// SPDX-License-Identifier: GPL-2.0

#include <linux/frame.h>
#include <linux/percpu.h>

#include <asm/debugreg.h>
#include <asm/mmu_context.h>

#include "cpuid.h"
#include "hyperv.h"
#include "mmu.h"
#include "nested.h"
#include "trace.h"
#include "x86.h"

static bool __read_mostly enable_shadow_vmcs = 1;
module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);

static bool __read_mostly nested_early_check = 0;
module_param(nested_early_check, bool, S_IRUGO);

/*
 * Hyper-V requires all of these, so mark them as supported even though
 * they are just treated the same as all-context.
 */
#define VMX_VPID_EXTENT_SUPPORTED_MASK          \
        (VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |  \
        VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |    \
        VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |    \
        VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)

#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5

enum {
        VMX_VMREAD_BITMAP,
        VMX_VMWRITE_BITMAP,
        VMX_BITMAP_NR
};
static unsigned long *vmx_bitmap[VMX_BITMAP_NR];

#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])

struct shadow_vmcs_field {
        u16     encoding;
        u16     offset;
};
static struct shadow_vmcs_field shadow_read_only_fields[] = {
#define SHADOW_FIELD_RO(x, y) { x, offsetof(struct vmcs12, y) },
#include "vmcs_shadow_fields.h"
};
static int max_shadow_read_only_fields =
        ARRAY_SIZE(shadow_read_only_fields);

static struct shadow_vmcs_field shadow_read_write_fields[] = {
#define SHADOW_FIELD_RW(x, y) { x, offsetof(struct vmcs12, y) },
#include "vmcs_shadow_fields.h"
};
static int max_shadow_read_write_fields =
        ARRAY_SIZE(shadow_read_write_fields);

static void init_vmcs_shadow_fields(void)
{
        int i, j;

        memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
        memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);

        for (i = j = 0; i < max_shadow_read_only_fields; i++) {
                struct shadow_vmcs_field entry = shadow_read_only_fields[i];
                u16 field = entry.encoding;

                if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
                    (i + 1 == max_shadow_read_only_fields ||
                     shadow_read_only_fields[i + 1].encoding != field + 1))
                        pr_err("Missing field from shadow_read_only_field %x\n",
                               field + 1);

                clear_bit(field, vmx_vmread_bitmap);
                if (field & 1)
#ifdef CONFIG_X86_64
                        continue;
#else
                        entry.offset += sizeof(u32);
#endif
                shadow_read_only_fields[j++] = entry;
        }
        max_shadow_read_only_fields = j;

        for (i = j = 0; i < max_shadow_read_write_fields; i++) {
                struct shadow_vmcs_field entry = shadow_read_write_fields[i];
                u16 field = entry.encoding;

                if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
                    (i + 1 == max_shadow_read_write_fields ||
                     shadow_read_write_fields[i + 1].encoding != field + 1))
                        pr_err("Missing field from shadow_read_write_field %x\n",
                               field + 1);

                WARN_ONCE(field >= GUEST_ES_AR_BYTES &&
                          field <= GUEST_TR_AR_BYTES,
                          "Update vmcs12_write_any() to drop reserved bits from AR_BYTES");

                /*
                 * PML and the preemption timer can be emulated, but the
                 * processor cannot vmwrite to fields that don't exist
                 * on bare metal.
                 */
                switch (field) {
                case GUEST_PML_INDEX:
                        if (!cpu_has_vmx_pml())
                                continue;
                        break;
                case VMX_PREEMPTION_TIMER_VALUE:
                        if (!cpu_has_vmx_preemption_timer())
                                continue;
                        break;
                case GUEST_INTR_STATUS:
                        if (!cpu_has_vmx_apicv())
                                continue;
                        break;
                default:
                        break;
                }

                clear_bit(field, vmx_vmwrite_bitmap);
                clear_bit(field, vmx_vmread_bitmap);
                if (field & 1)
#ifdef CONFIG_X86_64
                        continue;
#else
                        entry.offset += sizeof(u32);
#endif
                shadow_read_write_fields[j++] = entry;
        }
        max_shadow_read_write_fields = j;
}

/*
 * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
 * set the success or error code of an emulated VMX instruction (as specified
 * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
 * instruction.
 */
static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
{
        vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
                        & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
                            X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
        return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
{
        vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
                        & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
                            X86_EFLAGS_SF | X86_EFLAGS_OF))
                        | X86_EFLAGS_CF);
        return kvm_skip_emulated_instruction(vcpu);
}

static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
                                u32 vm_instruction_error)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        /*
         * failValid writes the error number to the current VMCS, which
         * can't be done if there isn't a current VMCS.
         */
        if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
                return nested_vmx_failInvalid(vcpu);

        vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
                        & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
                            X86_EFLAGS_SF | X86_EFLAGS_OF))
                        | X86_EFLAGS_ZF);
        get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
        /*
         * We don't need to force a shadow sync because
         * VM_INSTRUCTION_ERROR is not shadowed
         */
        return kvm_skip_emulated_instruction(vcpu);
}

static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
{
        /* TODO: not to reset guest simply here. */
        kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
        pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
}

static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
{
        secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
        vmcs_write64(VMCS_LINK_POINTER, -1ull);
        vmx->nested.need_vmcs12_to_shadow_sync = false;
}

static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!vmx->nested.hv_evmcs)
                return;

        kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
        vmx->nested.hv_evmcs_vmptr = -1ull;
        vmx->nested.hv_evmcs = NULL;
}

/*
 * Free whatever needs to be freed from vmx->nested when L1 goes down, or
 * just stops using VMX.
 */
static void free_nested(struct kvm_vcpu *vcpu)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
                return;

        kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);

        vmx->nested.vmxon = false;
        vmx->nested.smm.vmxon = false;
        free_vpid(vmx->nested.vpid02);
        vmx->nested.posted_intr_nv = -1;
        vmx->nested.current_vmptr = -1ull;
        if (enable_shadow_vmcs) {
                vmx_disable_shadow_vmcs(vmx);
                vmcs_clear(vmx->vmcs01.shadow_vmcs);
                free_vmcs(vmx->vmcs01.shadow_vmcs);
                vmx->vmcs01.shadow_vmcs = NULL;
        }
        kfree(vmx->nested.cached_vmcs12);
        vmx->nested.cached_vmcs12 = NULL;
        kfree(vmx->nested.cached_shadow_vmcs12);
        vmx->nested.cached_shadow_vmcs12 = NULL;
        /* Unpin physical memory we referred to in the vmcs02 */
        if (vmx->nested.apic_access_page) {
                kvm_release_page_dirty(vmx->nested.apic_access_page);
                vmx->nested.apic_access_page = NULL;
        }
        kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
        kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
        vmx->nested.pi_desc = NULL;

        kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);

        nested_release_evmcs(vcpu);

        free_loaded_vmcs(&vmx->nested.vmcs02);
}

static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
                                     struct loaded_vmcs *prev)
{
        struct vmcs_host_state *dest, *src;

        if (unlikely(!vmx->guest_state_loaded))
                return;

        src = &prev->host_state;
        dest = &vmx->loaded_vmcs->host_state;

        vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
        dest->ldt_sel = src->ldt_sel;
#ifdef CONFIG_X86_64
        dest->ds_sel = src->ds_sel;
        dest->es_sel = src->es_sel;
#endif
}

static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        struct loaded_vmcs *prev;
        int cpu;

        if (vmx->loaded_vmcs == vmcs)
                return;

        cpu = get_cpu();
        prev = vmx->loaded_vmcs;
        vmx->loaded_vmcs = vmcs;
        vmx_vcpu_load_vmcs(vcpu, cpu);
        vmx_sync_vmcs_host_state(vmx, prev);
        put_cpu();

        vmx_segment_cache_clear(vmx);
}

/*
 * Ensure that the current vmcs of the logical processor is the
 * vmcs01 of the vcpu before calling free_nested().
 */
void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
        vcpu_load(vcpu);
        vmx_leave_nested(vcpu);
        vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
        free_nested(vcpu);
        vcpu_put(vcpu);
}

static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
                struct x86_exception *fault)
{
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        u32 exit_reason;
        unsigned long exit_qualification = vcpu->arch.exit_qualification;

        if (vmx->nested.pml_full) {
                exit_reason = EXIT_REASON_PML_FULL;
                vmx->nested.pml_full = false;
                exit_qualification &= INTR_INFO_UNBLOCK_NMI;
        } else if (fault->error_code & PFERR_RSVD_MASK)
                exit_reason = EXIT_REASON_EPT_MISCONFIG;
        else
                exit_reason = EXIT_REASON_EPT_VIOLATION;

        nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
        vmcs12->guest_physical_address = fault->address;
}

static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
        WARN_ON(mmu_is_nested(vcpu));

        vcpu->arch.mmu = &vcpu->arch.guest_mmu;
        kvm_init_shadow_ept_mmu(vcpu,
                        to_vmx(vcpu)->nested.msrs.ept_caps &
                        VMX_EPT_EXECUTE_ONLY_BIT,
                        nested_ept_ad_enabled(vcpu),
                        nested_ept_get_cr3(vcpu));
        vcpu->arch.mmu->set_cr3           = vmx_set_cr3;
        vcpu->arch.mmu->get_cr3           = nested_ept_get_cr3;
        vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
        vcpu->arch.mmu->get_pdptr         = kvm_pdptr_read;

        vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
}

static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
        vcpu->arch.mmu = &vcpu->arch.root_mmu;
        vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}

static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
                                            u16 error_code)
{
        bool inequality, bit;

        bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0;
        inequality =
                (error_code & vmcs12->page_fault_error_code_mask) !=
                 vmcs12->page_fault_error_code_match;
        return inequality ^ bit;
}


