/*
 * ioport.h	Definitions of routines for detecting, reserving and
 *		allocating system resources.
 *
 * Authors:	Linus Torvalds
 */

#ifndef _LINUX_IOPORT_H
#define _LINUX_IOPORT_H

#ifndef __ASSEMBLY__
#include <linux/compiler.h>
#include <linux/types.h>
/*
 * Resources are tree-like, allowing
 * nesting etc..
 */
struct resource {
	resource_size_t start;
	resource_size_t end;
	const char *name;
	unsigned long flags;
	struct resource *parent, *sibling, *child;
};

/*
 * IO resources have these defined flags.
 */
#define IORESOURCE_BITS		0x000000ff	/* Bus-specific bits */

#define IORESOURCE_TYPE_BITS	0x00001f00	/* Resource type */
#define IORESOURCE_IO		0x00000100	/* PCI/ISA I/O ports */
#define IORESOURCE_MEM		0x00000200
#define IORESOURCE_REG		0x00000300	/* Register offsets */
#define IORESOURCE_IRQ		0x00000400
#define IORESOURCE_DMA		0x00000800
#define IORESOURCE_BUS		0x00001000

#define IORESOURCE_PREFETCH	0x00002000	/* No side effects */
#define IORESOURCE_READONLY	0x00004000
#define IORESOURCE_CACHEABLE	0x00008000
#define IORESOURCE_RANGELENGTH	0x00010000
#define IORESOURCE_SHADOWABLE	0x00020000

#define IORESOURCE_SIZEALIGN	0x00040000	/* size indicates alignment */
#define IORESOURCE_STARTALIGN	0x00080000	/* start field is alignment */

#define IORESOURCE_MEM_64	0x00100000
#define IORESOURCE_WINDOW	0x00200000	/* forwarded by bridge */
#define IORESOURCE_MUXED	0x00400000	/* Resource is software muxed */

#define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
#define IORESOURCE_DISABLED	0x10000000
#define IORESOURCE_UNSET	0x20000000	/* No address assigned yet */
#define IORESOURCE_AUTO		0x40000000
#define IORESOURCE_BUSY		0x80000000	/* Driver has marked this resource busy */

/* PnP IRQ specific bits (IORESOURCE_BITS) */
#define IORESOURCE_IRQ_HIGHEDGE		(1<<0)
#define IORESOURCE_IRQ_LOWEDGE		(1<<1)
#define IORESOURCE_IRQ_HIGHLEVEL	(1<<2)
#define IORESOURCE_IRQ_LOWLEVEL		(1<<3)
#define IORESOURCE_IRQ_SHAREABLE	(1<<4)
#define IORESOURCE_IRQ_OPTIONAL 	(1<<5)

/* PnP DMA specific bits (IORESOURCE_BITS) */
#define IORESOURCE_DMA_TYPE_MASK	(3<<0)
#define IORESOURCE_DMA_8BIT		(0<<0)
#define IORESOURCE_DMA_8AND16BIT	(1<<0)
#define IORESOURCE_DMA_16BIT		(2<<0)

#define IORESOURCE_DMA_MASTER		(1<<2)
#define IORESOURCE_DMA_BYTE		(1<<3)
#define IORESOURCE_DMA_WORD		(1<<4)

#define IORESOURCE_DMA_SPEED_MASK	(3<<6)
#define IORESOURCE_DMA_COMPATIBLE	(0<<6)
#define IORESOURCE_DMA_TYPEA		(1<<6)
#define IORESOURCE_DMA_TYPEB		(2<<6)
#define IORESOURCE_DMA_TYPEF		(3<<6)

/* PnP memory I/O specific bits (IORESOURCE_BITS) */
#define IORESOURCE_MEM_WRITEABLE	(1<<0)	/* dup: IORESOURCE_READONLY */
#define IORESOURCE_MEM_CACHEABLE	(1<<1)	/* dup: IORESOURCE_CACHEABLE */
#define IORESOURCE_MEM_RANGELENGTH	(1<<2)	/* dup: IORESOURCE_RANGELENGTH */
#define IORESOURCE_MEM_TYPE_MASK	(3<<3)
#define IORESOURCE_MEM_8BIT		(0<<3)
#define IORESOURCE_MEM_16BIT		(1<<3)
#define IORESOURCE_MEM_8AND16BIT	(2<<3)
#define IORESOURCE_MEM_32BIT		(3<<3)
#define IORESOURCE_MEM_SHADOWABLE	(1<<5)	/* dup: IORESOURCE_SHADOWABLE */
#define IORESOURCE_MEM_EXPANSIONROM	(1<<6)

/* PnP I/O specific bits (IORESOURCE_BITS) */
#define IORESOURCE_IO_16BIT_ADDR	(1<<0)
#define IORESOURCE_IO_FIXED		(1<<1)
#define IORESOURCE_IO_SPARSE		(1<<2)

