/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * derived from drivers/kvm/kvm_main.c
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2008 Qumranet, Inc.
 * Copyright IBM Corporation, 2008
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <linux/kvm_host.h>
#include "irq.h"
#include "mmu.h"
#include "i8254.h"
#include "tss.h"
#include "kvm_cache_regs.h"
#include "x86.h"

#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/mman.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
#include <linux/cpufreq.h>

#include <asm/uaccess.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mtrr.h>

#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS                                               \
        (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
                          | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
                          | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
#define CR4_RESERVED_BITS                                               \
        (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
                          | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
                          | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR  \
                          | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))

#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
/* EFER defaults:
 * - enable syscall per default because its emulated by KVM
 * - enable LME and LMA per default on 64 bit KVM
 */
#ifdef CONFIG_X86_64
static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL;
#else
static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
#endif

#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
                                    struct kvm_cpuid_entry2 __user *entries);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
                                              u32 function, u32 index);

struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);

struct kvm_stats_debugfs_item debugfs_entries[] = {
        { "pf_fixed", VCPU_STAT(pf_fixed) },
        { "pf_guest", VCPU_STAT(pf_guest) },
        { "tlb_flush", VCPU_STAT(tlb_flush) },
        { "invlpg", VCPU_STAT(invlpg) },
        { "exits", VCPU_STAT(exits) },
        { "io_exits", VCPU_STAT(io_exits) },
        { "mmio_exits", VCPU_STAT(mmio_exits) },
        { "signal_exits", VCPU_STAT(signal_exits) },
        { "irq_window", VCPU_STAT(irq_window_exits) },
        { "nmi_window", VCPU_STAT(nmi_window_exits) },
        { "halt_exits", VCPU_STAT(halt_exits) },
        { "halt_wakeup", VCPU_STAT(halt_wakeup) },
        { "hypercalls", VCPU_STAT(hypercalls) },
        { "request_irq", VCPU_STAT(request_irq_exits) },
        { "irq_exits", VCPU_STAT(irq_exits) },
        { "host_state_reload", VCPU_STAT(host_state_reload) },
        { "efer_reload", VCPU_STAT(efer_reload) },
        { "fpu_reload", VCPU_STAT(fpu_reload) },
        { "insn_emulation", VCPU_STAT(insn_emulation) },
        { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
        { "irq_injections", VCPU_STAT(irq_injections) },
        { "nmi_injections", VCPU_STAT(nmi_injections) },
        { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
        { "mmu_pte_write", VM_STAT(mmu_pte_write) },
        { "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
        { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
        { "mmu_flooded", VM_STAT(mmu_flooded) },
        { "mmu_recycled", VM_STAT(mmu_recycled) },
        { "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
        { "mmu_unsync", VM_STAT(mmu_unsync) },
        { "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
        { "largepages", VM_STAT(lpages) },
        { NULL }
};

unsigned long segment_base(u16 selector)
{
        struct descriptor_table gdt;
        struct desc_struct *d;
        unsigned long table_base;
        unsigned long v;

        if (selector == 0)
                return 0;

        asm("sgdt %0" : "=m"(gdt));
        table_base = gdt.base;

        if (selector & 4) {           /* from ldt */
                u16 ldt_selector;

                asm("sldt %0" : "=g"(ldt_selector));
                table_base = segment_base(ldt_selector);
        }
        d = (struct desc_struct *)(table_base + (selector & ~7));
        v = d->base0 | ((unsigned long)d->base1 << 16) |
                ((unsigned long)d->base2 << 24);
#ifdef CONFIG_X86_64
        if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
                v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
#endif
        return v;
}
EXPORT_SYMBOL_GPL(segment_base);

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
        if (irqchip_in_kernel(vcpu->kvm))
                return vcpu->arch.apic_base;
        else
                return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);

void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
        /* TODO: reserve bits check */
        if (irqchip_in_kernel(vcpu->kvm))
                kvm_lapic_set_base(vcpu, data);
        else
                vcpu->arch.apic_base = data;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
        WARN_ON(vcpu->arch.exception.pending);
        vcpu->arch.exception.pending = true;
        vcpu->arch.exception.has_error_code = false;
        vcpu->arch.exception.nr = nr;
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);

void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
                           u32 error_code)
{
        ++vcpu->stat.pf_guest;

        if (vcpu->arch.exception.pending) {
                if (vcpu->arch.exception.nr == PF_VECTOR) {
                        printk(KERN_DEBUG "kvm: inject_page_fault:"
                                        " double fault 0x%lx\n", addr);
                        vcpu->arch.exception.nr = DF_VECTOR;
                        vcpu->arch.exception.error_code = 0;
                } else if (vcpu->arch.exception.nr == DF_VECTOR) {
                        /* triple fault -> shutdown */
                        set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
                }
                return;
        }
        vcpu->arch.cr2 = addr;
        kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
}

void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
        vcpu->arch.nmi_pending = 1;
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);

void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
        WARN_ON(vcpu->arch.exception.pending);
        vcpu->arch.exception.pending = true;
        vcpu->arch.exception.has_error_code = true;
        vcpu->arch.exception.nr = nr;
        vcpu->arch.exception.error_code = error_code;
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);

static void __queue_exception(struct kvm_vcpu *vcpu)
{
        kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
                                     vcpu->arch.exception.has_error_code,
                                     vcpu->arch.exception.error_code);
}

/*
 * Load the pae pdptrs.  Return true is they are all valid.
 */
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
{
        gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
        unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
        int i;
        int ret;
        u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];

        ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
                                  offset * sizeof(u64), sizeof(pdpte));
        if (ret < 0) {
                ret = 0;
                goto out;
        }
        for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
                if (is_present_pte(pdpte[i]) &&
                    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
                        ret = 0;
                        goto out;
                }
        }
        ret = 1;

        memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
out:

        return ret;
}
EXPORT_SYMBOL_GPL(load_pdptrs);

static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
        u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
        bool changed = true;
        int r;

        if (is_long_mode(vcpu) || !is_pae(vcpu))
                return false;

        r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
        if (r < 0)
                goto out;
        changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
out:

        return changed;
}

void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
        if (cr0 & CR0_RESERVED_BITS) {
                printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
                       cr0, vcpu->arch.cr0);
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
                printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
                printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
                       "and a clear PE flag\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
                if ((vcpu->arch.shadow_efer & EFER_LME)) {
                        int cs_db, cs_l;

                        if (!is_pae(vcpu)) {
                                printk(KERN_DEBUG "set_cr0: #GP, start paging "
                                       "in long mode while PAE is disabled\n");
                                kvm_inject_gp(vcpu, 0);
                                return;
                        }
                        kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
                        if (cs_l) {
                                printk(KERN_DEBUG "set_cr0: #GP, start paging "
                                       "in long mode while CS.L == 1\n");
                                kvm_inject_gp(vcpu, 0);
                                return;

                        }
                } else
#endif
                if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
                        printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
                               "reserved bits\n");
                        kvm_inject_gp(vcpu, 0);
                        return;
                }

        }

        kvm_x86_ops->set_cr0(vcpu, cr0);
        vcpu->arch.cr0 = cr0;

        kvm_mmu_reset_context(vcpu);
        return;
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);

void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
        kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
        KVMTRACE_1D(LMSW, vcpu,
                    (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)),
                    handler);
}
EXPORT_SYMBOL_GPL(kvm_lmsw);

void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
        unsigned long old_cr4 = vcpu->arch.cr4;
        unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;

        if (cr4 & CR4_RESERVED_BITS) {
                printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if (is_long_mode(vcpu)) {
                if (!(cr4 & X86_CR4_PAE)) {
                        printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
                               "in long mode\n");
                        kvm_inject_gp(vcpu, 0);
                        return;
                }
        } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
                   && ((cr4 ^ old_cr4) & pdptr_bits)
                   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
                printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if (cr4 & X86_CR4_VMXE) {
                printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }
        kvm_x86_ops->set_cr4(vcpu, cr4);
        vcpu->arch.cr4 = cr4;
        vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
        kvm_mmu_reset_context(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
        if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
                kvm_mmu_sync_roots(vcpu);
                kvm_mmu_flush_tlb(vcpu);
                return;
        }

        if (is_long_mode(vcpu)) {
                if (cr3 & CR3_L_MODE_RESERVED_BITS) {
                        printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
                        kvm_inject_gp(vcpu, 0);
                        return;
                }
        } else {
                if (is_pae(vcpu)) {
                        if (cr3 & CR3_PAE_RESERVED_BITS) {
                                printk(KERN_DEBUG
                                       "set_cr3: #GP, reserved bits\n");
                                kvm_inject_gp(vcpu, 0);
                                return;
                        }
                        if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
                                printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
                                       "reserved bits\n");
                                kvm_inject_gp(vcpu, 0);
                                return;
                        }
                }
                /*
                 * We don't check reserved bits in nonpae mode, because
                 * this isn't enforced, and VMware depends on this.
                 */
        }

