/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * MMU support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "irq.h"
#include "mmu.h"
#include "x86.h"
#include "kvm_cache_regs.h"
#include "cpuid.h"

#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/uaccess.h>

#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
#include <asm/kvm_page_track.h>

/*
 * When setting this variable to true it enables Two-Dimensional-Paging
 * where the hardware walks 2 page tables:
 * 1. the guest-virtual to guest-physical
 * 2. while doing 1. it walks guest-physical to host-physical
 * If the hardware supports that we don't need to do shadow paging.
 */
bool tdp_enabled = false;

enum {
        AUDIT_PRE_PAGE_FAULT,
        AUDIT_POST_PAGE_FAULT,
        AUDIT_PRE_PTE_WRITE,
        AUDIT_POST_PTE_WRITE,
        AUDIT_PRE_SYNC,
        AUDIT_POST_SYNC
};

#undef MMU_DEBUG

#ifdef MMU_DEBUG
static bool dbg = 0;
module_param(dbg, bool, 0644);

#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
#define rmap_printk(x...) do { if (dbg) printk(x); } while (0)
#define MMU_WARN_ON(x) WARN_ON(x)
#else
#define pgprintk(x...) do { } while (0)
#define rmap_printk(x...) do { } while (0)
#define MMU_WARN_ON(x) do { } while (0)
#endif

#define PTE_PREFETCH_NUM                8

#define PT_FIRST_AVAIL_BITS_SHIFT 10
#define PT64_SECOND_AVAIL_BITS_SHIFT 52

#define PT64_LEVEL_BITS 9

#define PT64_LEVEL_SHIFT(level) \
                (PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS)

#define PT64_INDEX(address, level)\
        (((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1))


#define PT32_LEVEL_BITS 10

#define PT32_LEVEL_SHIFT(level) \
                (PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS)

#define PT32_LVL_OFFSET_MASK(level) \
        (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
                                                * PT32_LEVEL_BITS))) - 1))

#define PT32_INDEX(address, level)\
        (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))


#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#define PT64_DIR_BASE_ADDR_MASK \
        (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
#define PT64_LVL_ADDR_MASK(level) \
        (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
                                                * PT64_LEVEL_BITS))) - 1))
#define PT64_LVL_OFFSET_MASK(level) \
        (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
                                                * PT64_LEVEL_BITS))) - 1))

#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
        (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
#define PT32_LVL_ADDR_MASK(level) \
        (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
                                            * PT32_LEVEL_BITS))) - 1))

#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
                        | shadow_x_mask | shadow_nx_mask)

#define ACC_EXEC_MASK    1
#define ACC_WRITE_MASK   PT_WRITABLE_MASK
#define ACC_USER_MASK    PT_USER_MASK
#define ACC_ALL          (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)

#include <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "mmutrace.h"

#define SPTE_HOST_WRITEABLE     (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define SPTE_MMU_WRITEABLE      (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))

#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)

/* make pte_list_desc fit well in cache line */
#define PTE_LIST_EXT 3

struct pte_list_desc {
        u64 *sptes[PTE_LIST_EXT];
        struct pte_list_desc *more;
};

struct kvm_shadow_walk_iterator {
        u64 addr;
        hpa_t shadow_addr;
        u64 *sptep;
        int level;
        unsigned index;
};

#define for_each_shadow_entry(_vcpu, _addr, _walker)    \
        for (shadow_walk_init(&(_walker), _vcpu, _addr);        \
             shadow_walk_okay(&(_walker));                      \
             shadow_walk_next(&(_walker)))

#define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte)     \
        for (shadow_walk_init(&(_walker), _vcpu, _addr);                \
             shadow_walk_okay(&(_walker)) &&                            \
                ({ spte = mmu_spte_get_lockless(_walker.sptep); 1; });  \
             __shadow_walk_next(&(_walker), spte))

static struct kmem_cache *pte_list_desc_cache;
static struct kmem_cache *mmu_page_header_cache;
static struct percpu_counter kvm_total_used_mmu_pages;

static u64 __read_mostly shadow_nx_mask;
static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
static u64 __read_mostly shadow_user_mask;
static u64 __read_mostly shadow_accessed_mask;
static u64 __read_mostly shadow_dirty_mask;
static u64 __read_mostly shadow_mmio_mask;
static u64 __read_mostly shadow_present_mask;

static void mmu_spte_set(u64 *sptep, u64 spte);
static void mmu_free_roots(struct kvm_vcpu *vcpu);

void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
{
        shadow_mmio_mask = mmio_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);

/*
 * the low bit of the generation number is always presumed to be zero.
 * This disables mmio caching during memslot updates.  The concept is
 * similar to a seqcount but instead of retrying the access we just punt
 * and ignore the cache.
 *
 * spte bits 3-11 are used as bits 1-9 of the generation number,
 * the bits 52-61 are used as bits 10-19 of the generation number.
 */
#define MMIO_SPTE_GEN_LOW_SHIFT         2
#define MMIO_SPTE_GEN_HIGH_SHIFT        52

#define MMIO_GEN_SHIFT                  20
#define MMIO_GEN_LOW_SHIFT              10
#define MMIO_GEN_LOW_MASK               ((1 << MMIO_GEN_LOW_SHIFT) - 2)
#define MMIO_GEN_MASK                   ((1 << MMIO_GEN_SHIFT) - 1)

static u64 generation_mmio_spte_mask(unsigned int gen)
{
        u64 mask;

        WARN_ON(gen & ~MMIO_GEN_MASK);

        mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT;
        mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT;
        return mask;
}

static unsigned int get_mmio_spte_generation(u64 spte)
{
        unsigned int gen;

        spte &= ~shadow_mmio_mask;

        gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK;
        gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT;
        return gen;
}

static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu)
{
        return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK;
}

static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
                           unsigned access)
{
        unsigned int gen = kvm_current_mmio_generation(vcpu);
        u64 mask = generation_mmio_spte_mask(gen);

        access &= ACC_WRITE_MASK | ACC_USER_MASK;
        mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT;

        trace_mark_mmio_spte(sptep, gfn, access, gen);
        mmu_spte_set(sptep, mask);
}

static bool is_mmio_spte(u64 spte)
{
        return (spte & shadow_mmio_mask) == shadow_mmio_mask;
}

static gfn_t get_mmio_spte_gfn(u64 spte)
{
        u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
        return (spte & ~mask) >> PAGE_SHIFT;
}

static unsigned get_mmio_spte_access(u64 spte)
{
        u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
        return (spte & ~mask) & ~PAGE_MASK;
}

static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
                          kvm_pfn_t pfn, unsigned access)
{
        if (unlikely(is_noslot_pfn(pfn))) {
                mark_mmio_spte(vcpu, sptep, gfn, access);
                return true;
        }

        return false;
}

static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
{
        unsigned int kvm_gen, spte_gen;

        kvm_gen = kvm_current_mmio_generation(vcpu);
        spte_gen = get_mmio_spte_generation(spte);

        trace_check_mmio_spte(spte, kvm_gen, spte_gen);
        return likely(kvm_gen == spte_gen);
}

void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
                u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
{
        shadow_user_mask = user_mask;
        shadow_accessed_mask = accessed_mask;
        shadow_dirty_mask = dirty_mask;
        shadow_nx_mask = nx_mask;
        shadow_x_mask = x_mask;
        shadow_present_mask = p_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);

static int is_cpuid_PSE36(void)
{
        return 1;
}

static int is_nx(struct kvm_vcpu *vcpu)
{
        return vcpu->arch.efer & EFER_NX;
}

static int is_shadow_present_pte(u64 pte)
{
        return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte);
}

static int is_large_pte(u64 pte)
{
        return pte & PT_PAGE_SIZE_MASK;
}

static int is_last_spte(u64 pte, int level)
{
        if (level == PT_PAGE_TABLE_LEVEL)
                return 1;
        if (is_large_pte(pte))
                return 1;
        return 0;
}

static kvm_pfn_t spte_to_pfn(u64 pte)
{
        return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
}

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

        return (gpte & PT32_DIR_PSE36_MASK) << shift;
}

#ifdef CONFIG_X86_64
static void __set_spte(u64 *sptep, u64 spte)
{
        WRITE_ONCE(*sptep, spte);
}

static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
        WRITE_ONCE(*sptep, spte);
}

static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
        return xchg(sptep, spte);
}

static u64 __get_spte_lockless(u64 *sptep)
{
        return ACCESS_ONCE(*sptep);
}
#else
union split_spte {
        struct {
                u32 spte_low;
                u32 spte_high;
        };
        u64 spte;
};

static void count_spte_clear(u64 *sptep, u64 spte)
{
        struct kvm_mmu_page *sp =  page_header(__pa(sptep));

        if (is_shadow_present_pte(spte))
                return;

        /* Ensure the spte is completely set before we increase the count */
        smp_wmb();
        sp->clear_spte_count++;
}

static void __set_spte(u64 *sptep, u64 spte)
{
        union split_spte *ssptep, sspte;

        ssptep = (union split_spte *)sptep;
        sspte = (union split_spte)spte;

        ssptep->spte_high = sspte.spte_high;

        /*
         * If we map the spte from nonpresent to present, We should store
         * the high bits firstly, then set present bit, so cpu can not
         * fetch this spte while we are setting the spte.
         */
        smp_wmb();

        WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
}

static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
        union split_spte *ssptep, sspte;

        ssptep = (union split_spte *)sptep;
        sspte = (union split_spte)spte;

        WRITE_ONCE(ssptep->spte_low, sspte.spte_low);

        /*
         * If we map the spte from present to nonpresent, we should clear
         * present bit firstly to avoid vcpu fetch the old high bits.
         */
        smp_wmb();

        ssptep->spte_high = sspte.spte_high;
        count_spte_clear(sptep, spte);
}

static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
        union split_spte *ssptep, sspte, orig;

        ssptep = (union split_spte *)sptep;
        sspte = (union split_spte)spte;

        /* xchg acts as a barrier before the setting of the high bits */
        orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
        orig.spte_high = ssptep->spte_high;
        ssptep->spte_high = sspte.spte_high;
        count_spte_clear(sptep, spte);

        return orig.spte;
}

/*
 * The idea using the light way get the spte on x86_32 guest is from
 * gup_get_pte(arch/x86/mm/gup.c).
 *
 * An spte tlb flush may be pending, because kvm_set_pte_rmapp
 * coalesces them and we are running out of the MMU lock.  Therefore
 * we need to protect against in-progress updates of the spte.
 *
 * Reading the spte while an update is in progress may get the old value
 * for the high part of the spte.  The race is fine for a present->non-present
 * change (because the high part of the spte is ignored for non-present spte),
 * but for a present->present change we must reread the spte.
 *
 * All such changes are done in two steps (present->non-present and
 * non-present->present), hence it is enough to count the number of
 * present->non-present updates: if it changed while reading the spte,
 * we might have hit the race.  This is done using clear_spte_count.
 */
static u64 __get_spte_lockless(u64 *sptep)
{
        struct kvm_mmu_page *sp =  page_header(__pa(sptep));
        union split_spte spte, *orig = (union split_spte *)sptep;
        int count;

retry:
        count = sp->clear_spte_count;
        smp_rmb();

        spte.spte_low = orig->spte_low;
        smp_rmb();

        spte.spte_high = orig->spte_high;
        smp_rmb();

        if (unlikely(spte.spte_low != orig->spte_low ||
              count != sp->clear_spte_count))
                goto retry;

        return spte.spte;
}
#endif

static bool spte_is_locklessly_modifiable(u64 spte)
{
        return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) ==
                (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE);
}

static bool spte_has_volatile_bits(u64 spte)
{
        /*
         * Always atomically update spte if it can be updated
         * out of mmu-lock, it can ensure dirty bit is not lost,
         * also, it can help us to get a stable is_writable_pte()
         * to ensure tlb flush is not missed.
         */
        if (spte_is_locklessly_modifiable(spte))
                return true;

        if (!shadow_accessed_mask)
                return false;

        if (!is_shadow_present_pte(spte))
                return false;

        if ((spte & shadow_accessed_mask) &&
              (!is_writable_pte(spte) || (spte & shadow_dirty_mask)))
                return false;

        return true;
}

static bool spte_is_bit_cleared(u64 old_spte, u64 new_spte, u64 bit_mask)
{
        return (old_spte & bit_mask) && !(new_spte & bit_mask);
}

static bool spte_is_bit_changed(u64 old_spte, u64 new_spte, u64 bit_mask)
{
        return (old_spte & bit_mask) != (new_spte & bit_mask);
}

/* Rules for using mmu_spte_set:
 * Set the sptep from nonpresent to present.
 * Note: the sptep being assigned *must* be either not present
 * or in a state where the hardware will not attempt to update
 * the spte.
 */
static void mmu_spte_set(u64 *sptep, u64 new_spte)
{
        WARN_ON(is_shadow_present_pte(*sptep));
        __set_spte(sptep, new_spte);
}

/* Rules for using mmu_spte_update:
 * Update the state bits, it means the mapped pfn is not changed.
 *
 * Whenever we overwrite a writable spte with a read-only one we
 * should flush remote TLBs. Otherwise rmap_write_protect
 * will find a read-only spte, even though the writable spte
 * might be cached on a CPU's TLB, the return value indicates this
 * case.
 */
static bool mmu_spte_update(u64 *sptep, u64 new_spte)
{
        u64 old_spte = *sptep;
        bool ret = false;

        WARN_ON(!is_shadow_present_pte(new_spte));

        if (!is_shadow_present_pte(old_spte)) {
                mmu_spte_set(sptep, new_spte);
                return ret;
        }

        if (!spte_has_volatile_bits(old_spte))
                __update_clear_spte_fast(sptep, new_spte);
        else
                old_spte = __update_clear_spte_slow(sptep, new_spte);

        /*
         * For the spte updated out of mmu-lock is safe, since
         * we always atomically update it, see the comments in
         * spte_has_volatile_bits().
         */
        if (spte_is_locklessly_modifiable(old_spte) &&
              !is_writable_pte(new_spte))
                ret = true;

        if (!shadow_accessed_mask) {
                /*
                 * We don't set page dirty when dropping non-writable spte.
                 * So do it now if the new spte is becoming non-writable.
                 */
                if (ret)
                        kvm_set_pfn_dirty(spte_to_pfn(old_spte));
                return ret;
        }

        /*
         * Flush TLB when accessed/dirty bits are changed in the page tables,
         * to guarantee consistency between TLB and page tables.
         */
        if (spte_is_bit_changed(old_spte, new_spte,
                                shadow_accessed_mask | shadow_dirty_mask))
                ret = true;

        if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask))
                kvm_set_pfn_accessed(spte_to_pfn(old_spte));
        if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask))
                kvm_set_pfn_dirty(spte_to_pfn(old_spte));

        return ret;
}

/*
 * Rules for using mmu_spte_clear_track_bits:
 * It sets the sptep from present to nonpresent, and track the
 * state bits, it is used to clear the last level sptep.
 */
static int mmu_spte_clear_track_bits(u64 *sptep)
{
        kvm_pfn_t pfn;
        u64 old_spte = *sptep;

        if (!spte_has_volatile_bits(old_spte))
                __update_clear_spte_fast(sptep, 0ull);
        else
                old_spte = __update_clear_spte_slow(sptep, 0ull);

        if (!is_shadow_present_pte(old_spte))
                return 0;

        pfn = spte_to_pfn(old_spte);

        /*
         * KVM does not hold the refcount of the page used by
         * kvm mmu, before reclaiming the page, we should
         * unmap it from mmu first.
         */
        WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));

        if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
                kvm_set_pfn_accessed(pfn);
        if (old_spte & (shadow_dirty_mask ? shadow_dirty_mask :
                                            PT_WRITABLE_MASK))
                kvm_set_pfn_dirty(pfn);
        return 1;
}

/*
 * Rules for using mmu_spte_clear_no_track:
 * Directly clear spte without caring the state bits of sptep,
 * it is used to set the upper level spte.
 */
static void mmu_spte_clear_no_track(u64 *sptep)
{
        __update_clear_spte_fast(sptep, 0ull);
}

static u64 mmu_spte_get_lockless(u64 *sptep)
{
        return __get_spte_lockless(sptep);
}

static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
{
        /*
         * Prevent page table teardown by making any free-er wait during
         * kvm_flush_remote_tlbs() IPI to all active vcpus.
         */
        local_irq_disable();

        /*
         * Make sure a following spte read is not reordered ahead of the write
         * to vcpu->mode.
         */
        smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES);
}

static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
        /*
         * Make sure the write to vcpu->mode is not reordered in front of
         * reads to sptes.  If it does, kvm_commit_zap_page() can see us
         * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
         */
        smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
        local_irq_enable();
}

static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
                                  struct kmem_cache *base_cache, int min)
{
        void *obj;

        if (cache->nobjs >= min)
                return 0;
        while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
                obj = kmem_cache_zalloc(base_cache, GFP_KERNEL);
                if (!obj)
                        return -ENOMEM;
                cache->objects[cache->nobjs++] = obj;
        }
        return 0;
}

static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache)
{
        return cache->nobjs;
}

static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc,
                                  struct kmem_cache *cache)
{
        while (mc->nobjs)
                kmem_cache_free(cache, mc->objects[--mc->nobjs]);
}

static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
                                       int min)
{
        void *page;

        if (cache->nobjs >= min)
                return 0;
        while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
                page = (void *)__get_free_page(GFP_KERNEL);
                if (!page)
                        return -ENOMEM;
                cache->objects[cache->nobjs++] = page;
        }
        return 0;
}

static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc)
{
        while (mc->nobjs)
                free_page((unsigned long)mc->objects[--mc->nobjs]);
}

static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
{
        int r;

        r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
                                   pte_list_desc_cache, 8 + PTE_PREFETCH_NUM);
        if (r)
                goto out;
        r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
        if (r)
                goto out;
        r = mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
                                   mmu_page_header_cache, 4);
out:
        return r;
}

static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
        mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
                                pte_list_desc_cache);
        mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache);
        mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache,
                                mmu_page_header_cache);
}

static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
{
        void *p;

        BUG_ON(!mc->nobjs);
        p = mc->objects[--mc->nobjs];
        return p;
}

static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
{
        return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
}

static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
{
        kmem_cache_free(pte_list_desc_cache, pte_list_desc);
}

static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
{
        if (!sp->role.direct)
                return sp->gfns[index];

        return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS));
}

static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
{
        if (sp->role.direct)
                BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index));
        else
                sp->gfns[index] = gfn;
}

