virt/kvm/kvm_main.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 */

#include <kvm/iodev.h>

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/syscore_ops.h>
#include <linux/cpu.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/sched/stat.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
#include <linux/kvm_para.h>
#include <linux/pagemap.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/compat.h>
#include <linux/srcu.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/bsearch.h>
#include <linux/io.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
#include <linux/suspend.h>

#include <asm/processor.h>
#include <asm/ioctl.h>
#include <linux/uaccess.h>

#include "coalesced_mmio.h"
#include "async_pf.h"
#include "kvm_mm.h"
#include "vfio.h"

#include <trace/events/ipi.h>

#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>

#include <linux/kvm_dirty_ring.h>


/* Worst case buffer size needed for holding an integer. */
#define ITOA_MAX_LEN 12

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

/* Architectures should define their poll value according to the halt latency */
unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
module_param(halt_poll_ns, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns);

/* Default doubles per-vcpu halt_poll_ns. */
unsigned int halt_poll_ns_grow = 2;
module_param(halt_poll_ns_grow, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow);

/* The start value to grow halt_poll_ns from */
unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
module_param(halt_poll_ns_grow_start, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);

/* Default resets per-vcpu halt_poll_ns . */
unsigned int halt_poll_ns_shrink;
module_param(halt_poll_ns_shrink, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);

/*
 * Ordering of locks:
 *
 *	kvm->lock --> kvm->slots_lock --> kvm->irq_lock
 */

DEFINE_MUTEX(kvm_lock);
LIST_HEAD(vm_list);

static struct kmem_cache *kvm_vcpu_cache;

static __read_mostly struct preempt_ops kvm_preempt_ops;
static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);

struct dentry *kvm_debugfs_dir;
EXPORT_SYMBOL_GPL(kvm_debugfs_dir);

static const struct file_operations stat_fops_per_vm;

static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
			   unsigned long arg);
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
				  unsigned long arg);
#define KVM_COMPAT(c)	.compat_ioctl	= (c)
#else
/*
 * For architectures that don't implement a compat infrastructure,
 * adopt a double line of defense:
 * - Prevent a compat task from opening /dev/kvm
 * - If the open has been done by a 64bit task, and the KVM fd
 *   passed to a compat task, let the ioctls fail.
 */
static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
				unsigned long arg) { return -EINVAL; }

static int kvm_no_compat_open(struct inode *inode, struct file *file)
{
	return is_compat_task() ? -ENODEV : 0;
}
#define KVM_COMPAT(c)	.compat_ioctl	= kvm_no_compat_ioctl,	\
			.open		= kvm_no_compat_open
#endif
static int hardware_enable_all(void);
static void hardware_disable_all(void);

static void kvm_io_bus_destroy(struct kvm_io_bus *bus);

#define KVM_EVENT_CREATE_VM 0
#define KVM_EVENT_DESTROY_VM 1
static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
static unsigned long long kvm_createvm_count;
static unsigned long long kvm_active_vms;

static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);

__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
{
}

bool kvm_is_zone_device_page(struct page *page)
{
	/*
	 * The metadata used by is_zone_device_page() to determine whether or
	 * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
	 * page_count() is zero to help detect bad usage of this helper.
	 */
	if (WARN_ON_ONCE(!page_count(page)))
		return false;

	return is_zone_device_page(page);
}

/*
 * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted
 * page, NULL otherwise.  Note, the list of refcounted PG_reserved page types
 * is likely incomplete, it has been compiled purely through people wanting to
 * back guest with a certain type of memory and encountering issues.
 */
struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn)
{
	struct page *page;

	if (!pfn_valid(pfn))
		return NULL;

	page = pfn_to_page(pfn);
	if (!PageReserved(page))
		return page;

	/* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */
	if (is_zero_pfn(pfn))
		return page;

	/*
	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
	 * perspective they are "normal" pages, albeit with slightly different
	 * usage rules.
	 */
	if (kvm_is_zone_device_page(page))
		return page;

	return NULL;
}

/*
 * Switches to specified vcpu, until a matching vcpu_put()
 */
void vcpu_load(struct kvm_vcpu *vcpu)
{
	int cpu = get_cpu();

	__this_cpu_write(kvm_running_vcpu, vcpu);
	preempt_notifier_register(&vcpu->preempt_notifier);
	kvm_arch_vcpu_load(vcpu, cpu);
	put_cpu();
}
EXPORT_SYMBOL_GPL(vcpu_load);

void vcpu_put(struct kvm_vcpu *vcpu)
{
	preempt_disable();
	kvm_arch_vcpu_put(vcpu);
	preempt_notifier_unregister(&vcpu->preempt_notifier);
	__this_cpu_write(kvm_running_vcpu, NULL);
	preempt_enable();
}
EXPORT_SYMBOL_GPL(vcpu_put);

/* TODO: merge with kvm_arch_vcpu_should_kick */
static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
{
	int mode = kvm_vcpu_exiting_guest_mode(vcpu);

	/*
	 * We need to wait for the VCPU to reenable interrupts and get out of
	 * READING_SHADOW_PAGE_TABLES mode.
	 */
	if (req & KVM_REQUEST_WAIT)
		return mode != OUTSIDE_GUEST_MODE;

	/*
	 * Need to kick a running VCPU, but otherwise there is nothing to do.
	 */
	return mode == IN_GUEST_MODE;
}

static void ack_kick(void *_completed)
{
}

static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
{
	if (cpumask_empty(cpus))
		return false;

	smp_call_function_many(cpus, ack_kick, NULL, wait);
	return true;
}

static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req,
				  struct cpumask *tmp, int current_cpu)
{
	int cpu;

	if (likely(!(req & KVM_REQUEST_NO_ACTION)))
		__kvm_make_request(req, vcpu);

	if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
		return;

	/*
	 * Note, the vCPU could get migrated to a different pCPU at any point
	 * after kvm_request_needs_ipi(), which could result in sending an IPI
	 * to the previous pCPU.  But, that's OK because the purpose of the IPI
	 * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is
	 * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES
	 * after this point is also OK, as the requirement is only that KVM wait
	 * for vCPUs that were reading SPTEs _before_ any changes were
	 * finalized. See kvm_vcpu_kick() for more details on handling requests.
	 */
	if (kvm_request_needs_ipi(vcpu, req)) {
		cpu = READ_ONCE(vcpu->cpu);
		if (cpu != -1 && cpu != current_cpu)
			__cpumask_set_cpu(cpu, tmp);
	}
}

bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
				 unsigned long *vcpu_bitmap)
{
	struct kvm_vcpu *vcpu;
	struct cpumask *cpus;
	int i, me;
	bool called;

	me = get_cpu();

	cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
	cpumask_clear(cpus);

	for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
		vcpu = kvm_get_vcpu(kvm, i);
		if (!vcpu)
			continue;
		kvm_make_vcpu_request(vcpu, req, cpus, me);
	}

	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
	put_cpu();

	return called;
}

bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
				      struct kvm_vcpu *except)
{
	struct kvm_vcpu *vcpu;
	struct cpumask *cpus;
	unsigned long i;
	bool called;
	int me;

	me = get_cpu();

	cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
	cpumask_clear(cpus);

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu == except)
			continue;
		kvm_make_vcpu_request(vcpu, req, cpus, me);
	}

	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
	put_cpu();

	return called;
}

bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
	return kvm_make_all_cpus_request_except(kvm, req, NULL);
}
EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);

void kvm_flush_remote_tlbs(struct kvm *kvm)
{
	++kvm->stat.generic.remote_tlb_flush_requests;

	/*
	 * We want to publish modifications to the page tables before reading
	 * mode. Pairs with a memory barrier in arch-specific code.
	 * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest
	 * and smp_mb in walk_shadow_page_lockless_begin/end.
	 * - powerpc: smp_mb in kvmppc_prepare_to_enter.
	 *
	 * There is already an smp_mb__after_atomic() before
	 * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
	 * barrier here.
	 */
	if (!kvm_arch_flush_remote_tlbs(kvm)
	    || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
		++kvm->stat.generic.remote_tlb_flush;
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);

void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
{
	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
		return;

	/*
	 * Fall back to a flushing entire TLBs if the architecture range-based
	 * TLB invalidation is unsupported or can't be performed for whatever
	 * reason.
	 */
	kvm_flush_remote_tlbs(kvm);
}

void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
				   const struct kvm_memory_slot *memslot)
{
	/*
	 * All current use cases for flushing the TLBs for a specific memslot
	 * are related to dirty logging, and many do the TLB flush out of
	 * mmu_lock. The interaction between the various operations on memslot
	 * must be serialized by slots_locks to ensure the TLB flush from one
	 * operation is observed by any other operation on the same memslot.
	 */
	lockdep_assert_held(&kvm->slots_lock);
	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
}

static void kvm_flush_shadow_all(struct kvm *kvm)
{
	kvm_arch_flush_shadow_all(kvm);
	kvm_arch_guest_memory_reclaimed(kvm);
}

#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
					       gfp_t gfp_flags)
{
	gfp_flags |= mc->gfp_zero;

	if (mc->kmem_cache)
		return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
	else
		return (void *)__get_free_page(gfp_flags);
}

int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
{
	gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT;
	void *obj;

	if (mc->nobjs >= min)
		return 0;

	if (unlikely(!mc->objects)) {
		if (WARN_ON_ONCE(!capacity))
			return -EIO;

		mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
		if (!mc->objects)
			return -ENOMEM;

		mc->capacity = capacity;
	}

	/* It is illegal to request a different capacity across topups. */
	if (WARN_ON_ONCE(mc->capacity != capacity))
		return -EIO;

	while (mc->nobjs < mc->capacity) {
		obj = mmu_memory_cache_alloc_obj(mc, gfp);
		if (!obj)
			return mc->nobjs >= min ? 0 : -ENOMEM;
		mc->objects[mc->nobjs++] = obj;
	}
	return 0;
}

int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
{
	return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
}

int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
{
	return mc->nobjs;
}

void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
{
	while (mc->nobjs) {
		if (mc->kmem_cache)
			kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]);
		else
			free_page((unsigned long)mc->objects[--mc->nobjs]);
	}

	kvfree(mc->objects);

	mc->objects = NULL;
	mc->capacity = 0;
}

void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
{
	void *p;

	if (WARN_ON(!mc->nobjs))
		p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT);
	else
		p = mc->objects[--mc->nobjs];
	BUG_ON(!p);
	return p;
}
#endif

static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
	mutex_init(&vcpu->mutex);
	vcpu->cpu = -1;
	vcpu->kvm = kvm;
	vcpu->vcpu_id = id;
	vcpu->pid = NULL;
#ifndef __KVM_HAVE_ARCH_WQP
	rcuwait_init(&vcpu->wait);
#endif
	kvm_async_pf_vcpu_init(vcpu);

	kvm_vcpu_set_in_spin_loop(vcpu, false);
	kvm_vcpu_set_dy_eligible(vcpu, false);
	vcpu->preempted = false;
	vcpu->ready = false;
	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
	vcpu->last_used_slot = NULL;

