x86.c

			case 0x01: /* VMMCALL */
				if (c->modrm_mod != 3 || c->modrm_rm != 1)
					return EMULATE_FAIL;
				break;
			case 0x34: /* sysenter */
			case 0x35: /* sysexit */
				if (c->modrm_mod != 0 || c->modrm_rm != 0)
					return EMULATE_FAIL;
				break;
			case 0x05: /* syscall */
				if (c->modrm_mod != 0 || c->modrm_rm != 0)
					return EMULATE_FAIL;
				break;
			default:
				return EMULATE_FAIL;
			}

			if (!(c->modrm_reg == 0 || c->modrm_reg == 3))
				return EMULATE_FAIL;
		}

		++vcpu->stat.insn_emulation;
		if (r)  {
			if (reexecute_instruction(vcpu, cr2))
				return EMULATE_DONE;
			if (emulation_type & EMULTYPE_SKIP)
				return EMULATE_FAIL;
			return handle_emulation_failure(vcpu);
		}
	}

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

	/* this is needed for vmware backdor interface to work since it
	   changes registers values  during IO operation */
	memcpy(c->regs, vcpu->arch.regs, sizeof c->regs);

restart:
	r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);

	if (r) { /* emulation failed */
		if (reexecute_instruction(vcpu, cr2))
			return EMULATE_DONE;

		return handle_emulation_failure(vcpu);
	}

	toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
	memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
	kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);

	if (vcpu->arch.emulate_ctxt.exception >= 0) {
		inject_emulated_exception(vcpu);
		return EMULATE_DONE;
	}

	if (vcpu->arch.pio.count) {
		if (!vcpu->arch.pio.in)
			vcpu->arch.pio.count = 0;
		return EMULATE_DO_MMIO;
	}

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

	if (vcpu->arch.emulate_ctxt.restart)
		goto restart;

	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);

int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
{
	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
	int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu);
	/* do not return to emulator after return from userspace */
	vcpu->arch.pio.count = 0;
	return ret;
}
EXPORT_SYMBOL_GPL(kvm_fast_pio_out);

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

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 (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) = freq->new;

	spin_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list) {
		kvm_for_each_vcpu(i, vcpu, kvm) {
			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
};

static void kvm_timer_init(void)
{
	int cpu;

	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
					  CPUFREQ_TRANSITION_NOTIFIER);
		for_each_online_cpu(cpu) {
			unsigned long khz = cpufreq_get(cpu);
			if (!khz)
				khz = tsc_khz;
			per_cpu(cpu_tsc_khz, cpu) = khz;
		}
	} else {
		for_each_possible_cpu(cpu)
			per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
	}
}

static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);

static int kvm_is_in_guest(void)
{
	return percpu_read(current_vcpu) != NULL;
}

static int kvm_is_user_mode(void)
{
	int user_mode = 3;

	if (percpu_read(current_vcpu))
		user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu));

	return user_mode != 0;
}

static unsigned long kvm_get_guest_ip(void)
{
	unsigned long ip = 0;

	if (percpu_read(current_vcpu))
		ip = kvm_rip_read(percpu_read(current_vcpu));

	return ip;
}

static struct perf_guest_info_callbacks kvm_guest_cbs = {
	.is_in_guest		= kvm_is_in_guest,
	.is_user_mode		= kvm_is_user_mode,
	.get_guest_ip		= kvm_get_guest_ip,
};

void kvm_before_handle_nmi(struct kvm_vcpu *vcpu)
{
	percpu_write(current_vcpu, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_before_handle_nmi);

void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
{
	percpu_write(current_vcpu, NULL);
}
EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);

int kvm_arch_init(void *opaque)
{
	int r;
	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);

	kvm_timer_init();

	perf_register_guest_info_callbacks(&kvm_guest_cbs);

	if (cpu_has_xsave)
		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);

	return 0;

out:
	return r;
}

void kvm_arch_exit(void)
{
	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);

	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;
	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_hv_hypercall(struct kvm_vcpu *vcpu)
{
	u64 param, ingpa, outgpa, ret;
	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
	bool fast, longmode;
	int cs_db, cs_l;

	/*
	 * hypercall generates UD from non zero cpl and real mode
	 * per HYPER-V spec
	 */
	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 0;
	}

	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
	longmode = is_long_mode(vcpu) && cs_l == 1;

	if (!longmode) {
		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
	}
#ifdef CONFIG_X86_64
	else {
		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
	}
#endif

	code = param & 0xffff;
	fast = (param >> 16) & 0x1;
	rep_cnt = (param >> 32) & 0xfff;
	rep_idx = (param >> 48) & 0xfff;

