x86.c

	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
		return -EINVAL;

	mutex_lock(&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);
	mutex_unlock(&kvm->slots_lock);
	return 0;
}

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

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:
		r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
		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:
		spin_lock(&pic_irqchip(kvm)->lock);
		memcpy(&pic_irqchip(kvm)->pics[0],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		spin_unlock(&pic_irqchip(kvm)->lock);
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		spin_lock(&pic_irqchip(kvm)->lock);
		memcpy(&pic_irqchip(kvm)->pics[1],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		spin_unlock(&pic_irqchip(kvm)->lock);
		break;
	case KVM_IRQCHIP_IOAPIC:
		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
		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;

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

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

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

static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	int r = 0;

	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
		sizeof(ps->channels));
	ps->flags = kvm->arch.vpit->pit_state.flags;
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	memset(&ps->reserved, 0, sizeof(ps->reserved));
	return r;
}

static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	int r = 0, start = 0;
	u32 prev_legacy, cur_legacy;
	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
	cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
	if (!prev_legacy && cur_legacy)
		start = 1;
	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
	       sizeof(kvm->arch.vpit->pit_state.channels));
	kvm->arch.vpit->pit_state.flags = ps->flags;
	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return r;
}

static int kvm_vm_ioctl_reinject(struct kvm *kvm,
				 struct kvm_reinject_control *control)
{
	if (!kvm->arch.vpit)
		return -ENXIO;
	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	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, i;
	struct kvm_memory_slot *memslot;
	unsigned long n;
	unsigned long is_dirty = 0;

	mutex_lock(&kvm->slots_lock);

	r = -EINVAL;
	if (log->slot >= KVM_MEMORY_SLOTS)
		goto out;

	memslot = &kvm->memslots->memslots[log->slot];
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	n = kvm_dirty_bitmap_bytes(memslot);

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

	/* If nothing is dirty, don't bother messing with page tables. */
	if (is_dirty) {
		struct kvm_memslots *slots, *old_slots;
		unsigned long *dirty_bitmap;

		r = -ENOMEM;
		dirty_bitmap = vmalloc(n);
		if (!dirty_bitmap)
			goto out;
		memset(dirty_bitmap, 0, n);

		r = -ENOMEM;
		slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
		if (!slots) {
			vfree(dirty_bitmap);
			goto out;
		}
		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
		slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;

		old_slots = kvm->memslots;
		rcu_assign_pointer(kvm->memslots, slots);
		synchronize_srcu_expedited(&kvm->srcu);
		dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap;
		kfree(old_slots);

		spin_lock(&kvm->mmu_lock);
		kvm_mmu_slot_remove_write_access(kvm, log->slot);
		spin_unlock(&kvm->mmu_lock);

		r = -EFAULT;
		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) {
			vfree(dirty_bitmap);
			goto out;
		}
		vfree(dirty_bitmap);
	} else {
		r = -EFAULT;
		if (clear_user(log->dirty_bitmap, n))
			goto out;
	}

	r = 0;
out:
	mutex_unlock(&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 = -ENOTTY;
	/*
	 * 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_pit_state2 ps2;
		struct kvm_pit_config pit_config;
	} 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_IDENTITY_MAP_ADDR: {
		u64 ident_addr;

		r = -EFAULT;
		if (copy_from_user(&ident_addr, argp, sizeof ident_addr))
			goto out;
		r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr);
		if (r < 0)
			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_CREATE_IRQCHIP: {
		struct kvm_pic *vpic;

		mutex_lock(&kvm->lock);
		r = -EEXIST;
		if (kvm->arch.vpic)
			goto create_irqchip_unlock;
		r = -ENOMEM;
		vpic = kvm_create_pic(kvm);
		if (vpic) {
			r = kvm_ioapic_init(kvm);
			if (r) {
				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
							  &vpic->dev);
				kfree(vpic);
				goto create_irqchip_unlock;
			}
		} else
			goto create_irqchip_unlock;
		smp_wmb();
		kvm->arch.vpic = vpic;
		smp_wmb();
		r = kvm_setup_default_irq_routing(kvm);
		if (r) {
			mutex_lock(&kvm->irq_lock);
			kvm_ioapic_destroy(kvm);
			kvm_destroy_pic(kvm);
			mutex_unlock(&kvm->irq_lock);
		}
	create_irqchip_unlock:
		mutex_unlock(&kvm->lock);
		break;
	}
	case KVM_CREATE_PIT:
		u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY;
		goto create_pit;
	case KVM_CREATE_PIT2:
		r = -EFAULT;
		if (copy_from_user(&u.pit_config, argp,
				   sizeof(struct kvm_pit_config)))
			goto out;
	create_pit:
		mutex_lock(&kvm->slots_lock);
		r = -EEXIST;
		if (kvm->arch.vpit)
			goto create_pit_unlock;
		r = -ENOMEM;
		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
		if (kvm->arch.vpit)
			r = 0;
	create_pit_unlock:
		mutex_unlock(&kvm->slots_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;
		r = -ENXIO;
		if (irqchip_in_kernel(kvm)) {
			__s32 status;
			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
					irq_event.irq, irq_event.level);
			if (ioctl == KVM_IRQ_LINE_STATUS) {
				r = -EFAULT;
				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_GET_PIT2: {
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto out;
		r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &u.ps2, sizeof(u.ps2)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_PIT2: {
		r = -EFAULT;
		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
			goto out;
		r = -ENXIO;
		if (!kvm->arch.vpit)
			goto out;
		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
		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;
	}
	case KVM_XEN_HVM_CONFIG: {
		r = -EFAULT;
		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
				   sizeof(struct kvm_xen_hvm_config)))
			goto out;
		r = -EINVAL;
		if (kvm->arch.xen_hvm_config.flags)
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_CLOCK: {
		struct kvm_clock_data user_ns;
		u64 now_ns;
		s64 delta;

