/*
 * 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.
 *
 * 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 "vmx.h"
#include "mmu.h"

#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>

#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.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;

#undef MMU_DEBUG

#undef AUDIT

#ifdef AUDIT
static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg);
#else
static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
#endif

#ifdef MMU_DEBUG

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

#else

#define pgprintk(x...) do { } while (0)
#define rmap_printk(x...) do { } while (0)

#endif

#if defined(MMU_DEBUG) || defined(AUDIT)
static int dbg = 0;
module_param(dbg, bool, 0644);
#endif

static int oos_shadow = 1;
module_param(oos_shadow, bool, 0644);

#ifndef MMU_DEBUG
#define ASSERT(x) do { } while (0)
#else
#define ASSERT(x)                                                       \
        if (!(x)) {                                                     \
                printk(KERN_WARNING "assertion failed %s:%d: %s\n",     \
                       __FILE__, __LINE__, #x);                         \
        }
#endif

#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52

#define VALID_PAGE(x) ((x) != INVALID_PAGE)

#define PT64_LEVEL_BITS 9

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

#define PT64_LEVEL_MASK(level) \
                (((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level))

#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_LEVEL_MASK(level) \
                (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level))

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

#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
                        | PT64_NX_MASK)

#define PFERR_PRESENT_MASK (1U << 0)
#define PFERR_WRITE_MASK (1U << 1)
#define PFERR_USER_MASK (1U << 2)
#define PFERR_FETCH_MASK (1U << 4)

#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1

#define RMAP_EXT 4

#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)

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

struct kvm_rmap_desc {
        u64 *shadow_ptes[RMAP_EXT];
        struct kvm_rmap_desc *more;
};

struct kvm_shadow_walk {
        int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu,
                     u64 addr, u64 *spte, int level);
};

struct kvm_unsync_walk {
        int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
};

typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp);

static struct kmem_cache *pte_chain_cache;
static struct kmem_cache *rmap_desc_cache;
static struct kmem_cache *mmu_page_header_cache;

static u64 __read_mostly shadow_trap_nonpresent_pte;
static u64 __read_mostly shadow_notrap_nonpresent_pte;
static u64 __read_mostly shadow_base_present_pte;
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;

void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
{
        shadow_trap_nonpresent_pte = trap_pte;
        shadow_notrap_nonpresent_pte = notrap_pte;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);

void kvm_mmu_set_base_ptes(u64 base_pte)
{
        shadow_base_present_pte = base_pte;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);

void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
                u64 dirty_mask, u64 nx_mask, u64 x_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;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);

static int is_write_protection(struct kvm_vcpu *vcpu)
{
        return vcpu->arch.cr0 & X86_CR0_WP;
}

static int is_cpuid_PSE36(void)
{
        return 1;
}

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

static int is_present_pte(unsigned long pte)
{
        return pte & PT_PRESENT_MASK;
}

static int is_shadow_present_pte(u64 pte)
{
        return pte != shadow_trap_nonpresent_pte
                && pte != shadow_notrap_nonpresent_pte;
}

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

static int is_writeble_pte(unsigned long pte)
{
        return pte & PT_WRITABLE_MASK;
}

static int is_dirty_pte(unsigned long pte)
{
        return pte & shadow_dirty_mask;
}

static int is_rmap_pte(u64 pte)
{
        return is_shadow_present_pte(pte);
}

static 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;
}

static void set_shadow_pte(u64 *sptep, u64 spte)
{
#ifdef CONFIG_X86_64
        set_64bit((unsigned long *)sptep, spte);
#else
        set_64bit((unsigned long long *)sptep, spte);
#endif
}

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 void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
{
        while (mc->nobjs)
                kfree(mc->objects[--mc->nobjs]);
}

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

        if (cache->nobjs >= min)
                return 0;
        while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
                page = alloc_page(GFP_KERNEL);
                if (!page)
                        return -ENOMEM;
                set_page_private(page, 0);
                cache->objects[cache->nobjs++] = page_address(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_chain_cache,
                                   pte_chain_cache, 4);
        if (r)
                goto out;
        r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache,
                                   rmap_desc_cache, 4);
        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_chain_cache);
        mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache);
        mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache);
        mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
}

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

        BUG_ON(!mc->nobjs);
        p = mc->objects[--mc->nobjs];
        memset(p, 0, size);
        return p;
}

static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu)
{
        return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_chain_cache,
                                      sizeof(struct kvm_pte_chain));
}

static void mmu_free_pte_chain(struct kvm_pte_chain *pc)
{
        kfree(pc);
}

static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu)
{
        return mmu_memory_cache_alloc(&vcpu->arch.mmu_rmap_desc_cache,
                                      sizeof(struct kvm_rmap_desc));
}

static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd)
{
        kfree(rd);
}

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

        idx = (gfn / KVM_PAGES_PER_HPAGE) -
              (slot->base_gfn / KVM_PAGES_PER_HPAGE);
        return &slot->lpage_info[idx].write_count;
}

static void account_shadowed(struct kvm *kvm, gfn_t gfn)
{
        int *write_count;

        write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
        *write_count += 1;
}

static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
{
        int *write_count;

        write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
        *write_count -= 1;
        WARN_ON(*write_count < 0);
}

static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
{
        struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
        int *largepage_idx;

        if (slot) {
                largepage_idx = slot_largepage_idx(gfn, slot);
                return *largepage_idx;
        }

        return 1;
}

static int host_largepage_backed(struct kvm *kvm, gfn_t gfn)
{
        struct vm_area_struct *vma;
        unsigned long addr;
        int ret = 0;