        /*
         * Does the new cr3 value map to physical memory? (Note, we
         * catch an invalid cr3 even in real-mode, because it would
         * cause trouble later on when we turn on paging anyway.)
         *
         * A real CPU would silently accept an invalid cr3 and would
         * attempt to use it - with largely undefined (and often hard
         * to debug) behavior on the guest side.
         */
        if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
                kvm_inject_gp(vcpu, 0);
        else {
                vcpu->arch.cr3 = cr3;
                vcpu->arch.mmu.new_cr3(vcpu);
        }
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);

void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
        if (cr8 & CR8_RESERVED_BITS) {
                printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
                kvm_inject_gp(vcpu, 0);
                return;
        }
        if (irqchip_in_kernel(vcpu->kvm))
                kvm_lapic_set_tpr(vcpu, cr8);
        else
                vcpu->arch.cr8 = cr8;
}
EXPORT_SYMBOL_GPL(kvm_set_cr8);

unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
{
        if (irqchip_in_kernel(vcpu->kvm))
                return kvm_lapic_get_cr8(vcpu);
        else
                return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);

static inline u32 bit(int bitno)
{
        return 1 << (bitno & 31);
}

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * This list is modified at module load time to reflect the
 * capabilities of the host cpu.
 */
static u32 msrs_to_save[] = {
        MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
        MSR_K6_STAR,
#ifdef CONFIG_X86_64
        MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
        MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
        MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
};

static unsigned num_msrs_to_save;

static u32 emulated_msrs[] = {
        MSR_IA32_MISC_ENABLE,
};

static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
        if (efer & efer_reserved_bits) {
                printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
                       efer);
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if (is_paging(vcpu)
            && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) {
                printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
                kvm_inject_gp(vcpu, 0);
                return;
        }

        if (efer & EFER_FFXSR) {
                struct kvm_cpuid_entry2 *feat;

                feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
                if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
                        printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
                        kvm_inject_gp(vcpu, 0);
                        return;
                }
        }

        if (efer & EFER_SVME) {
                struct kvm_cpuid_entry2 *feat;

                feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
                if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
                        printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
                        kvm_inject_gp(vcpu, 0);
                        return;
                }
        }

        kvm_x86_ops->set_efer(vcpu, efer);

        efer &= ~EFER_LMA;
        efer |= vcpu->arch.shadow_efer & EFER_LMA;

        vcpu->arch.shadow_efer = efer;

        vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
        kvm_mmu_reset_context(vcpu);
}

void kvm_enable_efer_bits(u64 mask)
{
       efer_reserved_bits &= ~mask;
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);


/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
        return kvm_x86_ops->set_msr(vcpu, msr_index, data);
}

/*
 * Adapt set_msr() to msr_io()'s calling convention
 */
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
        return kvm_set_msr(vcpu, index, *data);
}

static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
        static int version;
        struct pvclock_wall_clock wc;
        struct timespec now, sys, boot;

        if (!wall_clock)
                return;

        version++;

        kvm_write_guest(kvm, wall_clock, &version, sizeof(version));

        /*
         * The guest calculates current wall clock time by adding
         * system time (updated by kvm_write_guest_time below) to the
         * wall clock specified here.  guest system time equals host
         * system time for us, thus we must fill in host boot time here.
         */
        now = current_kernel_time();
        ktime_get_ts(&sys);
        boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));

        wc.sec = boot.tv_sec;
        wc.nsec = boot.tv_nsec;
        wc.version = version;

        kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));

        version++;
        kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
}

static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
        uint32_t quotient, remainder;

        /* Don't try to replace with do_div(), this one calculates
         * "(dividend << 32) / divisor" */
        __asm__ ( "divl %4"
                  : "=a" (quotient), "=d" (remainder)
                  : "0" (0), "1" (dividend), "r" (divisor) );
        return quotient;
}

static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
{
        uint64_t nsecs = 1000000000LL;
        int32_t  shift = 0;
        uint64_t tps64;
        uint32_t tps32;

        tps64 = tsc_khz * 1000LL;
        while (tps64 > nsecs*2) {
                tps64 >>= 1;
                shift--;
        }

        tps32 = (uint32_t)tps64;
        while (tps32 <= (uint32_t)nsecs) {
                tps32 <<= 1;
                shift++;
        }

        hv_clock->tsc_shift = shift;
        hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);

        pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
                 __func__, tsc_khz, hv_clock->tsc_shift,
                 hv_clock->tsc_to_system_mul);
}

static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);

static void kvm_write_guest_time(struct kvm_vcpu *v)
{
        struct timespec ts;
        unsigned long flags;
        struct kvm_vcpu_arch *vcpu = &v->arch;
        void *shared_kaddr;
        unsigned long this_tsc_khz;

        if ((!vcpu->time_page))
                return;

        this_tsc_khz = get_cpu_var(cpu_tsc_khz);
        if (unlikely(vcpu->hv_clock_tsc_khz != this_tsc_khz)) {
                kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
                vcpu->hv_clock_tsc_khz = this_tsc_khz;
        }
        put_cpu_var(cpu_tsc_khz);

        /* Keep irq disabled to prevent changes to the clock */
        local_irq_save(flags);
        kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
                          &vcpu->hv_clock.tsc_timestamp);
        ktime_get_ts(&ts);
        local_irq_restore(flags);

        /* With all the info we got, fill in the values */

        vcpu->hv_clock.system_time = ts.tv_nsec +
                                     (NSEC_PER_SEC * (u64)ts.tv_sec);
        /*
         * The interface expects us to write an even number signaling that the
         * update is finished. Since the guest won't see the intermediate
         * state, we just increase by 2 at the end.
         */
        vcpu->hv_clock.version += 2;

        shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);

        memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
               sizeof(vcpu->hv_clock));

        kunmap_atomic(shared_kaddr, KM_USER0);

        mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
}

static int kvm_request_guest_time_update(struct kvm_vcpu *v)
{
        struct kvm_vcpu_arch *vcpu = &v->arch;

        if (!vcpu->time_page)
                return 0;
        set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
        return 1;
}

static bool msr_mtrr_valid(unsigned msr)
{
        switch (msr) {
        case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
        case MSR_MTRRfix64K_00000:
        case MSR_MTRRfix16K_80000:
        case MSR_MTRRfix16K_A0000:
        case MSR_MTRRfix4K_C0000:
        case MSR_MTRRfix4K_C8000:
        case MSR_MTRRfix4K_D0000:
        case MSR_MTRRfix4K_D8000:
        case MSR_MTRRfix4K_E0000:
        case MSR_MTRRfix4K_E8000:
        case MSR_MTRRfix4K_F0000:
        case MSR_MTRRfix4K_F8000:
        case MSR_MTRRdefType:
        case MSR_IA32_CR_PAT:
                return true;
        case 0x2f8:
                return true;
        }
        return false;
}

static bool valid_pat_type(unsigned t)
{
        return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
}

static bool valid_mtrr_type(unsigned t)
{
        return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
}

static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
        int i;

        if (!msr_mtrr_valid(msr))
                return false;

        if (msr == MSR_IA32_CR_PAT) {
                for (i = 0; i < 8; i++)
                        if (!valid_pat_type((data >> (i * 8)) & 0xff))
                                return false;
                return true;
        } else if (msr == MSR_MTRRdefType) {
                if (data & ~0xcff)
                        return false;
                return valid_mtrr_type(data & 0xff);
        } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
                for (i = 0; i < 8 ; i++)
                        if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
                                return false;
                return true;
        }

        /* variable MTRRs */
        return valid_mtrr_type(data & 0xff);
}

static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
        u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

        if (!mtrr_valid(vcpu, msr, data))
                return 1;

        if (msr == MSR_MTRRdefType) {
                vcpu->arch.mtrr_state.def_type = data;
                vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
        } else if (msr == MSR_MTRRfix64K_00000)
                p[0] = data;
        else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
                p[1 + msr - MSR_MTRRfix16K_80000] = data;
        else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
                p[3 + msr - MSR_MTRRfix4K_C0000] = data;
        else if (msr == MSR_IA32_CR_PAT)
                vcpu->arch.pat = data;
        else {  /* Variable MTRRs */
                int idx, is_mtrr_mask;
                u64 *pt;

                idx = (msr - 0x200) / 2;
                is_mtrr_mask = msr - 0x200 - 2 * idx;
                if (!is_mtrr_mask)
                        pt =
                          (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
                else
                        pt =
                          (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
                *pt = data;
        }

        kvm_mmu_reset_context(vcpu);
        return 0;
}

int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
        switch (msr) {
        case MSR_EFER:
                set_efer(vcpu, data);
                break;
        case MSR_IA32_MC0_STATUS:
                pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
                       __func__, data);
                break;
        case MSR_IA32_MCG_STATUS:
                pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
                        __func__, data);
                break;
        case MSR_IA32_MCG_CTL:
                pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n",
                        __func__, data);
                break;
        case MSR_IA32_DEBUGCTLMSR:
                if (!data) {
                        /* We support the non-activated case already */
                        break;
                } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) {
                        /* Values other than LBR and BTF are vendor-specific,
                           thus reserved and should throw a #GP */
                        return 1;
                }
                pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
                        __func__, data);
                break;
        case MSR_IA32_UCODE_REV:
        case MSR_IA32_UCODE_WRITE:
        case MSR_VM_HSAVE_PA:
                break;
        case 0x200 ... 0x2ff:
                return set_msr_mtrr(vcpu, msr, data);
        case MSR_IA32_APICBASE:
                kvm_set_apic_base(vcpu, data);
                break;
        case MSR_IA32_MISC_ENABLE:
                vcpu->arch.ia32_misc_enable_msr = data;
                break;
        case MSR_KVM_WALL_CLOCK:
                vcpu->kvm->arch.wall_clock = data;
                kvm_write_wall_clock(vcpu->kvm, data);
                break;
        case MSR_KVM_SYSTEM_TIME: {
                if (vcpu->arch.time_page) {
                        kvm_release_page_dirty(vcpu->arch.time_page);
                        vcpu->arch.time_page = NULL;
                }

                vcpu->arch.time = data;