/*
 * KVM wants to inject page-faults which it got to the guest. This function
 * checks whether in a nested guest, we need to inject them to L1 or L2.
 */
static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
{
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
        unsigned int nr = vcpu->arch.exception.nr;
        bool has_payload = vcpu->arch.exception.has_payload;
        unsigned long payload = vcpu->arch.exception.payload;

        if (nr == PF_VECTOR) {
                if (vcpu->arch.exception.nested_apf) {
                        *exit_qual = vcpu->arch.apf.nested_apf_token;
                        return 1;
                }
                if (nested_vmx_is_page_fault_vmexit(vmcs12,
                                                    vcpu->arch.exception.error_code)) {
                        *exit_qual = has_payload ? payload : vcpu->arch.cr2;
                        return 1;
                }
        } else if (vmcs12->exception_bitmap & (1u << nr)) {
                if (nr == DB_VECTOR) {
                        if (!has_payload) {
                                payload = vcpu->arch.dr6;
                                payload &= ~(DR6_FIXED_1 | DR6_BT);
                                payload ^= DR6_RTM;
                        }
                        *exit_qual = payload;
                } else
                        *exit_qual = 0;
                return 1;
        }

        return 0;
}


static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
                struct x86_exception *fault)
{
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

        WARN_ON(!is_guest_mode(vcpu));

        if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
                !to_vmx(vcpu)->nested.nested_run_pending) {
                vmcs12->vm_exit_intr_error_code = fault->error_code;
                nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
                                  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
                                  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
                                  fault->address);
        } else {
                kvm_inject_page_fault(vcpu, fault);
        }
}

static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
{
        return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
}

static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
                                               struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
                return 0;

        if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) ||
            !page_address_valid(vcpu, vmcs12->io_bitmap_b))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
                                                struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
                return 0;

        if (!page_address_valid(vcpu, vmcs12->msr_bitmap))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
                                                struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
                return 0;

        if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))
                return -EINVAL;

        return 0;
}

/*
 * Check if MSR is intercepted for L01 MSR bitmap.
 */
static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
{
        unsigned long *msr_bitmap;
        int f = sizeof(unsigned long);

        if (!cpu_has_vmx_msr_bitmap())
                return true;

        msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;

        if (msr <= 0x1fff) {
                return !!test_bit(msr, msr_bitmap + 0x800 / f);
        } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
                msr &= 0x1fff;
                return !!test_bit(msr, msr_bitmap + 0xc00 / f);
        }

        return true;
}

/*
 * If a msr is allowed by L0, we should check whether it is allowed by L1.
 * The corresponding bit will be cleared unless both of L0 and L1 allow it.
 */
static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
                                               unsigned long *msr_bitmap_nested,
                                               u32 msr, int type)
{
        int f = sizeof(unsigned long);

        /*
         * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
         * have the write-low and read-high bitmap offsets the wrong way round.
         * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
         */
        if (msr <= 0x1fff) {
                if (type & MSR_TYPE_R &&
                   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
                        /* read-low */
                        __clear_bit(msr, msr_bitmap_nested + 0x000 / f);

                if (type & MSR_TYPE_W &&
                   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
                        /* write-low */
                        __clear_bit(msr, msr_bitmap_nested + 0x800 / f);

        } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
                msr &= 0x1fff;
                if (type & MSR_TYPE_R &&
                   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
                        /* read-high */
                        __clear_bit(msr, msr_bitmap_nested + 0x400 / f);

                if (type & MSR_TYPE_W &&
                   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
                        /* write-high */
                        __clear_bit(msr, msr_bitmap_nested + 0xc00 / f);

        }
}

static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
        int msr;

        for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
                unsigned word = msr / BITS_PER_LONG;

                msr_bitmap[word] = ~0;
                msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
        }
}

/*
 * Merge L0's and L1's MSR bitmap, return false to indicate that
 * we do not use the hardware.
 */
static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
                                                 struct vmcs12 *vmcs12)
{
        int msr;
        unsigned long *msr_bitmap_l1;
        unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
        struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map;

        /* Nothing to do if the MSR bitmap is not in use.  */
        if (!cpu_has_vmx_msr_bitmap() ||
            !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
                return false;

        if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
                return false;

        msr_bitmap_l1 = (unsigned long *)map->hva;

        /*
         * To keep the control flow simple, pay eight 8-byte writes (sixteen
         * 4-byte writes on 32-bit systems) up front to enable intercepts for
         * the x2APIC MSR range and selectively disable them below.
         */
        enable_x2apic_msr_intercepts(msr_bitmap_l0);

        if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
                if (nested_cpu_has_apic_reg_virt(vmcs12)) {
                        /*
                         * L0 need not intercept reads for MSRs between 0x800
                         * and 0x8ff, it just lets the processor take the value
                         * from the virtual-APIC page; take those 256 bits
                         * directly from the L1 bitmap.
                         */
                        for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
                                unsigned word = msr / BITS_PER_LONG;

                                msr_bitmap_l0[word] = msr_bitmap_l1[word];
                        }
                }

                nested_vmx_disable_intercept_for_msr(
                        msr_bitmap_l1, msr_bitmap_l0,
                        X2APIC_MSR(APIC_TASKPRI),
                        MSR_TYPE_R | MSR_TYPE_W);

                if (nested_cpu_has_vid(vmcs12)) {
                        nested_vmx_disable_intercept_for_msr(
                                msr_bitmap_l1, msr_bitmap_l0,
                                X2APIC_MSR(APIC_EOI),
                                MSR_TYPE_W);
                        nested_vmx_disable_intercept_for_msr(
                                msr_bitmap_l1, msr_bitmap_l0,
                                X2APIC_MSR(APIC_SELF_IPI),
                                MSR_TYPE_W);
                }
        }

        /* KVM unconditionally exposes the FS/GS base MSRs to L1. */
        nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
                                             MSR_FS_BASE, MSR_TYPE_RW);

        nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
                                             MSR_GS_BASE, MSR_TYPE_RW);

        nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
                                             MSR_KERNEL_GS_BASE, MSR_TYPE_RW);

        /*
         * Checking the L0->L1 bitmap is trying to verify two things:
         *
         * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
         *    ensures that we do not accidentally generate an L02 MSR bitmap
         *    from the L12 MSR bitmap that is too permissive.
         * 2. That L1 or L2s have actually used the MSR. This avoids
         *    unnecessarily merging of the bitmap if the MSR is unused. This
         *    works properly because we only update the L01 MSR bitmap lazily.
         *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
         *    updated to reflect this when L1 (or its L2s) actually write to
         *    the MSR.
         */
        if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL))
                nested_vmx_disable_intercept_for_msr(
                                        msr_bitmap_l1, msr_bitmap_l0,
                                        MSR_IA32_SPEC_CTRL,
                                        MSR_TYPE_R | MSR_TYPE_W);

        if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD))
                nested_vmx_disable_intercept_for_msr(
                                        msr_bitmap_l1, msr_bitmap_l0,
                                        MSR_IA32_PRED_CMD,
                                        MSR_TYPE_W);

        kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false);

        return true;
}

static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
                                       struct vmcs12 *vmcs12)
{
        struct kvm_host_map map;
        struct vmcs12 *shadow;

        if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
            vmcs12->vmcs_link_pointer == -1ull)
                return;

        shadow = get_shadow_vmcs12(vcpu);

        if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
                return;

        memcpy(shadow, map.hva, VMCS12_SIZE);
        kvm_vcpu_unmap(vcpu, &map, false);
}

static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
                                              struct vmcs12 *vmcs12)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
            vmcs12->vmcs_link_pointer == -1ull)
                return;

        kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
                        get_shadow_vmcs12(vcpu), VMCS12_SIZE);
}

/*
 * In nested virtualization, check if L1 has set
 * VM_EXIT_ACK_INTR_ON_EXIT
 */
static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
{
        return get_vmcs12(vcpu)->vm_exit_controls &
                VM_EXIT_ACK_INTR_ON_EXIT;
}

static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
{
        return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu));
}

static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
                                          struct vmcs12 *vmcs12)
{
        if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
            !page_address_valid(vcpu, vmcs12->apic_access_addr))
                return -EINVAL;
        else
                return 0;
}

static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
                                           struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
            !nested_cpu_has_apic_reg_virt(vmcs12) &&
            !nested_cpu_has_vid(vmcs12) &&
            !nested_cpu_has_posted_intr(vmcs12))
                return 0;

        /*
         * If virtualize x2apic mode is enabled,
         * virtualize apic access must be disabled.
         */
        if (nested_cpu_has_virt_x2apic_mode(vmcs12) &&
            nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
                return -EINVAL;

        /*
         * If virtual interrupt delivery is enabled,
         * we must exit on external interrupts.
         */
        if (nested_cpu_has_vid(vmcs12) &&
           !nested_exit_on_intr(vcpu))
                return -EINVAL;

        /*
         * bits 15:8 should be zero in posted_intr_nv,
         * the descriptor address has been already checked
         * in nested_get_vmcs12_pages.
         *
         * bits 5:0 of posted_intr_desc_addr should be zero.
         */
        if (nested_cpu_has_posted_intr(vmcs12) &&
           (!nested_cpu_has_vid(vmcs12) ||
            !nested_exit_intr_ack_set(vcpu) ||
            (vmcs12->posted_intr_nv & 0xff00) ||
            (vmcs12->posted_intr_desc_addr & 0x3f) ||
            (vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))
                return -EINVAL;

        /* tpr shadow is needed by all apicv features. */
        if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
                                       u32 count, u64 addr)
{
        int maxphyaddr;

        if (count == 0)
                return 0;
        maxphyaddr = cpuid_maxphyaddr(vcpu);
        if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
            (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr)
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu,
                                                     struct vmcs12 *vmcs12)
{
        if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_load_count,
                                        vmcs12->vm_exit_msr_load_addr) ||
            nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_store_count,
                                        vmcs12->vm_exit_msr_store_addr))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu,
                                                      struct vmcs12 *vmcs12)
{
        if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_entry_msr_load_count,
                                        vmcs12->vm_entry_msr_load_addr))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
                                         struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has_pml(vmcs12))
                return 0;

        if (!nested_cpu_has_ept(vmcs12) ||
            !page_address_valid(vcpu, vmcs12->pml_address))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu,
                                                        struct vmcs12 *vmcs12)
{
        if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) &&
            !nested_cpu_has_ept(vmcs12))
                return -EINVAL;
        return 0;
}

static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu,
                                                         struct vmcs12 *vmcs12)
{
        if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) &&
            !nested_cpu_has_ept(vmcs12))
                return -EINVAL;
        return 0;
}

static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu,
                                                 struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has_shadow_vmcs(vmcs12))
                return 0;

        if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) ||
            !page_address_valid(vcpu, vmcs12->vmwrite_bitmap))
                return -EINVAL;

        return 0;
}

static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
                                       struct vmx_msr_entry *e)
{
        /* x2APIC MSR accesses are not allowed */
        if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
                return -EINVAL;
        if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
            e->index == MSR_IA32_UCODE_REV)
                return -EINVAL;
        if (e->reserved != 0)
                return -EINVAL;
        return 0;
}

static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu,
                                     struct vmx_msr_entry *e)
{
        if (e->index == MSR_FS_BASE ||
            e->index == MSR_GS_BASE ||
            e->index == MSR_IA32_SMM_MONITOR_CTL || /* SMM is not supported */
            nested_vmx_msr_check_common(vcpu, e))
                return -EINVAL;
        return 0;
}

static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
                                      struct vmx_msr_entry *e)
{
        if (e->index == MSR_IA32_SMBASE || /* SMM is not supported */
            nested_vmx_msr_check_common(vcpu, e))
                return -EINVAL;
        return 0;
}