	/* Fill the stats id string for the vcpu */
	snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d",
		 task_pid_nr(current), id);
}

static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_destroy(vcpu);
	kvm_dirty_ring_free(&vcpu->dirty_ring);

	/*
	 * No need for rcu_read_lock as VCPU_RUN is the only place that changes
	 * the vcpu->pid pointer, and at destruction time all file descriptors
	 * are already gone.
	 */
	put_pid(rcu_dereference_protected(vcpu->pid, 1));

	free_page((unsigned long)vcpu->run);
	kmem_cache_free(kvm_vcpu_cache, vcpu);
}

void kvm_destroy_vcpus(struct kvm *kvm)
{
	unsigned long i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_vcpu_destroy(vcpu);
		xa_erase(&kvm->vcpu_array, i);
	}

	atomic_set(&kvm->online_vcpus, 0);
}
EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);

#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
{
	return container_of(mn, struct kvm, mmu_notifier);
}

typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);

typedef void (*on_lock_fn_t)(struct kvm *kvm);

struct kvm_mmu_notifier_range {
	/*
	 * 64-bit addresses, as KVM notifiers can operate on host virtual
	 * addresses (unsigned long) and guest physical addresses (64-bit).
	 */
	u64 start;
	u64 end;
	union kvm_mmu_notifier_arg arg;
	gfn_handler_t handler;
	on_lock_fn_t on_lock;
	bool flush_on_ret;
	bool may_block;
};

/*
 * The inner-most helper returns a tuple containing the return value from the
 * arch- and action-specific handler, plus a flag indicating whether or not at
 * least one memslot was found, i.e. if the handler found guest memory.
 *
 * Note, most notifiers are averse to booleans, so even though KVM tracks the
 * return from arch code as a bool, outer helpers will cast it to an int. :-(
 */
typedef struct kvm_mmu_notifier_return {
	bool ret;
	bool found_memslot;
} kvm_mn_ret_t;

/*
 * Use a dedicated stub instead of NULL to indicate that there is no callback
 * function/handler.  The compiler technically can't guarantee that a real
 * function will have a non-zero address, and so it will generate code to
 * check for !NULL, whereas comparing against a stub will be elided at compile
 * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
 */
static void kvm_null_fn(void)
{

}
#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)

static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;

/* Iterate over each memslot intersecting [start, last] (inclusive) range */
#define kvm_for_each_memslot_in_hva_range(node, slots, start, last)	     \
	for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
	     node;							     \
	     node = interval_tree_iter_next(node, start, last))	     \

static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
							   const struct kvm_mmu_notifier_range *range)
{
	struct kvm_mmu_notifier_return r = {
		.ret = false,
		.found_memslot = false,
	};
	struct kvm_gfn_range gfn_range;
	struct kvm_memory_slot *slot;
	struct kvm_memslots *slots;
	int i, idx;

	if (WARN_ON_ONCE(range->end <= range->start))
		return r;

	/* A null handler is allowed if and only if on_lock() is provided. */
	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
			 IS_KVM_NULL_FN(range->handler)))
		return r;

	idx = srcu_read_lock(&kvm->srcu);

	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
		struct interval_tree_node *node;

		slots = __kvm_memslots(kvm, i);
		kvm_for_each_memslot_in_hva_range(node, slots,
						  range->start, range->end - 1) {
			unsigned long hva_start, hva_end;

			slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
			hva_start = max_t(unsigned long, range->start, slot->userspace_addr);
			hva_end = min_t(unsigned long, range->end,
					slot->userspace_addr + (slot->npages << PAGE_SHIFT));

			/*
			 * To optimize for the likely case where the address
			 * range is covered by zero or one memslots, don't
			 * bother making these conditional (to avoid writes on
			 * the second or later invocation of the handler).
			 */
			gfn_range.arg = range->arg;
			gfn_range.may_block = range->may_block;

			/*
			 * {gfn(page) | page intersects with [hva_start, hva_end)} =
			 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
			 */
			gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
			gfn_range.slot = slot;

			if (!r.found_memslot) {
				r.found_memslot = true;
				KVM_MMU_LOCK(kvm);
				if (!IS_KVM_NULL_FN(range->on_lock))
					range->on_lock(kvm);

				if (IS_KVM_NULL_FN(range->handler))
					break;
			}
			r.ret |= range->handler(kvm, &gfn_range);
		}
	}

	if (range->flush_on_ret && r.ret)
		kvm_flush_remote_tlbs(kvm);

	if (r.found_memslot)
		KVM_MMU_UNLOCK(kvm);

	srcu_read_unlock(&kvm->srcu, idx);

	return r;
}

static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
						unsigned long start,
						unsigned long end,
						union kvm_mmu_notifier_arg arg,
						gfn_handler_t handler)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	const struct kvm_mmu_notifier_range range = {
		.start		= start,
		.end		= end,
		.arg		= arg,
		.handler	= handler,
		.on_lock	= (void *)kvm_null_fn,
		.flush_on_ret	= true,
		.may_block	= false,
	};

	return __kvm_handle_hva_range(kvm, &range).ret;
}

static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
							 unsigned long start,
							 unsigned long end,
							 gfn_handler_t handler)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	const struct kvm_mmu_notifier_range range = {
		.start		= start,
		.end		= end,
		.handler	= handler,
		.on_lock	= (void *)kvm_null_fn,
		.flush_on_ret	= false,
		.may_block	= false,
	};

	return __kvm_handle_hva_range(kvm, &range).ret;
}

static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	/*
	 * Skipping invalid memslots is correct if and only change_pte() is
	 * surrounded by invalidate_range_{start,end}(), which is currently
	 * guaranteed by the primary MMU.  If that ever changes, KVM needs to
	 * unmap the memslot instead of skipping the memslot to ensure that KVM
	 * doesn't hold references to the old PFN.
	 */
	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));

	if (range->slot->flags & KVM_MEMSLOT_INVALID)
		return false;

	return kvm_set_spte_gfn(kvm, range);
}

static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
					struct mm_struct *mm,
					unsigned long address,
					pte_t pte)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	const union kvm_mmu_notifier_arg arg = { .pte = pte };

	trace_kvm_set_spte_hva(address);

	/*
	 * .change_pte() must be surrounded by .invalidate_range_{start,end}().
	 * If mmu_invalidate_in_progress is zero, then no in-progress
	 * invalidations, including this one, found a relevant memslot at
	 * start(); rechecking memslots here is unnecessary.  Note, a false
	 * positive (count elevated by a different invalidation) is sub-optimal
	 * but functionally ok.
	 */
	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
		return;

	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
}

void kvm_mmu_invalidate_begin(struct kvm *kvm)
{
	lockdep_assert_held_write(&kvm->mmu_lock);
	/*
	 * The count increase must become visible at unlock time as no
	 * spte can be established without taking the mmu_lock and
	 * count is also read inside the mmu_lock critical section.
	 */
	kvm->mmu_invalidate_in_progress++;

	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
		kvm->mmu_invalidate_range_start = INVALID_GPA;
		kvm->mmu_invalidate_range_end = INVALID_GPA;
	}
}

void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
{
	lockdep_assert_held_write(&kvm->mmu_lock);

	WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);

	if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
		kvm->mmu_invalidate_range_start = start;
		kvm->mmu_invalidate_range_end = end;
	} else {
		/*
		 * Fully tracking multiple concurrent ranges has diminishing
		 * returns. Keep things simple and just find the minimal range
		 * which includes the current and new ranges. As there won't be
		 * enough information to subtract a range after its invalidate
		 * completes, any ranges invalidated concurrently will
		 * accumulate and persist until all outstanding invalidates
		 * complete.
		 */
		kvm->mmu_invalidate_range_start =
			min(kvm->mmu_invalidate_range_start, start);
		kvm->mmu_invalidate_range_end =
			max(kvm->mmu_invalidate_range_end, end);
	}
}

bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
	return kvm_unmap_gfn_range(kvm, range);
}

static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
					const struct mmu_notifier_range *range)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	const struct kvm_mmu_notifier_range hva_range = {
		.start		= range->start,
		.end		= range->end,
		.handler	= kvm_mmu_unmap_gfn_range,
		.on_lock	= kvm_mmu_invalidate_begin,
		.flush_on_ret	= true,
		.may_block	= mmu_notifier_range_blockable(range),
	};

	trace_kvm_unmap_hva_range(range->start, range->end);

	/*
	 * Prevent memslot modification between range_start() and range_end()
	 * so that conditionally locking provides the same result in both
	 * functions.  Without that guarantee, the mmu_invalidate_in_progress
	 * adjustments will be imbalanced.
	 *
	 * Pairs with the decrement in range_end().
	 */
	spin_lock(&kvm->mn_invalidate_lock);
	kvm->mn_active_invalidate_count++;
	spin_unlock(&kvm->mn_invalidate_lock);

	/*
	 * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
	 * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
	 * each cache's lock.  There are relatively few caches in existence at
	 * any given time, and the caches themselves can check for hva overlap,
	 * i.e. don't need to rely on memslot overlap checks for performance.
	 * Because this runs without holding mmu_lock, the pfn caches must use
	 * mn_active_invalidate_count (see above) instead of
	 * mmu_invalidate_in_progress.
	 */
	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
					  hva_range.may_block);

	/*
	 * If one or more memslots were found and thus zapped, notify arch code
	 * that guest memory has been reclaimed.  This needs to be done *after*
	 * dropping mmu_lock, as x86's reclaim path is slooooow.
	 */
	if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot)
		kvm_arch_guest_memory_reclaimed(kvm);

	return 0;
}

void kvm_mmu_invalidate_end(struct kvm *kvm)
{
	lockdep_assert_held_write(&kvm->mmu_lock);

	/*
	 * This sequence increase will notify the kvm page fault that
	 * the page that is going to be mapped in the spte could have
	 * been freed.
	 */
	kvm->mmu_invalidate_seq++;
	smp_wmb();
	/*
	 * The above sequence increase must be visible before the
	 * below count decrease, which is ensured by the smp_wmb above
	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
	 */
	kvm->mmu_invalidate_in_progress--;
	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);