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr))
                return ret;

        down_read(&current->mm->mmap_sem);
        vma = find_vma(current->mm, addr);
        if (vma && is_vm_hugetlb_page(vma))
                ret = 1;
        up_read(&current->mm->mmap_sem);

        return ret;
}

static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
        struct kvm_memory_slot *slot;

        if (has_wrprotected_page(vcpu->kvm, large_gfn))
                return 0;

        if (!host_largepage_backed(vcpu->kvm, large_gfn))
                return 0;

        slot = gfn_to_memslot(vcpu->kvm, large_gfn);
        if (slot && slot->dirty_bitmap)
                return 0;

        return 1;
}

/*
 * Take gfn and return the reverse mapping to it.
 * Note: gfn must be unaliased before this function get called
 */

static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
{
        struct kvm_memory_slot *slot;
        unsigned long idx;

        slot = gfn_to_memslot(kvm, gfn);
        if (!lpage)
                return &slot->rmap[gfn - slot->base_gfn];

        idx = (gfn / KVM_PAGES_PER_HPAGE) -
              (slot->base_gfn / KVM_PAGES_PER_HPAGE);

        return &slot->lpage_info[idx].rmap_pde;
}

/*
 * Reverse mapping data structures:
 *
 * If rmapp bit zero is zero, then rmapp point to the shadw page table entry
 * that points to page_address(page).
 *
 * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
 * containing more mappings.
 */
static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
{
        struct kvm_mmu_page *sp;
        struct kvm_rmap_desc *desc;
        unsigned long *rmapp;
        int i;

        if (!is_rmap_pte(*spte))
                return;
        gfn = unalias_gfn(vcpu->kvm, gfn);
        sp = page_header(__pa(spte));
        sp->gfns[spte - sp->spt] = gfn;
        rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
        if (!*rmapp) {
                rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
                *rmapp = (unsigned long)spte;
        } else if (!(*rmapp & 1)) {
                rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
                desc = mmu_alloc_rmap_desc(vcpu);
                desc->shadow_ptes[0] = (u64 *)*rmapp;
                desc->shadow_ptes[1] = spte;
                *rmapp = (unsigned long)desc | 1;
        } else {
                rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
                desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
                while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
                        desc = desc->more;
                if (desc->shadow_ptes[RMAP_EXT-1]) {
                        desc->more = mmu_alloc_rmap_desc(vcpu);
                        desc = desc->more;
                }
                for (i = 0; desc->shadow_ptes[i]; ++i)
                        ;
                desc->shadow_ptes[i] = spte;
        }
}

static void rmap_desc_remove_entry(unsigned long *rmapp,
                                   struct kvm_rmap_desc *desc,
                                   int i,
                                   struct kvm_rmap_desc *prev_desc)
{
        int j;

        for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j)
                ;
        desc->shadow_ptes[i] = desc->shadow_ptes[j];
        desc->shadow_ptes[j] = NULL;
        if (j != 0)
                return;
        if (!prev_desc && !desc->more)
                *rmapp = (unsigned long)desc->shadow_ptes[0];
        else
                if (prev_desc)
                        prev_desc->more = desc->more;
                else
                        *rmapp = (unsigned long)desc->more | 1;
        mmu_free_rmap_desc(desc);
}

static void rmap_remove(struct kvm *kvm, u64 *spte)
{
        struct kvm_rmap_desc *desc;
        struct kvm_rmap_desc *prev_desc;
        struct kvm_mmu_page *sp;
        pfn_t pfn;
        unsigned long *rmapp;
        int i;

        if (!is_rmap_pte(*spte))
                return;
        sp = page_header(__pa(spte));
        pfn = spte_to_pfn(*spte);
        if (*spte & shadow_accessed_mask)
                kvm_set_pfn_accessed(pfn);
        if (is_writeble_pte(*spte))
                kvm_release_pfn_dirty(pfn);
        else
                kvm_release_pfn_clean(pfn);
        rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
        if (!*rmapp) {
                printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
                BUG();
        } else if (!(*rmapp & 1)) {
                rmap_printk("rmap_remove:  %p %llx 1->0\n", spte, *spte);
                if ((u64 *)*rmapp != spte) {
                        printk(KERN_ERR "rmap_remove:  %p %llx 1->BUG\n",
                               spte, *spte);
                        BUG();
                }
                *rmapp = 0;
        } else {
                rmap_printk("rmap_remove:  %p %llx many->many\n", spte, *spte);
                desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
                prev_desc = NULL;
                while (desc) {
                        for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
                                if (desc->shadow_ptes[i] == spte) {
                                        rmap_desc_remove_entry(rmapp,
                                                               desc, i,
                                                               prev_desc);
                                        return;
                                }
                        prev_desc = desc;
                        desc = desc->more;
                }
                BUG();
        }
}

static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
{
        struct kvm_rmap_desc *desc;
        struct kvm_rmap_desc *prev_desc;
        u64 *prev_spte;
        int i;

        if (!*rmapp)
                return NULL;
        else if (!(*rmapp & 1)) {
                if (!spte)
                        return (u64 *)*rmapp;
                return NULL;
        }
        desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
        prev_desc = NULL;
        prev_spte = NULL;
        while (desc) {
                for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) {
                        if (prev_spte == spte)
                                return desc->shadow_ptes[i];
                        prev_spte = desc->shadow_ptes[i];
                }
                desc = desc->more;
        }
        return NULL;
}

static void rmap_write_protect(struct kvm *kvm, u64 gfn)
{
        unsigned long *rmapp;
        u64 *spte;
        int write_protected = 0;

        gfn = unalias_gfn(kvm, gfn);
        rmapp = gfn_to_rmap(kvm, gfn, 0);

        spte = rmap_next(kvm, rmapp, NULL);
        while (spte) {
                BUG_ON(!spte);
                BUG_ON(!(*spte & PT_PRESENT_MASK));
                rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
                if (is_writeble_pte(*spte)) {
                        set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK);
                        write_protected = 1;
                }
                spte = rmap_next(kvm, rmapp, spte);
        }
        if (write_protected) {
                pfn_t pfn;

                spte = rmap_next(kvm, rmapp, NULL);
                pfn = spte_to_pfn(*spte);
                kvm_set_pfn_dirty(pfn);
        }