/*
 * Load guest's/host's msr at nested entry/exit.
 * return 0 for success, entry index for failure.
 */
static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
        u32 i;
        struct vmx_msr_entry e;
        struct msr_data msr;

        msr.host_initiated = false;
        for (i = 0; i < count; i++) {
                if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
                                        &e, sizeof(e))) {
                        pr_debug_ratelimited(
                                "%s cannot read MSR entry (%u, 0x%08llx)\n",
                                __func__, i, gpa + i * sizeof(e));
                        goto fail;
                }
                if (nested_vmx_load_msr_check(vcpu, &e)) {
                        pr_debug_ratelimited(
                                "%s check failed (%u, 0x%x, 0x%x)\n",
                                __func__, i, e.index, e.reserved);
                        goto fail;
                }
                msr.index = e.index;
                msr.data = e.value;
                if (kvm_set_msr(vcpu, &msr)) {
                        pr_debug_ratelimited(
                                "%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
                                __func__, i, e.index, e.value);
                        goto fail;
                }
        }
        return 0;
fail:
        return i + 1;
}

static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
        u32 i;
        struct vmx_msr_entry e;

        for (i = 0; i < count; i++) {
                struct msr_data msr_info;
                if (kvm_vcpu_read_guest(vcpu,
                                        gpa + i * sizeof(e),
                                        &e, 2 * sizeof(u32))) {
                        pr_debug_ratelimited(
                                "%s cannot read MSR entry (%u, 0x%08llx)\n",
                                __func__, i, gpa + i * sizeof(e));
                        return -EINVAL;
                }
                if (nested_vmx_store_msr_check(vcpu, &e)) {
                        pr_debug_ratelimited(
                                "%s check failed (%u, 0x%x, 0x%x)\n",
                                __func__, i, e.index, e.reserved);
                        return -EINVAL;
                }
                msr_info.host_initiated = false;
                msr_info.index = e.index;
                if (kvm_get_msr(vcpu, &msr_info)) {
                        pr_debug_ratelimited(
                                "%s cannot read MSR (%u, 0x%x)\n",
                                __func__, i, e.index);
                        return -EINVAL;
                }
                if (kvm_vcpu_write_guest(vcpu,
                                         gpa + i * sizeof(e) +
                                             offsetof(struct vmx_msr_entry, value),
                                         &msr_info.data, sizeof(msr_info.data))) {
                        pr_debug_ratelimited(
                                "%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
                                __func__, i, e.index, msr_info.data);
                        return -EINVAL;
                }
        }
        return 0;
}

static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
        unsigned long invalid_mask;

        invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
        return (val & invalid_mask) == 0;
}

/*
 * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
 * emulating VM entry into a guest with EPT enabled.
 * Returns 0 on success, 1 on failure. Invalid state exit qualification code
 * is assigned to entry_failure_code on failure.
 */
static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
                               u32 *entry_failure_code)
{
        if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
                if (!nested_cr3_valid(vcpu, cr3)) {
                        *entry_failure_code = ENTRY_FAIL_DEFAULT;
                        return -EINVAL;
                }

                /*
                 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
                 * must not be dereferenced.
                 */
                if (is_pae_paging(vcpu) && !nested_ept) {
                        if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) {
                                *entry_failure_code = ENTRY_FAIL_PDPTE;
                                return -EINVAL;
                        }
                }
        }

        if (!nested_ept)
                kvm_mmu_new_cr3(vcpu, cr3, false);

        vcpu->arch.cr3 = cr3;
        __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);

        kvm_init_mmu(vcpu, false);

        return 0;
}

/*
 * Returns if KVM is able to config CPU to tag TLB entries
 * populated by L2 differently than TLB entries populated
 * by L1.
 *
 * If L1 uses EPT, then TLB entries are tagged with different EPTP.
 *
 * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
 * with different VPID (L1 entries are tagged with vmx->vpid
 * while L2 entries are tagged with vmx->nested.vpid02).
 */
static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
{
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

        return nested_cpu_has_ept(vmcs12) ||
               (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
}

static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
}


static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
{
        return fixed_bits_valid(control, low, high);
}

static inline u64 vmx_control_msr(u32 low, u32 high)
{
        return low | ((u64)high << 32);
}

static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
{
        superset &= mask;
        subset &= mask;

        return (superset | subset) == superset;
}

static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
{
        const u64 feature_and_reserved =
                /* feature (except bit 48; see below) */
                BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
                /* reserved */
                BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
        u64 vmx_basic = vmx->nested.msrs.basic;

        if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
                return -EINVAL;

        /*
         * KVM does not emulate a version of VMX that constrains physical
         * addresses of VMX structures (e.g. VMCS) to 32-bits.
         */
        if (data & BIT_ULL(48))
                return -EINVAL;

        if (vmx_basic_vmcs_revision_id(vmx_basic) !=
            vmx_basic_vmcs_revision_id(data))
                return -EINVAL;

        if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
                return -EINVAL;

        vmx->nested.msrs.basic = data;
        return 0;
}

static int
vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
{
        u64 supported;
        u32 *lowp, *highp;

        switch (msr_index) {
        case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
                lowp = &vmx->nested.msrs.pinbased_ctls_low;
                highp = &vmx->nested.msrs.pinbased_ctls_high;
                break;
        case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
                lowp = &vmx->nested.msrs.procbased_ctls_low;
                highp = &vmx->nested.msrs.procbased_ctls_high;
                break;
        case MSR_IA32_VMX_TRUE_EXIT_CTLS:
                lowp = &vmx->nested.msrs.exit_ctls_low;
                highp = &vmx->nested.msrs.exit_ctls_high;
                break;
        case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
                lowp = &vmx->nested.msrs.entry_ctls_low;
                highp = &vmx->nested.msrs.entry_ctls_high;
                break;
        case MSR_IA32_VMX_PROCBASED_CTLS2:
                lowp = &vmx->nested.msrs.secondary_ctls_low;
                highp = &vmx->nested.msrs.secondary_ctls_high;
                break;
        default:
                BUG();
        }

        supported = vmx_control_msr(*lowp, *highp);

        /* Check must-be-1 bits are still 1. */
        if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
                return -EINVAL;

        /* Check must-be-0 bits are still 0. */
        if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
                return -EINVAL;

        *lowp = data;
        *highp = data >> 32;
        return 0;
}

static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
{
        const u64 feature_and_reserved_bits =
                /* feature */
                BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
                BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
                /* reserved */
                GENMASK_ULL(13, 9) | BIT_ULL(31);
        u64 vmx_misc;

        vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
                                   vmx->nested.msrs.misc_high);

        if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
                return -EINVAL;

        if ((vmx->nested.msrs.pinbased_ctls_high &
             PIN_BASED_VMX_PREEMPTION_TIMER) &&
            vmx_misc_preemption_timer_rate(data) !=
            vmx_misc_preemption_timer_rate(vmx_misc))
                return -EINVAL;

        if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
                return -EINVAL;

        if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
                return -EINVAL;

        if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
                return -EINVAL;

        vmx->nested.msrs.misc_low = data;
        vmx->nested.msrs.misc_high = data >> 32;

        return 0;
}

static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
{
        u64 vmx_ept_vpid_cap;

        vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.msrs.ept_caps,
                                           vmx->nested.msrs.vpid_caps);

        /* Every bit is either reserved or a feature bit. */
        if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
                return -EINVAL;

        vmx->nested.msrs.ept_caps = data;
        vmx->nested.msrs.vpid_caps = data >> 32;
        return 0;
}

static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
{
        u64 *msr;

        switch (msr_index) {
        case MSR_IA32_VMX_CR0_FIXED0:
                msr = &vmx->nested.msrs.cr0_fixed0;
                break;
        case MSR_IA32_VMX_CR4_FIXED0:
                msr = &vmx->nested.msrs.cr4_fixed0;
                break;
        default:
                BUG();
        }

        /*
         * 1 bits (which indicates bits which "must-be-1" during VMX operation)
         * must be 1 in the restored value.
         */
        if (!is_bitwise_subset(data, *msr, -1ULL))
                return -EINVAL;