                /* we verify if the enable bit is set... */
                if (!(data & 1))
                        break;

                /* ...but clean it before doing the actual write */
                vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);

                vcpu->arch.time_page =
                                gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);

                if (is_error_page(vcpu->arch.time_page)) {
                        kvm_release_page_clean(vcpu->arch.time_page);
                        vcpu->arch.time_page = NULL;
                }

                kvm_request_guest_time_update(vcpu);
                break;
        }
        default:
                pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
                return 1;
        }
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);


/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
        return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
}

static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
        u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

        if (!msr_mtrr_valid(msr))
                return 1;

        if (msr == MSR_MTRRdefType)
                *pdata = vcpu->arch.mtrr_state.def_type +
                         (vcpu->arch.mtrr_state.enabled << 10);
        else if (msr == MSR_MTRRfix64K_00000)
                *pdata = p[0];
        else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
                *pdata = p[1 + msr - MSR_MTRRfix16K_80000];
        else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
                *pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
        else if (msr == MSR_IA32_CR_PAT)
                *pdata = vcpu->arch.pat;
        else {  /* Variable MTRRs */
                int idx, is_mtrr_mask;
                u64 *pt;

                idx = (msr - 0x200) / 2;
                is_mtrr_mask = msr - 0x200 - 2 * idx;
                if (!is_mtrr_mask)
                        pt =
                          (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
                else
                        pt =
                          (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
                *pdata = *pt;
        }

        return 0;
}

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
        u64 data;

        switch (msr) {
        case 0xc0010010: /* SYSCFG */
        case 0xc0010015: /* HWCR */
        case MSR_IA32_PLATFORM_ID:
        case MSR_IA32_P5_MC_ADDR:
        case MSR_IA32_P5_MC_TYPE:
        case MSR_IA32_MC0_CTL:
        case MSR_IA32_MCG_STATUS:
        case MSR_IA32_MCG_CAP:
        case MSR_IA32_MCG_CTL:
        case MSR_IA32_MC0_MISC:
        case MSR_IA32_MC0_MISC+4:
        case MSR_IA32_MC0_MISC+8:
        case MSR_IA32_MC0_MISC+12:
        case MSR_IA32_MC0_MISC+16:
        case MSR_IA32_MC0_MISC+20:
        case MSR_IA32_UCODE_REV:
        case MSR_IA32_EBL_CR_POWERON:
        case MSR_IA32_DEBUGCTLMSR:
        case MSR_IA32_LASTBRANCHFROMIP:
        case MSR_IA32_LASTBRANCHTOIP:
        case MSR_IA32_LASTINTFROMIP:
        case MSR_IA32_LASTINTTOIP:
        case MSR_VM_HSAVE_PA:
        case MSR_P6_EVNTSEL0:
        case MSR_P6_EVNTSEL1:
        case MSR_K7_EVNTSEL0:
                data = 0;
                break;
        case MSR_MTRRcap:
                data = 0x500 | KVM_NR_VAR_MTRR;
                break;
        case 0x200 ... 0x2ff:
                return get_msr_mtrr(vcpu, msr, pdata);
        case 0xcd: /* fsb frequency */
                data = 3;
                break;
        case MSR_IA32_APICBASE:
                data = kvm_get_apic_base(vcpu);
                break;
        case MSR_IA32_MISC_ENABLE:
                data = vcpu->arch.ia32_misc_enable_msr;
                break;
        case MSR_IA32_PERF_STATUS:
                /* TSC increment by tick */
                data = 1000ULL;
                /* CPU multiplier */
                data |= (((uint64_t)4ULL) << 40);
                break;
        case MSR_EFER:
                data = vcpu->arch.shadow_efer;
                break;
        case MSR_KVM_WALL_CLOCK:
                data = vcpu->kvm->arch.wall_clock;
                break;
        case MSR_KVM_SYSTEM_TIME:
                data = vcpu->arch.time;
                break;
        default:
                pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
                return 1;
        }
        *pdata = data;
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);

/*
 * Read or write a bunch of msrs. All parameters are kernel addresses.
 *
 * @return number of msrs set successfully.
 */
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
                    struct kvm_msr_entry *entries,
                    int (*do_msr)(struct kvm_vcpu *vcpu,
                                  unsigned index, u64 *data))
{
        int i;

        vcpu_load(vcpu);

        down_read(&vcpu->kvm->slots_lock);
        for (i = 0; i < msrs->nmsrs; ++i)
                if (do_msr(vcpu, entries[i].index, &entries[i].data))
                        break;
        up_read(&vcpu->kvm->slots_lock);

        vcpu_put(vcpu);

        return i;
}

/*
 * Read or write a bunch of msrs. Parameters are user addresses.
 *
 * @return number of msrs set successfully.
 */
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
                  int (*do_msr)(struct kvm_vcpu *vcpu,
                                unsigned index, u64 *data),
                  int writeback)
{
        struct kvm_msrs msrs;
        struct kvm_msr_entry *entries;
        int r, n;
        unsigned size;

        r = -EFAULT;
        if (copy_from_user(&msrs, user_msrs, sizeof msrs))
                goto out;

        r = -E2BIG;
        if (msrs.nmsrs >= MAX_IO_MSRS)
                goto out;

        r = -ENOMEM;
        size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
        entries = vmalloc(size);
        if (!entries)
                goto out;

        r = -EFAULT;
        if (copy_from_user(entries, user_msrs->entries, size))
                goto out_free;

        r = n = __msr_io(vcpu, &msrs, entries, do_msr);
        if (r < 0)
                goto out_free;

        r = -EFAULT;
        if (writeback && copy_to_user(user_msrs->entries, entries, size))
                goto out_free;

        r = n;

out_free:
        vfree(entries);
out:
        return r;
}

int kvm_dev_ioctl_check_extension(long ext)
{
        int r;

        switch (ext) {
        case KVM_CAP_IRQCHIP:
        case KVM_CAP_HLT:
        case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
        case KVM_CAP_SET_TSS_ADDR:
        case KVM_CAP_EXT_CPUID:
        case KVM_CAP_CLOCKSOURCE:
        case KVM_CAP_PIT:
        case KVM_CAP_NOP_IO_DELAY:
        case KVM_CAP_MP_STATE:
        case KVM_CAP_SYNC_MMU:
        case KVM_CAP_REINJECT_CONTROL:
        case KVM_CAP_IRQ_INJECT_STATUS:
        case KVM_CAP_ASSIGN_DEV_IRQ:
                r = 1;
                break;
        case KVM_CAP_COALESCED_MMIO:
                r = KVM_COALESCED_MMIO_PAGE_OFFSET;
                break;
        case KVM_CAP_VAPIC:
                r = !kvm_x86_ops->cpu_has_accelerated_tpr();
                break;
        case KVM_CAP_NR_VCPUS:
                r = KVM_MAX_VCPUS;
                break;
        case KVM_CAP_NR_MEMSLOTS:
                r = KVM_MEMORY_SLOTS;
                break;
        case KVM_CAP_PV_MMU:
                r = !tdp_enabled;
                break;
        case KVM_CAP_IOMMU:
                r = iommu_found();
                break;
        default:
                r = 0;
                break;
        }
        return r;

}

long kvm_arch_dev_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
{
        void __user *argp = (void __user *)arg;
        long r;

        switch (ioctl) {
        case KVM_GET_MSR_INDEX_LIST: {
                struct kvm_msr_list __user *user_msr_list = argp;
                struct kvm_msr_list msr_list;
                unsigned n;

                r = -EFAULT;
                if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
                        goto out;
                n = msr_list.nmsrs;
                msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
                if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
                        goto out;
                r = -E2BIG;
                if (n < msr_list.nmsrs)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(user_msr_list->indices, &msrs_to_save,
                                 num_msrs_to_save * sizeof(u32)))
                        goto out;
                if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
                                 &emulated_msrs,
                                 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
                        goto out;
                r = 0;
                break;
        }
        case KVM_GET_SUPPORTED_CPUID: {
                struct kvm_cpuid2 __user *cpuid_arg = argp;
                struct kvm_cpuid2 cpuid;

                r = -EFAULT;
                if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
                        goto out;
                r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
                                                      cpuid_arg->entries);
                if (r)
                        goto out;

                r = -EFAULT;
                if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
                        goto out;
                r = 0;
                break;
        }
        default:
                r = -EINVAL;
        }
out:
        return r;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
        kvm_x86_ops->vcpu_load(vcpu, cpu);
        kvm_request_guest_time_update(vcpu);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
        kvm_x86_ops->vcpu_put(vcpu);
        kvm_put_guest_fpu(vcpu);
}

static int is_efer_nx(void)
{
        unsigned long long efer = 0;

        rdmsrl_safe(MSR_EFER, &efer);
        return efer & EFER_NX;
}

static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
{
        int i;
        struct kvm_cpuid_entry2 *e, *entry;

        entry = NULL;
        for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
                e = &vcpu->arch.cpuid_entries[i];
                if (e->function == 0x80000001) {
                        entry = e;
                        break;
                }
        }
        if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
                entry->edx &= ~(1 << 20);
                printk(KERN_INFO "kvm: guest NX capability removed\n");
        }
}