/*
 * Return the pointer to the large page information for a given gfn,
 * handling slots that are not large page aligned.
 */
static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
                                              struct kvm_memory_slot *slot,
                                              int level)
{
        unsigned long idx;

        idx = gfn_to_index(gfn, slot->base_gfn, level);
        return &slot->arch.lpage_info[level - 2][idx];
}

static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
                                            gfn_t gfn, int count)
{
        struct kvm_lpage_info *linfo;
        int i;

        for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
                linfo = lpage_info_slot(gfn, slot, i);
                linfo->disallow_lpage += count;
                WARN_ON(linfo->disallow_lpage < 0);
        }
}

void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
{
        update_gfn_disallow_lpage_count(slot, gfn, 1);
}

void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
{
        update_gfn_disallow_lpage_count(slot, gfn, -1);
}

static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        struct kvm_memslots *slots;
        struct kvm_memory_slot *slot;
        gfn_t gfn;

        kvm->arch.indirect_shadow_pages++;
        gfn = sp->gfn;
        slots = kvm_memslots_for_spte_role(kvm, sp->role);
        slot = __gfn_to_memslot(slots, gfn);

        /* the non-leaf shadow pages are keeping readonly. */
        if (sp->role.level > PT_PAGE_TABLE_LEVEL)
                return kvm_slot_page_track_add_page(kvm, slot, gfn,
                                                    KVM_PAGE_TRACK_WRITE);

        kvm_mmu_gfn_disallow_lpage(slot, gfn);
}

static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        struct kvm_memslots *slots;
        struct kvm_memory_slot *slot;
        gfn_t gfn;

        kvm->arch.indirect_shadow_pages--;
        gfn = sp->gfn;
        slots = kvm_memslots_for_spte_role(kvm, sp->role);
        slot = __gfn_to_memslot(slots, gfn);
        if (sp->role.level > PT_PAGE_TABLE_LEVEL)
                return kvm_slot_page_track_remove_page(kvm, slot, gfn,
                                                       KVM_PAGE_TRACK_WRITE);

        kvm_mmu_gfn_allow_lpage(slot, gfn);
}

static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
                                          struct kvm_memory_slot *slot)
{
        struct kvm_lpage_info *linfo;

        if (slot) {
                linfo = lpage_info_slot(gfn, slot, level);
                return !!linfo->disallow_lpage;
        }

        return true;
}

static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
                                        int level)
{
        struct kvm_memory_slot *slot;

        slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
        return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}

static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
{
        unsigned long page_size;
        int i, ret = 0;

        page_size = kvm_host_page_size(kvm, gfn);

        for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
                if (page_size >= KVM_HPAGE_SIZE(i))
                        ret = i;
                else
                        break;
        }

        return ret;
}

static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot,
                                          bool no_dirty_log)
{
        if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
                return false;
        if (no_dirty_log && slot->dirty_bitmap)
                return false;

        return true;
}

static struct kvm_memory_slot *
gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
                            bool no_dirty_log)
{
        struct kvm_memory_slot *slot;

        slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
        if (!memslot_valid_for_gpte(slot, no_dirty_log))
                slot = NULL;

        return slot;
}

static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
                         bool *force_pt_level)
{
        int host_level, level, max_level;
        struct kvm_memory_slot *slot;

        if (unlikely(*force_pt_level))
                return PT_PAGE_TABLE_LEVEL;

        slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn);
        *force_pt_level = !memslot_valid_for_gpte(slot, true);
        if (unlikely(*force_pt_level))
                return PT_PAGE_TABLE_LEVEL;

        host_level = host_mapping_level(vcpu->kvm, large_gfn);

        if (host_level == PT_PAGE_TABLE_LEVEL)
                return host_level;

        max_level = min(kvm_x86_ops->get_lpage_level(), host_level);

        for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
                if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
                        break;

        return level - 1;
}

/*
 * About rmap_head encoding:
 *
 * If the bit zero of rmap_head->val is clear, then it points to the only spte
 * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
 * pte_list_desc containing more mappings.
 */

/*
 * Returns the number of pointers in the rmap chain, not counting the new one.
 */
static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
                        struct kvm_rmap_head *rmap_head)
{
        struct pte_list_desc *desc;
        int i, count = 0;

        if (!rmap_head->val) {
                rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte);
                rmap_head->val = (unsigned long)spte;
        } else if (!(rmap_head->val & 1)) {
                rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte);
                desc = mmu_alloc_pte_list_desc(vcpu);
                desc->sptes[0] = (u64 *)rmap_head->val;
                desc->sptes[1] = spte;
                rmap_head->val = (unsigned long)desc | 1;
                ++count;
        } else {
                rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
                desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
                while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
                        desc = desc->more;
                        count += PTE_LIST_EXT;
                }
                if (desc->sptes[PTE_LIST_EXT-1]) {
                        desc->more = mmu_alloc_pte_list_desc(vcpu);
                        desc = desc->more;
                }
                for (i = 0; desc->sptes[i]; ++i)
                        ++count;
                desc->sptes[i] = spte;
        }
        return count;
}

static void
pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
                           struct pte_list_desc *desc, int i,
                           struct pte_list_desc *prev_desc)
{
        int j;

        for (j = PTE_LIST_EXT - 1; !desc->sptes[j] && j > i; --j)
                ;
        desc->sptes[i] = desc->sptes[j];
        desc->sptes[j] = NULL;
        if (j != 0)
                return;
        if (!prev_desc && !desc->more)
                rmap_head->val = (unsigned long)desc->sptes[0];
        else

                if (prev_desc)
                        prev_desc->more = desc->more;
                else
                        rmap_head->val = (unsigned long)desc->more | 1;
        mmu_free_pte_list_desc(desc);
}

static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
{
        struct pte_list_desc *desc;
        struct pte_list_desc *prev_desc;
        int i;

        if (!rmap_head->val) {
                printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
                BUG();
        } else if (!(rmap_head->val & 1)) {
                rmap_printk("pte_list_remove:  %p 1->0\n", spte);
                if ((u64 *)rmap_head->val != spte) {
                        printk(KERN_ERR "pte_list_remove:  %p 1->BUG\n", spte);
                        BUG();
                }
                rmap_head->val = 0;
        } else {
                rmap_printk("pte_list_remove:  %p many->many\n", spte);
                desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
                prev_desc = NULL;
                while (desc) {
                        for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
                                if (desc->sptes[i] == spte) {
                                        pte_list_desc_remove_entry(rmap_head,
                                                        desc, i, prev_desc);
                                        return;
                                }
                        }
                        prev_desc = desc;
                        desc = desc->more;
                }
                pr_err("pte_list_remove: %p many->many\n", spte);
                BUG();
        }
}

static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
                                           struct kvm_memory_slot *slot)
{
        unsigned long idx;

        idx = gfn_to_index(gfn, slot->base_gfn, level);
        return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
}

static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn,
                                         struct kvm_mmu_page *sp)
{
        struct kvm_memslots *slots;
        struct kvm_memory_slot *slot;

        slots = kvm_memslots_for_spte_role(kvm, sp->role);
        slot = __gfn_to_memslot(slots, gfn);
        return __gfn_to_rmap(gfn, sp->role.level, slot);
}

static bool rmap_can_add(struct kvm_vcpu *vcpu)
{
        struct kvm_mmu_memory_cache *cache;

        cache = &vcpu->arch.mmu_pte_list_desc_cache;
        return mmu_memory_cache_free_objects(cache);
}

static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
        struct kvm_mmu_page *sp;
        struct kvm_rmap_head *rmap_head;

        sp = page_header(__pa(spte));
        kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
        rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
        return pte_list_add(vcpu, spte, rmap_head);
}

static void rmap_remove(struct kvm *kvm, u64 *spte)
{
        struct kvm_mmu_page *sp;
        gfn_t gfn;
        struct kvm_rmap_head *rmap_head;

        sp = page_header(__pa(spte));
        gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
        rmap_head = gfn_to_rmap(kvm, gfn, sp);
        pte_list_remove(spte, rmap_head);
}

/*
 * Used by the following functions to iterate through the sptes linked by a
 * rmap.  All fields are private and not assumed to be used outside.
 */
struct rmap_iterator {
        /* private fields */
        struct pte_list_desc *desc;     /* holds the sptep if not NULL */
        int pos;                        /* index of the sptep */
};

/*
 * Iteration must be started by this function.  This should also be used after
 * removing/dropping sptes from the rmap link because in such cases the
 * information in the itererator may not be valid.
 *
 * Returns sptep if found, NULL otherwise.
 */
static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
                           struct rmap_iterator *iter)
{
        u64 *sptep;

        if (!rmap_head->val)
                return NULL;

        if (!(rmap_head->val & 1)) {
                iter->desc = NULL;
                sptep = (u64 *)rmap_head->val;
                goto out;
        }

        iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
        iter->pos = 0;
        sptep = iter->desc->sptes[iter->pos];
out:
        BUG_ON(!is_shadow_present_pte(*sptep));
        return sptep;
}