        *msr = data;
        return 0;
}

/*
 * Called when userspace is restoring VMX MSRs.
 *
 * Returns 0 on success, non-0 otherwise.
 */
int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        /*
         * Don't allow changes to the VMX capability MSRs while the vCPU
         * is in VMX operation.
         */
        if (vmx->nested.vmxon)
                return -EBUSY;

        switch (msr_index) {
        case MSR_IA32_VMX_BASIC:
                return vmx_restore_vmx_basic(vmx, data);
        case MSR_IA32_VMX_PINBASED_CTLS:
        case MSR_IA32_VMX_PROCBASED_CTLS:
        case MSR_IA32_VMX_EXIT_CTLS:
        case MSR_IA32_VMX_ENTRY_CTLS:
                /*
                 * The "non-true" VMX capability MSRs are generated from the
                 * "true" MSRs, so we do not support restoring them directly.
                 *
                 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
                 * should restore the "true" MSRs with the must-be-1 bits
                 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
                 * DEFAULT SETTINGS".
                 */
                return -EINVAL;
        case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
        case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
        case MSR_IA32_VMX_TRUE_EXIT_CTLS:
        case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
        case MSR_IA32_VMX_PROCBASED_CTLS2:
                return vmx_restore_control_msr(vmx, msr_index, data);
        case MSR_IA32_VMX_MISC:
                return vmx_restore_vmx_misc(vmx, data);
        case MSR_IA32_VMX_CR0_FIXED0:
        case MSR_IA32_VMX_CR4_FIXED0:
                return vmx_restore_fixed0_msr(vmx, msr_index, data);
        case MSR_IA32_VMX_CR0_FIXED1:
        case MSR_IA32_VMX_CR4_FIXED1:
                /*
                 * These MSRs are generated based on the vCPU's CPUID, so we
                 * do not support restoring them directly.
                 */
                return -EINVAL;
        case MSR_IA32_VMX_EPT_VPID_CAP:
                return vmx_restore_vmx_ept_vpid_cap(vmx, data);
        case MSR_IA32_VMX_VMCS_ENUM:
                vmx->nested.msrs.vmcs_enum = data;
                return 0;
        case MSR_IA32_VMX_VMFUNC:
                if (data & ~vmx->nested.msrs.vmfunc_controls)
                        return -EINVAL;
                vmx->nested.msrs.vmfunc_controls = data;
                return 0;
        default:
                /*
                 * The rest of the VMX capability MSRs do not support restore.
                 */
                return -EINVAL;
        }
}

/* Returns 0 on success, non-0 otherwise. */
int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
{
        switch (msr_index) {
        case MSR_IA32_VMX_BASIC:
                *pdata = msrs->basic;
                break;
        case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
        case MSR_IA32_VMX_PINBASED_CTLS:
                *pdata = vmx_control_msr(
                        msrs->pinbased_ctls_low,
                        msrs->pinbased_ctls_high);
                if (msr_index == MSR_IA32_VMX_PINBASED_CTLS)
                        *pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
                break;
        case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
        case MSR_IA32_VMX_PROCBASED_CTLS:
                *pdata = vmx_control_msr(
                        msrs->procbased_ctls_low,
                        msrs->procbased_ctls_high);
                if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS)
                        *pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
                break;
        case MSR_IA32_VMX_TRUE_EXIT_CTLS:
        case MSR_IA32_VMX_EXIT_CTLS:
                *pdata = vmx_control_msr(
                        msrs->exit_ctls_low,
                        msrs->exit_ctls_high);
                if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
                        *pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
                break;
        case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
        case MSR_IA32_VMX_ENTRY_CTLS:
                *pdata = vmx_control_msr(
                        msrs->entry_ctls_low,
                        msrs->entry_ctls_high);
                if (msr_index == MSR_IA32_VMX_ENTRY_CTLS)
                        *pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
                break;
        case MSR_IA32_VMX_MISC:
                *pdata = vmx_control_msr(
                        msrs->misc_low,
                        msrs->misc_high);
                break;
        case MSR_IA32_VMX_CR0_FIXED0:
                *pdata = msrs->cr0_fixed0;
                break;
        case MSR_IA32_VMX_CR0_FIXED1:
                *pdata = msrs->cr0_fixed1;
                break;
        case MSR_IA32_VMX_CR4_FIXED0:
                *pdata = msrs->cr4_fixed0;
                break;
        case MSR_IA32_VMX_CR4_FIXED1:
                *pdata = msrs->cr4_fixed1;
                break;
        case MSR_IA32_VMX_VMCS_ENUM:
                *pdata = msrs->vmcs_enum;
                break;
        case MSR_IA32_VMX_PROCBASED_CTLS2:
                *pdata = vmx_control_msr(
                        msrs->secondary_ctls_low,
                        msrs->secondary_ctls_high);
                break;
        case MSR_IA32_VMX_EPT_VPID_CAP:
                *pdata = msrs->ept_caps |
                        ((u64)msrs->vpid_caps << 32);
                break;
        case MSR_IA32_VMX_VMFUNC:
                *pdata = msrs->vmfunc_controls;
                break;
        default:
                return 1;
        }

        return 0;
}

/*
 * Copy the writable VMCS shadow fields back to the VMCS12, in case they have
 * been modified by the L1 guest.  Note, "writable" in this context means
 * "writable by the guest", i.e. tagged SHADOW_FIELD_RW; the set of
 * fields tagged SHADOW_FIELD_RO may or may not align with the "read-only"
 * VM-exit information fields (which are actually writable if the vCPU is
 * configured to support "VMWRITE to any supported field in the VMCS").
 */
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
{
        struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
        struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
        struct shadow_vmcs_field field;
        unsigned long val;
        int i;

        if (WARN_ON(!shadow_vmcs))
                return;

        preempt_disable();

        vmcs_load(shadow_vmcs);

        for (i = 0; i < max_shadow_read_write_fields; i++) {
                field = shadow_read_write_fields[i];
                val = __vmcs_readl(field.encoding);
                vmcs12_write_any(vmcs12, field.encoding, field.offset, val);
        }

        vmcs_clear(shadow_vmcs);
        vmcs_load(vmx->loaded_vmcs->vmcs);

        preempt_enable();
}

static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
{
        const struct shadow_vmcs_field *fields[] = {
                shadow_read_write_fields,
                shadow_read_only_fields
        };
        const int max_fields[] = {
                max_shadow_read_write_fields,
                max_shadow_read_only_fields
        };
        struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
        struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
        struct shadow_vmcs_field field;
        unsigned long val;
        int i, q;

        if (WARN_ON(!shadow_vmcs))
                return;

        vmcs_load(shadow_vmcs);

        for (q = 0; q < ARRAY_SIZE(fields); q++) {
                for (i = 0; i < max_fields[q]; i++) {
                        field = fields[q][i];
                        val = vmcs12_read_any(vmcs12, field.encoding,
                                              field.offset);
                        __vmcs_writel(field.encoding, val);
                }
        }

        vmcs_clear(shadow_vmcs);
        vmcs_load(vmx->loaded_vmcs->vmcs);
}

static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
{
        struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
        struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;

        /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
        vmcs12->tpr_threshold = evmcs->tpr_threshold;
        vmcs12->guest_rip = evmcs->guest_rip;

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
                vmcs12->guest_rsp = evmcs->guest_rsp;
                vmcs12->guest_rflags = evmcs->guest_rflags;
                vmcs12->guest_interruptibility_info =
                        evmcs->guest_interruptibility_info;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
                vmcs12->cpu_based_vm_exec_control =
                        evmcs->cpu_based_vm_exec_control;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) {
                vmcs12->exception_bitmap = evmcs->exception_bitmap;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
                vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
                vmcs12->vm_entry_intr_info_field =
                        evmcs->vm_entry_intr_info_field;
                vmcs12->vm_entry_exception_error_code =
                        evmcs->vm_entry_exception_error_code;
                vmcs12->vm_entry_instruction_len =
                        evmcs->vm_entry_instruction_len;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
                vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
                vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
                vmcs12->host_cr0 = evmcs->host_cr0;
                vmcs12->host_cr3 = evmcs->host_cr3;
                vmcs12->host_cr4 = evmcs->host_cr4;
                vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp;
                vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip;
                vmcs12->host_rip = evmcs->host_rip;
                vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs;
                vmcs12->host_es_selector = evmcs->host_es_selector;
                vmcs12->host_cs_selector = evmcs->host_cs_selector;
                vmcs12->host_ss_selector = evmcs->host_ss_selector;
                vmcs12->host_ds_selector = evmcs->host_ds_selector;
                vmcs12->host_fs_selector = evmcs->host_fs_selector;
                vmcs12->host_gs_selector = evmcs->host_gs_selector;
                vmcs12->host_tr_selector = evmcs->host_tr_selector;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) {
                vmcs12->pin_based_vm_exec_control =
                        evmcs->pin_based_vm_exec_control;
                vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
                vmcs12->secondary_vm_exec_control =
                        evmcs->secondary_vm_exec_control;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
                vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
                vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
                vmcs12->msr_bitmap = evmcs->msr_bitmap;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
                vmcs12->guest_es_base = evmcs->guest_es_base;
                vmcs12->guest_cs_base = evmcs->guest_cs_base;
                vmcs12->guest_ss_base = evmcs->guest_ss_base;
                vmcs12->guest_ds_base = evmcs->guest_ds_base;
                vmcs12->guest_fs_base = evmcs->guest_fs_base;
                vmcs12->guest_gs_base = evmcs->guest_gs_base;
                vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base;
                vmcs12->guest_tr_base = evmcs->guest_tr_base;
                vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base;
                vmcs12->guest_idtr_base = evmcs->guest_idtr_base;
                vmcs12->guest_es_limit = evmcs->guest_es_limit;
                vmcs12->guest_cs_limit = evmcs->guest_cs_limit;
                vmcs12->guest_ss_limit = evmcs->guest_ss_limit;
                vmcs12->guest_ds_limit = evmcs->guest_ds_limit;
                vmcs12->guest_fs_limit = evmcs->guest_fs_limit;
                vmcs12->guest_gs_limit = evmcs->guest_gs_limit;
                vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit;
                vmcs12->guest_tr_limit = evmcs->guest_tr_limit;
                vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit;
                vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit;
                vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes;
                vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes;
                vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes;
                vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes;
                vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes;
                vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes;
                vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes;
                vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes;
                vmcs12->guest_es_selector = evmcs->guest_es_selector;
                vmcs12->guest_cs_selector = evmcs->guest_cs_selector;
                vmcs12->guest_ss_selector = evmcs->guest_ss_selector;
                vmcs12->guest_ds_selector = evmcs->guest_ds_selector;
                vmcs12->guest_fs_selector = evmcs->guest_fs_selector;
                vmcs12->guest_gs_selector = evmcs->guest_gs_selector;
                vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector;
                vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
                vmcs12->tsc_offset = evmcs->tsc_offset;
                vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
                vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
                vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
                vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
                vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow;
                vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow;
                vmcs12->guest_cr0 = evmcs->guest_cr0;
                vmcs12->guest_cr3 = evmcs->guest_cr3;
                vmcs12->guest_cr4 = evmcs->guest_cr4;
                vmcs12->guest_dr7 = evmcs->guest_dr7;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
                vmcs12->host_fs_base = evmcs->host_fs_base;
                vmcs12->host_gs_base = evmcs->host_gs_base;
                vmcs12->host_tr_base = evmcs->host_tr_base;
                vmcs12->host_gdtr_base = evmcs->host_gdtr_base;
                vmcs12->host_idtr_base = evmcs->host_idtr_base;
                vmcs12->host_rsp = evmcs->host_rsp;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
                vmcs12->ept_pointer = evmcs->ept_pointer;
                vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
        }

        if (unlikely(!(evmcs->hv_clean_fields &
                       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
                vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
                vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
                vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat;
                vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer;
                vmcs12->guest_pdptr0 = evmcs->guest_pdptr0;
                vmcs12->guest_pdptr1 = evmcs->guest_pdptr1;
                vmcs12->guest_pdptr2 = evmcs->guest_pdptr2;
                vmcs12->guest_pdptr3 = evmcs->guest_pdptr3;
                vmcs12->guest_pending_dbg_exceptions =
                        evmcs->guest_pending_dbg_exceptions;
                vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp;
                vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip;
                vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
                vmcs12->guest_activity_state = evmcs->guest_activity_state;
                vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
        }