	/*
	 * Assert that at least one range was added between start() and end().
	 * Not adding a range isn't fatal, but it is a KVM bug.
	 */
	WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
}

static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
					const struct mmu_notifier_range *range)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	const struct kvm_mmu_notifier_range hva_range = {
		.start		= range->start,
		.end		= range->end,
		.handler	= (void *)kvm_null_fn,
		.on_lock	= kvm_mmu_invalidate_end,
		.flush_on_ret	= false,
		.may_block	= mmu_notifier_range_blockable(range),
	};
	bool wake;

	__kvm_handle_hva_range(kvm, &hva_range);

	/* Pairs with the increment in range_start(). */
	spin_lock(&kvm->mn_invalidate_lock);
	wake = (--kvm->mn_active_invalidate_count == 0);
	spin_unlock(&kvm->mn_invalidate_lock);

	/*
	 * There can only be one waiter, since the wait happens under
	 * slots_lock.
	 */
	if (wake)
		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
}

static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
					      struct mm_struct *mm,
					      unsigned long start,
					      unsigned long end)
{
	trace_kvm_age_hva(start, end);

	return kvm_handle_hva_range(mn, start, end, KVM_MMU_NOTIFIER_NO_ARG,
				    kvm_age_gfn);
}

static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
					struct mm_struct *mm,
					unsigned long start,
					unsigned long end)
{
	trace_kvm_age_hva(start, end);

	/*
	 * Even though we do not flush TLB, this will still adversely
	 * affect performance on pre-Haswell Intel EPT, where there is
	 * no EPT Access Bit to clear so that we have to tear down EPT
	 * tables instead. If we find this unacceptable, we can always
	 * add a parameter to kvm_age_hva so that it effectively doesn't
	 * do anything on clear_young.
	 *
	 * Also note that currently we never issue secondary TLB flushes
	 * from clear_young, leaving this job up to the regular system
	 * cadence. If we find this inaccurate, we might come up with a
	 * more sophisticated heuristic later.
	 */
	return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn);
}

static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
				       struct mm_struct *mm,
				       unsigned long address)
{
	trace_kvm_test_age_hva(address);

	return kvm_handle_hva_range_no_flush(mn, address, address + 1,
					     kvm_test_age_gfn);
}

static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
				     struct mm_struct *mm)
{
	struct kvm *kvm = mmu_notifier_to_kvm(mn);
	int idx;

	idx = srcu_read_lock(&kvm->srcu);
	kvm_flush_shadow_all(kvm);
	srcu_read_unlock(&kvm->srcu, idx);
}

static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
	.clear_young		= kvm_mmu_notifier_clear_young,
	.test_young		= kvm_mmu_notifier_test_young,
	.change_pte		= kvm_mmu_notifier_change_pte,
	.release		= kvm_mmu_notifier_release,
};

static int kvm_init_mmu_notifier(struct kvm *kvm)
{
	kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;
	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
}

#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */

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

#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */

#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
static int kvm_pm_notifier_call(struct notifier_block *bl,
				unsigned long state,
				void *unused)
{
	struct kvm *kvm = container_of(bl, struct kvm, pm_notifier);

	return kvm_arch_pm_notifier(kvm, state);
}

static void kvm_init_pm_notifier(struct kvm *kvm)
{
	kvm->pm_notifier.notifier_call = kvm_pm_notifier_call;
	/* Suspend KVM before we suspend ftrace, RCU, etc. */
	kvm->pm_notifier.priority = INT_MAX;
	register_pm_notifier(&kvm->pm_notifier);
}

static void kvm_destroy_pm_notifier(struct kvm *kvm)
{
	unregister_pm_notifier(&kvm->pm_notifier);
}
#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */
static void kvm_init_pm_notifier(struct kvm *kvm)
{
}

static void kvm_destroy_pm_notifier(struct kvm *kvm)
{
}
#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */

static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
{
	if (!memslot->dirty_bitmap)
		return;

	kvfree(memslot->dirty_bitmap);
	memslot->dirty_bitmap = NULL;
}

/* This does not remove the slot from struct kvm_memslots data structures */
static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
	if (slot->flags & KVM_MEM_GUEST_MEMFD)
		kvm_gmem_unbind(slot);

	kvm_destroy_dirty_bitmap(slot);

	kvm_arch_free_memslot(kvm, slot);

	kfree(slot);
}

static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
{
	struct hlist_node *idnode;
	struct kvm_memory_slot *memslot;
	int bkt;

	/*
	 * The same memslot objects live in both active and inactive sets,
	 * arbitrarily free using index '1' so the second invocation of this
	 * function isn't operating over a structure with dangling pointers
	 * (even though this function isn't actually touching them).
	 */
	if (!slots->node_idx)
		return;

	hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1])
		kvm_free_memslot(kvm, memslot);
}

static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
{
	switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
	case KVM_STATS_TYPE_INSTANT:
		return 0444;
	case KVM_STATS_TYPE_CUMULATIVE:
	case KVM_STATS_TYPE_PEAK:
	default:
		return 0644;
	}
}


static void kvm_destroy_vm_debugfs(struct kvm *kvm)
{
	int i;
	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
				      kvm_vcpu_stats_header.num_desc;

	if (IS_ERR(kvm->debugfs_dentry))
		return;

	debugfs_remove_recursive(kvm->debugfs_dentry);

	if (kvm->debugfs_stat_data) {
		for (i = 0; i < kvm_debugfs_num_entries; i++)
			kfree(kvm->debugfs_stat_data[i]);
		kfree(kvm->debugfs_stat_data);
	}
}

static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
{
	static DEFINE_MUTEX(kvm_debugfs_lock);
	struct dentry *dent;
	char dir_name[ITOA_MAX_LEN * 2];
	struct kvm_stat_data *stat_data;
	const struct _kvm_stats_desc *pdesc;
	int i, ret = -ENOMEM;
	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
				      kvm_vcpu_stats_header.num_desc;

	if (!debugfs_initialized())
		return 0;

	snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname);
	mutex_lock(&kvm_debugfs_lock);
	dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
	if (dent) {
		pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
		dput(dent);
		mutex_unlock(&kvm_debugfs_lock);
		return 0;
	}
	dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
	mutex_unlock(&kvm_debugfs_lock);
	if (IS_ERR(dent))
		return 0;

	kvm->debugfs_dentry = dent;
	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
					 sizeof(*kvm->debugfs_stat_data),
					 GFP_KERNEL_ACCOUNT);
	if (!kvm->debugfs_stat_data)
		goto out_err;

	for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
		pdesc = &kvm_vm_stats_desc[i];
		stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
		if (!stat_data)
			goto out_err;

		stat_data->kvm = kvm;
		stat_data->desc = pdesc;
		stat_data->kind = KVM_STAT_VM;
		kvm->debugfs_stat_data[i] = stat_data;
		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
				    kvm->debugfs_dentry, stat_data,
				    &stat_fops_per_vm);
	}

	for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
		pdesc = &kvm_vcpu_stats_desc[i];
		stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
		if (!stat_data)
			goto out_err;

		stat_data->kvm = kvm;
		stat_data->desc = pdesc;
		stat_data->kind = KVM_STAT_VCPU;
		kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
				    kvm->debugfs_dentry, stat_data,
				    &stat_fops_per_vm);
	}

	ret = kvm_arch_create_vm_debugfs(kvm);
	if (ret)
		goto out_err;

	return 0;
out_err:
	kvm_destroy_vm_debugfs(kvm);
	return ret;
}

/*
 * Called after the VM is otherwise initialized, but just before adding it to
 * the vm_list.
 */
int __weak kvm_arch_post_init_vm(struct kvm *kvm)
{
	return 0;
}

/*
 * Called just after removing the VM from the vm_list, but before doing any
 * other destruction.
 */
void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
{
}

/*
 * Called after per-vm debugfs created.  When called kvm->debugfs_dentry should
 * be setup already, so we can create arch-specific debugfs entries under it.
 * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so
 * a per-arch destroy interface is not needed.
 */
int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
{
	return 0;
}

static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
{
	struct kvm *kvm = kvm_arch_alloc_vm();
	struct kvm_memslots *slots;
	int r = -ENOMEM;
	int i, j;

	if (!kvm)
		return ERR_PTR(-ENOMEM);

	KVM_MMU_LOCK_INIT(kvm);
	mmgrab(current->mm);
	kvm->mm = current->mm;
	kvm_eventfd_init(kvm);
	mutex_init(&kvm->lock);
	mutex_init(&kvm->irq_lock);
	mutex_init(&kvm->slots_lock);
	mutex_init(&kvm->slots_arch_lock);
	spin_lock_init(&kvm->mn_invalidate_lock);
	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
	xa_init(&kvm->vcpu_array);
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
	xa_init(&kvm->mem_attr_array);
#endif

	INIT_LIST_HEAD(&kvm->gpc_list);
	spin_lock_init(&kvm->gpc_lock);

	INIT_LIST_HEAD(&kvm->devices);
	kvm->max_vcpus = KVM_MAX_VCPUS;

	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);

	/*
	 * Force subsequent debugfs file creations to fail if the VM directory
	 * is not created (by kvm_create_vm_debugfs()).
	 */
	kvm->debugfs_dentry = ERR_PTR(-ENOENT);

	snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d",
		 task_pid_nr(current));

	if (init_srcu_struct(&kvm->srcu))
		goto out_err_no_srcu;
	if (init_srcu_struct(&kvm->irq_srcu))
		goto out_err_no_irq_srcu;

	refcount_set(&kvm->users_count, 1);
	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
		for (j = 0; j < 2; j++) {
			slots = &kvm->__memslots[i][j];

			atomic_long_set(&slots->last_used_slot, (unsigned long)NULL);
			slots->hva_tree = RB_ROOT_CACHED;
			slots->gfn_tree = RB_ROOT;
			hash_init(slots->id_hash);
			slots->node_idx = j;

			/* Generations must be different for each address space. */
			slots->generation = i;
		}

		rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]);
	}

	for (i = 0; i < KVM_NR_BUSES; i++) {
		rcu_assign_pointer(kvm->buses[i],
			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
		if (!kvm->buses[i])
			goto out_err_no_arch_destroy_vm;
	}

	r = kvm_arch_init_vm(kvm, type);
	if (r)
		goto out_err_no_arch_destroy_vm;

	r = hardware_enable_all();
	if (r)
		goto out_err_no_disable;