/*
 * Must be used with a valid iterator: e.g. after rmap_get_first().
 *
 * Returns sptep if found, NULL otherwise.
 */
static u64 *rmap_get_next(struct rmap_iterator *iter)
{
        u64 *sptep;

        if (iter->desc) {
                if (iter->pos < PTE_LIST_EXT - 1) {
                        ++iter->pos;
                        sptep = iter->desc->sptes[iter->pos];
                        if (sptep)
                                goto out;
                }

                iter->desc = iter->desc->more;

                if (iter->desc) {
                        iter->pos = 0;
                        /* desc->sptes[0] cannot be NULL */
                        sptep = iter->desc->sptes[iter->pos];
                        goto out;
                }
        }

        return NULL;
out:
        BUG_ON(!is_shadow_present_pte(*sptep));
        return sptep;
}

#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_)                 \
        for (_spte_ = rmap_get_first(_rmap_head_, _iter_);              \
             _spte_; _spte_ = rmap_get_next(_iter_))

static void drop_spte(struct kvm *kvm, u64 *sptep)
{
        if (mmu_spte_clear_track_bits(sptep))
                rmap_remove(kvm, sptep);
}


static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
{
        if (is_large_pte(*sptep)) {
                WARN_ON(page_header(__pa(sptep))->role.level ==
                        PT_PAGE_TABLE_LEVEL);
                drop_spte(kvm, sptep);
                --kvm->stat.lpages;
                return true;
        }

        return false;
}

static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
{
        if (__drop_large_spte(vcpu->kvm, sptep))
                kvm_flush_remote_tlbs(vcpu->kvm);
}

/*
 * Write-protect on the specified @sptep, @pt_protect indicates whether
 * spte write-protection is caused by protecting shadow page table.
 *
 * Note: write protection is difference between dirty logging and spte
 * protection:
 * - for dirty logging, the spte can be set to writable at anytime if
 *   its dirty bitmap is properly set.
 * - for spte protection, the spte can be writable only after unsync-ing
 *   shadow page.
 *
 * Return true if tlb need be flushed.
 */
static bool spte_write_protect(u64 *sptep, bool pt_protect)
{
        u64 spte = *sptep;

        if (!is_writable_pte(spte) &&
              !(pt_protect && spte_is_locklessly_modifiable(spte)))
                return false;

        rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);

        if (pt_protect)
                spte &= ~SPTE_MMU_WRITEABLE;
        spte = spte & ~PT_WRITABLE_MASK;

        return mmu_spte_update(sptep, spte);
}

static bool __rmap_write_protect(struct kvm *kvm,
                                 struct kvm_rmap_head *rmap_head,
                                 bool pt_protect)
{
        u64 *sptep;
        struct rmap_iterator iter;
        bool flush = false;

        for_each_rmap_spte(rmap_head, &iter, sptep)
                flush |= spte_write_protect(sptep, pt_protect);

        return flush;
}

static bool spte_clear_dirty(u64 *sptep)
{
        u64 spte = *sptep;

        rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);

        spte &= ~shadow_dirty_mask;

        return mmu_spte_update(sptep, spte);
}

static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
        u64 *sptep;
        struct rmap_iterator iter;
        bool flush = false;

        for_each_rmap_spte(rmap_head, &iter, sptep)
                flush |= spte_clear_dirty(sptep);

        return flush;
}

static bool spte_set_dirty(u64 *sptep)
{
        u64 spte = *sptep;

        rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);

        spte |= shadow_dirty_mask;

        return mmu_spte_update(sptep, spte);
}

static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
        u64 *sptep;
        struct rmap_iterator iter;
        bool flush = false;

        for_each_rmap_spte(rmap_head, &iter, sptep)
                flush |= spte_set_dirty(sptep);

        return flush;
}

/**
 * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
 * @kvm: kvm instance
 * @slot: slot to protect
 * @gfn_offset: start of the BITS_PER_LONG pages we care about
 * @mask: indicates which pages we should protect
 *
 * Used when we do not need to care about huge page mappings: e.g. during dirty
 * logging we do not have any such mappings.
 */
static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
                                     struct kvm_memory_slot *slot,
                                     gfn_t gfn_offset, unsigned long mask)
{
        struct kvm_rmap_head *rmap_head;

        while (mask) {
                rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
                                          PT_PAGE_TABLE_LEVEL, slot);
                __rmap_write_protect(kvm, rmap_head, false);

                /* clear the first set bit */
                mask &= mask - 1;
        }
}

/**
 * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages
 * @kvm: kvm instance
 * @slot: slot to clear D-bit
 * @gfn_offset: start of the BITS_PER_LONG pages we care about
 * @mask: indicates which pages we should clear D-bit
 *
 * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap.
 */
void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
                                     struct kvm_memory_slot *slot,
                                     gfn_t gfn_offset, unsigned long mask)
{
        struct kvm_rmap_head *rmap_head;

        while (mask) {
                rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
                                          PT_PAGE_TABLE_LEVEL, slot);
                __rmap_clear_dirty(kvm, rmap_head);

                /* clear the first set bit */
                mask &= mask - 1;
        }
}
EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked);

/**
 * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
 * PT level pages.
 *
 * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
 * enable dirty logging for them.
 *
 * Used when we do not need to care about huge page mappings: e.g. during dirty
 * logging we do not have any such mappings.
 */
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
                                struct kvm_memory_slot *slot,
                                gfn_t gfn_offset, unsigned long mask)
{
        if (kvm_x86_ops->enable_log_dirty_pt_masked)
                kvm_x86_ops->enable_log_dirty_pt_masked(kvm, slot, gfn_offset,
                                mask);
        else
                kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}

bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
                                    struct kvm_memory_slot *slot, u64 gfn)
{
        struct kvm_rmap_head *rmap_head;
        int i;
        bool write_protected = false;

        for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
                rmap_head = __gfn_to_rmap(gfn, i, slot);
                write_protected |= __rmap_write_protect(kvm, rmap_head, true);
        }

        return write_protected;
}

static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
{
        struct kvm_memory_slot *slot;

        slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
        return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
}

static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
        u64 *sptep;
        struct rmap_iterator iter;
        bool flush = false;

        while ((sptep = rmap_get_first(rmap_head, &iter))) {
                rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);

                drop_spte(kvm, sptep);
                flush = true;
        }

        return flush;
}

static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
                           struct kvm_memory_slot *slot, gfn_t gfn, int level,
                           unsigned long data)
{
        return kvm_zap_rmapp(kvm, rmap_head);
}

static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
                             struct kvm_memory_slot *slot, gfn_t gfn, int level,
                             unsigned long data)
{
        u64 *sptep;
        struct rmap_iterator iter;
        int need_flush = 0;
        u64 new_spte;
        pte_t *ptep = (pte_t *)data;
        kvm_pfn_t new_pfn;

        WARN_ON(pte_huge(*ptep));
        new_pfn = pte_pfn(*ptep);

restart:
        for_each_rmap_spte(rmap_head, &iter, sptep) {
                rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
                             sptep, *sptep, gfn, level);

                need_flush = 1;

                if (pte_write(*ptep)) {
                        drop_spte(kvm, sptep);
                        goto restart;
                } else {
                        new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
                        new_spte |= (u64)new_pfn << PAGE_SHIFT;

                        new_spte &= ~PT_WRITABLE_MASK;
                        new_spte &= ~SPTE_HOST_WRITEABLE;
                        new_spte &= ~shadow_accessed_mask;

                        mmu_spte_clear_track_bits(sptep);
                        mmu_spte_set(sptep, new_spte);
                }
        }

        if (need_flush)
                kvm_flush_remote_tlbs(kvm);

        return 0;
}

struct slot_rmap_walk_iterator {
        /* input fields. */
        struct kvm_memory_slot *slot;
        gfn_t start_gfn;
        gfn_t end_gfn;
        int start_level;
        int end_level;

        /* output fields. */
        gfn_t gfn;
        struct kvm_rmap_head *rmap;
        int level;

        /* private field. */
        struct kvm_rmap_head *end_rmap;
};

static void
rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
{
        iterator->level = level;
        iterator->gfn = iterator->start_gfn;
        iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot);
        iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level,
                                           iterator->slot);
}

static void
slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
                    struct kvm_memory_slot *slot, int start_level,
                    int end_level, gfn_t start_gfn, gfn_t end_gfn)
{
        iterator->slot = slot;
        iterator->start_level = start_level;
        iterator->end_level = end_level;
        iterator->start_gfn = start_gfn;
        iterator->end_gfn = end_gfn;

        rmap_walk_init_level(iterator, iterator->start_level);
}

static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
{
        return !!iterator->rmap;
}

static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
{
        if (++iterator->rmap <= iterator->end_rmap) {
                iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
                return;
        }

        if (++iterator->level > iterator->end_level) {
                iterator->rmap = NULL;
                return;
        }

        rmap_walk_init_level(iterator, iterator->level);
}

#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_,    \
           _start_gfn, _end_gfn, _iter_)                                \
        for (slot_rmap_walk_init(_iter_, _slot_, _start_level_,         \
                                 _end_level_, _start_gfn, _end_gfn);    \
             slot_rmap_walk_okay(_iter_);                               \
             slot_rmap_walk_next(_iter_))

static int kvm_handle_hva_range(struct kvm *kvm,
                                unsigned long start,
                                unsigned long end,
                                unsigned long data,
                                int (*handler)(struct kvm *kvm,
                                               struct kvm_rmap_head *rmap_head,
                                               struct kvm_memory_slot *slot,
                                               gfn_t gfn,
                                               int level,
                                               unsigned long data))
{
        struct kvm_memslots *slots;
        struct kvm_memory_slot *memslot;
        struct slot_rmap_walk_iterator iterator;
        int ret = 0;
        int i;

        for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
                slots = __kvm_memslots(kvm, i);
                kvm_for_each_memslot(memslot, slots) {
                        unsigned long hva_start, hva_end;
                        gfn_t gfn_start, gfn_end;