        /*
         * Not used?
         * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
         * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
         * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
         * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0;
         * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1;
         * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2;
         * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3;
         * vmcs12->page_fault_error_code_mask =
         *              evmcs->page_fault_error_code_mask;
         * vmcs12->page_fault_error_code_match =
         *              evmcs->page_fault_error_code_match;
         * vmcs12->cr3_target_count = evmcs->cr3_target_count;
         * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count;
         * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count;
         * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count;
         */

        /*
         * Read only fields:
         * vmcs12->guest_physical_address = evmcs->guest_physical_address;
         * vmcs12->vm_instruction_error = evmcs->vm_instruction_error;
         * vmcs12->vm_exit_reason = evmcs->vm_exit_reason;
         * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info;
         * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code;
         * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field;
         * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code;
         * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len;
         * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info;
         * vmcs12->exit_qualification = evmcs->exit_qualification;
         * vmcs12->guest_linear_address = evmcs->guest_linear_address;
         *
         * Not present in struct vmcs12:
         * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx;
         * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi;
         * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi;
         * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip;
         */

        return 0;
}

static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
{
        struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
        struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;

        /*
         * Should not be changed by KVM:
         *
         * evmcs->host_es_selector = vmcs12->host_es_selector;
         * evmcs->host_cs_selector = vmcs12->host_cs_selector;
         * evmcs->host_ss_selector = vmcs12->host_ss_selector;
         * evmcs->host_ds_selector = vmcs12->host_ds_selector;
         * evmcs->host_fs_selector = vmcs12->host_fs_selector;
         * evmcs->host_gs_selector = vmcs12->host_gs_selector;
         * evmcs->host_tr_selector = vmcs12->host_tr_selector;
         * evmcs->host_ia32_pat = vmcs12->host_ia32_pat;
         * evmcs->host_ia32_efer = vmcs12->host_ia32_efer;
         * evmcs->host_cr0 = vmcs12->host_cr0;
         * evmcs->host_cr3 = vmcs12->host_cr3;
         * evmcs->host_cr4 = vmcs12->host_cr4;
         * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp;
         * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip;
         * evmcs->host_rip = vmcs12->host_rip;
         * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs;
         * evmcs->host_fs_base = vmcs12->host_fs_base;
         * evmcs->host_gs_base = vmcs12->host_gs_base;
         * evmcs->host_tr_base = vmcs12->host_tr_base;
         * evmcs->host_gdtr_base = vmcs12->host_gdtr_base;
         * evmcs->host_idtr_base = vmcs12->host_idtr_base;
         * evmcs->host_rsp = vmcs12->host_rsp;
         * sync_vmcs02_to_vmcs12() doesn't read these:
         * evmcs->io_bitmap_a = vmcs12->io_bitmap_a;
         * evmcs->io_bitmap_b = vmcs12->io_bitmap_b;
         * evmcs->msr_bitmap = vmcs12->msr_bitmap;
         * evmcs->ept_pointer = vmcs12->ept_pointer;
         * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap;
         * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
         * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
         * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
         * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0;
         * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1;
         * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2;
         * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3;
         * evmcs->tpr_threshold = vmcs12->tpr_threshold;
         * evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
         * evmcs->exception_bitmap = vmcs12->exception_bitmap;
         * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer;
         * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control;
         * evmcs->vm_exit_controls = vmcs12->vm_exit_controls;
         * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control;
         * evmcs->page_fault_error_code_mask =
         *              vmcs12->page_fault_error_code_mask;
         * evmcs->page_fault_error_code_match =
         *              vmcs12->page_fault_error_code_match;
         * evmcs->cr3_target_count = vmcs12->cr3_target_count;
         * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr;
         * evmcs->tsc_offset = vmcs12->tsc_offset;
         * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl;
         * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask;
         * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask;
         * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow;
         * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow;
         * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
         * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
         * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
         *
         * Not present in struct vmcs12:
         * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
         * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
         * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
         * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
         */

        evmcs->guest_es_selector = vmcs12->guest_es_selector;
        evmcs->guest_cs_selector = vmcs12->guest_cs_selector;
        evmcs->guest_ss_selector = vmcs12->guest_ss_selector;
        evmcs->guest_ds_selector = vmcs12->guest_ds_selector;
        evmcs->guest_fs_selector = vmcs12->guest_fs_selector;
        evmcs->guest_gs_selector = vmcs12->guest_gs_selector;
        evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector;
        evmcs->guest_tr_selector = vmcs12->guest_tr_selector;

        evmcs->guest_es_limit = vmcs12->guest_es_limit;
        evmcs->guest_cs_limit = vmcs12->guest_cs_limit;
        evmcs->guest_ss_limit = vmcs12->guest_ss_limit;
        evmcs->guest_ds_limit = vmcs12->guest_ds_limit;
        evmcs->guest_fs_limit = vmcs12->guest_fs_limit;
        evmcs->guest_gs_limit = vmcs12->guest_gs_limit;
        evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit;
        evmcs->guest_tr_limit = vmcs12->guest_tr_limit;
        evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit;
        evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit;

        evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes;
        evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes;
        evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes;
        evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes;
        evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes;
        evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes;
        evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes;
        evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes;

        evmcs->guest_es_base = vmcs12->guest_es_base;
        evmcs->guest_cs_base = vmcs12->guest_cs_base;
        evmcs->guest_ss_base = vmcs12->guest_ss_base;
        evmcs->guest_ds_base = vmcs12->guest_ds_base;
        evmcs->guest_fs_base = vmcs12->guest_fs_base;
        evmcs->guest_gs_base = vmcs12->guest_gs_base;
        evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base;
        evmcs->guest_tr_base = vmcs12->guest_tr_base;
        evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base;
        evmcs->guest_idtr_base = vmcs12->guest_idtr_base;

        evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat;
        evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer;

        evmcs->guest_pdptr0 = vmcs12->guest_pdptr0;
        evmcs->guest_pdptr1 = vmcs12->guest_pdptr1;
        evmcs->guest_pdptr2 = vmcs12->guest_pdptr2;
        evmcs->guest_pdptr3 = vmcs12->guest_pdptr3;

        evmcs->guest_pending_dbg_exceptions =
                vmcs12->guest_pending_dbg_exceptions;
        evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp;
        evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip;

        evmcs->guest_activity_state = vmcs12->guest_activity_state;
        evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs;

        evmcs->guest_cr0 = vmcs12->guest_cr0;
        evmcs->guest_cr3 = vmcs12->guest_cr3;
        evmcs->guest_cr4 = vmcs12->guest_cr4;
        evmcs->guest_dr7 = vmcs12->guest_dr7;

        evmcs->guest_physical_address = vmcs12->guest_physical_address;

        evmcs->vm_instruction_error = vmcs12->vm_instruction_error;
        evmcs->vm_exit_reason = vmcs12->vm_exit_reason;
        evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info;
        evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code;
        evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field;
        evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code;
        evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len;
        evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info;

        evmcs->exit_qualification = vmcs12->exit_qualification;

        evmcs->guest_linear_address = vmcs12->guest_linear_address;
        evmcs->guest_rsp = vmcs12->guest_rsp;
        evmcs->guest_rflags = vmcs12->guest_rflags;

        evmcs->guest_interruptibility_info =
                vmcs12->guest_interruptibility_info;
        evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control;
        evmcs->vm_entry_controls = vmcs12->vm_entry_controls;
        evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field;
        evmcs->vm_entry_exception_error_code =
                vmcs12->vm_entry_exception_error_code;
        evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len;

        evmcs->guest_rip = vmcs12->guest_rip;

        evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;

        return 0;
}

/*
 * This is an equivalent of the nested hypervisor executing the vmptrld
 * instruction.
 */
static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
                                                 bool from_launch)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        bool evmcs_gpa_changed = false;
        u64 evmcs_gpa;

        if (likely(!vmx->nested.enlightened_vmcs_enabled))
                return 1;

        if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
                return 1;

        if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
                if (!vmx->nested.hv_evmcs)
                        vmx->nested.current_vmptr = -1ull;

                nested_release_evmcs(vcpu);

                if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa),
                                 &vmx->nested.hv_evmcs_map))
                        return 0;

                vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva;