#ifdef CONFIG_HAVE_KVM_IRQCHIP
	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif

	r = kvm_init_mmu_notifier(kvm);
	if (r)
		goto out_err_no_mmu_notifier;

	r = kvm_coalesced_mmio_init(kvm);
	if (r < 0)
		goto out_no_coalesced_mmio;

	r = kvm_create_vm_debugfs(kvm, fdname);
	if (r)
		goto out_err_no_debugfs;

	r = kvm_arch_post_init_vm(kvm);
	if (r)
		goto out_err;

	mutex_lock(&kvm_lock);
	list_add(&kvm->vm_list, &vm_list);
	mutex_unlock(&kvm_lock);

	preempt_notifier_inc();
	kvm_init_pm_notifier(kvm);

	return kvm;

out_err:
	kvm_destroy_vm_debugfs(kvm);
out_err_no_debugfs:
	kvm_coalesced_mmio_free(kvm);
out_no_coalesced_mmio:
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
	if (kvm->mmu_notifier.ops)
		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
#endif
out_err_no_mmu_notifier:
	hardware_disable_all();
out_err_no_disable:
	kvm_arch_destroy_vm(kvm);
out_err_no_arch_destroy_vm:
	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
	for (i = 0; i < KVM_NR_BUSES; i++)
		kfree(kvm_get_bus(kvm, i));
	cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
	cleanup_srcu_struct(&kvm->srcu);
out_err_no_srcu:
	kvm_arch_free_vm(kvm);
	mmdrop(current->mm);
	return ERR_PTR(r);
}

static void kvm_destroy_devices(struct kvm *kvm)
{
	struct kvm_device *dev, *tmp;

	/*
	 * We do not need to take the kvm->lock here, because nobody else
	 * has a reference to the struct kvm at this point and therefore
	 * cannot access the devices list anyhow.
	 */
	list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
		list_del(&dev->vm_node);
		dev->ops->destroy(dev);
	}
}

static void kvm_destroy_vm(struct kvm *kvm)
{
	int i;
	struct mm_struct *mm = kvm->mm;

	kvm_destroy_pm_notifier(kvm);
	kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
	kvm_destroy_vm_debugfs(kvm);
	kvm_arch_sync_events(kvm);
	mutex_lock(&kvm_lock);
	list_del(&kvm->vm_list);
	mutex_unlock(&kvm_lock);
	kvm_arch_pre_destroy_vm(kvm);

	kvm_free_irq_routing(kvm);
	for (i = 0; i < KVM_NR_BUSES; i++) {
		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);

		if (bus)
			kvm_io_bus_destroy(bus);
		kvm->buses[i] = NULL;
	}
	kvm_coalesced_mmio_free(kvm);
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
	/*
	 * At this point, pending calls to invalidate_range_start()
	 * have completed but no more MMU notifiers will run, so
	 * mn_active_invalidate_count may remain unbalanced.
	 * No threads can be waiting in kvm_swap_active_memslots() as the
	 * last reference on KVM has been dropped, but freeing
	 * memslots would deadlock without this manual intervention.
	 *
	 * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU
	 * notifier between a start() and end(), then there shouldn't be any
	 * in-progress invalidations.
	 */
	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
	if (kvm->mn_active_invalidate_count)
		kvm->mn_active_invalidate_count = 0;
	else
		WARN_ON(kvm->mmu_invalidate_in_progress);
#else
	kvm_flush_shadow_all(kvm);
#endif
	kvm_arch_destroy_vm(kvm);
	kvm_destroy_devices(kvm);
	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
		kvm_free_memslots(kvm, &kvm->__memslots[i][0]);
		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
	}
	cleanup_srcu_struct(&kvm->irq_srcu);
	cleanup_srcu_struct(&kvm->srcu);
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
	xa_destroy(&kvm->mem_attr_array);
#endif
	kvm_arch_free_vm(kvm);
	preempt_notifier_dec();
	hardware_disable_all();
	mmdrop(mm);
}

void kvm_get_kvm(struct kvm *kvm)
{
	refcount_inc(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm);

/*
 * Make sure the vm is not during destruction, which is a safe version of
 * kvm_get_kvm().  Return true if kvm referenced successfully, false otherwise.
 */
bool kvm_get_kvm_safe(struct kvm *kvm)
{
	return refcount_inc_not_zero(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm_safe);

void kvm_put_kvm(struct kvm *kvm)
{
	if (refcount_dec_and_test(&kvm->users_count))
		kvm_destroy_vm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_put_kvm);

/*
 * Used to put a reference that was taken on behalf of an object associated
 * with a user-visible file descriptor, e.g. a vcpu or device, if installation
 * of the new file descriptor fails and the reference cannot be transferred to
 * its final owner.  In such cases, the caller is still actively using @kvm and
 * will fail miserably if the refcount unexpectedly hits zero.
 */
void kvm_put_kvm_no_destroy(struct kvm *kvm)
{
	WARN_ON(refcount_dec_and_test(&kvm->users_count));
}
EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy);

static int kvm_vm_release(struct inode *inode, struct file *filp)
{
	struct kvm *kvm = filp->private_data;

	kvm_irqfd_release(kvm);

	kvm_put_kvm(kvm);
	return 0;
}

/*
 * Allocation size is twice as large as the actual dirty bitmap size.
 * See kvm_vm_ioctl_get_dirty_log() why this is needed.
 */
static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot)
{
	unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot);

	memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT);
	if (!memslot->dirty_bitmap)
		return -ENOMEM;

	return 0;
}

static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id)
{
	struct kvm_memslots *active = __kvm_memslots(kvm, as_id);
	int node_idx_inactive = active->node_idx ^ 1;

	return &kvm->__memslots[as_id][node_idx_inactive];
}

/*
 * Helper to get the address space ID when one of memslot pointers may be NULL.
 * This also serves as a sanity that at least one of the pointers is non-NULL,
 * and that their address space IDs don't diverge.
 */
static int kvm_memslots_get_as_id(struct kvm_memory_slot *a,
				  struct kvm_memory_slot *b)
{
	if (WARN_ON_ONCE(!a && !b))
		return 0;

	if (!a)
		return b->as_id;
	if (!b)
		return a->as_id;

	WARN_ON_ONCE(a->as_id != b->as_id);
	return a->as_id;
}

static void kvm_insert_gfn_node(struct kvm_memslots *slots,
				struct kvm_memory_slot *slot)
{
	struct rb_root *gfn_tree = &slots->gfn_tree;
	struct rb_node **node, *parent;
	int idx = slots->node_idx;

	parent = NULL;
	for (node = &gfn_tree->rb_node; *node; ) {
		struct kvm_memory_slot *tmp;

		tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]);
		parent = *node;
		if (slot->base_gfn < tmp->base_gfn)
			node = &(*node)->rb_left;
		else if (slot->base_gfn > tmp->base_gfn)
			node = &(*node)->rb_right;
		else
			BUG();
	}

	rb_link_node(&slot->gfn_node[idx], parent, node);
	rb_insert_color(&slot->gfn_node[idx], gfn_tree);
}

static void kvm_erase_gfn_node(struct kvm_memslots *slots,
			       struct kvm_memory_slot *slot)
{
	rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree);
}

static void kvm_replace_gfn_node(struct kvm_memslots *slots,
				 struct kvm_memory_slot *old,
				 struct kvm_memory_slot *new)
{
	int idx = slots->node_idx;

	WARN_ON_ONCE(old->base_gfn != new->base_gfn);

	rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx],
			&slots->gfn_tree);
}

/*
 * Replace @old with @new in the inactive memslots.
 *
 * With NULL @old this simply adds @new.
 * With NULL @new this simply removes @old.
 *
 * If @new is non-NULL its hva_node[slots_idx] range has to be set
 * appropriately.
 */
static void kvm_replace_memslot(struct kvm *kvm,
				struct kvm_memory_slot *old,
				struct kvm_memory_slot *new)
{
	int as_id = kvm_memslots_get_as_id(old, new);
	struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
	int idx = slots->node_idx;

	if (old) {
		hash_del(&old->id_node[idx]);
		interval_tree_remove(&old->hva_node[idx], &slots->hva_tree);

		if ((long)old == atomic_long_read(&slots->last_used_slot))
			atomic_long_set(&slots->last_used_slot, (long)new);

		if (!new) {
			kvm_erase_gfn_node(slots, old);
			return;
		}
	}

	/*
	 * Initialize @new's hva range.  Do this even when replacing an @old
	 * slot, kvm_copy_memslot() deliberately does not touch node data.
	 */
	new->hva_node[idx].start = new->userspace_addr;
	new->hva_node[idx].last = new->userspace_addr +
				  (new->npages << PAGE_SHIFT) - 1;

	/*
	 * (Re)Add the new memslot.  There is no O(1) interval_tree_replace(),
	 * hva_node needs to be swapped with remove+insert even though hva can't
	 * change when replacing an existing slot.
	 */
	hash_add(slots->id_hash, &new->id_node[idx], new->id);
	interval_tree_insert(&new->hva_node[idx], &slots->hva_tree);

	/*
	 * If the memslot gfn is unchanged, rb_replace_node() can be used to
	 * switch the node in the gfn tree instead of removing the old and
	 * inserting the new as two separate operations. Replacement is a
	 * single O(1) operation versus two O(log(n)) operations for
	 * remove+insert.
	 */
	if (old && old->base_gfn == new->base_gfn) {
		kvm_replace_gfn_node(slots, old, new);
	} else {
		if (old)
			kvm_erase_gfn_node(slots, old);
		kvm_insert_gfn_node(slots, new);
	}
}

/*
 * Flags that do not access any of the extra space of struct
 * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
 * only allows these.
 */
#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)

static int check_memory_region_flags(struct kvm *kvm,
				     const struct kvm_userspace_memory_region2 *mem)
{
	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;

	if (kvm_arch_has_private_mem(kvm))
		valid_flags |= KVM_MEM_GUEST_MEMFD;

	/* Dirty logging private memory is not currently supported. */
	if (mem->flags & KVM_MEM_GUEST_MEMFD)
		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;

#ifdef __KVM_HAVE_READONLY_MEM
	valid_flags |= KVM_MEM_READONLY;
#endif

	if (mem->flags & ~valid_flags)
		return -EINVAL;

	return 0;
}

static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
{
	struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);

	/* Grab the generation from the activate memslots. */
	u64 gen = __kvm_memslots(kvm, as_id)->generation;