		r = -EFAULT;
		if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
			goto out;

		r = -EINVAL;
		if (user_ns.flags)
			goto out;

		r = 0;
		local_irq_disable();
		now_ns = get_kernel_ns();
		delta = user_ns.clock - now_ns;
		local_irq_enable();
		kvm->arch.kvmclock_offset = delta;
		break;
	}
	case KVM_GET_CLOCK: {
		struct kvm_clock_data user_ns;
		u64 now_ns;

		local_irq_disable();
		now_ns = get_kernel_ns();
		user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
		local_irq_enable();
		user_ns.flags = 0;
		memset(&user_ns.pad, 0, sizeof(user_ns.pad));

		r = -EFAULT;
		if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
			goto out;
		r = 0;
		break;
	}

	default:
		;
	}
out:
	return r;
}

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

	/* skip the first msrs in the list. KVM-specific */
	for (i = j = KVM_SAVE_MSRS_BEGIN; 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;
}

static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
			   const void *v)
{
	if (vcpu->arch.apic &&
	    !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v))
		return 0;

	return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}

static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
{
	if (vcpu->arch.apic &&
	    !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v))
		return 0;

	return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}

static void kvm_set_segment(struct kvm_vcpu *vcpu,
			struct kvm_segment *var, int seg)
{
	kvm_x86_ops->set_segment(vcpu, var, seg);
}

void kvm_get_segment(struct kvm_vcpu *vcpu,
		     struct kvm_segment *var, int seg)
{
	kvm_x86_ops->get_segment(vcpu, var, seg);
}

static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
{
	return gpa;
}

static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
{
	gpa_t t_gpa;
	u32 error;

	BUG_ON(!mmu_is_nested(vcpu));

	/* NPT walks are always user-walks */
	access |= PFERR_USER_MASK;
	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &error);
	if (t_gpa == UNMAPPED_GVA)
		vcpu->arch.fault.nested = true;

	return t_gpa;
}

gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}

 gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
	access |= PFERR_FETCH_MASK;
	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}

gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
	access |= PFERR_WRITE_MASK;
	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}

/* uses this to access any guest's mapped memory without checking CPL */
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, error);
}

static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
				      struct kvm_vcpu *vcpu, u32 access,
				      u32 *error)
{
	void *data = val;
	int r = X86EMUL_CONTINUE;

	while (bytes) {
		gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access,
							    error);
		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_IO_NEEDED;
			goto out;
		}

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

/* used for instruction fetching */
static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes,
				struct kvm_vcpu *vcpu, u32 *error)
{
	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
					  access | PFERR_FETCH_MASK, error);
}

static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
			       struct kvm_vcpu *vcpu, u32 *error)
{
	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
					  error);
}

static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
			       struct kvm_vcpu *vcpu, u32 *error)
{
	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
}

static int kvm_write_guest_virt_system(gva_t addr, void *val,
				       unsigned int bytes,
				       struct kvm_vcpu *vcpu,
				       u32 *error)
{
	void *data = val;
	int r = X86EMUL_CONTINUE;

	while (bytes) {
		gpa_t gpa =  vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
							     PFERR_WRITE_MASK,
							     error);
		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_IO_NEEDED;
			goto out;
		}

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

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

	if (vcpu->mmio_read_completed) {
		memcpy(val, vcpu->mmio_data, bytes);
		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
			       vcpu->mmio_phys_addr, *(u64 *)val);
		vcpu->mmio_read_completed = 0;
		return X86EMUL_CONTINUE;
	}

	gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, error_code);

	if (gpa == UNMAPPED_GVA)
		return X86EMUL_PROPAGATE_FAULT;

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

	if (kvm_read_guest_virt(addr, val, bytes, vcpu, NULL)
				== X86EMUL_CONTINUE)
		return X86EMUL_CONTINUE;

mmio:
	/*
	 * Is this MMIO handled locally?
	 */
	if (!vcpu_mmio_read(vcpu, gpa, bytes, val)) {
		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, gpa, *(u64 *)val);
		return X86EMUL_CONTINUE;
	}

	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);

	vcpu->mmio_needed = 1;
	vcpu->run->exit_reason = KVM_EXIT_MMIO;
	vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
	vcpu->run->mmio.len = vcpu->mmio_size = bytes;
	vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0;

	return X86EMUL_IO_NEEDED;
}

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,
					   unsigned int *error_code,
					   struct kvm_vcpu *vcpu)
{
	gpa_t                 gpa;

