigset;
	struct kvm_vcpu_stat stat;

#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
	struct kvm_vcpu_arch arch;
};

static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
	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 flags;
	unsigned long *dirty_bitmap;
	struct kvm_arch_memory_slot arch;
	unsigned long userspace_addr;
	int user_alloc;
	int id;
};

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

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);
	union {
		struct {
			unsigned irqchip;
			unsigned pin;
		} irqchip;
		struct msi_msg msi;
	};
	struct hlist_node link;
};

#ifdef __KVM_HAVE_IOAPIC

struct kvm_irq_routing_table {
	int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS];
	struct kvm_kernel_irq_routing_entry *rt_entries;
	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];
};

#else

struct kvm_irq_routing_table {};

#endif

#ifndef KVM_MEM_SLOTS_NUM
#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
#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[]. */
	int id_to_index[KVM_MEM_SLOTS_NUM];
};

struct kvm {
	spinlock_t mmu_lock;
	struct mutex slots_lock;
	struct mm_struct *mm; /* userspace tied to this vm */
	struct kvm_memslots *memslots;
	struct srcu_struct srcu;
#ifdef CONFIG_KVM_APIC_ARCHITECTURE
	u32 bsp_vcpu_id;
#endif
	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
	atomic_t online_vcpus;
	int last_boosted_vcpu;
	struct list_head vm_list;
	struct mutex lock;
	struct kvm_io_bus *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;
	atomic_t users_count;
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
	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 and,
	 * if configured, irqfds.lock.
	 */
	struct kvm_irq_routing_table __rcu *irq_routing;
	struct hlist_head mask_notifier_list;
	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;
};

#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_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 " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)

static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
	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++)

#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);

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

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);
void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new);

static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
{
	return rcu_dereference_check(kvm->memslots,
			srcu_read_lock_held(&kvm->srcu)
			|| lockdep_is_held(&kvm->slots_lock));
}

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;
}

int kvm_set_memory_region(struct kvm *kvm,
			  struct kvm_userspace_memory_region *mem,
			  int user_alloc);
int __kvm_set_memory_region(struct kvm *kvm,
			    struct kvm_userspace_memory_region *mem,
			    int user_alloc);
void kvm_arch_free_memslot(struct kvm_memory_slot *free,
			   struct kvm_memory_slot *dont);
int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *memslot,
				struct kvm_memory_slot old,
				struct kvm_userspace_memory_region *mem,
				int user_alloc);
void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				struct kvm_memory_slot old,
				int user_alloc);
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 *kvm, 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_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
void kvm_set_page_dirty(struct page *page);
void kvm_set_page_accessed(struct page *page);

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

void kvm_release_pfn_dirty(pfn_t pfn);
void kvm_release_pfn_clean(pfn_t pfn);
void kvm_set_pfn_dirty(pfn_t pfn);
void kvm_set_pfn_accessed(pfn_t pfn);
void kvm_get_pfn(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_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);
int 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);
void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
			     gfn_t gfn);

void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);

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

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);
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);

int kvm_dev_ioctl_check_extension(long ext);

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

int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
				   struct
				   kvm_userspace_memory_region *mem,
				   int user_alloc);
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
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_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);
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);

int kvm_arch_hardware_enable(void *garbage);
void kvm_arch_hardware_disable(void *garbage);
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);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);

void kvm_free_physmem(struct kvm *kvm);

void *kvm_kvzalloc(unsigned long size);
void kvm_kvfree(const void *addr);

#ifndef __KVM_HAVE_ARCH_VM_ALLOC
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

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

int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
void kvm_free_all_assigned_devices(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_mmio_pfn(pfn_t pfn);

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

struct kvm_assigned_dev_kernel {
	struct kvm_irq_ack_notifier ack_notifier;
	struct list_head list;
	int assigned_dev_id;
	int host_segnr;
	int host_busnr;
	int host_devfn;
	unsigned int entries_nr;
	int host_irq;
	bool host_irq_disabled;
	bool pci_2_3;
	struct msix_entry *host_msix_entries;
	int guest_irq;
	struct msix_entry *guest_msix_entries;
	unsigned long irq_requested_type;
	int irq_source_id;
	int flags;
	struct pci_dev *dev;
	struct kvm *kvm;
	spinlock_t intx_lock;
	spinlock_t intx_mask_lock;
	char irq_name[32];
	struct pci_saved_state *pci_saved_state;
};

struct kvm_irq_mask_notifier {
	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
	int irq;
	struct hlist_node link;
};

void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
				    struct kvm_irq_mask_notifier *kimn);
void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
				      struct kvm_irq_mask_notifier *kimn);
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
			     bool mask);