        /* check for huge page mappings */
        rmapp = gfn_to_rmap(kvm, gfn, 1);
        spte = rmap_next(kvm, rmapp, NULL);
        while (spte) {
                BUG_ON(!spte);
                BUG_ON(!(*spte & PT_PRESENT_MASK));
                BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
                pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
                if (is_writeble_pte(*spte)) {
                        rmap_remove(kvm, spte);
                        --kvm->stat.lpages;
                        set_shadow_pte(spte, shadow_trap_nonpresent_pte);
                        spte = NULL;
                        write_protected = 1;
                }
                spte = rmap_next(kvm, rmapp, spte);
        }

        if (write_protected)
                kvm_flush_remote_tlbs(kvm);
}

static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
{
        u64 *spte;
        int need_tlb_flush = 0;

        while ((spte = rmap_next(kvm, rmapp, NULL))) {
                BUG_ON(!(*spte & PT_PRESENT_MASK));
                rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
                rmap_remove(kvm, spte);
                set_shadow_pte(spte, shadow_trap_nonpresent_pte);
                need_tlb_flush = 1;
        }
        return need_tlb_flush;
}

static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
                          int (*handler)(struct kvm *kvm, unsigned long *rmapp))
{
        int i;
        int retval = 0;

        /*
         * If mmap_sem isn't taken, we can look the memslots with only
         * the mmu_lock by skipping over the slots with userspace_addr == 0.
         */
        for (i = 0; i < kvm->nmemslots; i++) {
                struct kvm_memory_slot *memslot = &kvm->memslots[i];
                unsigned long start = memslot->userspace_addr;
                unsigned long end;

                /* mmu_lock protects userspace_addr */
                if (!start)
                        continue;

                end = start + (memslot->npages << PAGE_SHIFT);
                if (hva >= start && hva < end) {
                        gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
                        retval |= handler(kvm, &memslot->rmap[gfn_offset]);
                        retval |= handler(kvm,
                                          &memslot->lpage_info[
                                                  gfn_offset /
                                                  KVM_PAGES_PER_HPAGE].rmap_pde);
                }
        }

        return retval;
}

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

static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
{
        u64 *spte;
        int young = 0;

        /* always return old for EPT */
        if (!shadow_accessed_mask)
                return 0;

        spte = rmap_next(kvm, rmapp, NULL);
        while (spte) {
                int _young;
                u64 _spte = *spte;
                BUG_ON(!(_spte & PT_PRESENT_MASK));
                _young = _spte & PT_ACCESSED_MASK;
                if (_young) {
                        young = 1;
                        clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
                }
                spte = rmap_next(kvm, rmapp, spte);
        }
        return young;
}

int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
        return kvm_handle_hva(kvm, hva, kvm_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

static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        ASSERT(is_empty_shadow_page(sp->spt));
        list_del(&sp->link);
        __free_page(virt_to_page(sp->spt));
        __free_page(virt_to_page(sp->gfns));
        kfree(sp);
        ++kvm->arch.n_free_mmu_pages;
}

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

static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
                                               u64 *parent_pte)
{
        struct kvm_mmu_page *sp;

        sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, sizeof *sp);
        sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
        sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
        set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
        list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
        ASSERT(is_empty_shadow_page(sp->spt));
        sp->slot_bitmap = 0;
        sp->multimapped = 0;
        sp->parent_pte = parent_pte;
        --vcpu->kvm->arch.n_free_mmu_pages;
        return sp;
}

static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
                                    struct kvm_mmu_page *sp, u64 *parent_pte)
{
        struct kvm_pte_chain *pte_chain;
        struct hlist_node *node;
        int i;

        if (!parent_pte)
                return;
        if (!sp->multimapped) {
                u64 *old = sp->parent_pte;

                if (!old) {
                        sp->parent_pte = parent_pte;
                        return;
                }
                sp->multimapped = 1;
                pte_chain = mmu_alloc_pte_chain(vcpu);
                INIT_HLIST_HEAD(&sp->parent_ptes);
                hlist_add_head(&pte_chain->link, &sp->parent_ptes);
                pte_chain->parent_ptes[0] = old;
        }
        hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) {
                if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1])
                        continue;
                for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i)
                        if (!pte_chain->parent_ptes[i]) {
                                pte_chain->parent_ptes[i] = parent_pte;
                                return;
                        }
        }
        pte_chain = mmu_alloc_pte_chain(vcpu);
        BUG_ON(!pte_chain);
        hlist_add_head(&pte_chain->link, &sp->parent_ptes);
        pte_chain->parent_ptes[0] = parent_pte;
}

static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
                                       u64 *parent_pte)
{
        struct kvm_pte_chain *pte_chain;
        struct hlist_node *node;
        int i;

        if (!sp->multimapped) {
                BUG_ON(sp->parent_pte != parent_pte);
                sp->parent_pte = NULL;
                return;
        }
        hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
                for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
                        if (!pte_chain->parent_ptes[i])
                                break;
                        if (pte_chain->parent_ptes[i] != parent_pte)
                                continue;
                        while (i + 1 < NR_PTE_CHAIN_ENTRIES
                                && pte_chain->parent_ptes[i + 1]) {
                                pte_chain->parent_ptes[i]
                                        = pte_chain->parent_ptes[i + 1];
                                ++i;
                        }
                        pte_chain->parent_ptes[i] = NULL;
                        if (i == 0) {
                                hlist_del(&pte_chain->link);
                                mmu_free_pte_chain(pte_chain);
                                if (hlist_empty(&sp->parent_ptes)) {
                                        sp->multimapped = 0;
                                        sp->parent_pte = NULL;
                                }
                        }
                        return;
                }
        BUG();
}


static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                            mmu_parent_walk_fn fn)
{
        struct kvm_pte_chain *pte_chain;
        struct hlist_node *node;
        struct kvm_mmu_page *parent_sp;
        int i;