	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error_code);

	if (gpa == UNMAPPED_GVA)
		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:
	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
	/*
	 * Is this MMIO handled locally?
	 */
	if (!vcpu_mmio_write(vcpu, gpa, bytes, val))
		return X86EMUL_CONTINUE;

	vcpu->mmio_needed = 1;
	vcpu->run->exit_reason = KVM_EXIT_MMIO;
	vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
	vcpu->run->mmio.len = vcpu->mmio_size = bytes;
	vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1;
	memcpy(vcpu->run->mmio.data, val, bytes);

	return X86EMUL_CONTINUE;
}

int emulator_write_emulated(unsigned long addr,
			    const void *val,
			    unsigned int bytes,
			    unsigned int *error_code,
			    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, error_code,
						     vcpu);
		if (rc != X86EMUL_CONTINUE)
			return rc;
		addr += now;
		val += now;
		bytes -= now;
	}
	return emulator_write_emulated_onepage(addr, val, bytes, error_code,
					       vcpu);
}

#define CMPXCHG_TYPE(t, ptr, old, new) \
	(cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))

#ifdef CONFIG_X86_64
#  define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
#else
#  define CMPXCHG64(ptr, old, new) \
	(cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
#endif

static int emulator_cmpxchg_emulated(unsigned long addr,
				     const void *old,
				     const void *new,
				     unsigned int bytes,
				     unsigned int *error_code,
				     struct kvm_vcpu *vcpu)
{
	gpa_t gpa;
	struct page *page;
	char *kaddr;
	bool exchanged;

	/* guests cmpxchg8b have to be emulated atomically */
	if (bytes > 8 || (bytes & (bytes - 1)))
		goto emul_write;

	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);

	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;

	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
	if (is_error_page(page)) {
		kvm_release_page_clean(page);
		goto emul_write;
	}

	kaddr = kmap_atomic(page, KM_USER0);
	kaddr += offset_in_page(gpa);
	switch (bytes) {
	case 1:
		exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
		break;
	case 2:
		exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
		break;
	case 4:
		exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
		break;
	case 8:
		exchanged = CMPXCHG64(kaddr, old, new);
		break;
	default:
		BUG();
	}
	kunmap_atomic(kaddr, KM_USER0);
	kvm_release_page_dirty(page);

	if (!exchanged)
		return X86EMUL_CMPXCHG_FAILED;

	kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);

	return X86EMUL_CONTINUE;

emul_write:
	printk_once(KERN_WARNING "kvm: emulating exchange as write\n");

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

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

	if (vcpu->arch.pio.in)
		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
				    vcpu->arch.pio.size, pd);
	else
		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
				     vcpu->arch.pio.port, vcpu->arch.pio.size,
				     pd);
	return r;
}


static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
			     unsigned int count, struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.pio.count)
		goto data_avail;

	trace_kvm_pio(0, port, size, 1);

	vcpu->arch.pio.port = port;
	vcpu->arch.pio.in = 1;
	vcpu->arch.pio.count  = count;
	vcpu->arch.pio.size = size;

	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
	data_avail:
		memcpy(val, vcpu->arch.pio_data, size * count);
		vcpu->arch.pio.count = 0;
		return 1;
	}

	vcpu->run->exit_reason = KVM_EXIT_IO;
	vcpu->run->io.direction = KVM_EXIT_IO_IN;
	vcpu->run->io.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = count;
	vcpu->run->io.port = port;

	return 0;
}

static int emulator_pio_out_emulated(int size, unsigned short port,
			      const void *val, unsigned int count,
			      struct kvm_vcpu *vcpu)
{
	trace_kvm_pio(1, port, size, 1);

	vcpu->arch.pio.port = port;
	vcpu->arch.pio.in = 0;
	vcpu->arch.pio.count = count;
	vcpu->arch.pio.size = size;

	memcpy(vcpu->arch.pio_data, val, size * count);

	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
		vcpu->arch.pio.count = 0;
		return 1;
	}

	vcpu->run->exit_reason = KVM_EXIT_IO;
	vcpu->run->io.direction = KVM_EXIT_IO_OUT;
	vcpu->run->io.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = count;
	vcpu->run->io.port = port;

	return 0;
}

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 kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
{
	if (!need_emulate_wbinvd(vcpu))
		return X86EMUL_CONTINUE;

	if (kvm_x86_ops->has_wbinvd_exit()) {
		preempt_disable();
		smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
				wbinvd_ipi, NULL, 1);
		preempt_enable();
		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
	}
	wbinvd();
	return X86EMUL_CONTINUE;
}
EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);

int emulate_clts(struct kvm_vcpu *vcpu)
{
	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
	kvm_x86_ops->fpu_activate(vcpu);
	return X86EMUL_CONTINUE;
}

int emulator_get_dr(int dr, unsigned long *dest, struct kvm_vcpu *vcpu)
{
	return _kvm_get_dr(vcpu, dr, dest);
}

int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu)
{