	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);

	switch (code) {
	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
		kvm_vcpu_on_spin(vcpu);
		break;
	default:
		res = HV_STATUS_INVALID_HYPERCALL_CODE;
		break;
	}

	ret = res | (((u64)rep_done & 0xfff) << 32);
	if (longmode) {
		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
	} else {
		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
	}

	return 1;
}

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

	if (kvm_hv_hypercall_enabled(vcpu->kvm))
		return kvm_hv_hypercall(vcpu);

	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);

	trace_kvm_hypercall(nr, a0, a1, a2, a3);

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

	if (kvm_x86_ops->get_cpl(vcpu) != 0) {
		ret = -KVM_EPERM;
		goto out;
	}

	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;
	}
out:
	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];
	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);

	return emulator_write_emulated(rip, instruction, 3, NULL, vcpu);
}

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

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

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

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

static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
	int j, nent = vcpu->arch.cpuid_nent;

	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
	/* when no next entry is found, the current entry[i] is reselected */
	for (j = i + 1; ; j = (j + 1) % nent) {
		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
		if (ej->function == e->function) {
			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
			return j;
		}
	}
	return 0; /* silence gcc, even though control never reaches here */
}

/* find an entry with matching function, matching index (if needed), and that
 * should be read next (if it's stateful) */
static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
	u32 function, u32 index)
{
	if (e->function != function)
		return 0;
	if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
		return 0;
	if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
	    !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
		return 0;
	return 1;
}

struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
					      u32 function, u32 index)
{
	int i;
	struct kvm_cpuid_entry2 *best = NULL;

	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		struct kvm_cpuid_entry2 *e;

		e = &vcpu->arch.cpuid_entries[i];
		if (is_matching_cpuid_entry(e, function, index)) {
			if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC)
				move_to_next_stateful_cpuid_entry(vcpu, i);
			best = e;
			break;
		}
		/*
		 * Both basic or both extended?
		 */
		if (((e->function ^ function) & 0x80000000) == 0)
			if (!best || e->function > best->function)
				best = e;
	}
	return best;
}
EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);

int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
{
	struct kvm_cpuid_entry2 *best;

	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
	if (!best || best->eax < 0x80000008)
		goto not_found;
	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
	if (best)
		return best->eax & 0xff;
not_found:
	return 36;
}

void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	u32 function, index;
	struct kvm_cpuid_entry2 *best;

	function = kvm_register_read(vcpu, VCPU_REGS_RAX);
	index = kvm_register_read(vcpu, VCPU_REGS_RCX);
	kvm_register_write(vcpu, VCPU_REGS_RAX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RBX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
	best = kvm_find_cpuid_entry(vcpu, function, index);
	if (best) {
		kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
		kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
		kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx);
		kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx);
	}
	kvm_x86_ops->skip_emulated_instruction(vcpu);
	trace_kvm_cpuid(function,
			kvm_register_read(vcpu, VCPU_REGS_RAX),
			kvm_register_read(vcpu, VCPU_REGS_RBX),
			kvm_register_read(vcpu, VCPU_REGS_RCX),
			kvm_register_read(vcpu, VCPU_REGS_RDX));
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);

/*
 * Check if userspace requested an interrupt window, and that the
 * interrupt window is open.
 *
 * No need to exit to userspace if we already have an interrupt queued.
 */
static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
{
	return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
		vcpu->run->request_interrupt_window &&
		kvm_arch_interrupt_allowed(vcpu));
}

static void post_kvm_run_save(struct kvm_vcpu *vcpu)
{
	struct kvm_run *kvm_run = vcpu->run;

	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
	kvm_run->cr8 = kvm_get_cr8(vcpu);
	kvm_run->apic_base = kvm_get_apic_base(vcpu);
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_run->ready_for_interrupt_injection = 1;
	else
		kvm_run->ready_for_interrupt_injection =
			kvm_arch_interrupt_allowed(vcpu) &&
			!kvm_cpu_has_interrupt(vcpu) &&
			!kvm_event_needs_reinjection(vcpu);
}

static void vapic_enter(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	struct page *page;

	if (!apic || !apic->vapic_addr)
		return;

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

	vcpu->arch.apic->vapic_page = page;
}

static void vapic_exit(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	int idx;

	if (!apic || !apic->vapic_addr)
		return;

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	kvm_release_page_dirty(apic->vapic_page);
	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
}

static void update_cr8_intercept(struct kvm_vcpu *vcpu)
{
	int max_irr, tpr;

	if (!kvm_x86_ops->update_cr8_intercept)
		return;

	if (!vcpu->arch.apic)
		return;

	if (!vcpu->arch.apic->vapic_addr)
		max_irr = kvm_lapic_find_highest_irr(vcpu);
	else
		max_irr = -1;

	if (max_irr != -1)
		max_irr >>= 4;

	tpr = kvm_lapic_get_cr8(vcpu);