	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
	slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;

	/*
	 * Do not store the new memslots while there are invalidations in
	 * progress, otherwise the locking in invalidate_range_start and
	 * invalidate_range_end will be unbalanced.
	 */
	spin_lock(&kvm->mn_invalidate_lock);
	prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait);
	while (kvm->mn_active_invalidate_count) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		spin_unlock(&kvm->mn_invalidate_lock);
		schedule();
		spin_lock(&kvm->mn_invalidate_lock);
	}
	finish_rcuwait(&kvm->mn_memslots_update_rcuwait);
	rcu_assign_pointer(kvm->memslots[as_id], slots);
	spin_unlock(&kvm->mn_invalidate_lock);

	/*
	 * Acquired in kvm_set_memslot. Must be released before synchronize
	 * SRCU below in order to avoid deadlock with another thread
	 * acquiring the slots_arch_lock in an srcu critical section.
	 */
	mutex_unlock(&kvm->slots_arch_lock);

	synchronize_srcu_expedited(&kvm->srcu);

	/*
	 * Increment the new memslot generation a second time, dropping the
	 * update in-progress flag and incrementing the generation based on
	 * the number of address spaces.  This provides a unique and easily
	 * identifiable generation number while the memslots are in flux.
	 */
	gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;

	/*
	 * Generations must be unique even across address spaces.  We do not need
	 * a global counter for that, instead the generation space is evenly split
	 * across address spaces.  For example, with two address spaces, address
	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
	 * use generations 1, 3, 5, ...
	 */
	gen += kvm_arch_nr_memslot_as_ids(kvm);

	kvm_arch_memslots_updated(kvm, gen);

	slots->generation = gen;
}

static int kvm_prepare_memory_region(struct kvm *kvm,
				     const struct kvm_memory_slot *old,
				     struct kvm_memory_slot *new,
				     enum kvm_mr_change change)
{
	int r;

	/*
	 * If dirty logging is disabled, nullify the bitmap; the old bitmap
	 * will be freed on "commit".  If logging is enabled in both old and
	 * new, reuse the existing bitmap.  If logging is enabled only in the
	 * new and KVM isn't using a ring buffer, allocate and initialize a
	 * new bitmap.
	 */
	if (change != KVM_MR_DELETE) {
		if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
			new->dirty_bitmap = NULL;
		else if (old && old->dirty_bitmap)
			new->dirty_bitmap = old->dirty_bitmap;
		else if (kvm_use_dirty_bitmap(kvm)) {
			r = kvm_alloc_dirty_bitmap(new);
			if (r)
				return r;

			if (kvm_dirty_log_manual_protect_and_init_set(kvm))
				bitmap_set(new->dirty_bitmap, 0, new->npages);
		}
	}

	r = kvm_arch_prepare_memory_region(kvm, old, new, change);

	/* Free the bitmap on failure if it was allocated above. */
	if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
		kvm_destroy_dirty_bitmap(new);

	return r;
}

static void kvm_commit_memory_region(struct kvm *kvm,
				     struct kvm_memory_slot *old,
				     const struct kvm_memory_slot *new,
				     enum kvm_mr_change change)
{
	int old_flags = old ? old->flags : 0;
	int new_flags = new ? new->flags : 0;
	/*
	 * Update the total number of memslot pages before calling the arch
	 * hook so that architectures can consume the result directly.
	 */
	if (change == KVM_MR_DELETE)
		kvm->nr_memslot_pages -= old->npages;
	else if (change == KVM_MR_CREATE)
		kvm->nr_memslot_pages += new->npages;

	if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) {
		int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1;
		atomic_set(&kvm->nr_memslots_dirty_logging,
			   atomic_read(&kvm->nr_memslots_dirty_logging) + change);
	}

	kvm_arch_commit_memory_region(kvm, old, new, change);

	switch (change) {
	case KVM_MR_CREATE:
		/* Nothing more to do. */
		break;
	case KVM_MR_DELETE:
		/* Free the old memslot and all its metadata. */
		kvm_free_memslot(kvm, old);
		break;
	case KVM_MR_MOVE:
	case KVM_MR_FLAGS_ONLY:
		/*
		 * Free the dirty bitmap as needed; the below check encompasses
		 * both the flags and whether a ring buffer is being used)
		 */
		if (old->dirty_bitmap && !new->dirty_bitmap)
			kvm_destroy_dirty_bitmap(old);

		/*
		 * The final quirk.  Free the detached, old slot, but only its
		 * memory, not any metadata.  Metadata, including arch specific
		 * data, may be reused by @new.
		 */
		kfree(old);
		break;
	default:
		BUG();
	}
}

/*
 * Activate @new, which must be installed in the inactive slots by the caller,
 * by swapping the active slots and then propagating @new to @old once @old is
 * unreachable and can be safely modified.
 *
 * With NULL @old this simply adds @new to @active (while swapping the sets).
 * With NULL @new this simply removes @old from @active and frees it
 * (while also swapping the sets).
 */
static void kvm_activate_memslot(struct kvm *kvm,
				 struct kvm_memory_slot *old,
				 struct kvm_memory_slot *new)
{
	int as_id = kvm_memslots_get_as_id(old, new);

	kvm_swap_active_memslots(kvm, as_id);

	/* Propagate the new memslot to the now inactive memslots. */
	kvm_replace_memslot(kvm, old, new);
}

static void kvm_copy_memslot(struct kvm_memory_slot *dest,
			     const struct kvm_memory_slot *src)
{
	dest->base_gfn = src->base_gfn;
	dest->npages = src->npages;
	dest->dirty_bitmap = src->dirty_bitmap;
	dest->arch = src->arch;
	dest->userspace_addr = src->userspace_addr;
	dest->flags = src->flags;
	dest->id = src->id;
	dest->as_id = src->as_id;
}

static void kvm_invalidate_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *old,
				   struct kvm_memory_slot *invalid_slot)
{
	/*
	 * Mark the current slot INVALID.  As with all memslot modifications,
	 * this must be done on an unreachable slot to avoid modifying the
	 * current slot in the active tree.
	 */
	kvm_copy_memslot(invalid_slot, old);
	invalid_slot->flags |= KVM_MEMSLOT_INVALID;
	kvm_replace_memslot(kvm, old, invalid_slot);

	/*
	 * Activate the slot that is now marked INVALID, but don't propagate
	 * the slot to the now inactive slots. The slot is either going to be
	 * deleted or recreated as a new slot.
	 */
	kvm_swap_active_memslots(kvm, old->as_id);

	/*
	 * From this point no new shadow pages pointing to a deleted, or moved,
	 * memslot will be created.  Validation of sp->gfn happens in:
	 *	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
	 *	- kvm_is_visible_gfn (mmu_check_root)
	 */
	kvm_arch_flush_shadow_memslot(kvm, old);
	kvm_arch_guest_memory_reclaimed(kvm);

	/* Was released by kvm_swap_active_memslots(), reacquire. */
	mutex_lock(&kvm->slots_arch_lock);

	/*
	 * Copy the arch-specific field of the newly-installed slot back to the
	 * old slot as the arch data could have changed between releasing
	 * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock
	 * above.  Writers are required to retrieve memslots *after* acquiring
	 * slots_arch_lock, thus the active slot's data is guaranteed to be fresh.
	 */
	old->arch = invalid_slot->arch;
}

static void kvm_create_memslot(struct kvm *kvm,
			       struct kvm_memory_slot *new)
{
	/* Add the new memslot to the inactive set and activate. */
	kvm_replace_memslot(kvm, NULL, new);
	kvm_activate_memslot(kvm, NULL, new);
}

static void kvm_delete_memslot(struct kvm *kvm,
			       struct kvm_memory_slot *old,
			       struct kvm_memory_slot *invalid_slot)
{
	/*
	 * Remove the old memslot (in the inactive memslots) by passing NULL as
	 * the "new" slot, and for the invalid version in the active slots.
	 */
	kvm_replace_memslot(kvm, old, NULL);
	kvm_activate_memslot(kvm, invalid_slot, NULL);
}

static void kvm_move_memslot(struct kvm *kvm,
			     struct kvm_memory_slot *old,
			     struct kvm_memory_slot *new,
			     struct kvm_memory_slot *invalid_slot)
{
	/*
	 * Replace the old memslot in the inactive slots, and then swap slots
	 * and replace the current INVALID with the new as well.
	 */
	kvm_replace_memslot(kvm, old, new);
	kvm_activate_memslot(kvm, invalid_slot, new);
}

static void kvm_update_flags_memslot(struct kvm *kvm,
				     struct kvm_memory_slot *old,
				     struct kvm_memory_slot *new)
{
	/*
	 * Similar to the MOVE case, but the slot doesn't need to be zapped as
	 * an intermediate step. Instead, the old memslot is simply replaced
	 * with a new, updated copy in both memslot sets.
	 */
	kvm_replace_memslot(kvm, old, new);
	kvm_activate_memslot(kvm, old, new);
}

static int kvm_set_memslot(struct kvm *kvm,
			   struct kvm_memory_slot *old,
			   struct kvm_memory_slot *new,
			   enum kvm_mr_change change)
{
	struct kvm_memory_slot *invalid_slot;
	int r;

	/*
	 * Released in kvm_swap_active_memslots().
	 *
	 * Must be held from before the current memslots are copied until after
	 * the new memslots are installed with rcu_assign_pointer, then
	 * released before the synchronize srcu in kvm_swap_active_memslots().
	 *
	 * When modifying memslots outside of the slots_lock, must be held
	 * before reading the pointer to the current memslots until after all
	 * changes to those memslots are complete.
	 *
	 * These rules ensure that installing new memslots does not lose
	 * changes made to the previous memslots.
	 */
	mutex_lock(&kvm->slots_arch_lock);

	/*
	 * Invalidate the old slot if it's being deleted or moved.  This is
	 * done prior to actually deleting/moving the memslot to allow vCPUs to
	 * continue running by ensuring there are no mappings or shadow pages
	 * for the memslot when it is deleted/moved.  Without pre-invalidation
	 * (and without a lock), a window would exist between effecting the
	 * delete/move and committing the changes in arch code where KVM or a
	 * guest could access a non-existent memslot.
	 *
	 * Modifications are done on a temporary, unreachable slot.  The old
	 * slot needs to be preserved in case a later step fails and the
	 * invalidation needs to be reverted.
	 */
	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
		invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT);
		if (!invalid_slot) {
			mutex_unlock(&kvm->slots_arch_lock);
			return -ENOMEM;
		}
		kvm_invalidate_memslot(kvm, old, invalid_slot);
	}

	r = kvm_prepare_memory_region(kvm, old, new, change);
	if (r) {
		/*
		 * For DELETE/MOVE, revert the above INVALID change.  No
		 * modifications required since the original slot was preserved
		 * in the inactive slots.  Changing the active memslots also
		 * release slots_arch_lock.
		 */
		if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
			kvm_activate_memslot(kvm, invalid_slot, old);
			kfree(invalid_slot);
		} else {
			mutex_unlock(&kvm->slots_arch_lock);
		}
		return r;
	}