/* when an old userspace process fills a new kernel module */
static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
                                    struct kvm_cpuid *cpuid,
                                    struct kvm_cpuid_entry __user *entries)
{
        int r, i;
        struct kvm_cpuid_entry *cpuid_entries;

        r = -E2BIG;
        if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
                goto out;
        r = -ENOMEM;
        cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
        if (!cpuid_entries)
                goto out;
        r = -EFAULT;
        if (copy_from_user(cpuid_entries, entries,
                           cpuid->nent * sizeof(struct kvm_cpuid_entry)))
                goto out_free;
        for (i = 0; i < cpuid->nent; i++) {
                vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
                vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
                vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
                vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
                vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
                vcpu->arch.cpuid_entries[i].index = 0;
                vcpu->arch.cpuid_entries[i].flags = 0;
                vcpu->arch.cpuid_entries[i].padding[0] = 0;
                vcpu->arch.cpuid_entries[i].padding[1] = 0;
                vcpu->arch.cpuid_entries[i].padding[2] = 0;
        }
        vcpu->arch.cpuid_nent = cpuid->nent;
        cpuid_fix_nx_cap(vcpu);
        r = 0;

out_free:
        vfree(cpuid_entries);
out:
        return r;
}

static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
                                     struct kvm_cpuid2 *cpuid,
                                     struct kvm_cpuid_entry2 __user *entries)
{
        int r;

        r = -E2BIG;
        if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
                goto out;
        r = -EFAULT;
        if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
                           cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
                goto out;
        vcpu->arch.cpuid_nent = cpuid->nent;
        return 0;

out:
        return r;
}

static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
                                     struct kvm_cpuid2 *cpuid,
                                     struct kvm_cpuid_entry2 __user *entries)
{
        int r;

        r = -E2BIG;
        if (cpuid->nent < vcpu->arch.cpuid_nent)
                goto out;
        r = -EFAULT;
        if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
                         vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
                goto out;
        return 0;

out:
        cpuid->nent = vcpu->arch.cpuid_nent;
        return r;
}

static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
                           u32 index)
{
        entry->function = function;
        entry->index = index;
        cpuid_count(entry->function, entry->index,
                    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
        entry->flags = 0;
}

#define F(x) bit(X86_FEATURE_##x)

static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
                         u32 index, int *nent, int maxnent)
{
        unsigned f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
        unsigned f_lm = F(LM);
#else
        unsigned f_lm = 0;
#endif

        /* cpuid 1.edx */
        const u32 kvm_supported_word0_x86_features =
                F(FPU) | F(VME) | F(DE) | F(PSE) |
                F(TSC) | F(MSR) | F(PAE) | F(MCE) |
                F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
                F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
                F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
                0 /* Reserved, DS, ACPI */ | F(MMX) |
                F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
                0 /* HTT, TM, Reserved, PBE */;
        /* cpuid 0x80000001.edx */
        const u32 kvm_supported_word1_x86_features =
                F(FPU) | F(VME) | F(DE) | F(PSE) |
                F(TSC) | F(MSR) | F(PAE) | F(MCE) |
                F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
                F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
                F(PAT) | F(PSE36) | 0 /* Reserved */ |
                f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
                F(FXSR) | F(FXSR_OPT) | 0 /* GBPAGES */ | 0 /* RDTSCP */ |
                0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
        /* cpuid 1.ecx */
        const u32 kvm_supported_word4_x86_features =
                F(XMM3) | 0 /* Reserved, DTES64, MONITOR */ |
                0 /* DS-CPL, VMX, SMX, EST */ |
                0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
                0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
                0 /* Reserved, DCA */ | F(XMM4_1) |
                F(XMM4_2) | 0 /* x2APIC */ | F(MOVBE) | F(POPCNT) |
                0 /* Reserved, XSAVE, OSXSAVE */;
        /* cpuid 0x80000001.ecx */
        const u32 kvm_supported_word6_x86_features =
                F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
                F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
                F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
                0 /* SKINIT */ | 0 /* WDT */;

        /* all calls to cpuid_count() should be made on the same cpu */
        get_cpu();
        do_cpuid_1_ent(entry, function, index);
        ++*nent;

        switch (function) {
        case 0:
                entry->eax = min(entry->eax, (u32)0xb);
                break;
        case 1:
                entry->edx &= kvm_supported_word0_x86_features;
                entry->ecx &= kvm_supported_word4_x86_features;
                break;
        /* function 2 entries are STATEFUL. That is, repeated cpuid commands
         * may return different values. This forces us to get_cpu() before
         * issuing the first command, and also to emulate this annoying behavior
         * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
        case 2: {
                int t, times = entry->eax & 0xff;

                entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
                entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
                for (t = 1; t < times && *nent < maxnent; ++t) {
                        do_cpuid_1_ent(&entry[t], function, 0);
                        entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
                        ++*nent;
                }
                break;
        }
        /* function 4 and 0xb have additional index. */
        case 4: {
                int i, cache_type;

                entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                /* read more entries until cache_type is zero */
                for (i = 1; *nent < maxnent; ++i) {
                        cache_type = entry[i - 1].eax & 0x1f;
                        if (!cache_type)
                                break;
                        do_cpuid_1_ent(&entry[i], function, i);
                        entry[i].flags |=
                               KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                        ++*nent;
                }
                break;
        }
        case 0xb: {
                int i, level_type;

                entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                /* read more entries until level_type is zero */
                for (i = 1; *nent < maxnent; ++i) {
                        level_type = entry[i - 1].ecx & 0xff00;
                        if (!level_type)
                                break;
                        do_cpuid_1_ent(&entry[i], function, i);
                        entry[i].flags |=
                               KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                        ++*nent;
                }
                break;
        }
        case 0x80000000:
                entry->eax = min(entry->eax, 0x8000001a);
                break;
        case 0x80000001:
                entry->edx &= kvm_supported_word1_x86_features;
                entry->ecx &= kvm_supported_word6_x86_features;
                break;
        }
        put_cpu();
}

#undef F

static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
                                     struct kvm_cpuid_entry2 __user *entries)
{
        struct kvm_cpuid_entry2 *cpuid_entries;
        int limit, nent = 0, r = -E2BIG;
        u32 func;

        if (cpuid->nent < 1)
                goto out;
        r = -ENOMEM;
        cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
        if (!cpuid_entries)
                goto out;

        do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent);
        limit = cpuid_entries[0].eax;
        for (func = 1; func <= limit && nent < cpuid->nent; ++func)
                do_cpuid_ent(&cpuid_entries[nent], func, 0,
                             &nent, cpuid->nent);
        r = -E2BIG;
        if (nent >= cpuid->nent)
                goto out_free;

        do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent);
        limit = cpuid_entries[nent - 1].eax;
        for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
                do_cpuid_ent(&cpuid_entries[nent], func, 0,
                             &nent, cpuid->nent);
        r = -EFAULT;
        if (copy_to_user(entries, cpuid_entries,
                         nent * sizeof(struct kvm_cpuid_entry2)))
                goto out_free;
        cpuid->nent = nent;
        r = 0;

out_free:
        vfree(cpuid_entries);
out:
        return r;
}

static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
                                    struct kvm_lapic_state *s)
{
        vcpu_load(vcpu);
        memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
        vcpu_put(vcpu);

        return 0;
}

static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
                                    struct kvm_lapic_state *s)
{
        vcpu_load(vcpu);
        memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
        kvm_apic_post_state_restore(vcpu);
        vcpu_put(vcpu);

        return 0;
}

static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
                                    struct kvm_interrupt *irq)
{
        if (irq->irq < 0 || irq->irq >= 256)
                return -EINVAL;
        if (irqchip_in_kernel(vcpu->kvm))
                return -ENXIO;
        vcpu_load(vcpu);

        kvm_queue_interrupt(vcpu, irq->irq, false);

        vcpu_put(vcpu);

        return 0;
}

static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
{
        vcpu_load(vcpu);
        kvm_inject_nmi(vcpu);
        vcpu_put(vcpu);

        return 0;
}

static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
                                           struct kvm_tpr_access_ctl *tac)
{
        if (tac->flags)
                return -EINVAL;
        vcpu->arch.tpr_access_reporting = !!tac->enabled;
        return 0;
}

long kvm_arch_vcpu_ioctl(struct file *filp,
                         unsigned int ioctl, unsigned long arg)
{
        struct kvm_vcpu *vcpu = filp->private_data;
        void __user *argp = (void __user *)arg;
        int r;
        struct kvm_lapic_state *lapic = NULL;

        switch (ioctl) {
        case KVM_GET_LAPIC: {
                lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);