                        hva_start = max(start, memslot->userspace_addr);
                        hva_end = min(end, memslot->userspace_addr +
                                      (memslot->npages << PAGE_SHIFT));
                        if (hva_start >= hva_end)
                                continue;
                        /*
                         * {gfn(page) | page intersects with [hva_start, hva_end)} =
                         * {gfn_start, gfn_start+1, ..., gfn_end-1}.
                         */
                        gfn_start = hva_to_gfn_memslot(hva_start, memslot);
                        gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);

                        for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL,
                                                 PT_MAX_HUGEPAGE_LEVEL,
                                                 gfn_start, gfn_end - 1,
                                                 &iterator)
                                ret |= handler(kvm, iterator.rmap, memslot,
                                               iterator.gfn, iterator.level, data);
                }
        }

        return ret;
}

static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
                          unsigned long data,
                          int (*handler)(struct kvm *kvm,
                                         struct kvm_rmap_head *rmap_head,
                                         struct kvm_memory_slot *slot,
                                         gfn_t gfn, int level,
                                         unsigned long data))
{
        return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
}

int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
        return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
}

int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
{
        return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
}

void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
        kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
}

static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
                         struct kvm_memory_slot *slot, gfn_t gfn, int level,
                         unsigned long data)
{
        u64 *sptep;
        struct rmap_iterator uninitialized_var(iter);
        int young = 0;

        BUG_ON(!shadow_accessed_mask);

        for_each_rmap_spte(rmap_head, &iter, sptep) {
                if (*sptep & shadow_accessed_mask) {
                        young = 1;
                        clear_bit((ffs(shadow_accessed_mask) - 1),
                                 (unsigned long *)sptep);
                }
        }

        trace_kvm_age_page(gfn, level, slot, young);
        return young;
}

static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
                              struct kvm_memory_slot *slot, gfn_t gfn,
                              int level, unsigned long data)
{
        u64 *sptep;
        struct rmap_iterator iter;
        int young = 0;

        /*
         * If there's no access bit in the secondary pte set by the
         * hardware it's up to gup-fast/gup to set the access bit in
         * the primary pte or in the page structure.
         */
        if (!shadow_accessed_mask)
                goto out;

        for_each_rmap_spte(rmap_head, &iter, sptep) {
                if (*sptep & shadow_accessed_mask) {
                        young = 1;
                        break;
                }
        }
out:
        return young;
}

#define RMAP_RECYCLE_THRESHOLD 1000

static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
        struct kvm_rmap_head *rmap_head;
        struct kvm_mmu_page *sp;

        sp = page_header(__pa(spte));

        rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);

        kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0);
        kvm_flush_remote_tlbs(vcpu->kvm);
}

int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
        /*
         * In case of absence of EPT Access and Dirty Bits supports,
         * emulate the accessed bit for EPT, by checking if this page has
         * an EPT mapping, and clearing it if it does. On the next access,
         * a new EPT mapping will be established.
         * This has some overhead, but not as much as the cost of swapping
         * out actively used pages or breaking up actively used hugepages.
         */
        if (!shadow_accessed_mask) {
                /*
                 * We are holding the kvm->mmu_lock, and we are blowing up
                 * shadow PTEs. MMU notifier consumers need to be kept at bay.
                 * This is correct as long as we don't decouple the mmu_lock
                 * protected regions (like invalidate_range_start|end does).
                 */
                kvm->mmu_notifier_seq++;
                return kvm_handle_hva_range(kvm, start, end, 0,
                                            kvm_unmap_rmapp);
        }

        return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
        return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp);
}

#ifdef MMU_DEBUG
static int is_empty_shadow_page(u64 *spt)
{
        u64 *pos;
        u64 *end;

        for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
                if (is_shadow_present_pte(*pos)) {
                        printk(KERN_ERR "%s: %p %llx\n", __func__,
                               pos, *pos);
                        return 0;
                }
        return 1;
}
#endif

/*
 * This value is the sum of all of the kvm instances's
 * kvm->arch.n_used_mmu_pages values.  We need a global,
 * aggregate version in order to make the slab shrinker
 * faster
 */
static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
{
        kvm->arch.n_used_mmu_pages += nr;
        percpu_counter_add(&kvm_total_used_mmu_pages, nr);
}

static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
{
        MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
        hlist_del(&sp->hash_link);
        list_del(&sp->link);
        free_page((unsigned long)sp->spt);
        if (!sp->role.direct)
                free_page((unsigned long)sp->gfns);
        kmem_cache_free(mmu_page_header_cache, sp);
}

static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
        return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
}

static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
                                    struct kvm_mmu_page *sp, u64 *parent_pte)
{
        if (!parent_pte)
                return;

        pte_list_add(vcpu, parent_pte, &sp->parent_ptes);
}

static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
                                       u64 *parent_pte)
{
        pte_list_remove(parent_pte, &sp->parent_ptes);
}

static void drop_parent_pte(struct kvm_mmu_page *sp,
                            u64 *parent_pte)
{
        mmu_page_remove_parent_pte(sp, parent_pte);
        mmu_spte_clear_no_track(parent_pte);
}

static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct)
{
        struct kvm_mmu_page *sp;

        sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
        sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
        if (!direct)
                sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
        set_page_private(virt_to_page(sp->spt), (unsigned long)sp);

        /*
         * The active_mmu_pages list is the FIFO list, do not move the
         * page until it is zapped. kvm_zap_obsolete_pages depends on
         * this feature. See the comments in kvm_zap_obsolete_pages().
         */
        list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
        kvm_mod_used_mmu_pages(vcpu->kvm, +1);
        return sp;
}

static void mark_unsync(u64 *spte);
static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
{
        u64 *sptep;
        struct rmap_iterator iter;

        for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) {
                mark_unsync(sptep);
        }
}

static void mark_unsync(u64 *spte)
{
        struct kvm_mmu_page *sp;
        unsigned int index;

        sp = page_header(__pa(spte));
        index = spte - sp->spt;
        if (__test_and_set_bit(index, sp->unsync_child_bitmap))
                return;
        if (sp->unsync_children++)
                return;
        kvm_mmu_mark_parents_unsync(sp);
}

static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
                               struct kvm_mmu_page *sp)
{
        return 0;
}

static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
}

static void nonpaging_update_pte(struct kvm_vcpu *vcpu,
                                 struct kvm_mmu_page *sp, u64 *spte,
                                 const void *pte)
{
        WARN_ON(1);
}

#define KVM_PAGE_ARRAY_NR 16

struct kvm_mmu_pages {
        struct mmu_page_and_offset {
                struct kvm_mmu_page *sp;
                unsigned int idx;
        } page[KVM_PAGE_ARRAY_NR];
        unsigned int nr;
};

static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
                         int idx)
{
        int i;

        if (sp->unsync)
                for (i=0; i < pvec->nr; i++)
                        if (pvec->page[i].sp == sp)
                                return 0;

        pvec->page[pvec->nr].sp = sp;
        pvec->page[pvec->nr].idx = idx;
        pvec->nr++;
        return (pvec->nr == KVM_PAGE_ARRAY_NR);
}

static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
{
        --sp->unsync_children;
        WARN_ON((int)sp->unsync_children < 0);
        __clear_bit(idx, sp->unsync_child_bitmap);
}

static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
                           struct kvm_mmu_pages *pvec)
{
        int i, ret, nr_unsync_leaf = 0;

        for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
                struct kvm_mmu_page *child;
                u64 ent = sp->spt[i];

                if (!is_shadow_present_pte(ent) || is_large_pte(ent)) {
                        clear_unsync_child_bit(sp, i);
                        continue;
                }

                child = page_header(ent & PT64_BASE_ADDR_MASK);

                if (child->unsync_children) {
                        if (mmu_pages_add(pvec, child, i))
                                return -ENOSPC;

                        ret = __mmu_unsync_walk(child, pvec);
                        if (!ret) {
                                clear_unsync_child_bit(sp, i);
                                continue;
                        } else if (ret > 0) {
                                nr_unsync_leaf += ret;
                        } else
                                return ret;
                } else if (child->unsync) {
                        nr_unsync_leaf++;
                        if (mmu_pages_add(pvec, child, i))
                                return -ENOSPC;
                } else
                        clear_unsync_child_bit(sp, i);
        }

        return nr_unsync_leaf;
}

#define INVALID_INDEX (-1)

static int mmu_unsync_walk(struct kvm_mmu_page *sp,
                           struct kvm_mmu_pages *pvec)
{
        pvec->nr = 0;
        if (!sp->unsync_children)
                return 0;

        mmu_pages_add(pvec, sp, INVALID_INDEX);
        return __mmu_unsync_walk(sp, pvec);
}

static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        WARN_ON(!sp->unsync);
        trace_kvm_mmu_sync_page(sp);
        sp->unsync = 0;
        --kvm->stat.mmu_unsync;
}

static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
                                    struct list_head *invalid_list);
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
                                    struct list_head *invalid_list);