        if (!sp->multimapped && sp->parent_pte) {
                parent_sp = page_header(__pa(sp->parent_pte));
                fn(vcpu, parent_sp);
                mmu_parent_walk(vcpu, parent_sp, fn);
                return;
        }
        hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
                for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
                        if (!pte_chain->parent_ptes[i])
                                break;
                        parent_sp = page_header(__pa(pte_chain->parent_ptes[i]));
                        fn(vcpu, parent_sp);
                        mmu_parent_walk(vcpu, parent_sp, fn);
                }
}

static void kvm_mmu_update_unsync_bitmap(u64 *spte)
{
        unsigned int index;
        struct kvm_mmu_page *sp = page_header(__pa(spte));

        index = spte - sp->spt;
        __set_bit(index, sp->unsync_child_bitmap);
        sp->unsync_children = 1;
}

static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
{
        struct kvm_pte_chain *pte_chain;
        struct hlist_node *node;
        int i;

        if (!sp->parent_pte)
                return;

        if (!sp->multimapped) {
                kvm_mmu_update_unsync_bitmap(sp->parent_pte);
                return;
        }

        hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
                for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) {
                        if (!pte_chain->parent_ptes[i])
                                break;
                        kvm_mmu_update_unsync_bitmap(pte_chain->parent_ptes[i]);
                }
}

static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
        sp->unsync_children = 1;
        kvm_mmu_update_parents_unsync(sp);
        return 1;
}

static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu,
                                        struct kvm_mmu_page *sp)
{
        mmu_parent_walk(vcpu, sp, unsync_walk_fn);
        kvm_mmu_update_parents_unsync(sp);
}

static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
                                    struct kvm_mmu_page *sp)
{
        int i;

        for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
                sp->spt[i] = shadow_trap_nonpresent_pte;
}

static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
                               struct kvm_mmu_page *sp)
{
        return 1;
}

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

#define for_each_unsync_children(bitmap, idx)           \
        for (idx = find_first_bit(bitmap, 512);         \
             idx < 512;                                 \
             idx = find_next_bit(bitmap, 512, idx+1))

static int mmu_unsync_walk(struct kvm_mmu_page *sp,
                           struct kvm_unsync_walk *walker)
{
        int i, ret;

        if (!sp->unsync_children)
                return 0;

        for_each_unsync_children(sp->unsync_child_bitmap, i) {
                u64 ent = sp->spt[i];

                if (is_shadow_present_pte(ent)) {
                        struct kvm_mmu_page *child;
                        child = page_header(ent & PT64_BASE_ADDR_MASK);

                        if (child->unsync_children) {
                                ret = mmu_unsync_walk(child, walker);
                                if (ret)
                                        return ret;
                                __clear_bit(i, sp->unsync_child_bitmap);
                        }

                        if (child->unsync) {
                                ret = walker->entry(child, walker);
                                __clear_bit(i, sp->unsync_child_bitmap);
                                if (ret)
                                        return ret;
                        }
                }
        }

        if (find_first_bit(sp->unsync_child_bitmap, 512) == 512)
                sp->unsync_children = 0;

        return 0;
}

static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
{
        unsigned index;
        struct hlist_head *bucket;
        struct kvm_mmu_page *sp;
        struct hlist_node *node;

        pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
        index = kvm_page_table_hashfn(gfn);
        bucket = &kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry(sp, node, bucket, hash_link)
                if (sp->gfn == gfn && !sp->role.metaphysical
                    && !sp->role.invalid) {
                        pgprintk("%s: found role %x\n",
                                 __func__, sp->role.word);
                        return sp;
                }
        return NULL;
}

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

static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp);

static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
        if (sp->role.glevels != vcpu->arch.mmu.root_level) {
                kvm_mmu_zap_page(vcpu->kvm, sp);
                return 1;
        }

        rmap_write_protect(vcpu->kvm, sp->gfn);
        kvm_unlink_unsync_page(vcpu->kvm, sp);
        if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
                kvm_mmu_zap_page(vcpu->kvm, sp);
                return 1;
        }

        kvm_mmu_flush_tlb(vcpu);
        return 0;
}

struct sync_walker {
        struct kvm_vcpu *vcpu;
        struct kvm_unsync_walk walker;
};

static int mmu_sync_fn(struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk)
{
        struct sync_walker *sync_walk = container_of(walk, struct sync_walker,
                                                     walker);
        struct kvm_vcpu *vcpu = sync_walk->vcpu;

        kvm_sync_page(vcpu, sp);
        return (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock));
}

static void mmu_sync_children(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
        struct sync_walker walker = {
                .walker = { .entry = mmu_sync_fn, },
                .vcpu = vcpu,
        };

        while (mmu_unsync_walk(sp, &walker.walker))
                cond_resched_lock(&vcpu->kvm->mmu_lock);
}

static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
                                             gfn_t gfn,
                                             gva_t gaddr,
                                             unsigned level,
                                             int metaphysical,
                                             unsigned access,
                                             u64 *parent_pte)
{
        union kvm_mmu_page_role role;
        unsigned index;
        unsigned quadrant;
        struct hlist_head *bucket;
        struct kvm_mmu_page *sp;
        struct hlist_node *node, *tmp;

        role.word = 0;
        role.glevels = vcpu->arch.mmu.root_level;
        role.level = level;
        role.metaphysical = metaphysical;
        role.access = access;
        if (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;
        }
        pgprintk("%s: looking gfn %lx role %x\n", __func__,
                 gfn, role.word);
        index = kvm_page_table_hashfn(gfn);
        bucket = &vcpu->kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry_safe(sp, node, tmp, bucket, hash_link)
                if (sp->gfn == gfn) {
                        if (sp->unsync)
                                if (kvm_sync_page(vcpu, sp))
                                        continue;

