x86.c

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_CLOCK_UPDATE, vcpu)) {
			r = kvm_guest_time_update(vcpu);
			if (unlikely(r))
				goto out;
		}
		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;

	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
		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);
		}
	}

	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();
		kvm_x86_ops->cancel_injection(vcpu);
		r = 1;
		goto out;
	}

	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();

	kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);

	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) {
		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;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	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);

	kvm_x86_ops->get_idt(vcpu, &dt);
	sregs->idt.limit = dt.size;
	sregs->idt.base = dt.address;
	kvm_x86_ops->get_gdt(vcpu, &dt);
	sregs->gdt.limit = dt.size;
	sregs->gdt.base = dt.address;

	sregs->cr0 = kvm_read_cr0(vcpu);
	sregs->cr2 = vcpu->arch.cr2;
	sregs->cr3 = vcpu->arch.cr3;
	sregs->cr4 = kvm_read_cr4(vcpu);
	sregs->cr8 = kvm_get_cr8(vcpu);
	sregs->efer = vcpu->arch.efer;
	sregs->apic_base = kvm_get_apic_base(vcpu);

	memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap);

	if (vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft)
		set_bit(vcpu->arch.interrupt.nr,
			(unsigned long *)sregs->interrupt_bitmap);

	return 0;
}

int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	mp_state->mp_state = vcpu->arch.mp_state;
	return 0;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	vcpu->arch.mp_state = mp_state->mp_state;
	kvm_make_request(KVM_REQ_EVENT, vcpu);
	return 0;
}

int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
		    bool has_error_code, u32 error_code)
{
	struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
	int ret;

	init_emulate_ctxt(vcpu);

	ret = emulator_task_switch(&vcpu->arch.emulate_ctxt,
				   tss_selector, reason, has_error_code,
				   error_code);

	if (ret)
		return EMULATE_FAIL;

	memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
	kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
	kvm_make_request(KVM_REQ_EVENT, vcpu);
	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	int mmu_reset_needed = 0;
	int pending_vec, max_bits;
	struct desc_ptr dt;

	dt.size = sregs->idt.limit;
	dt.address = sregs->idt.base;
	kvm_x86_ops->set_idt(vcpu, &dt);
	dt.size = sregs->gdt.limit;
	dt.address = sregs->gdt.base;
	kvm_x86_ops->set_gdt(vcpu, &dt);

	vcpu->arch.cr2 = sregs->cr2;
	mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
	vcpu->arch.cr3 = sregs->cr3;

	kvm_set_cr8(vcpu, sregs->cr8);

	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
	kvm_x86_ops->set_efer(vcpu, sregs->efer);
	kvm_set_apic_base(vcpu, sregs->apic_base);

	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
	vcpu->arch.cr0 = sregs->cr0;

	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
	if (sregs->cr4 & X86_CR4_OSXSAVE)
		update_cpuid(vcpu);
	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
		load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
		mmu_reset_needed = 1;
	}

	if (mmu_reset_needed)
		kvm_mmu_reset_context(vcpu);

	max_bits = (sizeof sregs->interrupt_bitmap) << 3;
	pending_vec = find_first_bit(
		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
	if (pending_vec < max_bits) {
		kvm_queue_interrupt(vcpu, pending_vec, false);
		pr_debug("Set back pending irq %d\n", pending_vec);
		if (irqchip_in_kernel(vcpu->kvm))
			kvm_pic_clear_isr_ack(vcpu->kvm);
	}

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

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

	update_cr8_intercept(vcpu);

	/* Older userspace won't unhalt the vcpu on reset. */
	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
	    !is_protmode(vcpu))
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
{
	unsigned long rflags;
	int i, r;

	if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
		r = -EBUSY;
		if (vcpu->arch.exception.pending)
			goto out;
		if (dbg->control & KVM_GUESTDBG_INJECT_DB)
			kvm_queue_exception(vcpu, DB_VECTOR);
		else
			kvm_queue_exception(vcpu, BP_VECTOR);
	}

	/*
	 * Read rflags as long as potentially injected trace flags are still
	 * filtered out.
	 */
	rflags = kvm_get_rflags(vcpu);

	vcpu->guest_debug = dbg->control;
	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
		vcpu->guest_debug = 0;

	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
		for (i = 0; i < KVM_NR_DB_REGS; ++i)
			vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
		vcpu->arch.switch_db_regs =
			(dbg->arch.debugreg[7] & DR7_BP_EN_MASK);
	} else {
		for (i = 0; i < KVM_NR_DB_REGS; i++)
			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
		vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
	}

	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
			get_segment_base(vcpu, VCPU_SREG_CS);