	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
}

static void inject_pending_event(struct kvm_vcpu *vcpu)
{
	/* try to reinject previous events if any */
	if (vcpu->arch.exception.pending) {
		trace_kvm_inj_exception(vcpu->arch.exception.nr,
					vcpu->arch.exception.has_error_code,
					vcpu->arch.exception.error_code);
		kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
					  vcpu->arch.exception.has_error_code,
					  vcpu->arch.exception.error_code,
					  vcpu->arch.exception.reinject);
		return;
	}

	if (vcpu->arch.nmi_injected) {
		kvm_x86_ops->set_nmi(vcpu);
		return;
	}

	if (vcpu->arch.interrupt.pending) {
		kvm_x86_ops->set_irq(vcpu);
		return;
	}

	/* try to inject new event if pending */
	if (vcpu->arch.nmi_pending) {
		if (kvm_x86_ops->nmi_allowed(vcpu)) {
			vcpu->arch.nmi_pending = false;
			vcpu->arch.nmi_injected = true;
			kvm_x86_ops->set_nmi(vcpu);
		}
	} else if (kvm_cpu_has_interrupt(vcpu)) {
		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
					    false);
			kvm_x86_ops->set_irq(vcpu);
		}
	}
}

static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
			!vcpu->guest_xcr0_loaded) {
		/* kvm_set_xcr() also depends on this */
		xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
		vcpu->guest_xcr0_loaded = 1;
	}
}

static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
	if (vcpu->guest_xcr0_loaded) {
		if (vcpu->arch.xcr0 != host_xcr0)
			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
		vcpu->guest_xcr0_loaded = 0;
	}
}

static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
{
	int r;
	bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
		vcpu->run->request_interrupt_window;

	if (vcpu->requests) {
		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
			kvm_mmu_unload(vcpu);
		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
			__kvm_migrate_timers(vcpu);
		if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu))
			kvm_write_guest_time(vcpu);
		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
			kvm_mmu_sync_roots(vcpu);
		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
			kvm_x86_ops->tlb_flush(vcpu);
		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
			r = 0;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
			r = 0;
			goto out;
		}
		if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) {
			vcpu->fpu_active = 0;
			kvm_x86_ops->fpu_deactivate(vcpu);
		}
	}

	r = kvm_mmu_reload(vcpu);
	if (unlikely(r))
		goto out;

	preempt_disable();

	kvm_x86_ops->prepare_guest_switch(vcpu);
	if (vcpu->fpu_active)
		kvm_load_guest_fpu(vcpu);
	kvm_load_guest_xcr0(vcpu);

	atomic_set(&vcpu->guest_mode, 1);
	smp_wmb();

	local_irq_disable();

	if (!atomic_read(&vcpu->guest_mode) || vcpu->requests
	    || need_resched() || signal_pending(current)) {
		atomic_set(&vcpu->guest_mode, 0);
		smp_wmb();
		local_irq_enable();
		preempt_enable();
		r = 1;
		goto out;
	}

	inject_pending_event(vcpu);

	/* enable NMI/IRQ window open exits if needed */
	if (vcpu->arch.nmi_pending)
		kvm_x86_ops->enable_nmi_window(vcpu);
	else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
		kvm_x86_ops->enable_irq_window(vcpu);

	if (kvm_lapic_enabled(vcpu)) {
		update_cr8_intercept(vcpu);
		kvm_lapic_sync_to_vapic(vcpu);
	}

	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);

	kvm_guest_enter();

	if (unlikely(vcpu->arch.switch_db_regs)) {
		set_debugreg(0, 7);
		set_debugreg(vcpu->arch.eff_db[0], 0);
		set_debugreg(vcpu->arch.eff_db[1], 1);
		set_debugreg(vcpu->arch.eff_db[2], 2);
		set_debugreg(vcpu->arch.eff_db[3], 3);
	}

	trace_kvm_entry(vcpu->vcpu_id);
	kvm_x86_ops->run(vcpu);

	/*
	 * If the guest has used debug registers, at least dr7
	 * will be disabled while returning to the host.
	 * If we don't have active breakpoints in the host, we don't
	 * care about the messed up debug address registers. But if
	 * we have some of them active, restore the old state.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_restore();

	atomic_set(&vcpu->guest_mode, 0);
	smp_wmb();
	local_irq_enable();

	++vcpu->stat.exits;