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

                        mmu_page_add_parent_pte(vcpu, sp, parent_pte);
                        if (sp->unsync_children) {
                                set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
                                kvm_mmu_mark_parents_unsync(vcpu, sp);
                        }
                        pgprintk("%s: found\n", __func__);
                        return sp;
                }
        ++vcpu->kvm->stat.mmu_cache_miss;
        sp = kvm_mmu_alloc_page(vcpu, parent_pte);
        if (!sp)
                return sp;
        pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
        sp->gfn = gfn;
        sp->role = role;
        hlist_add_head(&sp->hash_link, bucket);
        if (!metaphysical) {
                rmap_write_protect(vcpu->kvm, gfn);
                account_shadowed(vcpu->kvm, gfn);
        }
        if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte)
                vcpu->arch.mmu.prefetch_page(vcpu, sp);
        else
                nonpaging_prefetch_page(vcpu, sp);
        return sp;
}

static int walk_shadow(struct kvm_shadow_walk *walker,
                       struct kvm_vcpu *vcpu, u64 addr)
{
        hpa_t shadow_addr;
        int level;
        int r;
        u64 *sptep;
        unsigned index;

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

        while (level >= PT_PAGE_TABLE_LEVEL) {
                index = SHADOW_PT_INDEX(addr, level);
                sptep = ((u64 *)__va(shadow_addr)) + index;
                r = walker->entry(walker, vcpu, addr, sptep, level);
                if (r)
                        return r;
                shadow_addr = *sptep & PT64_BASE_ADDR_MASK;
                --level;
        }
        return 0;
}

static void kvm_mmu_page_unlink_children(struct kvm *kvm,
                                         struct kvm_mmu_page *sp)
{
        unsigned i;
        u64 *pt;
        u64 ent;

        pt = sp->spt;

        if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
                for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
                        if (is_shadow_present_pte(pt[i]))
                                rmap_remove(kvm, &pt[i]);
                        pt[i] = shadow_trap_nonpresent_pte;
                }
                return;
        }

        for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
                ent = pt[i];

                if (is_shadow_present_pte(ent)) {
                        if (!is_large_pte(ent)) {
                                ent &= PT64_BASE_ADDR_MASK;
                                mmu_page_remove_parent_pte(page_header(ent),
                                                           &pt[i]);
                        } else {
                                --kvm->stat.lpages;
                                rmap_remove(kvm, &pt[i]);
                        }
                }
                pt[i] = shadow_trap_nonpresent_pte;
        }
}

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

static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm)
{
        int i;

        for (i = 0; i < KVM_MAX_VCPUS; ++i)
                if (kvm->vcpus[i])
                        kvm->vcpus[i]->arch.last_pte_updated = NULL;
}

static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        u64 *parent_pte;

        while (sp->multimapped || sp->parent_pte) {
                if (!sp->multimapped)
                        parent_pte = sp->parent_pte;
                else {
                        struct kvm_pte_chain *chain;

                        chain = container_of(sp->parent_ptes.first,
                                             struct kvm_pte_chain, link);
                        parent_pte = chain->parent_ptes[0];
                }
                BUG_ON(!parent_pte);
                kvm_mmu_put_page(sp, parent_pte);
                set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte);
        }
}

struct zap_walker {
        struct kvm_unsync_walk walker;
        struct kvm *kvm;
        int zapped;
};

static int mmu_zap_fn(struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk)
{
        struct zap_walker *zap_walk = container_of(walk, struct zap_walker,
                                                     walker);
        kvm_mmu_zap_page(zap_walk->kvm, sp);
        zap_walk->zapped = 1;
        return 0;
}

static int mmu_zap_unsync_children(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        struct zap_walker walker = {
                .walker = { .entry = mmu_zap_fn, },
                .kvm = kvm,
                .zapped = 0,
        };

        if (sp->role.level == PT_PAGE_TABLE_LEVEL)
                return 0;
        mmu_unsync_walk(sp, &walker.walker);
        return walker.zapped;
}

static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
        int ret;
        ++kvm->stat.mmu_shadow_zapped;
        ret = mmu_zap_unsync_children(kvm, sp);
        kvm_mmu_page_unlink_children(kvm, sp);
        kvm_mmu_unlink_parents(kvm, sp);
        kvm_flush_remote_tlbs(kvm);
        if (!sp->role.invalid && !sp->role.metaphysical)
                unaccount_shadowed(kvm, sp->gfn);
        if (sp->unsync)
                kvm_unlink_unsync_page(kvm, sp);
        if (!sp->root_count) {
                hlist_del(&sp->hash_link);
                kvm_mmu_free_page(kvm, sp);
        } else {
                sp->role.invalid = 1;
                list_move(&sp->link, &kvm->arch.active_mmu_pages);
                kvm_reload_remote_mmus(kvm);
        }
        kvm_mmu_reset_last_pte_updated(kvm);
        return ret;
}

/*
 * Changing the number of mmu pages allocated to the vm
 * Note: if kvm_nr_mmu_pages is too small, you will get dead lock
 */
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
{
        /*
         * If we set the number of mmu pages to be smaller be than the
         * number of actived pages , we must to free some mmu pages before we
         * change the value
         */

        if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) >
            kvm_nr_mmu_pages) {
                int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages
                                       - kvm->arch.n_free_mmu_pages;

                while (n_used_mmu_pages > kvm_nr_mmu_pages) {
                        struct kvm_mmu_page *page;

                        page = container_of(kvm->arch.active_mmu_pages.prev,
                                            struct kvm_mmu_page, link);
                        kvm_mmu_zap_page(kvm, page);
                        n_used_mmu_pages--;
                }
                kvm->arch.n_free_mmu_pages = 0;
        }
        else
                kvm->arch.n_free_mmu_pages += kvm_nr_mmu_pages
                                         - kvm->arch.n_alloc_mmu_pages;

        kvm->arch.n_alloc_mmu_pages = kvm_nr_mmu_pages;
}

static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
{
        unsigned index;
        struct hlist_head *bucket;
        struct kvm_mmu_page *sp;
        struct hlist_node *node, *n;
        int r;

        pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
        r = 0;
        index = kvm_page_table_hashfn(gfn);
        bucket = &kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
                if (sp->gfn == gfn && !sp->role.metaphysical) {
                        pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
                                 sp->role.word);
                        r = 1;
                        if (kvm_mmu_zap_page(kvm, sp))
                                n = bucket->first;
                }
        return r;
}

static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
{
        struct kvm_mmu_page *sp;

        while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
                pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
                kvm_mmu_zap_page(kvm, sp);
        }
}

static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
{
        int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
        struct kvm_mmu_page *sp = page_header(__pa(pte));

