x86.c

	u16	swd;
	u16	twd;
	u16	fop;
	u64	rip;
	u64	rdp;
	u32	mxcsr;
	u32	mxcsr_mask;
	u32	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
#ifdef CONFIG_X86_64
	u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg = 256 bytes */
#else
	u32	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
#endif
};

/*
 * 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;

	vcpu_load(vcpu);
	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;
	vcpu_put(vcpu);

	return 0;
}

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

	vcpu_load(vcpu);

	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);

	vcpu_put(vcpu);

	return 0;
}

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

	vcpu_load(vcpu);

	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);

	vcpu_put(vcpu);

	return 0;
}

void fx_init(struct kvm_vcpu *vcpu)
{
	unsigned after_mxcsr_mask;

	/*
	 * Touch the fpu the first time in non atomic context as if
	 * this is the first fpu instruction the exception handler
	 * will fire before the instruction returns and it'll have to
	 * allocate ram with GFP_KERNEL.
	 */
	if (!used_math())
		kvm_fx_save(&vcpu->arch.host_fx_image);

	/* Initialize guest FPU by resetting ours and saving into guest's */
	preempt_disable();
	kvm_fx_save(&vcpu->arch.host_fx_image);
	kvm_fx_finit();
	kvm_fx_save(&vcpu->arch.guest_fx_image);
	kvm_fx_restore(&vcpu->arch.host_fx_image);
	preempt_enable();

	vcpu->arch.cr0 |= X86_CR0_ET;
	after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
	vcpu->arch.guest_fx_image.mxcsr = 0x1f80;
	memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask,
	       0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
}
EXPORT_SYMBOL_GPL(fx_init);

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

	vcpu->guest_fpu_loaded = 1;
	kvm_fx_save(&vcpu->arch.host_fx_image);
	kvm_fx_restore(&vcpu->arch.guest_fx_image);
	trace_kvm_fpu(1);
}

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

	vcpu->guest_fpu_loaded = 0;
	kvm_fx_save(&vcpu->arch.guest_fx_image);
	kvm_fx_restore(&vcpu->arch.host_fx_image);
	++vcpu->stat.fpu_reload;
	set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
	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;
	}

	kvm_x86_ops->vcpu_free(vcpu);
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
						unsigned int id)
{
	return kvm_x86_ops->vcpu_create(kvm, id);
}

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

	/* We do fxsave: this must be aligned. */
	BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);

	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);

	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;

	return kvm_x86_ops->vcpu_reset(vcpu);
}

int kvm_arch_hardware_enable(void *garbage)
{
	/*
	 * Since this may be called from a hotplug notifcation,
	 * we can't get the CPU frequency directly.
	 */
	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
		int cpu = raw_smp_processor_id();
		per_cpu(cpu_tsc_khz, cpu) = 0;
	}

	kvm_shared_msr_cpu_online();

	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.mmu.root_hpa = INVALID_PAGE;
	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);

	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;

	return 0;
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);

	kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
	if (!kvm->arch.aliases) {
		kfree(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);

	rdtscll(kvm->arch.vm_init_tsc);

	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);
}

void kvm_arch_destroy_vm(struct kvm *kvm)
{
	kvm_iommu_unmap_guest(kvm);
	kvm_free_pit(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->arch.aliases);
	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;

	/*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_PRIVATE | MAP_ANONYMOUS,
						 0);
			up_write(&current->mm->mmap_sem);

			if (IS_ERR((void *)userspace_addr))
				return PTR_ERR((void *)userspace_addr);

			memslot->userspace_addr = userspace_addr;
		}
	}


	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				struct kvm_memory_slot old,
				int user_alloc)
{

	int npages = mem->memory_size >> PAGE_SHIFT;

	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
		int ret;

		down_write(&current->mm->mmap_sem);
		ret = do_munmap(current->mm, old.userspace_addr,
				old.npages * PAGE_SIZE);
		up_write(&current->mm->mmap_sem);
		if (ret < 0)
			printk(KERN_WARNING
			       "kvm_vm_ioctl_set_memory_region: "
			       "failed to munmap memory\n");
	}

	spin_lock(&kvm->mmu_lock);
	if (!kvm->arch.n_requested_mmu_pages) {
		unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
	}

	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
	spin_unlock(&kvm->mmu_lock);
}

void kvm_arch_flush_shadow(struct kvm *kvm)
{
	kvm_mmu_zap_all(kvm);
	kvm_reload_remote_mmus(kvm);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
		|| vcpu->arch.nmi_pending ||
		(kvm_arch_interrupt_allowed(vcpu) &&
		 kvm_cpu_has_interrupt(vcpu));
}

void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
	int me;
	int cpu = vcpu->cpu;

	if (waitqueue_active(&vcpu->wq)) {
		wake_up_interruptible(&vcpu->wq);
		++vcpu->stat.halt_wakeup;
	}

	me = get_cpu();
	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
			smp_send_reschedule(cpu);
	put_cpu();
}

int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
{
	return kvm_x86_ops->interrupt_allowed(vcpu);
}

bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
{
	unsigned long current_rip = kvm_rip_read(vcpu) +
		get_segment_base(vcpu, VCPU_SREG_CS);

	return current_rip == linear_rip;
}
EXPORT_SYMBOL_GPL(kvm_is_linear_rip);

unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
{
	unsigned long rflags;

	rflags = kvm_x86_ops->get_rflags(vcpu);
	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
		rflags &= ~X86_EFLAGS_TF;
	return rflags;
}
EXPORT_SYMBOL_GPL(kvm_get_rflags);

void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
	    kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
		rflags |= X86_EFLAGS_TF;
	kvm_x86_ops->set_rflags(vcpu, rflags);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);

EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);