#ifdef __KVM_HAVE_IOAPIC
void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
				   union kvm_ioapic_redirect_entry *entry,
				   unsigned long *deliver_bitmask);
#endif
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
		int irq_source_id, int level);
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);

/* For vcpu->arch.iommu_flags */
#define KVM_IOMMU_CACHE_COHERENCY	0x1

#ifdef CONFIG_IOMMU_API
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
int kvm_iommu_map_guest(struct kvm *kvm);
int kvm_iommu_unmap_guest(struct kvm *kvm);
int kvm_assign_device(struct kvm *kvm,
		      struct kvm_assigned_dev_kernel *assigned_dev);
int kvm_deassign_device(struct kvm *kvm,
			struct kvm_assigned_dev_kernel *assigned_dev);
#else /* CONFIG_IOMMU_API */
static inline int kvm_iommu_map_pages(struct kvm *kvm,
				      struct kvm_memory_slot *slot)
{
	return 0;
}

static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
					 struct kvm_memory_slot *slot)
{
}

static inline int kvm_iommu_map_guest(struct kvm *kvm)
{
	return -ENODEV;
}

static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
{
	return 0;
}

static inline int kvm_assign_device(struct kvm *kvm,
		struct kvm_assigned_dev_kernel *assigned_dev)
{
	return 0;
}

static inline int kvm_deassign_device(struct kvm *kvm,
		struct kvm_assigned_dev_kernel *assigned_dev)
{
	return 0;
}
#endif /* CONFIG_IOMMU_API */

static inline void kvm_guest_enter(void)
{
	BUG_ON(preemptible());
	/*
	 * This is running in ioctl context so we can avoid
	 * the call to vtime_account() with its unnecessary idle check.
	 */
	vtime_account_system_irqsafe(current);
	current->flags |= PF_VCPU;
	/* KVM does not hold any references to rcu protected data when it
	 * switches CPU into a guest mode. In fact switching to a guest mode
	 * is very similar to exiting to userspase from rcu point of view. In
	 * addition CPU may stay in a guest mode for quite a long time (up to
	 * one time slice). Lets treat guest mode as quiescent state, just like
	 * we do with user-mode execution.
	 */
	rcu_virt_note_context_switch(smp_processor_id());
}

static inline void kvm_guest_exit(void)
{
	/*
	 * This is running in ioctl context so we can avoid
	 * the call to vtime_account() with its unnecessary idle check.
	 */
	vtime_account_system_irqsafe(current);
	current->flags &= ~PF_VCPU;
}

/*
 * 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)
{
	struct kvm_memory_slot *memslot;

	kvm_for_each_memslot(memslot, slots)
		if (gfn >= memslot->base_gfn &&
		      gfn < memslot->base_gfn + memslot->npages)
			return memslot;

	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 gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
{
	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
}

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(pfn_t pfn)
{
	return (hpa_t)pfn << PAGE_SHIFT;
}

static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
}

enum kvm_stat_kind {
	KVM_STAT_VM,
	KVM_STAT_VCPU,
};

struct kvm_stats_debugfs_item {
	const char *name;
	int offset;
	enum kvm_stat_kind kind;
	struct dentry *dentry;
};
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 KVM_CAP_IRQ_ROUTING

#define KVM_MAX_IRQ_ROUTES 1024

int kvm_setup_default_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
			const struct kvm_irq_routing_entry *entries,
			unsigned nr,
			unsigned flags);
void kvm_free_irq_routing(struct kvm *kvm);

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

#else

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

#endif

#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_IRQCHIP
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
#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,
					  struct kvm_irq_routing_table *irq_rt)
{
	rcu_assign_pointer(kvm->irq_routing, irq_rt);
}
#endif

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

#endif /* CONFIG_HAVE_KVM_EVENTFD */

#ifdef CONFIG_KVM_APIC_ARCHITECTURE
static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
{
	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
}

bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);

#else

static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }

#endif

#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT

long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
				  unsigned long arg);

#else

static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
						unsigned long arg)
{
	return -ENOTTY;
}

#endif

static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
	set_bit(req, &vcpu->requests);
}

static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
{
	if (test_bit(req, &vcpu->requests)) {
		clear_bit(req, &vcpu->requests);
		return true;
	} else {
		return false;
	}
}

#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)
{
}

static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
{
	return true;
}

#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
#endif