        __set_bit(slot, &sp->slot_bitmap);
}

static void mmu_convert_notrap(struct kvm_mmu_page *sp)
{
        int i;
        u64 *pt = sp->spt;

        if (shadow_trap_nonpresent_pte == shadow_notrap_nonpresent_pte)
                return;

        for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
                if (pt[i] == shadow_notrap_nonpresent_pte)
                        set_shadow_pte(&pt[i], shadow_trap_nonpresent_pte);
        }
}

struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
{
        struct page *page;

        gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);

        if (gpa == UNMAPPED_GVA)
                return NULL;

        page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);

        return page;
}

static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
        unsigned index;
        struct hlist_head *bucket;
        struct kvm_mmu_page *s;
        struct hlist_node *node, *n;

        index = kvm_page_table_hashfn(sp->gfn);
        bucket = &vcpu->kvm->arch.mmu_page_hash[index];
        /* don't unsync if pagetable is shadowed with multiple roles */
        hlist_for_each_entry_safe(s, node, n, bucket, hash_link) {
                if (s->gfn != sp->gfn || s->role.metaphysical)
                        continue;
                if (s->role.word != sp->role.word)
                        return 1;
        }
        kvm_mmu_mark_parents_unsync(vcpu, sp);
        ++vcpu->kvm->stat.mmu_unsync;
        sp->unsync = 1;
        mmu_convert_notrap(sp);
        return 0;
}

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

        shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
        if (shadow) {
                if (shadow->role.level != PT_PAGE_TABLE_LEVEL)
                        return 1;
                if (shadow->unsync)
                        return 0;
                if (can_unsync && oos_shadow)
                        return kvm_unsync_page(vcpu, shadow);
                return 1;
        }
        return 0;
}

static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                    unsigned pte_access, int user_fault,
                    int write_fault, int dirty, int largepage,
                    gfn_t gfn, pfn_t pfn, bool speculative,
                    bool can_unsync)
{
        u64 spte;
        int ret = 0;
        /*
         * We don't set the accessed bit, since we sometimes want to see
         * whether the guest actually used the pte (in order to detect
         * demand paging).
         */
        spte = shadow_base_present_pte | shadow_dirty_mask;
        if (!speculative)
                spte |= shadow_accessed_mask;
        if (!dirty)
                pte_access &= ~ACC_WRITE_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 (largepage)
                spte |= PT_PAGE_SIZE_MASK;

        spte |= (u64)pfn << PAGE_SHIFT;

        if ((pte_access & ACC_WRITE_MASK)
            || (write_fault && !is_write_protection(vcpu) && !user_fault)) {

                if (largepage && has_wrprotected_page(vcpu->kvm, gfn)) {
                        ret = 1;
                        spte = shadow_trap_nonpresent_pte;
                        goto set_pte;
                }

                spte |= PT_WRITABLE_MASK;

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

        if (pte_access & ACC_WRITE_MASK)
                mark_page_dirty(vcpu->kvm, gfn);

set_pte:
        set_shadow_pte(shadow_pte, spte);
        return ret;
}

static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                         unsigned pt_access, unsigned pte_access,
                         int user_fault, int write_fault, int dirty,
                         int *ptwrite, int largepage, gfn_t gfn,
                         pfn_t pfn, bool speculative)
{
        int was_rmapped = 0;
        int was_writeble = is_writeble_pte(*shadow_pte);

        pgprintk("%s: spte %llx access %x write_fault %d"
                 " user_fault %d gfn %lx\n",
                 __func__, *shadow_pte, pt_access,
                 write_fault, user_fault, gfn);

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

                        child = page_header(pte & PT64_BASE_ADDR_MASK);
                        mmu_page_remove_parent_pte(child, shadow_pte);
                } else if (pfn != spte_to_pfn(*shadow_pte)) {
                        pgprintk("hfn old %lx new %lx\n",
                                 spte_to_pfn(*shadow_pte), pfn);
                        rmap_remove(vcpu->kvm, shadow_pte);
                } else {
                        if (largepage)
                                was_rmapped = is_large_pte(*shadow_pte);
                        else
                                was_rmapped = 1;
                }
        }
        if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
                      dirty, largepage, gfn, pfn, speculative, true)) {
                if (write_fault)
                        *ptwrite = 1;
                kvm_x86_ops->tlb_flush(vcpu);
        }

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

        page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
        if (!was_rmapped) {
                rmap_add(vcpu, shadow_pte, gfn, largepage);
                if (!is_rmap_pte(*shadow_pte))
                        kvm_release_pfn_clean(pfn);
        } else {
                if (was_writeble)
                        kvm_release_pfn_dirty(pfn);
                else
                        kvm_release_pfn_clean(pfn);
        }
        if (speculative) {
                vcpu->arch.last_pte_updated = shadow_pte;
                vcpu->arch.last_pte_gfn = gfn;
        }
}

static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
{
}

struct direct_shadow_walk {
        struct kvm_shadow_walk walker;
        pfn_t pfn;
        int write;
        int largepage;
        int pt_write;
};

static int direct_map_entry(struct kvm_shadow_walk *_walk,
                            struct kvm_vcpu *vcpu,
                            u64 addr, u64 *sptep, int level)
{
        struct direct_shadow_walk *walk =
                container_of(_walk, struct direct_shadow_walk, walker);
        struct kvm_mmu_page *sp;
        gfn_t pseudo_gfn;
        gfn_t gfn = addr >> PAGE_SHIFT;