                r = -ENOMEM;
                if (!lapic)
                        goto out;
                r = kvm_vcpu_ioctl_get_lapic(vcpu, lapic);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, lapic, sizeof(struct kvm_lapic_state)))
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_LAPIC: {
                lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
                r = -ENOMEM;
                if (!lapic)
                        goto out;
                r = -EFAULT;
                if (copy_from_user(lapic, argp, sizeof(struct kvm_lapic_state)))
                        goto out;
                r = kvm_vcpu_ioctl_set_lapic(vcpu, lapic);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_INTERRUPT: {
                struct kvm_interrupt irq;

                r = -EFAULT;
                if (copy_from_user(&irq, argp, sizeof irq))
                        goto out;
                r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_NMI: {
                r = kvm_vcpu_ioctl_nmi(vcpu);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_CPUID: {
                struct kvm_cpuid __user *cpuid_arg = argp;
                struct kvm_cpuid cpuid;

                r = -EFAULT;
                if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
                        goto out;
                r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
                if (r)
                        goto out;
                break;
        }
        case KVM_SET_CPUID2: {
                struct kvm_cpuid2 __user *cpuid_arg = argp;
                struct kvm_cpuid2 cpuid;

                r = -EFAULT;
                if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
                        goto out;
                r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
                                              cpuid_arg->entries);
                if (r)
                        goto out;
                break;
        }
        case KVM_GET_CPUID2: {
                struct kvm_cpuid2 __user *cpuid_arg = argp;
                struct kvm_cpuid2 cpuid;

                r = -EFAULT;
                if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
                        goto out;
                r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
                                              cpuid_arg->entries);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
                        goto out;
                r = 0;
                break;
        }
        case KVM_GET_MSRS:
                r = msr_io(vcpu, argp, kvm_get_msr, 1);
                break;
        case KVM_SET_MSRS:
                r = msr_io(vcpu, argp, do_set_msr, 0);
                break;
        case KVM_TPR_ACCESS_REPORTING: {
                struct kvm_tpr_access_ctl tac;

                r = -EFAULT;
                if (copy_from_user(&tac, argp, sizeof tac))
                        goto out;
                r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, &tac, sizeof tac))
                        goto out;
                r = 0;
                break;
        };
        case KVM_SET_VAPIC_ADDR: {
                struct kvm_vapic_addr va;

                r = -EINVAL;
                if (!irqchip_in_kernel(vcpu->kvm))
                        goto out;
                r = -EFAULT;
                if (copy_from_user(&va, argp, sizeof va))
                        goto out;
                r = 0;
                kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
                break;
        }
        default:
                r = -EINVAL;
        }
out:
        kfree(lapic);
        return r;
}

static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
{
        int ret;

        if (addr > (unsigned int)(-3 * PAGE_SIZE))
                return -1;
        ret = kvm_x86_ops->set_tss_addr(kvm, addr);
        return ret;
}

static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
                                          u32 kvm_nr_mmu_pages)
{
        if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
                return -EINVAL;

        down_write(&kvm->slots_lock);
        spin_lock(&kvm->mmu_lock);

        kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
        kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;

        spin_unlock(&kvm->mmu_lock);
        up_write(&kvm->slots_lock);
        return 0;
}

static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
        return kvm->arch.n_alloc_mmu_pages;
}

gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
        int i;
        struct kvm_mem_alias *alias;

        for (i = 0; i < kvm->arch.naliases; ++i) {
                alias = &kvm->arch.aliases[i];
                if (gfn >= alias->base_gfn
                    && gfn < alias->base_gfn + alias->npages)
                        return alias->target_gfn + gfn - alias->base_gfn;
        }
        return gfn;
}

/*
 * Set a new alias region.  Aliases map a portion of physical memory into
 * another portion.  This is useful for memory windows, for example the PC
 * VGA region.
 */
static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
                                         struct kvm_memory_alias *alias)
{
        int r, n;
        struct kvm_mem_alias *p;

        r = -EINVAL;
        /* General sanity checks */
        if (alias->memory_size & (PAGE_SIZE - 1))
                goto out;
        if (alias->guest_phys_addr & (PAGE_SIZE - 1))
                goto out;
        if (alias->slot >= KVM_ALIAS_SLOTS)
                goto out;
        if (alias->guest_phys_addr + alias->memory_size
            < alias->guest_phys_addr)
                goto out;
        if (alias->target_phys_addr + alias->memory_size
            < alias->target_phys_addr)
                goto out;

        down_write(&kvm->slots_lock);
        spin_lock(&kvm->mmu_lock);

        p = &kvm->arch.aliases[alias->slot];
        p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
        p->npages = alias->memory_size >> PAGE_SHIFT;
        p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;

        for (n = KVM_ALIAS_SLOTS; n > 0; --n)
                if (kvm->arch.aliases[n - 1].npages)
                        break;
        kvm->arch.naliases = n;

        spin_unlock(&kvm->mmu_lock);
        kvm_mmu_zap_all(kvm);

        up_write(&kvm->slots_lock);

        return 0;

out:
        return r;
}

static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
        int r;

        r = 0;
        switch (chip->chip_id) {
        case KVM_IRQCHIP_PIC_MASTER:
                memcpy(&chip->chip.pic,
                        &pic_irqchip(kvm)->pics[0],
                        sizeof(struct kvm_pic_state));
                break;
        case KVM_IRQCHIP_PIC_SLAVE:
                memcpy(&chip->chip.pic,
                        &pic_irqchip(kvm)->pics[1],
                        sizeof(struct kvm_pic_state));
                break;
        case KVM_IRQCHIP_IOAPIC:
                memcpy(&chip->chip.ioapic,
                        ioapic_irqchip(kvm),
                        sizeof(struct kvm_ioapic_state));
                break;
        default:
                r = -EINVAL;
                break;
        }
        return r;
}

static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
        int r;

        r = 0;
        switch (chip->chip_id) {
        case KVM_IRQCHIP_PIC_MASTER:
                memcpy(&pic_irqchip(kvm)->pics[0],
                        &chip->chip.pic,
                        sizeof(struct kvm_pic_state));
                break;
        case KVM_IRQCHIP_PIC_SLAVE:
                memcpy(&pic_irqchip(kvm)->pics[1],
                        &chip->chip.pic,
                        sizeof(struct kvm_pic_state));
                break;
        case KVM_IRQCHIP_IOAPIC:
                memcpy(ioapic_irqchip(kvm),
                        &chip->chip.ioapic,
                        sizeof(struct kvm_ioapic_state));
                break;
        default:
                r = -EINVAL;
                break;
        }
        kvm_pic_update_irq(pic_irqchip(kvm));
        return r;
}

static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
        int r = 0;

        memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
        return r;
}

static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
        int r = 0;

        memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
        kvm_pit_load_count(kvm, 0, ps->channels[0].count);
        return r;
}

static int kvm_vm_ioctl_reinject(struct kvm *kvm,
                                 struct kvm_reinject_control *control)
{
        if (!kvm->arch.vpit)
                return -ENXIO;
        kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
        return 0;
}

/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
                                      struct kvm_dirty_log *log)
{
        int r;
        int n;
        struct kvm_memory_slot *memslot;
        int is_dirty = 0;

        down_write(&kvm->slots_lock);

        r = kvm_get_dirty_log(kvm, log, &is_dirty);
        if (r)
                goto out;

        /* If nothing is dirty, don't bother messing with page tables. */
        if (is_dirty) {
                spin_lock(&kvm->mmu_lock);
                kvm_mmu_slot_remove_write_access(kvm, log->slot);
                spin_unlock(&kvm->mmu_lock);
                kvm_flush_remote_tlbs(kvm);
                memslot = &kvm->memslots[log->slot];
                n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
                memset(memslot->dirty_bitmap, 0, n);
        }
        r = 0;
out:
        up_write(&kvm->slots_lock);
        return r;
}

long kvm_arch_vm_ioctl(struct file *filp,
                       unsigned int ioctl, unsigned long arg)
{
        struct kvm *kvm = filp->private_data;
        void __user *argp = (void __user *)arg;
        int r = -EINVAL;
        /*
         * This union makes it completely explicit to gcc-3.x
         * that these two variables' stack usage should be
         * combined, not added together.
         */
        union {
                struct kvm_pit_state ps;
                struct kvm_memory_alias alias;
        } u;

        switch (ioctl) {
        case KVM_SET_TSS_ADDR:
                r = kvm_vm_ioctl_set_tss_addr(kvm, arg);
                if (r < 0)
                        goto out;
                break;
        case KVM_SET_MEMORY_REGION: {
                struct kvm_memory_region kvm_mem;
                struct kvm_userspace_memory_region kvm_userspace_mem;