	/*
	 * We must have an instruction between local_irq_enable() and
	 * kvm_guest_exit(), so the timer interrupt isn't delayed by
	 * the interrupt shadow.  The stat.exits increment will do nicely.
	 * But we need to prevent reordering, hence this barrier():
	 */
	barrier();

	kvm_guest_exit();

	preempt_enable();

	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

	/*
	 * Profile KVM exit RIPs:
	 */
	if (unlikely(prof_on == KVM_PROFILING)) {
		unsigned long rip = kvm_rip_read(vcpu);
		profile_hit(KVM_PROFILING, (void *)rip);
	}


	kvm_lapic_sync_from_vapic(vcpu);

	r = kvm_x86_ops->handle_exit(vcpu);
out:
	return r;
}


static int __vcpu_run(struct kvm_vcpu *vcpu)
{
	int r;
	struct kvm *kvm = vcpu->kvm;

	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
		pr_debug("vcpu %d received sipi with vector # %x\n",
			 vcpu->vcpu_id, vcpu->arch.sipi_vector);
		kvm_lapic_reset(vcpu);
		r = kvm_arch_vcpu_reset(vcpu);
		if (r)
			return r;
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
	}

	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
	vapic_enter(vcpu);

	r = 1;
	while (r > 0) {
		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
			r = vcpu_enter_guest(vcpu);
		else {
			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
			kvm_vcpu_block(vcpu);
			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
			if (kvm_check_request(KVM_REQ_UNHALT, vcpu))
			{
				switch(vcpu->arch.mp_state) {
				case KVM_MP_STATE_HALTED:
					vcpu->arch.mp_state =
						KVM_MP_STATE_RUNNABLE;
				case KVM_MP_STATE_RUNNABLE:
					break;
				case KVM_MP_STATE_SIPI_RECEIVED:
				default:
					r = -EINTR;
					break;
				}
			}
		}

		if (r <= 0)
			break;

		clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
		if (kvm_cpu_has_pending_timer(vcpu))
			kvm_inject_pending_timer_irqs(vcpu);

		if (dm_request_for_irq_injection(vcpu)) {
			r = -EINTR;
			vcpu->run->exit_reason = KVM_EXIT_INTR;
			++vcpu->stat.request_irq_exits;
		}
		if (signal_pending(current)) {
			r = -EINTR;
			vcpu->run->exit_reason = KVM_EXIT_INTR;
			++vcpu->stat.signal_exits;
		}
		if (need_resched()) {
			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
			kvm_resched(vcpu);
			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
		}
	}

	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);

	vapic_exit(vcpu);

	return r;
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	int r;
	sigset_t sigsaved;

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
		kvm_vcpu_block(vcpu);
		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
		r = -EAGAIN;
		goto out;
	}

	/* re-sync apic's tpr */
	if (!irqchip_in_kernel(vcpu->kvm))
		kvm_set_cr8(vcpu, kvm_run->cr8);

	if (vcpu->arch.pio.count || vcpu->mmio_needed ||
	    vcpu->arch.emulate_ctxt.restart) {
		if (vcpu->mmio_needed) {
			memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
			vcpu->mmio_read_completed = 1;
			vcpu->mmio_needed = 0;
		}
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
		if (r != EMULATE_DONE) {
			r = 0;
			goto out;
		}
	}
	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
		kvm_register_write(vcpu, VCPU_REGS_RAX,
				     kvm_run->hypercall.ret);

	r = __vcpu_run(vcpu);

out:
	post_kvm_run_save(vcpu);
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	return r;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
	regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX);
	regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX);
	regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX);
	regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI);
	regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI);
	regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
	regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP);
#ifdef CONFIG_X86_64
	regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8);
	regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9);
	regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10);
	regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11);
	regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12);
	regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13);
	regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14);
	regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15);
#endif

	regs->rip = kvm_rip_read(vcpu);
	regs->rflags = kvm_get_rflags(vcpu);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax);
	kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx);
	kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx);
	kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx);
	kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi);
	kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi);
	kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp);
	kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp);
#ifdef CONFIG_X86_64
	kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8);
	kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9);
	kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10);
	kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11);
	kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12);
	kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13);
	kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14);
	kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15);
#endif

	kvm_rip_write(vcpu, regs->rip);
	kvm_set_rflags(vcpu, regs->rflags);

	vcpu->arch.exception.pending = false;

	return 0;
}

void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
	struct kvm_segment cs;

	kvm_get_segment(vcpu, &cs, VCPU_SREG_CS);
	*db = cs.db;
	*l = cs.l;
}
EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	struct desc_ptr dt;

	kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
	kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
	kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
	kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
	kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
	kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS);

	kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
	kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);