/* PCI ROM control bits (IORESOURCE_BITS) */
#define IORESOURCE_ROM_ENABLE		(1<<0)	/* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */
#define IORESOURCE_ROM_SHADOW		(1<<1)	/* ROM is copy at C000:0 */
#define IORESOURCE_ROM_COPY		(1<<2)	/* ROM is alloc'd copy, resource field overlaid */
#define IORESOURCE_ROM_BIOS_COPY	(1<<3)	/* ROM is BIOS copy, resource field overlaid */

/* PCI control bits.  Shares IORESOURCE_BITS with above PCI ROM.  */
#define IORESOURCE_PCI_FIXED		(1<<4)	/* Do not move resource */


/* helpers to define resources */
#define DEFINE_RES_NAMED(_start, _size, _name, _flags)			\
	{								\
		.start = (_start),					\
		.end = (_start) + (_size) - 1,				\
		.name = (_name),					\
		.flags = (_flags),					\
	}

#define DEFINE_RES_IO_NAMED(_start, _size, _name)			\
	DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_IO)
#define DEFINE_RES_IO(_start, _size)					\
	DEFINE_RES_IO_NAMED((_start), (_size), NULL)

#define DEFINE_RES_MEM_NAMED(_start, _size, _name)			\
	DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_MEM)
#define DEFINE_RES_MEM(_start, _size)					\
	DEFINE_RES_MEM_NAMED((_start), (_size), NULL)

#define DEFINE_RES_IRQ_NAMED(_irq, _name)				\
	DEFINE_RES_NAMED((_irq), 1, (_name), IORESOURCE_IRQ)
#define DEFINE_RES_IRQ(_irq)						\
	DEFINE_RES_IRQ_NAMED((_irq), NULL)

#define DEFINE_RES_DMA_NAMED(_dma, _name)				\
	DEFINE_RES_NAMED((_dma), 1, (_name), IORESOURCE_DMA)
#define DEFINE_RES_DMA(_dma)						\
	DEFINE_RES_DMA_NAMED((_dma), NULL)

/* PC/ISA/whatever - the normal PC address spaces: IO and memory */
extern struct resource ioport_resource;
extern struct resource iomem_resource;

extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
extern int request_resource(struct resource *root, struct resource *new);
extern int release_resource(struct resource *new);
void release_child_resources(struct resource *new);
extern void reserve_region_with_split(struct resource *root,
			     resource_size_t start, resource_size_t end,
			     const char *name);
extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new);
extern int insert_resource(struct resource *parent, struct resource *new);
extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new);
extern void arch_remove_reservations(struct resource *avail);
extern int allocate_resource(struct resource *root, struct resource *new,
			     resource_size_t size, resource_size_t min,
			     resource_size_t max, resource_size_t align,
			     resource_size_t (*alignf)(void *,
						       const struct resource *,
						       resource_size_t,
						       resource_size_t),
			     void *alignf_data);
struct resource *lookup_resource(struct resource *root, resource_size_t start);
int adjust_resource(struct resource *res, resource_size_t start,
		    resource_size_t size);
resource_size_t resource_alignment(struct resource *res);
static inline resource_size_t resource_size(const struct resource *res)
{
	return res->end - res->start + 1;
}
static inline unsigned long resource_type(const struct resource *res)
{
	return res->flags & IORESOURCE_TYPE_BITS;
}
/* True iff r1 completely contains r2 */
static inline bool resource_contains(struct resource *r1, struct resource *r2)
{
	if (resource_type(r1) != resource_type(r2))
		return false;
	if (r1->flags & IORESOURCE_UNSET || r2->flags & IORESOURCE_UNSET)
		return false;
	return r1->start <= r2->start && r1->end >= r2->end;
}


/* Convenience shorthand with allocation */
#define request_region(start,n,name)		__request_region(&ioport_resource, (start), (n), (name), 0)
#define request_muxed_region(start,n,name)	__request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED)
#define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl)
#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0)
#define request_mem_region_exclusive(start,n,name) \
	__request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE)
#define rename_region(region, newname) do { (region)->name = (newname); } while (0)

extern struct resource * __request_region(struct resource *,
					resource_size_t start,
					resource_size_t n,
					const char *name, int flags);

/* Compatibility cruft */
#define release_region(start,n)	__release_region(&ioport_resource, (start), (n))
#define release_mem_region(start,n)	__release_region(&iomem_resource, (start), (n))

extern void __release_region(struct resource *, resource_size_t,
				resource_size_t);
#ifdef CONFIG_MEMORY_HOTREMOVE
extern int release_mem_region_adjustable(struct resource *, resource_size_t,
				resource_size_t);
#endif

/* Wrappers for managed devices */
struct device;

extern int devm_request_resource(struct device *dev, struct resource *root,
				 struct resource *new);
extern void devm_release_resource(struct device *dev, struct resource *new);