                r = -EFAULT;
                if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
                        goto out;
                kvm_userspace_mem.slot = kvm_mem.slot;
                kvm_userspace_mem.flags = kvm_mem.flags;
                kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr;
                kvm_userspace_mem.memory_size = kvm_mem.memory_size;
                r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0);
                if (r)
                        goto out;
                break;
        }
        case KVM_SET_NR_MMU_PAGES:
                r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
                if (r)
                        goto out;
                break;
        case KVM_GET_NR_MMU_PAGES:
                r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
                break;
        case KVM_SET_MEMORY_ALIAS:
                r = -EFAULT;
                if (copy_from_user(&u.alias, argp, sizeof(struct kvm_memory_alias)))
                        goto out;
                r = kvm_vm_ioctl_set_memory_alias(kvm, &u.alias);
                if (r)
                        goto out;
                break;
        case KVM_CREATE_IRQCHIP:
                r = -ENOMEM;
                kvm->arch.vpic = kvm_create_pic(kvm);
                if (kvm->arch.vpic) {
                        r = kvm_ioapic_init(kvm);
                        if (r) {
                                kfree(kvm->arch.vpic);
                                kvm->arch.vpic = NULL;
                                goto out;
                        }
                } else
                        goto out;
                r = kvm_setup_default_irq_routing(kvm);
                if (r) {
                        kfree(kvm->arch.vpic);
                        kfree(kvm->arch.vioapic);
                        goto out;
                }
                break;
        case KVM_CREATE_PIT:
                mutex_lock(&kvm->lock);
                r = -EEXIST;
                if (kvm->arch.vpit)
                        goto create_pit_unlock;
                r = -ENOMEM;
                kvm->arch.vpit = kvm_create_pit(kvm);
                if (kvm->arch.vpit)
                        r = 0;
        create_pit_unlock:
                mutex_unlock(&kvm->lock);
                break;
        case KVM_IRQ_LINE_STATUS:
        case KVM_IRQ_LINE: {
                struct kvm_irq_level irq_event;

                r = -EFAULT;
                if (copy_from_user(&irq_event, argp, sizeof irq_event))
                        goto out;
                if (irqchip_in_kernel(kvm)) {
                        __s32 status;
                        mutex_lock(&kvm->lock);
                        status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
                                        irq_event.irq, irq_event.level);
                        mutex_unlock(&kvm->lock);
                        if (ioctl == KVM_IRQ_LINE_STATUS) {
                                irq_event.status = status;
                                if (copy_to_user(argp, &irq_event,
                                                        sizeof irq_event))
                                        goto out;
                        }
                        r = 0;
                }
                break;
        }
        case KVM_GET_IRQCHIP: {
                /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
                struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL);

                r = -ENOMEM;
                if (!chip)
                        goto out;
                r = -EFAULT;
                if (copy_from_user(chip, argp, sizeof *chip))
                        goto get_irqchip_out;
                r = -ENXIO;
                if (!irqchip_in_kernel(kvm))
                        goto get_irqchip_out;
                r = kvm_vm_ioctl_get_irqchip(kvm, chip);
                if (r)
                        goto get_irqchip_out;
                r = -EFAULT;
                if (copy_to_user(argp, chip, sizeof *chip))
                        goto get_irqchip_out;
                r = 0;
        get_irqchip_out:
                kfree(chip);
                if (r)
                        goto out;
                break;
        }
        case KVM_SET_IRQCHIP: {
                /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
                struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL);

                r = -ENOMEM;
                if (!chip)
                        goto out;
                r = -EFAULT;

                if (copy_from_user(chip, argp, sizeof *chip))
                        goto set_irqchip_out;
                r = -ENXIO;
                if (!irqchip_in_kernel(kvm))
                        goto set_irqchip_out;
                r = kvm_vm_ioctl_set_irqchip(kvm, chip);
                if (r)
                        goto set_irqchip_out;
                r = 0;
        set_irqchip_out:
                kfree(chip);
                if (r)
                        goto out;
                break;
        }
        case KVM_GET_PIT: {
                r = -EFAULT;
                if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state)))
                        goto out;
                r = -ENXIO;
                if (!kvm->arch.vpit)
                        goto out;
                r = kvm_vm_ioctl_get_pit(kvm, &u.ps);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state)))
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_PIT: {
                r = -EFAULT;
                if (copy_from_user(&u.ps, argp, sizeof u.ps))
                        goto out;
                r = -ENXIO;
                if (!kvm->arch.vpit)
                        goto out;
                r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_REINJECT_CONTROL: {
                struct kvm_reinject_control control;
                r =  -EFAULT;
                if (copy_from_user(&control, argp, sizeof(control)))
                        goto out;
                r = kvm_vm_ioctl_reinject(kvm, &control);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        default:
                ;
        }
out:
        return r;
}

static void kvm_init_msr_list(void)
{
        u32 dummy[2];
        unsigned i, j;

        for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
                if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
                        continue;
                if (j < i)
                        msrs_to_save[j] = msrs_to_save[i];
                j++;
        }
        num_msrs_to_save = j;
}

/*
 * Only apic need an MMIO device hook, so shortcut now..
 */
static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
                                                gpa_t addr, int len,
                                                int is_write)
{
        struct kvm_io_device *dev;

        if (vcpu->arch.apic) {
                dev = &vcpu->arch.apic->dev;
                if (dev->in_range(dev, addr, len, is_write))
                        return dev;
        }
        return NULL;
}


static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
                                                gpa_t addr, int len,
                                                int is_write)
{
        struct kvm_io_device *dev;

        dev = vcpu_find_pervcpu_dev(vcpu, addr, len, is_write);
        if (dev == NULL)
                dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len,
                                          is_write);
        return dev;
}

static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
                               struct kvm_vcpu *vcpu)
{
        void *data = val;
        int r = X86EMUL_CONTINUE;

        while (bytes) {
                gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
                unsigned offset = addr & (PAGE_SIZE-1);
                unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
                int ret;

                if (gpa == UNMAPPED_GVA) {
                        r = X86EMUL_PROPAGATE_FAULT;
                        goto out;
                }
                ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
                if (ret < 0) {
                        r = X86EMUL_UNHANDLEABLE;
                        goto out;
                }

                bytes -= toread;
                data += toread;
                addr += toread;
        }
out:
        return r;
}

static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
                                struct kvm_vcpu *vcpu)
{
        void *data = val;
        int r = X86EMUL_CONTINUE;

        while (bytes) {
                gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
                unsigned offset = addr & (PAGE_SIZE-1);
                unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
                int ret;

                if (gpa == UNMAPPED_GVA) {
                        r = X86EMUL_PROPAGATE_FAULT;
                        goto out;
                }
                ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
                if (ret < 0) {
                        r = X86EMUL_UNHANDLEABLE;
                        goto out;
                }

                bytes -= towrite;
                data += towrite;
                addr += towrite;
        }
out:
        return r;
}


static int emulator_read_emulated(unsigned long addr,
                                  void *val,
                                  unsigned int bytes,
                                  struct kvm_vcpu *vcpu)
{
        struct kvm_io_device *mmio_dev;
        gpa_t                 gpa;

        if (vcpu->mmio_read_completed) {
                memcpy(val, vcpu->mmio_data, bytes);
                vcpu->mmio_read_completed = 0;
                return X86EMUL_CONTINUE;
        }

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

        /* For APIC access vmexit */
        if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
                goto mmio;

        if (kvm_read_guest_virt(addr, val, bytes, vcpu)
                                == X86EMUL_CONTINUE)
                return X86EMUL_CONTINUE;
        if (gpa == UNMAPPED_GVA)
                return X86EMUL_PROPAGATE_FAULT;

mmio:
        /*
         * Is this MMIO handled locally?
         */
        mutex_lock(&vcpu->kvm->lock);
        mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 0);
        if (mmio_dev) {
                kvm_iodevice_read(mmio_dev, gpa, bytes, val);
                mutex_unlock(&vcpu->kvm->lock);
                return X86EMUL_CONTINUE;
        }
        mutex_unlock(&vcpu->kvm->lock);

        vcpu->mmio_needed = 1;
        vcpu->mmio_phys_addr = gpa;
        vcpu->mmio_size = bytes;
        vcpu->mmio_is_write = 0;

        return X86EMUL_UNHANDLEABLE;
}

int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
                          const void *val, int bytes)
{
        int ret;

        ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
        if (ret < 0)
                return 0;
        kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1);
        return 1;
}

static int emulator_write_emulated_onepage(unsigned long addr,
                                           const void *val,
                                           unsigned int bytes,
                                           struct kvm_vcpu *vcpu)
{
        struct kvm_io_device *mmio_dev;
        gpa_t                 gpa;

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

        if (gpa == UNMAPPED_GVA) {
                kvm_inject_page_fault(vcpu, addr, 2);
                return X86EMUL_PROPAGATE_FAULT;
        }

        /* For APIC access vmexit */
        if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
                goto mmio;

        if (emulator_write_phys(vcpu, gpa, val, bytes))
                return X86EMUL_CONTINUE;

mmio:
        /*
         * Is this MMIO handled locally?
         */
        mutex_lock(&vcpu->kvm->lock);
        mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 1);
        if (mmio_dev) {
                kvm_iodevice_write(mmio_dev, gpa, bytes, val);
                mutex_unlock(&vcpu->kvm->lock);
                return X86EMUL_CONTINUE;
        }
        mutex_unlock(&vcpu->kvm->lock);

        vcpu->mmio_needed = 1;
        vcpu->mmio_phys_addr = gpa;
        vcpu->mmio_size = bytes;
        vcpu->mmio_is_write = 1;
        memcpy(vcpu->mmio_data, val, bytes);

        return X86EMUL_CONTINUE;
}

int emulator_write_emulated(unsigned long addr,
                                   const void *val,
                                   unsigned int bytes,
                                   struct kvm_vcpu *vcpu)
{
        /* Crossing a page boundary? */
        if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
                int rc, now;

                now = -addr & ~PAGE_MASK;
                rc = emulator_write_emulated_onepage(addr, val, now, vcpu);
                if (rc != X86EMUL_CONTINUE)
                        return rc;
                addr += now;
                val += now;
                bytes -= now;
        }
        return emulator_write_emulated_onepage(addr, val, bytes, vcpu);
}
EXPORT_SYMBOL_GPL(emulator_write_emulated);

static int emulator_cmpxchg_emulated(unsigned long addr,
                                     const void *old,
                                     const void *new,
                                     unsigned int bytes,
                                     struct kvm_vcpu *vcpu)
{
        static int reported;

        if (!reported) {
                reported = 1;
                printk(KERN_WARNING "kvm: emulating exchange as write\n");
        }
#ifndef CONFIG_X86_64
        /* guests cmpxchg8b have to be emulated atomically */
        if (bytes == 8) {
                gpa_t gpa;
                struct page *page;
                char *kaddr;
                u64 val;