	/*
	 * For DELETE and MOVE, the working slot is now active as the INVALID
	 * version of the old slot.  MOVE is particularly special as it reuses
	 * the old slot and returns a copy of the old slot (in working_slot).
	 * For CREATE, there is no old slot.  For DELETE and FLAGS_ONLY, the
	 * old slot is detached but otherwise preserved.
	 */
	if (change == KVM_MR_CREATE)
		kvm_create_memslot(kvm, new);
	else if (change == KVM_MR_DELETE)
		kvm_delete_memslot(kvm, old, invalid_slot);
	else if (change == KVM_MR_MOVE)
		kvm_move_memslot(kvm, old, new, invalid_slot);
	else if (change == KVM_MR_FLAGS_ONLY)
		kvm_update_flags_memslot(kvm, old, new);
	else
		BUG();

	/* Free the temporary INVALID slot used for DELETE and MOVE. */
	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
		kfree(invalid_slot);

	/*
	 * No need to refresh new->arch, changes after dropping slots_arch_lock
	 * will directly hit the final, active memslot.  Architectures are
	 * responsible for knowing that new->arch may be stale.
	 */
	kvm_commit_memory_region(kvm, old, new, change);

	return 0;
}

static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
				      gfn_t start, gfn_t end)
{
	struct kvm_memslot_iter iter;

	kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) {
		if (iter.slot->id != id)
			return true;
	}

	return false;
}

/*
 * Allocate some memory and give it an address in the guest physical address
 * space.
 *
 * Discontiguous memory is allowed, mostly for framebuffers.
 *
 * Must be called holding kvm->slots_lock for write.
 */
int __kvm_set_memory_region(struct kvm *kvm,
			    const struct kvm_userspace_memory_region2 *mem)
{
	struct kvm_memory_slot *old, *new;
	struct kvm_memslots *slots;
	enum kvm_mr_change change;
	unsigned long npages;
	gfn_t base_gfn;
	int as_id, id;
	int r;

	r = check_memory_region_flags(kvm, mem);
	if (r)
		return r;

	as_id = mem->slot >> 16;
	id = (u16)mem->slot;

	/* General sanity checks */
	if ((mem->memory_size & (PAGE_SIZE - 1)) ||
	    (mem->memory_size != (unsigned long)mem->memory_size))
		return -EINVAL;
	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
		return -EINVAL;
	/* We can read the guest memory with __xxx_user() later on. */
	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
			mem->memory_size))
		return -EINVAL;
	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
		return -EINVAL;
	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
		return -EINVAL;
	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
		return -EINVAL;
	if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
		return -EINVAL;

	slots = __kvm_memslots(kvm, as_id);

	/*
	 * Note, the old memslot (and the pointer itself!) may be invalidated
	 * and/or destroyed by kvm_set_memslot().
	 */
	old = id_to_memslot(slots, id);

	if (!mem->memory_size) {
		if (!old || !old->npages)
			return -EINVAL;

		if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages))
			return -EIO;

		return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE);
	}

	base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT);
	npages = (mem->memory_size >> PAGE_SHIFT);

	if (!old || !old->npages) {
		change = KVM_MR_CREATE;

		/*
		 * To simplify KVM internals, the total number of pages across
		 * all memslots must fit in an unsigned long.
		 */
		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
			return -EINVAL;
	} else { /* Modify an existing slot. */
		/* Private memslots are immutable, they can only be deleted. */
		if (mem->flags & KVM_MEM_GUEST_MEMFD)
			return -EINVAL;
		if ((mem->userspace_addr != old->userspace_addr) ||
		    (npages != old->npages) ||
		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
			return -EINVAL;

		if (base_gfn != old->base_gfn)
			change = KVM_MR_MOVE;
		else if (mem->flags != old->flags)
			change = KVM_MR_FLAGS_ONLY;
		else /* Nothing to change. */
			return 0;
	}

	if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) &&
	    kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages))
		return -EEXIST;

	/* Allocate a slot that will persist in the memslot. */
	new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT);
	if (!new)
		return -ENOMEM;

	new->as_id = as_id;
	new->id = id;
	new->base_gfn = base_gfn;
	new->npages = npages;
	new->flags = mem->flags;
	new->userspace_addr = mem->userspace_addr;
	if (mem->flags & KVM_MEM_GUEST_MEMFD) {
		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
		if (r)
			goto out;
	}

	r = kvm_set_memslot(kvm, old, new, change);
	if (r)
		goto out_unbind;

	return 0;

out_unbind:
	if (mem->flags & KVM_MEM_GUEST_MEMFD)
		kvm_gmem_unbind(new);
out:
	kfree(new);
	return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);

int kvm_set_memory_region(struct kvm *kvm,
			  const struct kvm_userspace_memory_region2 *mem)
{
	int r;

	mutex_lock(&kvm->slots_lock);
	r = __kvm_set_memory_region(kvm, mem);
	mutex_unlock(&kvm->slots_lock);
	return r;
}
EXPORT_SYMBOL_GPL(kvm_set_memory_region);

static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
					  struct kvm_userspace_memory_region2 *mem)
{
	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
		return -EINVAL;

	return kvm_set_memory_region(kvm, mem);
}

#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
/**
 * kvm_get_dirty_log - get a snapshot of dirty pages
 * @kvm:	pointer to kvm instance
 * @log:	slot id and address to which we copy the log
 * @is_dirty:	set to '1' if any dirty pages were found
 * @memslot:	set to the associated memslot, always valid on success
 */
int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
		      int *is_dirty, struct kvm_memory_slot **memslot)
{
	struct kvm_memslots *slots;
	int i, as_id, id;
	unsigned long n;
	unsigned long any = 0;

	/* Dirty ring tracking may be exclusive to dirty log tracking */
	if (!kvm_use_dirty_bitmap(kvm))
		return -ENXIO;

	*memslot = NULL;
	*is_dirty = 0;

	as_id = log->slot >> 16;
	id = (u16)log->slot;
	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
		return -EINVAL;

	slots = __kvm_memslots(kvm, as_id);
	*memslot = id_to_memslot(slots, id);
	if (!(*memslot) || !(*memslot)->dirty_bitmap)
		return -ENOENT;

	kvm_arch_sync_dirty_log(kvm, *memslot);

	n = kvm_dirty_bitmap_bytes(*memslot);

	for (i = 0; !any && i < n/sizeof(long); ++i)
		any = (*memslot)->dirty_bitmap[i];

	if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n))
		return -EFAULT;

	if (any)
		*is_dirty = 1;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dirty_log);

#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
/**
 * kvm_get_dirty_log_protect - get a snapshot of dirty pages
 *	and reenable dirty page tracking for the corresponding pages.
 * @kvm:	pointer to kvm instance
 * @log:	slot id and address to which we copy the log
 *
 * We need to keep it in mind that VCPU threads can write to the bitmap
 * concurrently. So, to avoid losing track of dirty pages we keep the
 * following order:
 *
 *    1. Take a snapshot of the bit and clear it if needed.
 *    2. Write protect the corresponding page.
 *    3. Copy the snapshot to the userspace.
 *    4. Upon return caller flushes TLB's if needed.
 *
 * Between 2 and 4, the guest may write to the page using the remaining TLB
 * entry.  This is not a problem because the page is reported dirty using
 * the snapshot taken before and step 4 ensures that writes done after
 * exiting to userspace will be logged for the next call.
 *
 */
static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int i, as_id, id;
	unsigned long n;
	unsigned long *dirty_bitmap;
	unsigned long *dirty_bitmap_buffer;
	bool flush;

	/* Dirty ring tracking may be exclusive to dirty log tracking */
	if (!kvm_use_dirty_bitmap(kvm))
		return -ENXIO;

	as_id = log->slot >> 16;
	id = (u16)log->slot;
	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
		return -EINVAL;

	slots = __kvm_memslots(kvm, as_id);
	memslot = id_to_memslot(slots, id);
	if (!memslot || !memslot->dirty_bitmap)
		return -ENOENT;

	dirty_bitmap = memslot->dirty_bitmap;

	kvm_arch_sync_dirty_log(kvm, memslot);

	n = kvm_dirty_bitmap_bytes(memslot);
	flush = false;
	if (kvm->manual_dirty_log_protect) {
		/*
		 * Unlike kvm_get_dirty_log, we always return false in *flush,
		 * because no flush is needed until KVM_CLEAR_DIRTY_LOG.  There
		 * is some code duplication between this function and
		 * kvm_get_dirty_log, but hopefully all architecture
		 * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log
		 * can be eliminated.
		 */
		dirty_bitmap_buffer = dirty_bitmap;
	} else {
		dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
		memset(dirty_bitmap_buffer, 0, n);

		KVM_MMU_LOCK(kvm);
		for (i = 0; i < n / sizeof(long); i++) {
			unsigned long mask;
			gfn_t offset;

			if (!dirty_bitmap[i])
				continue;

			flush = true;
			mask = xchg(&dirty_bitmap[i], 0);
			dirty_bitmap_buffer[i] = mask;

			offset = i * BITS_PER_LONG;
			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
								offset, mask);
		}
		KVM_MMU_UNLOCK(kvm);
	}

	if (flush)
		kvm_flush_remote_tlbs_memslot(kvm, memslot);

	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
		return -EFAULT;
	return 0;
}