                /*
                 * Currently, KVM only supports eVMCS version 1
                 * (== KVM_EVMCS_VERSION) and thus we expect guest to set this
                 * value to first u32 field of eVMCS which should specify eVMCS
                 * VersionNumber.
                 *
                 * Guest should be aware of supported eVMCS versions by host by
                 * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is
                 * expected to set this CPUID leaf according to the value
                 * returned in vmcs_version from nested_enable_evmcs().
                 *
                 * However, it turns out that Microsoft Hyper-V fails to comply
                 * to their own invented interface: When Hyper-V use eVMCS, it
                 * just sets first u32 field of eVMCS to revision_id specified
                 * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number
                 * which is one of the supported versions specified in
                 * CPUID.0x4000000A.EAX[0:15].
                 *
                 * To overcome Hyper-V bug, we accept here either a supported
                 * eVMCS version or VMCS12 revision_id as valid values for first
                 * u32 field of eVMCS.
                 */
                if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) &&
                    (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) {
                        nested_release_evmcs(vcpu);
                        return 0;
                }

                vmx->nested.dirty_vmcs12 = true;
                vmx->nested.hv_evmcs_vmptr = evmcs_gpa;

                evmcs_gpa_changed = true;
                /*
                 * Unlike normal vmcs12, enlightened vmcs12 is not fully
                 * reloaded from guest's memory (read only fields, fields not
                 * present in struct hv_enlightened_vmcs, ...). Make sure there
                 * are no leftovers.
                 */
                if (from_launch) {
                        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
                        memset(vmcs12, 0, sizeof(*vmcs12));
                        vmcs12->hdr.revision_id = VMCS12_REVISION;
                }

        }

        /*
         * Clean fields data can't de used on VMLAUNCH and when we switch
         * between different L2 guests as KVM keeps a single VMCS12 per L1.
         */
        if (from_launch || evmcs_gpa_changed)
                vmx->nested.hv_evmcs->hv_clean_fields &=
                        ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;

        return 1;
}

void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        /*
         * hv_evmcs may end up being not mapped after migration (when
         * L2 was running), map it here to make sure vmcs12 changes are
         * properly reflected.
         */
        if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs)
                nested_vmx_handle_enlightened_vmptrld(vcpu, false);

        if (vmx->nested.hv_evmcs) {
                copy_vmcs12_to_enlightened(vmx);
                /* All fields are clean */
                vmx->nested.hv_evmcs->hv_clean_fields |=
                        HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
        } else {
                copy_vmcs12_to_shadow(vmx);
        }

        vmx->nested.need_vmcs12_to_shadow_sync = false;
}

static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
{
        struct vcpu_vmx *vmx =
                container_of(timer, struct vcpu_vmx, nested.preemption_timer);

        vmx->nested.preemption_timer_expired = true;
        kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu);
        kvm_vcpu_kick(&vmx->vcpu);

        return HRTIMER_NORESTART;
}

static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
{
        u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        /*
         * A timer value of zero is architecturally guaranteed to cause
         * a VMExit prior to executing any instructions in the guest.
         */
        if (preemption_timeout == 0) {
                vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
                return;
        }

        if (vcpu->arch.virtual_tsc_khz == 0)
                return;

        preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
        preemption_timeout *= 1000000;
        do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
        hrtimer_start(&vmx->nested.preemption_timer,
                      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
}

static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
        if (vmx->nested.nested_run_pending &&
            (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
                return vmcs12->guest_ia32_efer;
        else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
                return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME);
        else
                return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME);
}

static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
{
        /*
         * If vmcs02 hasn't been initialized, set the constant vmcs02 state
         * according to L0's settings (vmcs12 is irrelevant here).  Host
         * fields that come from L0 and are not constant, e.g. HOST_CR3,
         * will be set as needed prior to VMLAUNCH/VMRESUME.
         */
        if (vmx->nested.vmcs02_initialized)
                return;
        vmx->nested.vmcs02_initialized = true;

        /*
         * We don't care what the EPTP value is we just need to guarantee
         * it's valid so we don't get a false positive when doing early
         * consistency checks.
         */
        if (enable_ept && nested_early_check)
                vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));

        /* All VMFUNCs are currently emulated through L0 vmexits.  */
        if (cpu_has_vmx_vmfunc())
                vmcs_write64(VM_FUNCTION_CONTROL, 0);

        if (cpu_has_vmx_posted_intr())
                vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);

        if (cpu_has_vmx_msr_bitmap())
                vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));

        /*
         * The PML address never changes, so it is constant in vmcs02.
         * Conceptually we want to copy the PML index from vmcs01 here,
         * and then back to vmcs01 on nested vmexit.  But since we flush
         * the log and reset GUEST_PML_INDEX on each vmexit, the PML
         * index is also effectively constant in vmcs02.
         */
        if (enable_pml) {
                vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
                vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
        }

        if (cpu_has_vmx_encls_vmexit())
                vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);

        /*
         * Set the MSR load/store lists to match L0's settings.  Only the
         * addresses are constant (for vmcs02), the counts can change based
         * on L2's behavior, e.g. switching to/from long mode.
         */
        vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
        vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
        vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));

        vmx_set_constant_host_state(vmx);

}

static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
                                      struct vmcs12 *vmcs12)
{
        prepare_vmcs02_constant_state(vmx);

        vmcs_write64(VMCS_LINK_POINTER, -1ull);

        if (enable_vpid) {
                if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
                        vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
                else
                        vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
        }
}

static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
        u32 exec_control, vmcs12_exec_ctrl;
        u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);

        if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs)
                prepare_vmcs02_early_rare(vmx, vmcs12);

        /*
         * PIN CONTROLS
         */
        exec_control = vmx_pin_based_exec_ctrl(vmx);
        exec_control |= (vmcs12->pin_based_vm_exec_control &
                         ~PIN_BASED_VMX_PREEMPTION_TIMER);

        /* Posted interrupts setting is only taken from vmcs12.  */
        if (nested_cpu_has_posted_intr(vmcs12)) {
                vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
                vmx->nested.pi_pending = false;
        } else {
                exec_control &= ~PIN_BASED_POSTED_INTR;
        }
        pin_controls_set(vmx, exec_control);

        /*
         * EXEC CONTROLS
         */
        exec_control = vmx_exec_control(vmx); /* L0's desires */
        exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
        exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
        exec_control &= ~CPU_BASED_TPR_SHADOW;
        exec_control |= vmcs12->cpu_based_vm_exec_control;

        if (exec_control & CPU_BASED_TPR_SHADOW)
                vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
#ifdef CONFIG_X86_64
        else
                exec_control |= CPU_BASED_CR8_LOAD_EXITING |
                                CPU_BASED_CR8_STORE_EXITING;
#endif

        /*
         * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
         * for I/O port accesses.
         */
        exec_control |= CPU_BASED_UNCOND_IO_EXITING;
        exec_control &= ~CPU_BASED_USE_IO_BITMAPS;

        /*
         * This bit will be computed in nested_get_vmcs12_pages, because
         * we do not have access to L1's MSR bitmap yet.  For now, keep
         * the same bit as before, hoping to avoid multiple VMWRITEs that
         * only set/clear this bit.
         */
        exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
        exec_control |= exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS;

        exec_controls_set(vmx, exec_control);

        /*
         * SECONDARY EXEC CONTROLS
         */
        if (cpu_has_secondary_exec_ctrls()) {
                exec_control = vmx->secondary_exec_control;

                /* Take the following fields only from vmcs12 */
                exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
                                  SECONDARY_EXEC_ENABLE_INVPCID |
                                  SECONDARY_EXEC_RDTSCP |
                                  SECONDARY_EXEC_XSAVES |
                                  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
                                  SECONDARY_EXEC_APIC_REGISTER_VIRT |
                                  SECONDARY_EXEC_ENABLE_VMFUNC);
                if (nested_cpu_has(vmcs12,
                                   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
                        vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
                                ~SECONDARY_EXEC_ENABLE_PML;
                        exec_control |= vmcs12_exec_ctrl;
                }

                /* VMCS shadowing for L2 is emulated for now */
                exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;

                /*
                 * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4()
                 * will not have to rewrite the controls just for this bit.
                 */
                if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated() &&
                    (vmcs12->guest_cr4 & X86_CR4_UMIP))
                        exec_control |= SECONDARY_EXEC_DESC;

                if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
                        vmcs_write16(GUEST_INTR_STATUS,
                                vmcs12->guest_intr_status);

                secondary_exec_controls_set(vmx, exec_control);
        }

        /*
         * ENTRY CONTROLS
         *
         * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE
         * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
         * on the related bits (if supported by the CPU) in the hope that
         * we can avoid VMWrites during vmx_set_efer().
         */
        exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) &
                        ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER;
        if (cpu_has_load_ia32_efer()) {
                if (guest_efer & EFER_LMA)
                        exec_control |= VM_ENTRY_IA32E_MODE;
                if (guest_efer != host_efer)
                        exec_control |= VM_ENTRY_LOAD_IA32_EFER;
        }
        vm_entry_controls_set(vmx, exec_control);

        /*
         * EXIT CONTROLS
         *
         * L2->L1 exit controls are emulated - the hardware exit is to L0 so
         * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
         * bits may be modified by vmx_set_efer() in prepare_vmcs02().
         */
        exec_control = vmx_vmexit_ctrl();
        if (cpu_has_load_ia32_efer() && guest_efer != host_efer)
                exec_control |= VM_EXIT_LOAD_IA32_EFER;
        vm_exit_controls_set(vmx, exec_control);

        /*
         * Interrupt/Exception Fields
         */
        if (vmx->nested.nested_run_pending) {
                vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
                             vmcs12->vm_entry_intr_info_field);
                vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
                             vmcs12->vm_entry_exception_error_code);
                vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
                             vmcs12->vm_entry_instruction_len);
                vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
                             vmcs12->guest_interruptibility_info);
                vmx->loaded_vmcs->nmi_known_unmasked =
                        !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
        } else {
                vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
        }
}

static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
        struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;

        if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
                           HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
                vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
                vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
                vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
                vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
                vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
                vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
                vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
                vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
                vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
                vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
                vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
                vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
                vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
                vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
                vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
                vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
                vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
                vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
                vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
                vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
                vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
                vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
                vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
                vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
                vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
                vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
                vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
                vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
                vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
                vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
                vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
                vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
                vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
                vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
                vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
                vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
        }

        if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
                           HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
                vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
                vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
                            vmcs12->guest_pending_dbg_exceptions);
                vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
                vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);

                /*
                 * L1 may access the L2's PDPTR, so save them to construct
                 * vmcs12
                 */
                if (enable_ept) {
                        vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
                        vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
                        vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
                        vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
                }

                if (kvm_mpx_supported() && vmx->nested.nested_run_pending &&
                    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
                        vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
        }

        if (nested_cpu_has_xsaves(vmcs12))
                vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);