/*
 * NOTE: we should pay more attention on the zapped-obsolete page
 * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk
 * since it has been deleted from active_mmu_pages but still can be found
 * at hast list.
 *
 * for_each_gfn_valid_sp() has skipped that kind of pages.
 */
#define for_each_gfn_valid_sp(_kvm, _sp, _gfn)                          \
        hlist_for_each_entry(_sp,                                       \
          &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
                if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \
                        || (_sp)->role.invalid) {} else

#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)                 \
        for_each_gfn_valid_sp(_kvm, _sp, _gfn)                          \
                if ((_sp)->role.direct) {} else

/* @sp->gfn should be write-protected at the call site */
static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                            struct list_head *invalid_list)
{
        if (sp->role.cr4_pae != !!is_pae(vcpu)) {
                kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
                return false;
        }

        if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
                kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
                return false;
        }

        return true;
}

static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
                                 struct list_head *invalid_list,
                                 bool remote_flush, bool local_flush)
{
        if (!list_empty(invalid_list)) {
                kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list);
                return;
        }

        if (remote_flush)
                kvm_flush_remote_tlbs(vcpu->kvm);
        else if (local_flush)
                kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}

#ifdef CONFIG_KVM_MMU_AUDIT
#include "mmu_audit.c"
#else
static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
static void mmu_audit_disable(void) { }
#endif

static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
}

static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                         struct list_head *invalid_list)
{
        kvm_unlink_unsync_page(vcpu->kvm, sp);
        return __kvm_sync_page(vcpu, sp, invalid_list);
}

/* @gfn should be write-protected at the call site */
static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
                           struct list_head *invalid_list)
{
        struct kvm_mmu_page *s;
        bool ret = false;

        for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
                if (!s->unsync)
                        continue;

                WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
                ret |= kvm_sync_page(vcpu, s, invalid_list);
        }

        return ret;
}

struct mmu_page_path {
        struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
        unsigned int idx[PT64_ROOT_LEVEL];
};

#define for_each_sp(pvec, sp, parents, i)                       \
                for (i = mmu_pages_first(&pvec, &parents);      \
                        i < pvec.nr && ({ sp = pvec.page[i].sp; 1;});   \
                        i = mmu_pages_next(&pvec, &parents, i))

static int mmu_pages_next(struct kvm_mmu_pages *pvec,
                          struct mmu_page_path *parents,
                          int i)
{
        int n;

        for (n = i+1; n < pvec->nr; n++) {
                struct kvm_mmu_page *sp = pvec->page[n].sp;
                unsigned idx = pvec->page[n].idx;
                int level = sp->role.level;

                parents->idx[level-1] = idx;
                if (level == PT_PAGE_TABLE_LEVEL)
                        break;

                parents->parent[level-2] = sp;
        }

        return n;
}

static int mmu_pages_first(struct kvm_mmu_pages *pvec,
                           struct mmu_page_path *parents)
{
        struct kvm_mmu_page *sp;
        int level;

        if (pvec->nr == 0)
                return 0;

        WARN_ON(pvec->page[0].idx != INVALID_INDEX);

        sp = pvec->page[0].sp;
        level = sp->role.level;
        WARN_ON(level == PT_PAGE_TABLE_LEVEL);

        parents->parent[level-2] = sp;

        /* Also set up a sentinel.  Further entries in pvec are all
         * children of sp, so this element is never overwritten.
         */
        parents->parent[level-1] = NULL;
        return mmu_pages_next(pvec, parents, 0);
}

static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
        struct kvm_mmu_page *sp;
        unsigned int level = 0;

        do {
                unsigned int idx = parents->idx[level];
                sp = parents->parent[level];
                if (!sp)
                        return;

                WARN_ON(idx == INVALID_INDEX);
                clear_unsync_child_bit(sp, idx);
                level++;
        } while (!sp->unsync_children);
}

static void mmu_sync_children(struct kvm_vcpu *vcpu,
                              struct kvm_mmu_page *parent)
{
        int i;
        struct kvm_mmu_page *sp;
        struct mmu_page_path parents;
        struct kvm_mmu_pages pages;
        LIST_HEAD(invalid_list);
        bool flush = false;

        while (mmu_unsync_walk(parent, &pages)) {
                bool protected = false;

                for_each_sp(pages, sp, parents, i)
                        protected |= rmap_write_protect(vcpu, sp->gfn);

                if (protected) {
                        kvm_flush_remote_tlbs(vcpu->kvm);
                        flush = false;
                }

                for_each_sp(pages, sp, parents, i) {
                        flush |= kvm_sync_page(vcpu, sp, &invalid_list);
                        mmu_pages_clear_parents(&parents);
                }
                if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) {
                        kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
                        cond_resched_lock(&vcpu->kvm->mmu_lock);
                        flush = false;
                }
        }

        kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
}

static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
        atomic_set(&sp->write_flooding_count,  0);
}

static void clear_sp_write_flooding_count(u64 *spte)
{
        struct kvm_mmu_page *sp =  page_header(__pa(spte));

        __clear_sp_write_flooding_count(sp);
}

static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
                                             gfn_t gfn,
                                             gva_t gaddr,
                                             unsigned level,
                                             int direct,
                                             unsigned access)
{
        union kvm_mmu_page_role role;
        unsigned quadrant;
        struct kvm_mmu_page *sp;
        bool need_sync = false;
        bool flush = false;
        LIST_HEAD(invalid_list);

        role = vcpu->arch.mmu.base_role;
        role.level = level;
        role.direct = direct;
        if (role.direct)
                role.cr4_pae = 0;
        role.access = access;
        if (!vcpu->arch.mmu.direct_map
            && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
                quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
                quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
                role.quadrant = quadrant;
        }
        for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) {
                if (!need_sync && sp->unsync)
                        need_sync = true;

                if (sp->role.word != role.word)
                        continue;

                if (sp->unsync) {
                        /* The page is good, but __kvm_sync_page might still end
                         * up zapping it.  If so, break in order to rebuild it.
                         */
                        if (!__kvm_sync_page(vcpu, sp, &invalid_list))
                                break;

                        WARN_ON(!list_empty(&invalid_list));
                        kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
                }

                if (sp->unsync_children)
                        kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);

                __clear_sp_write_flooding_count(sp);
                trace_kvm_mmu_get_page(sp, false);
                return sp;
        }

        ++vcpu->kvm->stat.mmu_cache_miss;

        sp = kvm_mmu_alloc_page(vcpu, direct);

        sp->gfn = gfn;
        sp->role = role;
        hlist_add_head(&sp->hash_link,
                &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
        if (!direct) {
                /*
                 * we should do write protection before syncing pages
                 * otherwise the content of the synced shadow page may
                 * be inconsistent with guest page table.
                 */
                account_shadowed(vcpu->kvm, sp);
                if (level == PT_PAGE_TABLE_LEVEL &&
                      rmap_write_protect(vcpu, gfn))
                        kvm_flush_remote_tlbs(vcpu->kvm);

                if (level > PT_PAGE_TABLE_LEVEL && need_sync)
                        flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
        }
        sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
        clear_page(sp->spt);
        trace_kvm_mmu_get_page(sp, true);

        kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
        return sp;
}

static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
                             struct kvm_vcpu *vcpu, u64 addr)
{
        iterator->addr = addr;
        iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
        iterator->level = vcpu->arch.mmu.shadow_root_level;

        if (iterator->level == PT64_ROOT_LEVEL &&
            vcpu->arch.mmu.root_level < PT64_ROOT_LEVEL &&
            !vcpu->arch.mmu.direct_map)
                --iterator->level;

        if (iterator->level == PT32E_ROOT_LEVEL) {
                iterator->shadow_addr
                        = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
                iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
                --iterator->level;
                if (!iterator->shadow_addr)
                        iterator->level = 0;
        }
}

static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
{
        if (iterator->level < PT_PAGE_TABLE_LEVEL)
                return false;

        iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
        iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
        return true;
}

static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator,
                               u64 spte)
{
        if (is_last_spte(spte, iterator->level)) {
                iterator->level = 0;
                return;
        }

        iterator->shadow_addr = spte & PT64_BASE_ADDR_MASK;
        --iterator->level;
}

static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
{
        return __shadow_walk_next(iterator, *iterator->sptep);
}

static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
                             struct kvm_mmu_page *sp)
{
        u64 spte;

        BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);

        spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
               shadow_user_mask | shadow_x_mask | shadow_accessed_mask;

        mmu_spte_set(sptep, spte);

        mmu_page_add_parent_pte(vcpu, sp, sptep);

        if (sp->unsync_children || sp->unsync)
                mark_unsync(sptep);
}

static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
                                   unsigned direct_access)
{
        if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) {
                struct kvm_mmu_page *child;