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

                if (gpa == UNMAPPED_GVA ||
                   (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
                        goto emul_write;

                if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
                        goto emul_write;

                val = *(u64 *)new;

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

                kaddr = kmap_atomic(page, KM_USER0);
                set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
                kunmap_atomic(kaddr, KM_USER0);
                kvm_release_page_dirty(page);
        }
emul_write:
#endif

        return emulator_write_emulated(addr, new, bytes, vcpu);
}

static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
        return kvm_x86_ops->get_segment_base(vcpu, seg);
}

int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
{
        kvm_mmu_invlpg(vcpu, address);
        return X86EMUL_CONTINUE;
}

int emulate_clts(struct kvm_vcpu *vcpu)
{
        KVMTRACE_0D(CLTS, vcpu, handler);
        kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
        return X86EMUL_CONTINUE;
}

int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
        struct kvm_vcpu *vcpu = ctxt->vcpu;

        switch (dr) {
        case 0 ... 3:
                *dest = kvm_x86_ops->get_dr(vcpu, dr);
                return X86EMUL_CONTINUE;
        default:
                pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
                return X86EMUL_UNHANDLEABLE;
        }
}

int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
{
        unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
        int exception;

        kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
        if (exception) {
                /* FIXME: better handling */
                return X86EMUL_UNHANDLEABLE;
        }
        return X86EMUL_CONTINUE;
}

void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
{
        u8 opcodes[4];
        unsigned long rip = kvm_rip_read(vcpu);
        unsigned long rip_linear;

        if (!printk_ratelimit())
                return;

        rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);

        kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu);

        printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
               context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);

static struct x86_emulate_ops emulate_ops = {
        .read_std            = kvm_read_guest_virt,
        .read_emulated       = emulator_read_emulated,
        .write_emulated      = emulator_write_emulated,
        .cmpxchg_emulated    = emulator_cmpxchg_emulated,
};

static void cache_all_regs(struct kvm_vcpu *vcpu)
{
        kvm_register_read(vcpu, VCPU_REGS_RAX);
        kvm_register_read(vcpu, VCPU_REGS_RSP);
        kvm_register_read(vcpu, VCPU_REGS_RIP);
        vcpu->arch.regs_dirty = ~0;
}

int emulate_instruction(struct kvm_vcpu *vcpu,
                        struct kvm_run *run,
                        unsigned long cr2,
                        u16 error_code,
                        int emulation_type)
{
        int r, shadow_mask;
        struct decode_cache *c;

        kvm_clear_exception_queue(vcpu);
        vcpu->arch.mmio_fault_cr2 = cr2;
        /*
         * TODO: fix x86_emulate.c to use guest_read/write_register
         * instead of direct ->regs accesses, can save hundred cycles
         * on Intel for instructions that don't read/change RSP, for
         * for example.
         */
        cache_all_regs(vcpu);

        vcpu->mmio_is_write = 0;
        vcpu->arch.pio.string = 0;

        if (!(emulation_type & EMULTYPE_NO_DECODE)) {
                int cs_db, cs_l;
                kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);

                vcpu->arch.emulate_ctxt.vcpu = vcpu;
                vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
                vcpu->arch.emulate_ctxt.mode =
                        (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
                        ? X86EMUL_MODE_REAL : cs_l
                        ? X86EMUL_MODE_PROT64 : cs_db
                        ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;

                r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);

                /* Reject the instructions other than VMCALL/VMMCALL when
                 * try to emulate invalid opcode */
                c = &vcpu->arch.emulate_ctxt.decode;
                if ((emulation_type & EMULTYPE_TRAP_UD) &&
                    (!(c->twobyte && c->b == 0x01 &&
                      (c->modrm_reg == 0 || c->modrm_reg == 3) &&
                       c->modrm_mod == 3 && c->modrm_rm == 1)))
                        return EMULATE_FAIL;

                ++vcpu->stat.insn_emulation;
                if (r)  {
                        ++vcpu->stat.insn_emulation_fail;
                        if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
                                return EMULATE_DONE;
                        return EMULATE_FAIL;
                }
        }

        if (emulation_type & EMULTYPE_SKIP) {
                kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.decode.eip);
                return EMULATE_DONE;
        }

        r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
        shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;

        if (r == 0)
                kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);

        if (vcpu->arch.pio.string)
                return EMULATE_DO_MMIO;

        if ((r || vcpu->mmio_is_write) && run) {
                run->exit_reason = KVM_EXIT_MMIO;
                run->mmio.phys_addr = vcpu->mmio_phys_addr;
                memcpy(run->mmio.data, vcpu->mmio_data, 8);
                run->mmio.len = vcpu->mmio_size;
                run->mmio.is_write = vcpu->mmio_is_write;
        }

        if (r) {
                if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
                        return EMULATE_DONE;
                if (!vcpu->mmio_needed) {
                        kvm_report_emulation_failure(vcpu, "mmio");
                        return EMULATE_FAIL;
                }
                return EMULATE_DO_MMIO;
        }

        kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);

        if (vcpu->mmio_is_write) {
                vcpu->mmio_needed = 0;
                return EMULATE_DO_MMIO;
        }

        return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);

static int pio_copy_data(struct kvm_vcpu *vcpu)
{
        void *p = vcpu->arch.pio_data;
        gva_t q = vcpu->arch.pio.guest_gva;
        unsigned bytes;
        int ret;

        bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
        if (vcpu->arch.pio.in)
                ret = kvm_write_guest_virt(q, p, bytes, vcpu);
        else
                ret = kvm_read_guest_virt(q, p, bytes, vcpu);
        return ret;
}

int complete_pio(struct kvm_vcpu *vcpu)
{
        struct kvm_pio_request *io = &vcpu->arch.pio;
        long delta;
        int r;
        unsigned long val;

        if (!io->string) {
                if (io->in) {
                        val = kvm_register_read(vcpu, VCPU_REGS_RAX);
                        memcpy(&val, vcpu->arch.pio_data, io->size);
                        kvm_register_write(vcpu, VCPU_REGS_RAX, val);
                }
        } else {
                if (io->in) {
                        r = pio_copy_data(vcpu);
                        if (r)
                                return r;
                }

                delta = 1;
                if (io->rep) {
                        delta *= io->cur_count;
                        /*
                         * The size of the register should really depend on
                         * current address size.
                         */
                        val = kvm_register_read(vcpu, VCPU_REGS_RCX);
                        val -= delta;
                        kvm_register_write(vcpu, VCPU_REGS_RCX, val);
                }
                if (io->down)
                        delta = -delta;
                delta *= io->size;
                if (io->in) {
                        val = kvm_register_read(vcpu, VCPU_REGS_RDI);
                        val += delta;
                        kvm_register_write(vcpu, VCPU_REGS_RDI, val);
                } else {
                        val = kvm_register_read(vcpu, VCPU_REGS_RSI);
                        val += delta;
                        kvm_register_write(vcpu, VCPU_REGS_RSI, val);
                }
        }

        io->count -= io->cur_count;
        io->cur_count = 0;

        return 0;
}

static void kernel_pio(struct kvm_io_device *pio_dev,
                       struct kvm_vcpu *vcpu,
                       void *pd)
{
        /* TODO: String I/O for in kernel device */

        mutex_lock(&vcpu->kvm->lock);
        if (vcpu->arch.pio.in)
                kvm_iodevice_read(pio_dev, vcpu->arch.pio.port,
                                  vcpu->arch.pio.size,
                                  pd);
        else
                kvm_iodevice_write(pio_dev, vcpu->arch.pio.port,
                                   vcpu->arch.pio.size,
                                   pd);
        mutex_unlock(&vcpu->kvm->lock);
}

static void pio_string_write(struct kvm_io_device *pio_dev,
                             struct kvm_vcpu *vcpu)
{
        struct kvm_pio_request *io = &vcpu->arch.pio;
        void *pd = vcpu->arch.pio_data;
        int i;

        mutex_lock(&vcpu->kvm->lock);
        for (i = 0; i < io->cur_count; i++) {
                kvm_iodevice_write(pio_dev, io->port,
                                   io->size,
                                   pd);
                pd += io->size;
        }
        mutex_unlock(&vcpu->kvm->lock);
}

static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
                                               gpa_t addr, int len,
                                               int is_write)
{
        return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr, len, is_write);
}