	/*
	 * Trigger an rflags update that will inject or remove the trace
	 * flags.
	 */
	kvm_set_rflags(vcpu, rflags);

	kvm_x86_ops->set_guest_debug(vcpu, dbg);

	r = 0;

out:

	return r;
}

/*
 * Translate a guest virtual address to a guest physical address.
 */
int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				    struct kvm_translation *tr)
{
	unsigned long vaddr = tr->linear_address;
	gpa_t gpa;
	int idx;

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	tr->physical_address = gpa;
	tr->valid = gpa != UNMAPPED_GVA;
	tr->writeable = 1;
	tr->usermode = 0;

	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct i387_fxsave_struct *fxsave =
			&vcpu->arch.guest_fpu.state->fxsave;

	memcpy(fpu->fpr, fxsave->st_space, 128);
	fpu->fcw = fxsave->cwd;
	fpu->fsw = fxsave->swd;
	fpu->ftwx = fxsave->twd;
	fpu->last_opcode = fxsave->fop;
	fpu->last_ip = fxsave->rip;
	fpu->last_dp = fxsave->rdp;
	memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct i387_fxsave_struct *fxsave =
			&vcpu->arch.guest_fpu.state->fxsave;

	memcpy(fxsave->st_space, fpu->fpr, 128);
	fxsave->cwd = fpu->fcw;
	fxsave->swd = fpu->fsw;
	fxsave->twd = fpu->ftwx;
	fxsave->fop = fpu->last_opcode;
	fxsave->rip = fpu->last_ip;
	fxsave->rdp = fpu->last_dp;
	memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);

	return 0;
}

int fx_init(struct kvm_vcpu *vcpu)
{
	int err;

	err = fpu_alloc(&vcpu->arch.guest_fpu);
	if (err)
		return err;

	fpu_finit(&vcpu->arch.guest_fpu);

	/*
	 * Ensure guest xcr0 is valid for loading
	 */
	vcpu->arch.xcr0 = XSTATE_FP;

	vcpu->arch.cr0 |= X86_CR0_ET;

	return 0;
}
EXPORT_SYMBOL_GPL(fx_init);

static void fx_free(struct kvm_vcpu *vcpu)
{
	fpu_free(&vcpu->arch.guest_fpu);
}

void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
	if (vcpu->guest_fpu_loaded)
		return;

	/*
	 * Restore all possible states in the guest,
	 * and assume host would use all available bits.
	 * Guest xcr0 would be loaded later.
	 */
	kvm_put_guest_xcr0(vcpu);
	vcpu->guest_fpu_loaded = 1;
	unlazy_fpu(current);
	fpu_restore_checking(&vcpu->arch.guest_fpu);
	trace_kvm_fpu(1);
}

void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
	kvm_put_guest_xcr0(vcpu);

	if (!vcpu->guest_fpu_loaded)
		return;

	vcpu->guest_fpu_loaded = 0;
	fpu_save_init(&vcpu->arch.guest_fpu);
	++vcpu->stat.fpu_reload;
	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
	trace_kvm_fpu(0);
}

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.time_page) {
		kvm_release_page_dirty(vcpu->arch.time_page);
		vcpu->arch.time_page = NULL;
	}

	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
	fx_free(vcpu);
	kvm_x86_ops->vcpu_free(vcpu);
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
						unsigned int id)
{
	if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
		printk_once(KERN_WARNING
		"kvm: SMP vm created on host with unstable TSC; "
		"guest TSC will not be reliable\n");
	return kvm_x86_ops->vcpu_create(kvm, id);
}

int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
	int r;

	vcpu->arch.mtrr_state.have_fixed = 1;
	vcpu_load(vcpu);
	r = kvm_arch_vcpu_reset(vcpu);
	if (r == 0)
		r = kvm_mmu_setup(vcpu);
	vcpu_put(vcpu);
	if (r < 0)
		goto free_vcpu;

	return 0;
free_vcpu:
	kvm_x86_ops->vcpu_free(vcpu);
	return r;
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	vcpu_load(vcpu);
	kvm_mmu_unload(vcpu);
	vcpu_put(vcpu);

	fx_free(vcpu);
	kvm_x86_ops->vcpu_free(vcpu);
}

int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
{
	vcpu->arch.nmi_pending = false;
	vcpu->arch.nmi_injected = false;

	vcpu->arch.switch_db_regs = 0;
	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
	vcpu->arch.dr6 = DR6_FIXED_1;
	vcpu->arch.dr7 = DR7_FIXED_1;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	return kvm_x86_ops->vcpu_reset(vcpu);
}

int kvm_arch_hardware_enable(void *garbage)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	int i;

	kvm_shared_msr_cpu_online();
	list_for_each_entry(kvm, &vm_list, vm_list)
		kvm_for_each_vcpu(i, vcpu, kvm)
			if (vcpu->cpu == smp_processor_id())
				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
	return kvm_x86_ops->hardware_enable(garbage);
}

void kvm_arch_hardware_disable(void *garbage)
{
	kvm_x86_ops->hardware_disable(garbage);
	drop_user_return_notifiers(garbage);
}

int kvm_arch_hardware_setup(void)
{
	return kvm_x86_ops->hardware_setup();
}

void kvm_arch_hardware_unsetup(void)
{
	kvm_x86_ops->hardware_unsetup();
}

void kvm_arch_check_processor_compat(void *rtn)
{
	kvm_x86_ops->check_processor_compatibility(rtn);
}