        if (level == PT_PAGE_TABLE_LEVEL
            || (walk->largepage && level == PT_DIRECTORY_LEVEL)) {
                mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL,
                             0, walk->write, 1, &walk->pt_write,
                             walk->largepage, gfn, walk->pfn, false);
                ++vcpu->stat.pf_fixed;
                return 1;
        }

        if (*sptep == shadow_trap_nonpresent_pte) {
                pseudo_gfn = (addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
                sp = kvm_mmu_get_page(vcpu, pseudo_gfn, (gva_t)addr, level - 1,
                                      1, ACC_ALL, sptep);
                if (!sp) {
                        pgprintk("nonpaging_map: ENOMEM\n");
                        kvm_release_pfn_clean(walk->pfn);
                        return -ENOMEM;
                }

                set_shadow_pte(sptep,
                               __pa(sp->spt)
                               | PT_PRESENT_MASK | PT_WRITABLE_MASK
                               | shadow_user_mask | shadow_x_mask);
        }
        return 0;
}

static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
                        int largepage, gfn_t gfn, pfn_t pfn)
{
        int r;
        struct direct_shadow_walk walker = {
                .walker = { .entry = direct_map_entry, },
                .pfn = pfn,
                .largepage = largepage,
                .write = write,
                .pt_write = 0,
        };

        r = walk_shadow(&walker.walker, vcpu, gfn << PAGE_SHIFT);
        if (r < 0)
                return r;
        return walker.pt_write;
}

static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
{
        int r;
        int largepage = 0;
        pfn_t pfn;
        unsigned long mmu_seq;

        if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
                gfn &= ~(KVM_PAGES_PER_HPAGE-1);
                largepage = 1;
        }

        mmu_seq = vcpu->kvm->mmu_notifier_seq;
        smp_rmb();
        pfn = gfn_to_pfn(vcpu->kvm, gfn);

        /* mmio */
        if (is_error_pfn(pfn)) {
                kvm_release_pfn_clean(pfn);
                return 1;
        }

        spin_lock(&vcpu->kvm->mmu_lock);
        if (mmu_notifier_retry(vcpu, mmu_seq))
                goto out_unlock;
        kvm_mmu_free_some_pages(vcpu);
        r = __direct_map(vcpu, v, write, largepage, gfn, pfn);
        spin_unlock(&vcpu->kvm->mmu_lock);


        return r;

out_unlock:
        spin_unlock(&vcpu->kvm->mmu_lock);
        kvm_release_pfn_clean(pfn);
        return 0;
}


static void mmu_free_roots(struct kvm_vcpu *vcpu)
{
        int i;
        struct kvm_mmu_page *sp;

        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
                return;
        spin_lock(&vcpu->kvm->mmu_lock);
        if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
                hpa_t root = vcpu->arch.mmu.root_hpa;

                sp = page_header(root);
                --sp->root_count;
                if (!sp->root_count && sp->role.invalid)
                        kvm_mmu_zap_page(vcpu->kvm, sp);
                vcpu->arch.mmu.root_hpa = INVALID_PAGE;
                spin_unlock(&vcpu->kvm->mmu_lock);
                return;
        }
        for (i = 0; i < 4; ++i) {
                hpa_t root = vcpu->arch.mmu.pae_root[i];

                if (root) {
                        root &= PT64_BASE_ADDR_MASK;
                        sp = page_header(root);
                        --sp->root_count;
                        if (!sp->root_count && sp->role.invalid)
                                kvm_mmu_zap_page(vcpu->kvm, sp);
                }
                vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
        }
        spin_unlock(&vcpu->kvm->mmu_lock);
        vcpu->arch.mmu.root_hpa = INVALID_PAGE;
}

static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
        int i;
        gfn_t root_gfn;
        struct kvm_mmu_page *sp;
        int metaphysical = 0;

        root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;

        if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
                hpa_t root = vcpu->arch.mmu.root_hpa;

                ASSERT(!VALID_PAGE(root));
                if (tdp_enabled)
                        metaphysical = 1;
                sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
                                      PT64_ROOT_LEVEL, metaphysical,
                                      ACC_ALL, NULL);
                root = __pa(sp->spt);
                ++sp->root_count;
                vcpu->arch.mmu.root_hpa = root;
                return;
        }
        metaphysical = !is_paging(vcpu);
        if (tdp_enabled)
                metaphysical = 1;
        for (i = 0; i < 4; ++i) {
                hpa_t root = vcpu->arch.mmu.pae_root[i];

                ASSERT(!VALID_PAGE(root));
                if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
                        if (!is_present_pte(vcpu->arch.pdptrs[i])) {
                                vcpu->arch.mmu.pae_root[i] = 0;
                                continue;
                        }
                        root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT;
                } else if (vcpu->arch.mmu.root_level == 0)
                        root_gfn = 0;
                sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
                                      PT32_ROOT_LEVEL, metaphysical,
                                      ACC_ALL, NULL);
                root = __pa(sp->spt);
                ++sp->root_count;
                vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
        }
        vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
}

static void mmu_sync_roots(struct kvm_vcpu *vcpu)
{
        int i;
        struct kvm_mmu_page *sp;

        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
                return;
        if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
                hpa_t root = vcpu->arch.mmu.root_hpa;
                sp = page_header(root);
                mmu_sync_children(vcpu, sp);
                return;
        }
        for (i = 0; i < 4; ++i) {
                hpa_t root = vcpu->arch.mmu.pae_root[i];

                if (root) {
                        root &= PT64_BASE_ADDR_MASK;
                        sp = page_header(root);
                        mmu_sync_children(vcpu, sp);
                }
        }
}

void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
        spin_lock(&vcpu->kvm->mmu_lock);
        mmu_sync_roots(vcpu);
        spin_unlock(&vcpu->kvm->mmu_lock);
}

static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
{
        return vaddr;
}

static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
                                u32 error_code)
{
        gfn_t gfn;
        int r;

        pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
        r = mmu_topup_memory_caches(vcpu);
        if (r)
                return r;