int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
                  int size, unsigned port)
{
        struct kvm_io_device *pio_dev;
        unsigned long val;

        vcpu->run->exit_reason = KVM_EXIT_IO;
        vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
        vcpu->run->io.size = vcpu->arch.pio.size = size;
        vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
        vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
        vcpu->run->io.port = vcpu->arch.pio.port = port;
        vcpu->arch.pio.in = in;
        vcpu->arch.pio.string = 0;
        vcpu->arch.pio.down = 0;
        vcpu->arch.pio.rep = 0;

        if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
                KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
                            handler);
        else
                KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
                            handler);

        val = kvm_register_read(vcpu, VCPU_REGS_RAX);
        memcpy(vcpu->arch.pio_data, &val, 4);

        pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
        if (pio_dev) {
                kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
                complete_pio(vcpu);
                return 1;
        }
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_emulate_pio);

int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
                  int size, unsigned long count, int down,
                  gva_t address, int rep, unsigned port)
{
        unsigned now, in_page;
        int ret = 0;
        struct kvm_io_device *pio_dev;

        vcpu->run->exit_reason = KVM_EXIT_IO;
        vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
        vcpu->run->io.size = vcpu->arch.pio.size = size;
        vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
        vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
        vcpu->run->io.port = vcpu->arch.pio.port = port;
        vcpu->arch.pio.in = in;
        vcpu->arch.pio.string = 1;
        vcpu->arch.pio.down = down;
        vcpu->arch.pio.rep = rep;

        if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
                KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
                            handler);
        else
                KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
                            handler);

        if (!count) {
                kvm_x86_ops->skip_emulated_instruction(vcpu);
                return 1;
        }

        if (!down)
                in_page = PAGE_SIZE - offset_in_page(address);
        else
                in_page = offset_in_page(address) + size;
        now = min(count, (unsigned long)in_page / size);
        if (!now)
                now = 1;
        if (down) {
                /*
                 * String I/O in reverse.  Yuck.  Kill the guest, fix later.
                 */
                pr_unimpl(vcpu, "guest string pio down\n");
                kvm_inject_gp(vcpu, 0);
                return 1;
        }
        vcpu->run->io.count = now;
        vcpu->arch.pio.cur_count = now;

        if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
                kvm_x86_ops->skip_emulated_instruction(vcpu);

        vcpu->arch.pio.guest_gva = address;

        pio_dev = vcpu_find_pio_dev(vcpu, port,
                                    vcpu->arch.pio.cur_count,
                                    !vcpu->arch.pio.in);
        if (!vcpu->arch.pio.in) {
                /* string PIO write */
                ret = pio_copy_data(vcpu);
                if (ret == X86EMUL_PROPAGATE_FAULT) {
                        kvm_inject_gp(vcpu, 0);
                        return 1;
                }
                if (ret == 0 && pio_dev) {
                        pio_string_write(pio_dev, vcpu);
                        complete_pio(vcpu);
                        if (vcpu->arch.pio.count == 0)
                                ret = 1;
                }
        } else if (pio_dev)
                pr_unimpl(vcpu, "no string pio read support yet, "
                       "port %x size %d count %ld\n",
                        port, size, count);

        return ret;
}
EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);

static void bounce_off(void *info)
{
        /* nothing */
}

static unsigned int  ref_freq;
static unsigned long tsc_khz_ref;

static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
                                     void *data)
{
        struct cpufreq_freqs *freq = data;
        struct kvm *kvm;
        struct kvm_vcpu *vcpu;
        int i, send_ipi = 0;

        if (!ref_freq)
                ref_freq = freq->old;

        if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
                return 0;
        if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
                return 0;
        per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);

        spin_lock(&kvm_lock);
        list_for_each_entry(kvm, &vm_list, vm_list) {
                for (i = 0; i < KVM_MAX_VCPUS; ++i) {
                        vcpu = kvm->vcpus[i];
                        if (!vcpu)
                                continue;
                        if (vcpu->cpu != freq->cpu)
                                continue;
                        if (!kvm_request_guest_time_update(vcpu))
                                continue;
                        if (vcpu->cpu != smp_processor_id())
                                send_ipi++;
                }
        }
        spin_unlock(&kvm_lock);

        if (freq->old < freq->new && send_ipi) {
                /*
                 * We upscale the frequency.  Must make the guest
                 * doesn't see old kvmclock values while running with
                 * the new frequency, otherwise we risk the guest sees
                 * time go backwards.
                 *
                 * In case we update the frequency for another cpu
                 * (which might be in guest context) send an interrupt
                 * to kick the cpu out of guest context.  Next time
                 * guest context is entered kvmclock will be updated,
                 * so the guest will not see stale values.
                 */
                smp_call_function_single(freq->cpu, bounce_off, NULL, 1);
        }
        return 0;
}

static struct notifier_block kvmclock_cpufreq_notifier_block = {
        .notifier_call  = kvmclock_cpufreq_notifier
};

int kvm_arch_init(void *opaque)
{
        int r, cpu;
        struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;

        if (kvm_x86_ops) {
                printk(KERN_ERR "kvm: already loaded the other module\n");
                r = -EEXIST;
                goto out;
        }

        if (!ops->cpu_has_kvm_support()) {
                printk(KERN_ERR "kvm: no hardware support\n");
                r = -EOPNOTSUPP;
                goto out;
        }
        if (ops->disabled_by_bios()) {
                printk(KERN_ERR "kvm: disabled by bios\n");
                r = -EOPNOTSUPP;
                goto out;
        }

        r = kvm_mmu_module_init();
        if (r)
                goto out;

        kvm_init_msr_list();

        kvm_x86_ops = ops;
        kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
        kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
        kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
                        PT_DIRTY_MASK, PT64_NX_MASK, 0);

        for_each_possible_cpu(cpu)
                per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
                tsc_khz_ref = tsc_khz;
                cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
                                          CPUFREQ_TRANSITION_NOTIFIER);
        }

        return 0;

out:
        return r;
}

void kvm_arch_exit(void)
{
        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
                cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
                                            CPUFREQ_TRANSITION_NOTIFIER);
        kvm_x86_ops = NULL;
        kvm_mmu_module_exit();
}

int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
        ++vcpu->stat.halt_exits;
        KVMTRACE_0D(HLT, vcpu, handler);
        if (irqchip_in_kernel(vcpu->kvm)) {
                vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
                return 1;
        } else {
                vcpu->run->exit_reason = KVM_EXIT_HLT;
                return 0;
        }
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);

static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
                           unsigned long a1)
{
        if (is_long_mode(vcpu))
                return a0;
        else
                return a0 | ((gpa_t)a1 << 32);
}

int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
        unsigned long nr, a0, a1, a2, a3, ret;
        int r = 1;

        nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
        a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
        a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
        a2 = kvm_register_read(vcpu, VCPU_REGS_RDX);
        a3 = kvm_register_read(vcpu, VCPU_REGS_RSI);

        KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler);

        if (!is_long_mode(vcpu)) {
                nr &= 0xFFFFFFFF;
                a0 &= 0xFFFFFFFF;
                a1 &= 0xFFFFFFFF;
                a2 &= 0xFFFFFFFF;
                a3 &= 0xFFFFFFFF;
        }

        switch (nr) {
        case KVM_HC_VAPIC_POLL_IRQ:
                ret = 0;
                break;
        case KVM_HC_MMU_OP:
                r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
                break;
        default:
                ret = -KVM_ENOSYS;
                break;
        }
        kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
        ++vcpu->stat.hypercalls;
        return r;
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);

int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
{
        char instruction[3];
        int ret = 0;
        unsigned long rip = kvm_rip_read(vcpu);


        /*
         * Blow out the MMU to ensure that no other VCPU has an active mapping
         * to ensure that the updated hypercall appears atomically across all
         * VCPUs.
         */
        kvm_mmu_zap_all(vcpu->kvm);

        kvm_x86_ops->patch_hypercall(vcpu, instruction);
        if (emulator_write_emulated(rip, instruction, 3, vcpu)
            != X86EMUL_CONTINUE)
                ret = -EFAULT;

        return ret;
}

static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
        return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
}

void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
        struct descriptor_table dt = { limit, base };

        kvm_x86_ops->set_gdt(vcpu, &dt);
}

void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
        struct descriptor_table dt = { limit, base };

        kvm_x86_ops->set_idt(vcpu, &dt);
}

void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
                   unsigned long *rflags)
{
        kvm_lmsw(vcpu, msw);
        *rflags = kvm_x86_ops->get_rflags(vcpu);
}

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
        unsigned long value;

        kvm_x86_ops->decache_cr4_guest_bits(vcpu);
        switch (cr) {
        case 0:
                value = vcpu->arch.cr0;
                break;
        case 2:
                value = vcpu->arch.cr2;
                break;
        case 3:
                value = vcpu->arch.cr3;
                break;
        case 4:
                value = vcpu->arch.cr4;
                break;
        case 8:
                value = kvm_get_cr8(vcpu);
                break;
        default:
                vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
                return 0;
        }
        KVMTRACE_3D(CR_READ, vcpu, (u32)cr, (u32)value,
                    (u32)((u64)value >> 32), handler);

        return value;
}

void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
                     unsigned long *rflags)
{
        KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)val,