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
	struct page *page;
	struct kvm *kvm;
	int r;

	BUG_ON(vcpu->kvm == NULL);
	kvm = vcpu->kvm;

	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
	vcpu->arch.mmu.translate_gpa = translate_gpa;
	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
	else
		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;

	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
	if (!page) {
		r = -ENOMEM;
		goto fail;
	}
	vcpu->arch.pio_data = page_address(page);

	if (!kvm->arch.virtual_tsc_khz)
		kvm_arch_set_tsc_khz(kvm, max_tsc_khz);

	r = kvm_mmu_create(vcpu);
	if (r < 0)
		goto fail_free_pio_data;

	if (irqchip_in_kernel(kvm)) {
		r = kvm_create_lapic(vcpu);
		if (r < 0)
			goto fail_mmu_destroy;
	}

	vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
				       GFP_KERNEL);
	if (!vcpu->arch.mce_banks) {
		r = -ENOMEM;
		goto fail_free_lapic;
	}
	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;

	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
		goto fail_free_mce_banks;

	return 0;
fail_free_mce_banks:
	kfree(vcpu->arch.mce_banks);
fail_free_lapic:
	kvm_free_lapic(vcpu);
fail_mmu_destroy:
	kvm_mmu_destroy(vcpu);
fail_free_pio_data:
	free_page((unsigned long)vcpu->arch.pio_data);
fail:
	return r;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	int idx;

	kfree(vcpu->arch.mce_banks);
	kvm_free_lapic(vcpu);
	idx = srcu_read_lock(&vcpu->kvm->srcu);
	kvm_mmu_destroy(vcpu);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	free_page((unsigned long)vcpu->arch.pio_data);
}

struct  kvm *kvm_arch_create_vm(void)
{
	struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);

	if (!kvm)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);

	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);

	spin_lock_init(&kvm->arch.tsc_write_lock);

	return kvm;
}

static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
	vcpu_load(vcpu);
	kvm_mmu_unload(vcpu);
	vcpu_put(vcpu);
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
	struct kvm_vcpu *vcpu;

	/*
	 * Unpin any mmu pages first.
	 */
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_unload_vcpu_mmu(vcpu);
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_arch_vcpu_free(vcpu);

	mutex_lock(&kvm->lock);
	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
		kvm->vcpus[i] = NULL;

	atomic_set(&kvm->online_vcpus, 0);
	mutex_unlock(&kvm->lock);
}

void kvm_arch_sync_events(struct kvm *kvm)
{
	kvm_free_all_assigned_devices(kvm);
	kvm_free_pit(kvm);
}

void kvm_arch_destroy_vm(struct kvm *kvm)
{
	kvm_iommu_unmap_guest(kvm);
	kfree(kvm->arch.vpic);
	kfree(kvm->arch.vioapic);
	kvm_free_vcpus(kvm);
	kvm_free_physmem(kvm);
	if (kvm->arch.apic_access_page)
		put_page(kvm->arch.apic_access_page);
	if (kvm->arch.ept_identity_pagetable)
		put_page(kvm->arch.ept_identity_pagetable);
	cleanup_srcu_struct(&kvm->srcu);
	kfree(kvm);
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *memslot,
				struct kvm_memory_slot old,
				struct kvm_userspace_memory_region *mem,
				int user_alloc)
{
	int npages = memslot->npages;
	int map_flags = MAP_PRIVATE | MAP_ANONYMOUS;

	/* Prevent internal slot pages from being moved by fork()/COW. */
	if (memslot->id >= KVM_MEMORY_SLOTS)
		map_flags = MAP_SHARED | MAP_ANONYMOUS;

	/*To keep backward compatibility with older userspace,
	 *x86 needs to hanlde !user_alloc case.
	 */
	if (!user_alloc) {
		if (npages && !old.rmap) {
			unsigned long userspace_addr;

			down_write(&current->mm->mmap_sem);
			userspace_addr = do_mmap(NULL, 0,
						 npages * PAGE_SIZE,
						 PROT_READ | PROT_WRITE,
						 map_flags,
						 0);