/**
 * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
 * @kvm: kvm instance
 * @log: slot id and address to which we copy the log
 *
 * Steps 1-4 below provide general overview of dirty page logging. See
 * kvm_get_dirty_log_protect() function description for additional details.
 *
 * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
 * always flush the TLB (step 4) even if previous step failed  and the dirty
 * bitmap may be corrupt. Regardless of previous outcome the KVM logging API
 * does not preclude user space subsequent dirty log read. Flushing TLB ensures
 * writes will be marked dirty for next log read.
 *
 *   1. Take a snapshot of the bit and clear it if needed.
 *   2. Write protect the corresponding page.
 *   3. Copy the snapshot to the userspace.
 *   4. Flush TLB's if needed.
 */
static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				      struct kvm_dirty_log *log)
{
	int r;

	mutex_lock(&kvm->slots_lock);

	r = kvm_get_dirty_log_protect(kvm, log);

	mutex_unlock(&kvm->slots_lock);
	return r;
}

/**
 * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap
 *	and reenable dirty page tracking for the corresponding pages.
 * @kvm:	pointer to kvm instance
 * @log:	slot id and address from which to fetch the bitmap of dirty pages
 */
static int kvm_clear_dirty_log_protect(struct kvm *kvm,
				       struct kvm_clear_dirty_log *log)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int as_id, id;
	gfn_t offset;
	unsigned long i, n;
	unsigned long *dirty_bitmap;
	unsigned long *dirty_bitmap_buffer;
	bool flush;

	/* Dirty ring tracking may be exclusive to dirty log tracking */
	if (!kvm_use_dirty_bitmap(kvm))
		return -ENXIO;

	as_id = log->slot >> 16;
	id = (u16)log->slot;
	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
		return -EINVAL;

	if (log->first_page & 63)
		return -EINVAL;

	slots = __kvm_memslots(kvm, as_id);
	memslot = id_to_memslot(slots, id);
	if (!memslot || !memslot->dirty_bitmap)
		return -ENOENT;

	dirty_bitmap = memslot->dirty_bitmap;

	n = ALIGN(log->num_pages, BITS_PER_LONG) / 8;

	if (log->first_page > memslot->npages ||
	    log->num_pages > memslot->npages - log->first_page ||
	    (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
	    return -EINVAL;

	kvm_arch_sync_dirty_log(kvm, memslot);

	flush = false;
	dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
	if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
		return -EFAULT;

	KVM_MMU_LOCK(kvm);
	for (offset = log->first_page, i = offset / BITS_PER_LONG,
		 n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
	     i++, offset += BITS_PER_LONG) {
		unsigned long mask = *dirty_bitmap_buffer++;
		atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
		if (!mask)
			continue;

		mask &= atomic_long_fetch_andnot(mask, p);

		/*
		 * mask contains the bits that really have been cleared.  This
		 * never includes any bits beyond the length of the memslot (if
		 * the length is not aligned to 64 pages), therefore it is not
		 * a problem if userspace sets them in log->dirty_bitmap.
		*/
		if (mask) {
			flush = true;
			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
								offset, mask);
		}
	}
	KVM_MMU_UNLOCK(kvm);

	if (flush)
		kvm_flush_remote_tlbs_memslot(kvm, memslot);

	return 0;
}

static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
					struct kvm_clear_dirty_log *log)
{
	int r;

	mutex_lock(&kvm->slots_lock);

	r = kvm_clear_dirty_log_protect(kvm, log);

	mutex_unlock(&kvm->slots_lock);
	return r;
}
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */

#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
/*
 * Returns true if _all_ gfns in the range [@start, @end) have attributes
 * matching @attrs.
 */
bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
				     unsigned long attrs)
{
	XA_STATE(xas, &kvm->mem_attr_array, start);
	unsigned long index;
	bool has_attrs;
	void *entry;

	rcu_read_lock();

	if (!attrs) {
		has_attrs = !xas_find(&xas, end - 1);
		goto out;
	}

	has_attrs = true;
	for (index = start; index < end; index++) {
		do {
			entry = xas_next(&xas);
		} while (xas_retry(&xas, entry));

		if (xas.xa_index != index || xa_to_value(entry) != attrs) {
			has_attrs = false;
			break;
		}
	}

out:
	rcu_read_unlock();
	return has_attrs;
}

static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
	if (!kvm || kvm_arch_has_private_mem(kvm))
		return KVM_MEMORY_ATTRIBUTE_PRIVATE;

	return 0;
}

static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
						 struct kvm_mmu_notifier_range *range)
{
	struct kvm_gfn_range gfn_range;
	struct kvm_memory_slot *slot;
	struct kvm_memslots *slots;
	struct kvm_memslot_iter iter;
	bool found_memslot = false;
	bool ret = false;
	int i;

	gfn_range.arg = range->arg;
	gfn_range.may_block = range->may_block;

	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
		slots = __kvm_memslots(kvm, i);

		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
			slot = iter.slot;
			gfn_range.slot = slot;

			gfn_range.start = max(range->start, slot->base_gfn);
			gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
			if (gfn_range.start >= gfn_range.end)
				continue;

			if (!found_memslot) {
				found_memslot = true;
				KVM_MMU_LOCK(kvm);
				if (!IS_KVM_NULL_FN(range->on_lock))
					range->on_lock(kvm);
			}

			ret |= range->handler(kvm, &gfn_range);
		}
	}

	if (range->flush_on_ret && ret)
		kvm_flush_remote_tlbs(kvm);

	if (found_memslot)
		KVM_MMU_UNLOCK(kvm);
}

static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
					  struct kvm_gfn_range *range)
{
	/*
	 * Unconditionally add the range to the invalidation set, regardless of
	 * whether or not the arch callback actually needs to zap SPTEs.  E.g.
	 * if KVM supports RWX attributes in the future and the attributes are
	 * going from R=>RW, zapping isn't strictly necessary.  Unconditionally
	 * adding the range allows KVM to require that MMU invalidations add at
	 * least one range between begin() and end(), e.g. allows KVM to detect
	 * bugs where the add() is missed.  Relaxing the rule *might* be safe,
	 * but it's not obvious that allowing new mappings while the attributes
	 * are in flux is desirable or worth the complexity.
	 */
	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);

	return kvm_arch_pre_set_memory_attributes(kvm, range);
}

/* Set @attributes for the gfn range [@start, @end). */
static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
				     unsigned long attributes)
{
	struct kvm_mmu_notifier_range pre_set_range = {
		.start = start,
		.end = end,
		.handler = kvm_pre_set_memory_attributes,
		.on_lock = kvm_mmu_invalidate_begin,
		.flush_on_ret = true,
		.may_block = true,
	};
	struct kvm_mmu_notifier_range post_set_range = {
		.start = start,
		.end = end,
		.arg.attributes = attributes,
		.handler = kvm_arch_post_set_memory_attributes,
		.on_lock = kvm_mmu_invalidate_end,
		.may_block = true,
	};
	unsigned long i;
	void *entry;
	int r = 0;

	entry = attributes ? xa_mk_value(attributes) : NULL;

	mutex_lock(&kvm->slots_lock);

	/* Nothing to do if the entire range as the desired attributes. */
	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
		goto out_unlock;

	/*
	 * Reserve memory ahead of time to avoid having to deal with failures
	 * partway through setting the new attributes.
	 */
	for (i = start; i < end; i++) {
		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
		if (r)
			goto out_unlock;
	}

	kvm_handle_gfn_range(kvm, &pre_set_range);

	for (i = start; i < end; i++) {
		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
				    GFP_KERNEL_ACCOUNT));
		KVM_BUG_ON(r, kvm);
	}

	kvm_handle_gfn_range(kvm, &post_set_range);

out_unlock:
	mutex_unlock(&kvm->slots_lock);

	return r;
}
static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
					   struct kvm_memory_attributes *attrs)
{
	gfn_t start, end;

	/* flags is currently not used. */
	if (attrs->flags)
		return -EINVAL;
	if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
		return -EINVAL;
	if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
		return -EINVAL;
	if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
		return -EINVAL;

	start = attrs->address >> PAGE_SHIFT;
	end = (attrs->address + attrs->size) >> PAGE_SHIFT;

	/*
	 * xarray tracks data using "unsigned long", and as a result so does
	 * KVM.  For simplicity, supports generic attributes only on 64-bit
	 * architectures.
	 */
	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));

	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
}
#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */

struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_memslot);

struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
	u64 gen = slots->generation;
	struct kvm_memory_slot *slot;

	/*
	 * This also protects against using a memslot from a different address space,
	 * since different address spaces have different generation numbers.
	 */
	if (unlikely(gen != vcpu->last_used_slot_gen)) {
		vcpu->last_used_slot = NULL;
		vcpu->last_used_slot_gen = gen;
	}

	slot = try_get_memslot(vcpu->last_used_slot, gfn);
	if (slot)
		return slot;

	/*
	 * Fall back to searching all memslots. We purposely use
	 * search_memslots() instead of __gfn_to_memslot() to avoid
	 * thrashing the VM-wide last_used_slot in kvm_memslots.
	 */
	slot = search_memslots(slots, gfn, false);
	if (slot) {
		vcpu->last_used_slot = slot;
		return slot;
	}

	return NULL;
}

bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);

	return kvm_is_visible_memslot(memslot);
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);

bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);

	return kvm_is_visible_memslot(memslot);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn);

unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	struct vm_area_struct *vma;
	unsigned long addr, size;

	size = PAGE_SIZE;

	addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
	if (kvm_is_error_hva(addr))
		return PAGE_SIZE;

	mmap_read_lock(current->mm);
	vma = find_vma(current->mm, addr);
	if (!vma)
		goto out;

	size = vma_kernel_pagesize(vma);

out:
	mmap_read_unlock(current->mm);

	return size;
}

static bool memslot_is_readonly(const struct kvm_memory_slot *slot)
{
	return slot->flags & KVM_MEM_READONLY;
}

static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn,
				       gfn_t *nr_pages, bool write)
{
	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
		return KVM_HVA_ERR_BAD;

	if (memslot_is_readonly(slot) && write)
		return KVM_HVA_ERR_RO_BAD;

	if (nr_pages)
		*nr_pages = slot->npages - (gfn - slot->base_gfn);

	return __gfn_to_hva_memslot(slot, gfn);
}

static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
				     gfn_t *nr_pages)
{
	return __gfn_to_hva_many(slot, gfn, nr_pages, true);
}

unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
					gfn_t gfn)
{
	return gfn_to_hva_many(slot, gfn, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);

unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
{
	return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_hva);

unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva);