        /*
         * Whether page-faults are trapped is determined by a combination of
         * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
         * If enable_ept, L0 doesn't care about page faults and we should
         * set all of these to L1's desires. However, if !enable_ept, L0 does
         * care about (at least some) page faults, and because it is not easy
         * (if at all possible?) to merge L0 and L1's desires, we simply ask
         * to exit on each and every L2 page fault. This is done by setting
         * MASK=MATCH=0 and (see below) EB.PF=1.
         * Note that below we don't need special code to set EB.PF beyond the
         * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
         * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
         * !enable_ept, EB.PF is 1, so the "or" will always be 1.
         */
        vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
                enable_ept ? vmcs12->page_fault_error_code_mask : 0);
        vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
                enable_ept ? vmcs12->page_fault_error_code_match : 0);

        if (cpu_has_vmx_apicv()) {
                vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
                vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
                vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
                vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
        }

        vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
        vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);

        set_cr4_guest_host_mask(vmx);
}

/*
 * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
 * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
 * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
 * guest in a way that will both be appropriate to L1's requests, and our
 * needs. In addition to modifying the active vmcs (which is vmcs02), this
 * function also has additional necessary side-effects, like setting various
 * vcpu->arch fields.
 * Returns 0 on success, 1 on failure. Invalid state exit qualification code
 * is assigned to entry_failure_code on failure.
 */
static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
                          u32 *entry_failure_code)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
        bool load_guest_pdptrs_vmcs12 = false;

        if (vmx->nested.dirty_vmcs12 || hv_evmcs) {
                prepare_vmcs02_rare(vmx, vmcs12);
                vmx->nested.dirty_vmcs12 = false;

                load_guest_pdptrs_vmcs12 = !hv_evmcs ||
                        !(hv_evmcs->hv_clean_fields &
                          HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
        }

        if (vmx->nested.nested_run_pending &&
            (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
                kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
                vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
        } else {
                kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
                vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
        }
        if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
            !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
                vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
        vmx_set_rflags(vcpu, vmcs12->guest_rflags);

        /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
         * bitwise-or of what L1 wants to trap for L2, and what we want to
         * trap. Note that CR0.TS also needs updating - we do this later.
         */
        update_exception_bitmap(vcpu);
        vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
        vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);

        if (vmx->nested.nested_run_pending &&
            (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
                vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
                vcpu->arch.pat = vmcs12->guest_ia32_pat;
        } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
                vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
        }

        vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);

        if (kvm_has_tsc_control)
                decache_tsc_multiplier(vmx);

        if (enable_vpid) {
                /*
                 * There is no direct mapping between vpid02 and vpid12, the
                 * vpid02 is per-vCPU for L0 and reused while the value of
                 * vpid12 is changed w/ one invvpid during nested vmentry.
                 * The vpid12 is allocated by L1 for L2, so it will not
                 * influence global bitmap(for vpid01 and vpid02 allocation)
                 * even if spawn a lot of nested vCPUs.
                 */
                if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) {
                        if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
                                vmx->nested.last_vpid = vmcs12->virtual_processor_id;
                                __vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false);
                        }
                } else {
                        /*
                         * If L1 use EPT, then L0 needs to execute INVEPT on
                         * EPTP02 instead of EPTP01. Therefore, delay TLB
                         * flush until vmcs02->eptp is fully updated by
                         * KVM_REQ_LOAD_CR3. Note that this assumes
                         * KVM_REQ_TLB_FLUSH is evaluated after
                         * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
                         */
                        kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
                }
        }

        if (nested_cpu_has_ept(vmcs12))
                nested_ept_init_mmu_context(vcpu);
        else if (nested_cpu_has2(vmcs12,
                                 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
                vmx_flush_tlb(vcpu, true);

        /*
         * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
         * bits which we consider mandatory enabled.
         * The CR0_READ_SHADOW is what L2 should have expected to read given
         * the specifications by L1; It's not enough to take
         * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
         * have more bits than L1 expected.
         */
        vmx_set_cr0(vcpu, vmcs12->guest_cr0);
        vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));

        vmx_set_cr4(vcpu, vmcs12->guest_cr4);
        vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));

        vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12);
        /* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
        vmx_set_efer(vcpu, vcpu->arch.efer);

        /*
         * Guest state is invalid and unrestricted guest is disabled,
         * which means L1 attempted VMEntry to L2 with invalid state.
         * Fail the VMEntry.
         */
        if (vmx->emulation_required) {
                *entry_failure_code = ENTRY_FAIL_DEFAULT;
                return -EINVAL;
        }

        /* Shadow page tables on either EPT or shadow page tables. */
        if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
                                entry_failure_code))
                return -EINVAL;

        /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
        if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
            is_pae_paging(vcpu)) {
                vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
                vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
                vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
                vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
        }

        if (!enable_ept)
                vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;

        kvm_rsp_write(vcpu, vmcs12->guest_rsp);
        kvm_rip_write(vcpu, vmcs12->guest_rip);
        return 0;
}

static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
{
        if (!nested_cpu_has_nmi_exiting(vmcs12) &&
            nested_cpu_has_virtual_nmis(vmcs12))
                return -EINVAL;

        if (!nested_cpu_has_virtual_nmis(vmcs12) &&
            nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING))
                return -EINVAL;

        return 0;
}

static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        int maxphyaddr = cpuid_maxphyaddr(vcpu);

        /* Check for memory type validity */
        switch (address & VMX_EPTP_MT_MASK) {
        case VMX_EPTP_MT_UC:
                if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))
                        return false;
                break;
        case VMX_EPTP_MT_WB:
                if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT))
                        return false;
                break;
        default:
                return false;
        }

        /* only 4 levels page-walk length are valid */
        if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)
                return false;

        /* Reserved bits should not be set */
        if (address >> maxphyaddr || ((address >> 7) & 0x1f))
                return false;

        /* AD, if set, should be supported */
        if (address & VMX_EPTP_AD_ENABLE_BIT) {
                if (!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))
                        return false;
        }

        return true;
}

/*
 * Checks related to VM-Execution Control Fields
 */
static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu,
                                              struct vmcs12 *vmcs12)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!vmx_control_verify(vmcs12->pin_based_vm_exec_control,
                                vmx->nested.msrs.pinbased_ctls_low,
                                vmx->nested.msrs.pinbased_ctls_high) ||
            !vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
                                vmx->nested.msrs.procbased_ctls_low,
                                vmx->nested.msrs.procbased_ctls_high))
                return -EINVAL;

        if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
            !vmx_control_verify(vmcs12->secondary_vm_exec_control,
                                 vmx->nested.msrs.secondary_ctls_low,
                                 vmx->nested.msrs.secondary_ctls_high))
                return -EINVAL;

        if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu) ||
            nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) ||
            nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) ||
            nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) ||
            nested_vmx_check_apic_access_controls(vcpu, vmcs12) ||
            nested_vmx_check_apicv_controls(vcpu, vmcs12) ||
            nested_vmx_check_nmi_controls(vmcs12) ||
            nested_vmx_check_pml_controls(vcpu, vmcs12) ||
            nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) ||
            nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) ||
            nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) ||
            (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id))
                return -EINVAL;

        if (!nested_cpu_has_preemption_timer(vmcs12) &&
            nested_cpu_has_save_preemption_timer(vmcs12))
                return -EINVAL;

        if (nested_cpu_has_ept(vmcs12) &&
            !valid_ept_address(vcpu, vmcs12->ept_pointer))
                return -EINVAL;

        if (nested_cpu_has_vmfunc(vmcs12)) {
                if (vmcs12->vm_function_control &
                    ~vmx->nested.msrs.vmfunc_controls)
                        return -EINVAL;

                if (nested_cpu_has_eptp_switching(vmcs12)) {
                        if (!nested_cpu_has_ept(vmcs12) ||
                            !page_address_valid(vcpu, vmcs12->eptp_list_address))
                                return -EINVAL;
                }
        }

        return 0;
}

/*
 * Checks related to VM-Exit Control Fields
 */
static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu,
                                         struct vmcs12 *vmcs12)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!vmx_control_verify(vmcs12->vm_exit_controls,
                                vmx->nested.msrs.exit_ctls_low,
                                vmx->nested.msrs.exit_ctls_high) ||
            nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12))
                return -EINVAL;

        return 0;
}

/*
 * Checks related to VM-Entry Control Fields
 */
static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
                                          struct vmcs12 *vmcs12)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);

        if (!vmx_control_verify(vmcs12->vm_entry_controls,
                                vmx->nested.msrs.entry_ctls_low,
                                vmx->nested.msrs.entry_ctls_high))
                return -EINVAL;

        /*
         * From the Intel SDM, volume 3:
         * Fields relevant to VM-entry event injection must be set properly.
         * These fields are the VM-entry interruption-information field, the
         * VM-entry exception error code, and the VM-entry instruction length.
         */
        if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
                u32 intr_info = vmcs12->vm_entry_intr_info_field;
                u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
                u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
                bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
                bool should_have_error_code;
                bool urg = nested_cpu_has2(vmcs12,
                                           SECONDARY_EXEC_UNRESTRICTED_GUEST);
                bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;

                /* VM-entry interruption-info field: interruption type */
                if (intr_type == INTR_TYPE_RESERVED ||
                    (intr_type == INTR_TYPE_OTHER_EVENT &&
                     !nested_cpu_supports_monitor_trap_flag(vcpu)))
                        return -EINVAL;

                /* VM-entry interruption-info field: vector */
                if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
                    (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
                    (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
                        return -EINVAL;

                /* VM-entry interruption-info field: deliver error code */
                should_have_error_code =
                        intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
                        x86_exception_has_error_code(vector);
                if (has_error_code != should_have_error_code)
                        return -EINVAL;

                /* VM-entry exception error code */
                if (has_error_code &&
                    vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
                        return -EINVAL;

                /* VM-entry interruption-info field: reserved bits */
                if (intr_info & INTR_INFO_RESVD_BITS_MASK)
                        return -EINVAL;