        ASSERT(vcpu);
        ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));

        gfn = gva >> PAGE_SHIFT;

        return nonpaging_map(vcpu, gva & PAGE_MASK,
                             error_code & PFERR_WRITE_MASK, gfn);
}

static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
                                u32 error_code)
{
        pfn_t pfn;
        int r;
        int largepage = 0;
        gfn_t gfn = gpa >> PAGE_SHIFT;
        unsigned long mmu_seq;

        ASSERT(vcpu);
        ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));

        r = mmu_topup_memory_caches(vcpu);
        if (r)
                return r;

        if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
                gfn &= ~(KVM_PAGES_PER_HPAGE-1);
                largepage = 1;
        }
        mmu_seq = vcpu->kvm->mmu_notifier_seq;
        smp_rmb();
        pfn = gfn_to_pfn(vcpu->kvm, gfn);
        if (is_error_pfn(pfn)) {
                kvm_release_pfn_clean(pfn);
                return 1;
        }
        spin_lock(&vcpu->kvm->mmu_lock);
        if (mmu_notifier_retry(vcpu, mmu_seq))
                goto out_unlock;
        kvm_mmu_free_some_pages(vcpu);
        r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
                         largepage, gfn, pfn);
        spin_unlock(&vcpu->kvm->mmu_lock);

        return r;

out_unlock:
        spin_unlock(&vcpu->kvm->mmu_lock);
        kvm_release_pfn_clean(pfn);
        return 0;
}

static void nonpaging_free(struct kvm_vcpu *vcpu)
{
        mmu_free_roots(vcpu);
}

static int nonpaging_init_context(struct kvm_vcpu *vcpu)
{
        struct kvm_mmu *context = &vcpu->arch.mmu;

        context->new_cr3 = nonpaging_new_cr3;
        context->page_fault = nonpaging_page_fault;
        context->gva_to_gpa = nonpaging_gva_to_gpa;
        context->free = nonpaging_free;
        context->prefetch_page = nonpaging_prefetch_page;
        context->sync_page = nonpaging_sync_page;
        context->invlpg = nonpaging_invlpg;
        context->root_level = 0;
        context->shadow_root_level = PT32E_ROOT_LEVEL;
        context->root_hpa = INVALID_PAGE;
        return 0;
}

void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
        ++vcpu->stat.tlb_flush;
        kvm_x86_ops->tlb_flush(vcpu);
}

static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
        pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3);
        mmu_free_roots(vcpu);
}

static void inject_page_fault(struct kvm_vcpu *vcpu,
                              u64 addr,
                              u32 err_code)
{
        kvm_inject_page_fault(vcpu, addr, err_code);
}

static void paging_free(struct kvm_vcpu *vcpu)
{
        nonpaging_free(vcpu);
}

#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE

#define PTTYPE 32
#include "paging_tmpl.h"
#undef PTTYPE

static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
{
        struct kvm_mmu *context = &vcpu->arch.mmu;

        ASSERT(is_pae(vcpu));
        context->new_cr3 = paging_new_cr3;
        context->page_fault = paging64_page_fault;
        context->gva_to_gpa = paging64_gva_to_gpa;
        context->prefetch_page = paging64_prefetch_page;
        context->sync_page = paging64_sync_page;
        context->invlpg = paging64_invlpg;
        context->free = paging_free;
        context->root_level = level;
        context->shadow_root_level = level;
        context->root_hpa = INVALID_PAGE;
        return 0;
}

static int paging64_init_context(struct kvm_vcpu *vcpu)
{
        return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
}

static int paging32_init_context(struct kvm_vcpu *vcpu)
{
        struct kvm_mmu *context = &vcpu->arch.mmu;

        context->new_cr3 = paging_new_cr3;
        context->page_fault = paging32_page_fault;
        context->gva_to_gpa = paging32_gva_to_gpa;
        context->free = paging_free;
        context->prefetch_page = paging32_prefetch_page;
        context->sync_page = paging32_sync_page;
        context->invlpg = paging32_invlpg;
        context->root_level = PT32_ROOT_LEVEL;
        context->shadow_root_level = PT32E_ROOT_LEVEL;
        context->root_hpa = INVALID_PAGE;
        return 0;
}

static int paging32E_init_context(struct kvm_vcpu *vcpu)
{
        return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
}

static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
        struct kvm_mmu *context = &vcpu->arch.mmu;

        context->new_cr3 = nonpaging_new_cr3;
        context->page_fault = tdp_page_fault;
        context->free = nonpaging_free;
        context->prefetch_page = nonpaging_prefetch_page;
        context->sync_page = nonpaging_sync_page;
        context->invlpg = nonpaging_invlpg;
        context->shadow_root_level = kvm_x86_ops->get_tdp_level();
        context->root_hpa = INVALID_PAGE;

        if (!is_paging(vcpu)) {
                context->gva_to_gpa = nonpaging_gva_to_gpa;
                context->root_level = 0;
        } else if (is_long_mode(vcpu)) {
                context->gva_to_gpa = paging64_gva_to_gpa;
                context->root_level = PT64_ROOT_LEVEL;
        } else if (is_pae(vcpu)) {
                context->gva_to_gpa = paging64_gva_to_gpa;
                context->root_level = PT32E_ROOT_LEVEL;
        } else {
                context->gva_to_gpa = paging32_gva_to_gpa;
                context->root_level = PT32_ROOT_LEVEL;
        }

        return 0;
}

static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
        ASSERT(vcpu);
        ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

        if (!is_paging(vcpu))
                return nonpaging_init_context(vcpu);
        else if (is_long_mode(vcpu))
                return paging64_init_context(vcpu);
        else if (is_pae(vcpu))
                return paging32E_init_context(vcpu);
        else
                return paging32_init_context(vcpu);
}

static int init_kvm_mmu(struct kvm_vcpu *vcpu)
{
        vcpu->arch.update_pte.pfn = bad_pfn;

        if (tdp_enabled)
                return init_kvm_tdp_mmu(vcpu);