#define devm_request_region(dev,start,n,name) \
	__devm_request_region(dev, &ioport_resource, (start), (n), (name))
#define devm_request_mem_region(dev,start,n,name) \
	__devm_request_region(dev, &iomem_resource, (start), (n), (name))

extern struct resource * __devm_request_region(struct device *dev,
				struct resource *parent, resource_size_t start,
				resource_size_t n, const char *name);

#define devm_release_region(dev, start, n) \
	
#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 <linux/irqflags.h>
#include <linux/context_tracking.h>
#include <linux/irqbypass.h>
#include <linux/swait.h>
#include <asm/signal.h>

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

#include <linux/kvm_types.h>

#include <asm/kvm_host.h>

/*
 * 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)
#define KVM_MEMSLOT_INCOHERENT	(1UL << 17)

/* 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(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;
}

/*
 * 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);
}

/*
 * 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_PMU               15
#define KVM_REQ_PMI               16
#define KVM_REQ_WATCHDOG          17
#define KVM_REQ_MASTERCLOCK_UPDATE 18
#define KVM_REQ_MCLOCK_INPROGRESS 19
#define KVM_REQ_EPR_EXIT          20
#define KVM_REQ_SCAN_IOAPIC       21
#define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
#define KVM_REQ_ENABLE_IBS        23
#define KVM_REQ_DISABLE_IBS       24
#define KVM_REQ_APIC_PAGE_RELOAD  25
#define KVM_REQ_SMI               26
#define KVM_REQ_HV_CRASH          27
#define KVM_REQ_IOAPIC_EOI_EXIT   28
#define KVM_REQ_HV_RESET          29

#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);
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;
	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,
};

/*
 * 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;

	int pre_pcpu;
	struct list_head blocked_vcpu_list;

	struct mutex mutex;
	struct kvm_run *run;

	int fpu_active;
	int guest_fpu_loaded, guest_xcr0_loaded;
	unsigned char fpu_counter;
	struct swait_queue_head wq;
	struct pid *pid;
	int sigset_active;
	sigset_t sigset;
	struct kvm_vcpu_stat stat;
	unsigned int halt_poll_ns;

#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;
};

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 *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;
}

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

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 msi_msg msi;
		struct kvm_s390_adapter_int adapter;
	};
	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 *memslots[KVM_ADDRESS_SPACE_NUM];
	struct srcu_struct srcu;
	struct srcu_struct irq_srcu;
	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.
	 */
	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;
};

#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__)

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

static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
	 * the caller has read kvm->online_vcpus before (as is the case
	 * for kvm_for_each_vcpu, for example).
	 */
	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;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm)
		if (vcpu->vcpu_id == id)
			return vcpu;
	return NULL;
}

#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);

#ifdef __KVM_HAVE_IOAPIC
void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
void kvm_arch_irq_routing_update(struct kvm *kvm);
#else
static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
{
}
static inline void kvm_arch_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)
{
	return rcu_dereference_check(kvm->memslots[as_id],
			srcu_read_lock_held(&kvm->srcu)
			|| lockdep_is_held(&kvm->slots_lock));
}

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, struct kvm_memslots *slots);
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);

pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
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);
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(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);

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);
pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
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_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_unblocking(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);
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);
void kvm_make_scan_ioapic_request(struct kvm *kvm);
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);
int 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 *is_dirty);

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_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
			bool line_status);
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);

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);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);

void *kvm_kvzalloc(unsigned long size);

#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

#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(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);

#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
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);
#else
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)
{
}
#endif

/* must be called with irqs disabled */
static inline void __kvm_guest_enter(void)
{
	guest_enter();
	/* 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 userspace 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.
	 */
	if (!context_tracking_cpu_is_enabled())
		rcu_virt_note_context_switch(smp_processor_id());
}

/* must be called with irqs disabled */
static inline void __kvm_guest_exit(void)
{
	guest_exit();
}

static inline void kvm_guest_enter(void)
{
	unsigned long flags;

	local_irq_save(flags);
	__kvm_guest_enter();
	local_irq_restore(flags);
}

static inline void kvm_guest_exit(void)
{
	unsigned long flags;

	local_irq_save(flags);
	__kvm_guest_exit();
	local_irq_restore(flags);
}

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

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);
}

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 CONFIG_HAVE_KVM_IRQ_ROUTING

#ifdef CONFIG_S390
#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
#else
#define KVM_MAX_IRQ_ROUTES 1024
#endif

int kvm_setup_default_irq_routing(struct kvm *kvm);
int kvm_setup_empty_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_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 */

#ifdef CONFIG_KVM_APIC_ARCHITECTURE
bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
#else
static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
#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;
	}
}

extern bool kvm_rebooting;

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;
	int (*create)(struct kvm_device *dev, u32 type);

	/*
	 * 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);

	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);
};

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_xics_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
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 */

#endif