                /*
                 * For the direct sp, if the guest pte's dirty bit
                 * changed form clean to dirty, it will corrupt the
                 * sp's access: allow writable in the read-only sp,
                 * so we should update the spte at this point to get
                 * a new sp with the correct access.
                 */
                child = page_header(*sptep & PT64_BASE_ADDR_MASK);
                if (child->role.access == direct_access)
                        return;

                drop_parent_pte(child, sptep);
                kvm_flush_remote_tlbs(vcpu->kvm);
        }
}

static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
                             u64 *spte)
{
        u64 pte;
        struct kvm_mmu_page *child;

        pte = *spte;
        if (is_shadow_present_pte(pte)) {
                if (is_last_spte(pte, sp->role.level)) {
                        drop_spte(kvm, spte);
                        if (is_large_pte(pte))
                                --kvm->stat.lpages;
                } else {
                        child = page_header(pte & PT64_BASE_ADDR_MASK);
                        drop_parent_pte(child, spte);
                }
                return true;
        }

        if (is_mmio_spte(pte))
                mmu_spte_clear_no_track(spte);

        return false;
}

static void kvm_mmu_page_unlink_children(struct kvm *kvm,
                                         struct kvm_mmu_page *sp)
{
        unsigned i;

        for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
                mmu_page_zap_pte(kvm, sp, sp->spt + i);
}

static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        u64 *sptep;
        struct rmap_iterator iter;

        while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
                drop_parent_pte(sp, sptep);
}

static int mmu_zap_unsync_children(struct kvm *kvm,
                                   struct kvm_mmu_page *parent,
                                   struct list_head *invalid_list)
{
        int i, zapped = 0;
        struct mmu_page_path parents;
        struct kvm_mmu_pages pages;

        if (parent->role.level == PT_PAGE_TABLE_LEVEL)
                return 0;

        while (mmu_unsync_walk(parent, &pages)) {
                struct kvm_mmu_page *sp;

                for_each_sp(pages, sp, parents, i) {
                        kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
                        mmu_pages_clear_parents(&parents);
                        zapped++;
                }
        }

        return zapped;
}

static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
                                    struct list_head *invalid_list)
{
        int ret;

        trace_kvm_mmu_prepare_zap_page(sp);
        ++kvm->stat.mmu_shadow_zapped;
        ret = mmu_zap_unsync_children(kvm, sp, invalid_list);
        kvm_mmu_page_unlink_children(kvm, sp);
        kvm_mmu_unlink_parents(kvm, sp);

        if (!sp->role.invalid && !sp->role.direct)
                unaccount_shadowed(kvm, sp);

        if (sp->unsync)
                kvm_unlink_unsync_page(kvm, sp);
        if (!sp->root_count) {
                /* Count self */
                ret++;
                list_move(&sp->link, invalid_list);
                kvm_mod_used_mmu_pages(kvm, -1);
        } else {
                list_move(&sp->link, &kvm->arch.active_mmu_pages);

                /*
                 * The obsolete pages can not be used on any vcpus.
                 * See the comments in kvm_mmu_invalidate_zap_all_pages().
                 */
                if (!sp->role.invalid && !is_obsolete_sp(kvm, sp))
                        kvm_reload_remote_mmus(kvm);
        }

        sp->role.invalid = 1;
        return ret;
}

static void kvm_mmu_commit_zap_page(struct kvm *kvm,
                                    struct list_head *invalid_list)
{
        struct kvm_mmu_page *sp, *nsp;

        if (list_empty(invalid_list))
                return;

        /*
         * We need to make sure everyone sees our modifications to
         * the page tables and see changes to vcpu->mode here. The barrier
         * in the kvm_flush_remote_tlbs() achieves this. This pairs
         * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end.
         *
         * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit
         * guest mode and/or lockless shadow page table walks.
         */
        kvm_flush_remote_tlbs(kvm);

        list_for_each_entry_safe(sp, nsp, invalid_list, link) {
                WARN_ON(!sp->role.invalid || sp->root_count);
                kvm_mmu_free_page(sp);
        }
}

static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
                                        struct list_head *invalid_list)
{
        struct kvm_mmu_page *sp;

        if (list_empty(&kvm->arch.active_mmu_pages))
                return false;

        sp = list_last_entry(&kvm->arch.active_mmu_pages,
                             struct kvm_mmu_page, link);
        kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);

        return true;
}

/*
 * Changing the number of mmu pages allocated to the vm
 * Note: if goal_nr_mmu_pages is too small, you will get dead lock
 */
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
{
        LIST_HEAD(invalid_list);

        spin_lock(&kvm->mmu_lock);

        if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
                /* Need to free some mmu pages to achieve the goal. */
                while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages)
                        if (!prepare_zap_oldest_mmu_page(kvm, &invalid_list))
                                break;

                kvm_mmu_commit_zap_page(kvm, &invalid_list);
                goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
        }

        kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;

        spin_unlock(&kvm->mmu_lock);
}

int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
{
        struct kvm_mmu_page *sp;
        LIST_HEAD(invalid_list);
        int r;

        pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
        r = 0;
        spin_lock(&kvm->mmu_lock);
        for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
                pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
                         sp->role.word);
                r = 1;
                kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
        }
        kvm_mmu_commit_zap_page(kvm, &invalid_list);
        spin_unlock(&kvm->mmu_lock);

        return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);

static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
        trace_kvm_mmu_unsync_page(sp);
        ++vcpu->kvm->stat.mmu_unsync;
        sp->unsync = 1;

        kvm_mmu_mark_parents_unsync(sp);
}

static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
                                   bool can_unsync)
{
        struct kvm_mmu_page *sp;

        if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
                return true;

        for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
                if (!can_unsync)
                        return true;

                if (sp->unsync)
                        continue;

                WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
                kvm_unsync_page(vcpu, sp);
        }

        return false;
}

static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
        if (pfn_valid(pfn))
                return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));

        return true;
}

static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
                    unsigned pte_access, int level,
                    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
                    bool can_unsync, bool host_writable)
{
        u64 spte = 0;
        int ret = 0;

        if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
                return 0;

        /*
         * For the EPT case, shadow_present_mask is 0 if hardware
         * supports exec-only page table entries.  In that case,
         * ACC_USER_MASK and shadow_user_mask are used to represent
         * read access.  See FNAME(gpte_access) in paging_tmpl.h.
         */
        spte |= shadow_present_mask;
        if (!speculative)
                spte |= shadow_accessed_mask;

        if (pte_access & ACC_EXEC_MASK)
                spte |= shadow_x_mask;
        else
                spte |= shadow_nx_mask;

        if (pte_access & ACC_USER_MASK)
                spte |= shadow_user_mask;

        if (level > PT_PAGE_TABLE_LEVEL)
                spte |= PT_PAGE_SIZE_MASK;
        if (tdp_enabled)
                spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
                        kvm_is_mmio_pfn(pfn));

        if (host_writable)
                spte |= SPTE_HOST_WRITEABLE;
        else
                pte_access &= ~ACC_WRITE_MASK;

        spte |= (u64)pfn << PAGE_SHIFT;

        if (pte_access & ACC_WRITE_MASK) {

                /*
                 * Other vcpu creates new sp in the window between
                 * mapping_level() and acquiring mmu-lock. We can
                 * allow guest to retry the access, the mapping can
                 * be fixed if guest refault.
                 */
                if (level > PT_PAGE_TABLE_LEVEL &&
                    mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
                        goto done;

                spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;

                /*
                 * Optimization: for pte sync, if spte was writable the hash
                 * lookup is unnecessary (and expensive). Write protection
                 * is responsibility of mmu_get_page / kvm_sync_page.
                 * Same reasoning can be applied to dirty page accounting.
                 */
                if (!can_unsync && is_writable_pte(*sptep))
                        goto set_pte;

                if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
                        pgprintk("%s: found shadow page for %llx, marking ro\n",
                                 __func__, gfn);
                        ret = 1;
                        pte_access &= ~ACC_WRITE_MASK;
                        spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
                }
        }

        if (pte_access & ACC_WRITE_MASK) {
                kvm_vcpu_mark_page_dirty(vcpu, gfn);
                spte |= shadow_dirty_mask;
        }

set_pte:
        if (mmu_spte_update(sptep, spte))
                kvm_flush_remote_tlbs(vcpu->kvm);
done:
        return ret;
}

static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
                         int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn,
                         bool speculative, bool host_writable)
{
        int was_rmapped = 0;
        int rmap_count;
        bool emulate = false;

        pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
                 *sptep, write_fault, gfn);

        if (is_shadow_present_pte(*sptep)) {
                /*
                 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
                 * the parent of the now unreachable PTE.
                 */
                if (level > PT_PAGE_TABLE_LEVEL &&
                    !is_large_pte(*sptep)) {
                        struct kvm_mmu_page *child;
                        u64 pte = *sptep;