/*
 * Return the hva of a @gfn and the R/W attribute if possible.
 *
 * @slot: the kvm_memory_slot which contains @gfn
 * @gfn: the gfn to be translated
 * @writable: used to return the read/write attribute of the @slot if the hva
 * is valid and @writable is not NULL
 */
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
				      gfn_t gfn, bool *writable)
{
	unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);

	if (!kvm_is_error_hva(hva) && writable)
		*writable = !memslot_is_readonly(slot);

	return hva;
}

unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
{
	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);

	return gfn_to_hva_memslot_prot(slot, gfn, writable);
}

unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable)
{
	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);

	return gfn_to_hva_memslot_prot(slot, gfn, writable);
}

static inline int check_user_page_hwpoison(unsigned long addr)
{
	int rc, flags = FOLL_HWPOISON | FOLL_WRITE;

	rc = get_user_pages(addr, 1, flags, NULL);
	return rc == -EHWPOISON;
}

/*
 * The fast path to get the writable pfn which will be stored in @pfn,
 * true indicates success, otherwise false is returned.  It's also the
 * only part that runs if we can in atomic context.
 */
static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
			    bool *writable, kvm_pfn_t *pfn)
{
	struct page *page[1];

	/*
	 * Fast pin a writable pfn only if it is a write fault request
	 * or the caller allows to map a writable pfn for a read fault
	 * request.
	 */
	if (!(write_fault || writable))
		return false;

	if (get_user_page_fast_only(addr, FOLL_WRITE, page)) {
		*pfn = page_to_pfn(page[0]);

		if (writable)
			*writable = true;
		return true;
	}

	return false;
}

/*
 * The slow path to get the pfn of the specified host virtual address,
 * 1 indicates success, -errno is returned if error is detected.
 */
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
			   bool interruptible, bool *writable, kvm_pfn_t *pfn)
{
	/*
	 * When a VCPU accesses a page that is not mapped into the secondary
	 * MMU, we lookup the page using GUP to map it, so the guest VCPU can
	 * make progress. We always want to honor NUMA hinting faults in that
	 * case, because GUP usage corresponds to memory accesses from the VCPU.
	 * Otherwise, we'd not trigger NUMA hinting faults once a page is
	 * mapped into the secondary MMU and gets accessed by a VCPU.
	 *
	 * Note that get_user_page_fast_only() and FOLL_WRITE for now
	 * implicitly honor NUMA hinting faults and don't need this flag.
	 */
	unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT;
	struct page *page;
	int npages;

	might_sleep();

	if (writable)
		*writable = write_fault;

	if (write_fault)
		flags |= FOLL_WRITE;
	if (async)
		flags |= FOLL_NOWAIT;
	if (interruptible)
		flags |= FOLL_INTERRUPTIBLE;

	npages = get_user_pages_unlocked(addr, 1, &page, flags);
	if (npages != 1)
		return npages;

	/* map read fault as writable if possible */
	if (unlikely(!write_fault) && writable) {
		struct page *wpage;

		if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) {
			*writable = true;
			put_page(page);
			page = wpage;
		}
	}
	*pfn = page_to_pfn(page);
	return npages;
}

static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
{
	if (unlikely(!(vma->vm_flags & VM_READ)))
		return false;

	if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE))))
		return false;

	return true;
}

static int kvm_try_get_pfn(kvm_pfn_t pfn)
{
	struct page *page = kvm_pfn_to_refcounted_page(pfn);

	if (!page)
		return 1;

	return get_page_unless_zero(page);
}

static int hva_to_pfn_remapped(struct vm_area_struct *vma,
			       unsigned long addr, bool write_fault,
			       bool *writable, kvm_pfn_t *p_pfn)
{
	kvm_pfn_t pfn;
	pte_t *ptep;
	pte_t pte;
	spinlock_t *ptl;
	int r;

	r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
	if (r) {
		/*
		 * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
		 * not call the fault handler, so do it here.
		 */
		bool unlocked = false;
		r = fixup_user_fault(current->mm, addr,
				     (write_fault ? FAULT_FLAG_WRITE : 0),
				     &unlocked);
		if (unlocked)
			return -EAGAIN;
		if (r)
			return r;

		r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
		if (r)
			return r;
	}

	pte = ptep_get(ptep);

	if (write_fault && !pte_write(pte)) {
		pfn = KVM_PFN_ERR_RO_FAULT;
		goto out;
	}

	if (writable)
		*writable = pte_write(pte);
	pfn = pte_pfn(pte);

	/*
	 * Get a reference here because callers of *hva_to_pfn* and
	 * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
	 * returned pfn.  This is only needed if the VMA has VM_MIXEDMAP
	 * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will
	 * simply do nothing for reserved pfns.
	 *
	 * Whoever called remap_pfn_range is also going to call e.g.
	 * unmap_mapping_range before the underlying pages are freed,
	 * causing a call to our MMU notifier.
	 *
	 * Certain IO or PFNMAP mappings can be backed with valid
	 * struct pages, but be allocated without refcounting e.g.,
	 * tail pages of non-compound higher order allocations, which
	 * would then underflow the refcount when the caller does the
	 * required put_page. Don't allow those pages here.
	 */
	if (!kvm_try_get_pfn(pfn))
		r = -EFAULT;

out:
	pte_unmap_unlock(ptep, ptl);
	*p_pfn = pfn;

	return r;
}

/*
 * Pin guest page in memory and return its pfn.
 * @addr: host virtual address which maps memory to the guest
 * @atomic: whether this function can sleep
 * @interruptible: whether the process can be interrupted by non-fatal signals
 * @async: whether this function need to wait IO complete if the
 *         host page is not in the memory
 * @write_fault: whether we should get a writable host page
 * @writable: whether it allows to map a writable host page for !@write_fault
 *
 * The function will map a writable host page for these two cases:
 * 1): @write_fault = true
 * 2): @write_fault = false && @writable, @writable will tell the caller
 *     whether the mapping is writable.
 */
kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
		     bool *async, bool write_fault, bool *writable)
{
	struct vm_area_struct *vma;
	kvm_pfn_t pfn;
	int npages, r;

	/* we can do it either atomically or asynchronously, not both */
	BUG_ON(atomic && async);

	if (hva_to_pfn_fast(addr, write_fault, writable, &pfn))
		return pfn;

	if (atomic)
		return KVM_PFN_ERR_FAULT;

	npages = hva_to_pfn_slow(addr, async, write_fault, interruptible,
				 writable, &pfn);
	if (npages == 1)
		return pfn;
	if (npages == -EINTR)
		return KVM_PFN_ERR_SIGPENDING;

	mmap_read_lock(current->mm);
	if (npages == -EHWPOISON ||
	      (!async && check_user_page_hwpoison(addr))) {
		pfn = KVM_PFN_ERR_HWPOISON;
		goto exit;
	}

retry:
	vma = vma_lookup(current->mm, addr);

	if (vma == NULL)
		pfn = KVM_PFN_ERR_FAULT;
	else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
		r = hva_to_pfn_remapped(vma, addr, write_fault, writable, &pfn);
		if (r == -EAGAIN)
			goto retry;
		if (r < 0)
			pfn = KVM_PFN_ERR_FAULT;
	} else {
		if (async && vma_is_valid(vma, write_fault))
			*async = true;
		pfn = KVM_PFN_ERR_FAULT;
	}
exit:
	mmap_read_unlock(current->mm);
	return pfn;
}

kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
			       bool atomic, bool interruptible, bool *async,
			       bool write_fault, bool *writable, hva_t *hva)
{
	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);

	if (hva)
		*hva = addr;

	if (addr == KVM_HVA_ERR_RO_BAD) {
		if (writable)
			*writable = false;
		return KVM_PFN_ERR_RO_FAULT;
	}

	if (kvm_is_error_hva(addr)) {
		if (writable)
			*writable = false;
		return KVM_PFN_NOSLOT;
	}

	/* Do not map writable pfn in the readonly memslot. */
	if (writable && memslot_is_readonly(slot)) {
		*writable = false;
		writable = NULL;
	}

	return hva_to_pfn(addr, atomic, interruptible, async, write_fault,
			  writable);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);

kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
		      bool *writable)
{
	return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false,
				    NULL, write_fault, writable, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);

kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
	return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true,
				    NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);

kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn)
{
	return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true,
				    NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);

kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);

kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
{
	return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn);

kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn);

int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
			    struct page **pages, int nr_pages)
{
	unsigned long addr;
	gfn_t entry = 0;

	addr = gfn_to_hva_many(slot, gfn, &entry);
	if (kvm_is_error_hva(addr))
		return -1;

	if (entry < nr_pages)
		return 0;

	return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages);
}
EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);

/*
 * Do not use this helper unless you are absolutely certain the gfn _must_ be
 * backed by 'struct page'.  A valid example is if the backing memslot is
 * controlled by KVM.  Note, if the returned page is valid, it's refcount has
 * been elevated by gfn_to_pfn().
 */
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
	struct page *page;
	kvm_pfn_t pfn;

	pfn = gfn_to_pfn(kvm, gfn);

	if (is_error_noslot_pfn(pfn))
		return KVM_ERR_PTR_BAD_PAGE;

	page = kvm_pfn_to_refcounted_page(pfn);
	if (!page)
		return KVM_ERR_PTR_BAD_PAGE;

	return page;
}
EXPORT_SYMBOL_GPL(gfn_to_page);

void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
{
	if (dirty)
		kvm_release_pfn_dirty(pfn);
	else
		kvm_release_pfn_clean(pfn);
}

int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
{
	kvm_pfn_t pfn;
	void *hva = NULL;
	struct page *page = KVM_UNMAPPED_PAGE;

	if (!map)
		return -EINVAL;

	pfn = gfn_to_pfn(vcpu->kvm, gfn);
	if (is_error_noslot_pfn(pfn))
		return -EINVAL;

	if (pfn_valid(pfn)) {
		page = pfn_to_page(pfn);
		hva = kmap(page);
#ifdef CONFIG_HAS_IOMEM
	} else {
		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
#endif
	}

	if (!hva)
		return -EFAULT;

	map->page = page;
	map->hva = hva;
	map->pfn = pfn;
	map->gfn = gfn;

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_map);

void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
{
	if (!map)
		return;

	if (!map->hva)
		return;

	if (map->page != KVM_UNMAPPED_PAGE)
		kunmap(map->page);
#ifdef CONFIG_HAS_IOMEM
	else
		memunmap(map->hva);
#endif

	if (dirty)
		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);

	kvm_release_pfn(map->pfn, dirty);

	map->hva = NULL;
	map->page = NULL;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);

static bool kvm_is_ad_tracked_page(struct page *page)
{
	/*
	 * Per page-flags.h, pages tagged PG_reserved "should in general not be
	 * touched (e.g. set dirty) except by its owner".
	 */
	return !PageReserved(page);
}

static void kvm_set_page_dirty(struct page *page)
{
	if (kvm_is_ad_tracked_page(