                /* VM-entry instruction length */
                switch (intr_type) {
                case INTR_TYPE_SOFT_EXCEPTION:
                case INTR_TYPE_SOFT_INTR:
                case INTR_TYPE_PRIV_SW_EXCEPTION:
                        if ((vmcs12->vm_entry_instruction_len > 15) ||
                            (vmcs12->vm_entry_instruction_len == 0 &&
                             !nested_cpu_has_zero_length_injection(vcpu)))
                                return -EINVAL;
                }
        }

        if (nested_vmx_check_entry_msr_switch_controls(vcpu, vmcs12))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
                                     struct vmcs12 *vmcs12)
{
        if (nested_check_vm_execution_controls(vcpu, vmcs12) ||
            nested_check_vm_exit_controls(vcpu, vmcs12) ||
            nested_check_vm_entry_controls(vcpu, vmcs12))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
                                       struct vmcs12 *vmcs12)
{
        bool ia32e;

        if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
            !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
            !nested_cr3_valid(vcpu, vmcs12->host_cr3))
                return -EINVAL;

        if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) ||
            is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))
                return -EINVAL;

        if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
            !kvm_pat_valid(vmcs12->host_ia32_pat))
                return -EINVAL;

        ia32e = (vmcs12->vm_exit_controls &
                 VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;

        if (vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) ||
            vmcs12->host_cs_selector == 0 ||
            vmcs12->host_tr_selector == 0 ||
            (vmcs12->host_ss_selector == 0 && !ia32e))
                return -EINVAL;

#ifdef CONFIG_X86_64
        if (is_noncanonical_address(vmcs12->host_fs_base, vcpu) ||
            is_noncanonical_address(vmcs12->host_gs_base, vcpu) ||
            is_noncanonical_address(vmcs12->host_gdtr_base, vcpu) ||
            is_noncanonical_address(vmcs12->host_idtr_base, vcpu) ||
            is_noncanonical_address(vmcs12->host_tr_base, vcpu))
                return -EINVAL;
#endif

        /*
         * If the load IA32_EFER VM-exit control is 1, bits reserved in the
         * IA32_EFER MSR must be 0 in the field for that register. In addition,
         * the values of the LMA and LME bits in the field must each be that of
         * the host address-space size VM-exit control.
         */
        if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
                if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
                    ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
                    ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
                        return -EINVAL;
        }

        return 0;
}

static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
                                          struct vmcs12 *vmcs12)
{
        int r = 0;
        struct vmcs12 *shadow;
        struct kvm_host_map map;

        if (vmcs12->vmcs_link_pointer == -1ull)
                return 0;

        if (!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))
                return -EINVAL;

        if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
                return -EINVAL;

        shadow = map.hva;

        if (shadow->hdr.revision_id != VMCS12_REVISION ||
            shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))
                r = -EINVAL;

        kvm_vcpu_unmap(vcpu, &map, false);
        return r;
}

/*
 * Checks related to Guest Non-register State
 */
static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
{
        if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
            vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
                                        struct vmcs12 *vmcs12,
                                        u32 *exit_qual)
{
        bool ia32e;

        *exit_qual = ENTRY_FAIL_DEFAULT;

        if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) ||
            !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))
                return -EINVAL;

        if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
            !kvm_pat_valid(vmcs12->guest_ia32_pat))
                return -EINVAL;

        if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
                *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR;
                return -EINVAL;
        }

        /*
         * If the load IA32_EFER VM-entry control is 1, the following checks
         * are performed on the field for the IA32_EFER MSR:
         * - Bits reserved in the IA32_EFER MSR must be 0.
         * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of
         *   the IA-32e mode guest VM-exit control. It must also be identical
         *   to bit 8 (LME) if bit 31 in the CR0 field (corresponding to
         *   CR0.PG) is 1.
         */
        if (to_vmx(vcpu)->nested.nested_run_pending &&
            (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
                ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
                if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) ||
                    ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) ||
                    ((vmcs12->guest_cr0 & X86_CR0_PG) &&
                     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))
                        return -EINVAL;
        }

        if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
            (is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
             (vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
                return -EINVAL;

        if (nested_check_guest_non_reg_state(vmcs12))
                return -EINVAL;

        return 0;
}

static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        unsigned long cr3, cr4;
        bool vm_fail;

        if (!nested_early_check)
                return 0;

        if (vmx->msr_autoload.host.nr)
                vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
        if (vmx->msr_autoload.guest.nr)
                vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);

        preempt_disable();

        vmx_prepare_switch_to_guest(vcpu);

        /*
         * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
         * which is reserved to '1' by hardware.  GUEST_RFLAGS is guaranteed to
         * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
         * there is no need to preserve other bits or save/restore the field.
         */
        vmcs_writel(GUEST_RFLAGS, 0);

        cr3 = __get_current_cr3_fast();
        if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
                vmcs_writel(HOST_CR3, cr3);
                vmx->loaded_vmcs->host_state.cr3 = cr3;
        }

        cr4 = cr4_read_shadow();
        if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
                vmcs_writel(HOST_CR4, cr4);
                vmx->loaded_vmcs->host_state.cr4 = cr4;
        }

        asm(
                "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */
                "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
                "je 1f \n\t"
                __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t"
                "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
                "1: \n\t"
                "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */

                /* Check if vmlaunch or vmresume is needed */
                "cmpb $0, %c[launched](%[loaded_vmcs])\n\t"

                /*
                 * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set
                 * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail
                 * Valid.  vmx_vmenter() directly "returns" RFLAGS, and so the
                 * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail.
                 */
                "call vmx_vmenter\n\t"

                CC_SET(be)
              : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail)
              : [HOST_RSP]"r"((unsigned long)HOST_RSP),
                [loaded_vmcs]"r"(vmx->loaded_vmcs),
                [launched]"i"(offsetof(struct loaded_vmcs, launched)),
                [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)),
                [wordsize]"i"(sizeof(ulong))
              : "memory"
        );

        if (vmx->msr_autoload.host.nr)
                vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
        if (vmx->msr_autoload.guest.nr)
                vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);

        if (vm_fail) {
                preempt_enable();
                WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
                             VMXERR_ENTRY_INVALID_CONTROL_FIELD);
                return 1;
        }

        /*
         * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
         */
        local_irq_enable();
        if (hw_breakpoint_active())
                set_debugreg(__this_cpu_read(cpu_dr7), 7);
        preempt_enable();

        /*
         * A non-failing VMEntry means we somehow entered guest mode with
         * an illegal RIP, and that's just the tip of the iceberg.  There
         * is no telling what memory has been modified or what state has
         * been exposed to unknown code.  Hitting this all but guarantees
         * a (very critical) hardware issue.
         */
        WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
                VMX_EXIT_REASONS_FAILED_VMENTRY));

        return 0;
}

static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
                                                 struct vmcs12 *vmcs12);

static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
{
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        struct kvm_host_map *map;
        struct page *page;
        u64 hpa;

        if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
                /*
                 * Translate L1 physical address to host physical
                 * address for vmcs02. Keep the page pinned, so this
                 * physical address remains valid. We keep a reference
                 * to it so we can release it later.
                 */
                if (vmx->nested.apic_access_page) { /* shouldn't happen */
                        kvm_release_page_dirty(vmx->nested.apic_access_page);
                        vmx->nested.apic_access_page = NULL;
                }
                page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
                /*
                 * If translation failed, no matter: This feature asks
                 * to exit when accessing the given address, and if it
                 * can never be accessed, this feature won't do
                 * anything anyway.
                 */
                if (!is_error_page(page)) {
                        vmx->nested.apic_access_page = page;
                        hpa = page_to_phys(vmx->nested.apic_access_page);
                        vmcs_write64(APIC_ACCESS_ADDR, hpa);
                } else {
                        secondary_exec_controls_clearbit(vmx,
                                SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
                }
        }

        if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
                map = &vmx->nested.virtual_apic_map;

                if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->virtual_apic_page_addr), map)) {
                        vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, pfn_to_hpa(map->pfn));
                } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
                           nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
                           !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
                        /*
                         * The processor will never use the TPR shadow, simply
                         * clear the bit from the execution control.  Such a
                         * configuration is useless, but it happens in tests.
                         * For any other configuration, failing the vm entry is
                         * _not_ what the processor does but it's basically the
                         * only possibility we have.
                         */
                        exec_controls_clearbit(vmx, CPU_BASED_TPR_SHADOW);
                } else {
                        /*
                         * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to
                         * force VM-Entry to fail.
                         */
                        vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
                }
        }

        if (nested_cpu_has_posted_intr(vmcs12)) {
                map = &vmx->nested.pi_desc_map;

                if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->posted_intr_desc_addr), map)) {
                        vmx->nested.pi_desc =
                                (struct pi_desc *)(((void *)map->hva) +
                                offset_in_page(vmcs12->posted_intr_desc_addr));
                        vmcs_write64(POSTED_INTR_DESC_ADDR,
                                     pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr));
                }
        }
        if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
                exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
        else
                exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
}

/*
 * Intel's VMX Instruction Reference specifies a common set of prerequisites
 * for running VMX instructions (except VMXON, whose prerequisites are
 * slightly different). It also specifies what exception to inject otherwise.
 * Note that many of these exceptions have priority over VM exits, so they
 * don't have to be checked again here.
 */
static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
{
        if (!to_vmx(vcpu)->nested.vmxon) {
                kvm_queue_exception(vcpu, UD_VECTOR);
                return 0;
        }

        if (vmx_get_cpl(vcpu)) {
                kvm_inject_gp(vcpu, 0);
                return 0;
        }

        return 1;
}

static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
{
        u8 rvi = vmx_get_rvi();
        u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);

        return ((rvi & 0xf0) > (vppr & 0xf0));
}

static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
                                   struct vmcs12 *vmcs12);

/*
 * If from_vmentry is false, this is being called from state restore (either RSM
 * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
+ *
+ * Returns:
+ *   0 - success, i.e. proceed with actual VMEnter
+ *   1 - consistency check VMExit
+ *  -1 - consistency check VMFail
 */
int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
{
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
        bool evaluate_pending_interrupts;
        u32 exit_reason = EXIT_REASON_INVALID_STATE;