                        child = page_header(pte & PT64_BASE_ADDR_MASK);
                        drop_parent_pte(child, sptep);
                        kvm_flush_remote_tlbs(vcpu->kvm);
                } else if (pfn != spte_to_pfn(*sptep)) {
                        pgprintk("hfn old %llx new %llx\n",
                                 spte_to_pfn(*sptep), pfn);
                        drop_spte(vcpu->kvm, sptep);
                        kvm_flush_remote_tlbs(vcpu->kvm);
                } else
                        was_rmapped = 1;
        }

        if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
              true, host_writable)) {
                if (write_fault)
                        emulate = true;
                kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
        }

        if (unlikely(is_mmio_spte(*sptep)))
                emulate = true;

        pgprintk("%s: setting spte %llx\n", __func__, *sptep);
        pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
                 is_large_pte(*sptep)? "2MB" : "4kB",
                 *sptep & PT_PRESENT_MASK ?"RW":"R", gfn,
                 *sptep, sptep);
        if (!was_rmapped && is_large_pte(*sptep))
                ++vcpu->kvm->stat.lpages;

        if (is_shadow_present_pte(*sptep)) {
                if (!was_rmapped) {
                        rmap_count = rmap_add(vcpu, sptep, gfn);
                        if (rmap_count > RMAP_RECYCLE_THRESHOLD)
                                rmap_recycle(vcpu, sptep, gfn);
                }
        }

        kvm_release_pfn_clean(pfn);

        return emulate;
}

static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
                                     bool no_dirty_log)
{
        struct kvm_memory_slot *slot;

        slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
        if (!slot)
                return KVM_PFN_ERR_FAULT;

        return gfn_to_pfn_memslot_atomic(slot, gfn);
}

static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
                                    struct kvm_mmu_page *sp,
                                    u64 *start, u64 *end)
{
        struct page *pages[PTE_PREFETCH_NUM];
        struct kvm_memory_slot *slot;
        unsigned access = sp->role.access;
        int i, ret;
        gfn_t gfn;

        gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
        slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
        if (!slot)
                return -1;

        ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
        if (ret <= 0)
                return -1;

        for (i = 0; i < ret; i++, gfn++, start++)
                mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
                             page_to_pfn(pages[i]), true, true);

        return 0;
}

static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
                                  struct kvm_mmu_page *sp, u64 *sptep)
{
        u64 *spte, *start = NULL;
        int i;

        WARN_ON(!sp->role.direct);

        i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1);
        spte = sp->spt + i;

        for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
                if (is_shadow_present_pte(*spte) || spte == sptep) {
                        if (!start)
                                continue;
                        if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0)
                                break;
                        start = NULL;
                } else if (!start)
                        start = spte;
        }
}

static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
{
        struct kvm_mmu_page *sp;

        /*
         * Since it's no accessed bit on EPT, it's no way to
         * distinguish between actually accessed translations
         * and prefetched, so disable pte prefetch if EPT is
         * enabled.
         */
        if (!shadow_accessed_mask)
                return;

        sp = page_header(__pa(sptep));
        if (sp->role.level > PT_PAGE_TABLE_LEVEL)
                return;

        __direct_pte_prefetch(vcpu, sp, sptep);
}

static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
                        int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault)
{
        struct kvm_shadow_walk_iterator iterator;
        struct kvm_mmu_page *sp;
        int emulate = 0;
        gfn_t pseudo_gfn;

        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
                return 0;

        for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
                if (iterator.level == level) {
                        emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
                                               write, level, gfn, pfn, prefault,
                                               map_writable);
                        direct_pte_prefetch(vcpu, iterator.sptep);
                        ++vcpu->stat.pf_fixed;
                        break;
                }

                drop_large_spte(vcpu, iterator.sptep);
                if (!is_shadow_present_pte(*iterator.sptep)) {
                        u64 base_addr = iterator.addr;

                        base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
                        pseudo_gfn = base_addr >> PAGE_SHIFT;
                        sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
                                              iterator.level - 1, 1, ACC_ALL);

                        link_shadow_page(vcpu, iterator.sptep, sp);
                }
        }
        return emulate;
}

static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
{
        siginfo_t info;

        info.si_signo   = SIGBUS;
        info.si_errno   = 0;
        info.si_code    = BUS_MCEERR_AR;
        info.si_addr    = (void __user *)address;
        info.si_addr_lsb = PAGE_SHIFT;

        send_sig_info(SIGBUS, &info, tsk);
}

static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
{
        /*
         * Do not cache the mmio info caused by writing the readonly gfn
         * into the spte otherwise read access on readonly gfn also can
         * caused mmio page fault and treat it as mmio access.
         * Return 1 to tell kvm to emulate it.
         */
        if (pfn == KVM_PFN_ERR_RO_FAULT)
                return 1;

        if (pfn == KVM_PFN_ERR_HWPOISON) {
                kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
                return 0;
        }

        return -EFAULT;
}

static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
                                        gfn_t *gfnp, kvm_pfn_t *pfnp,
                                        int *levelp)
{
        kvm_pfn_t pfn = *pfnp;
        gfn_t gfn = *gfnp;
        int level = *levelp;

        /*
         * Check if it's a transparent hugepage. If this would be an
         * hugetlbfs page, level wouldn't be set to
         * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
         * here.
         */
        if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
            level == PT_PAGE_TABLE_LEVEL &&
            PageTransCompoundMap(pfn_to_page(pfn)) &&
            !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
                unsigned long mask;
                /*
                 * mmu_notifier_retry was successful and we hold the
                 * mmu_lock here, so the pmd can't become splitting
                 * from under us, and in turn
                 * __split_huge_page_refcount() can't run from under
                 * us and we can safely transfer the refcount from
                 * PG_tail to PG_head as we switch the pfn to tail to
                 * head.
                 */
                *levelp = level = PT_DIRECTORY_LEVEL;
                mask = KVM_PAGES_PER_HPAGE(level) - 1;
                VM_BUG_ON((gfn & mask) != (pfn & mask));
                if (pfn & mask) {
                        gfn &= ~mask;
                        *gfnp = gfn;
                        kvm_release_pfn_clean(pfn);
                        pfn &= ~mask;
                        kvm_get_pfn(pfn);
                        *pfnp = pfn;
                }
        }
}

static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
                                kvm_pfn_t pfn, unsigned access, int *ret_val)
{
        /* The pfn is invalid, report the error! */
        if (unlikely(is_error_pfn(pfn))) {
                *ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
                return true;
        }

        if (unlikely(is_noslot_pfn(pfn)))
                vcpu_cache_mmio_info(vcpu, gva, gfn, access);

        return false;
}

static bool page_fault_can_be_fast(u32 error_code)
{
        /*
         * Do not fix the mmio spte with invalid generation number which
         * need to be updated by slow page fault path.
         */
        if (unlikely(error_code & PFERR_RSVD_MASK))
                return false;

        /*
         * #PF can be fast only if the shadow page table is present and it
         * is caused by write-protect, that means we just need change the
         * W bit of the spte which can be done out of mmu-lock.
         */
        if (!(error_code & PFERR_PRESENT_MASK) ||
              !(error_code & PFERR_WRITE_MASK))
                return false;

        return true;
}

static bool
fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                        u64 *sptep, u64 spte)
{
        gfn_t gfn;

        WARN_ON(!sp->role.direct);

        /*
         * The gfn of direct spte is stable since it is calculated
         * by sp->gfn.
         */
        gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);

        /*
         * Theoretically we could also set dirty bit (and flush TLB) here in
         * order to eliminate unnecessary PML logging. See comments in
         * set_spte. But fast_page_fault is very unlikely to happen with PML
         * enabled, so we do not do this. This might result in the same GPA
         * to be logged in PML buffer again when the write really happens, and
         * eventually to be called by mark_page_dirty twice. But it's also no
         * harm. This also avoids the TLB flush needed after setting dirty bit
         * so non-PML cases won't be impacted.
         *
         * Compare with set_spte where instead shadow_dirty_mask is set.
         */
        if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte)
                kvm_vcpu_mark_page_dirty(vcpu, gfn);

        return true;
}

/*
 * Return value:
 * - true: let the vcpu to access on the same address again.
 * - false: let the real page fault path to fix it.
 */
static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
                            u32 error_code)
{
        struct kvm_shadow_walk_iterator iterator;
        struct kvm_mmu_page *sp;
        bool ret = false;
        u64 spte = 0ull;

        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
                return false;

        if (!page_fault_can_be_fast(error_code))
                return false;

        walk_shadow_page_lockless_begin(vcpu);
        for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
                if (!is_shadow_present_pte(spte) || iterator.level < level)
                        break;

        /*
         * If the mapping has been changed, let the vcpu fault on the
         * same address again.
         */
        if (!is_shadow_present_pte(spte)) {
                ret = true;
                goto exit;
        }

        sp = page_header(__pa(iterator.sptep));
        if (!is_last_spte(spte, sp->role.level))
                goto exit;

        /*
         * Check if it is a spurious fault caused by TLB lazily flushed.
         *
         * Need not check the access of upper level table entries since
         * they are always ACC_ALL.
         */
         if (is_writable_pte(spte)) {
                ret = true;
                goto exit;
        }

        /*
         * Currently, to simplify the code, only the spte write-protected
         * by dirty-log can be fast fixed.
         */
        if (!spte_is_locklessly_modifiable(spte))
                goto exit;

        /*
         * Do not fix write-permission on the large spte since we only dirty
         * the first page into the dirty-bitmap in fast_pf_fix_direct_spte()
         * that means other pages are missed if its slot is dirty-logged.
         *
         * Instead, we let the slow page fault path create a normal spte to
         * fix the access.
         *
         * See the comments in kvm_arch_commit_memory_region().
         */
        if (sp->role.level > PT_PAGE_TABLE_LEVEL)
                goto exit;

        /*
         * Currently, fast page fault only works for direct mapping since
         * the gfn is not stable for indirect shadow page.
         * See Documentation/virtual/kvm/locking.txt to get more detail.
         */
        ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte);
exit:
        trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
                              spte, ret);