x86.c

	if (vcpu->requests)
		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
			kvm_x86_ops->tlb_flush(vcpu);

	kvm_x86_ops->run(vcpu, kvm_run);

	vcpu->guest_mode = 0;
	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();

	/*
	 * Profile KVM exit RIPs:
	 */
	if (unlikely(prof_on == KVM_PROFILING)) {
		kvm_x86_ops->cache_regs(vcpu);
		profile_hit(KVM_PROFILING, (void *)vcpu->rip);
	}

	r = kvm_x86_ops->handle_exit(kvm_run, vcpu);

	if (r > 0) {
		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
			r = -EINTR;
			kvm_run->exit_reason = KVM_EXIT_INTR;
			++vcpu->stat.request_irq_exits;
			goto out;
		}
		if (!need_resched())
			goto again;
	}

out:
	if (r > 0) {
		kvm_resched(vcpu);
		goto preempted;
	}

	post_kvm_run_save(vcpu, kvm_run);

	return r;
}

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

	vcpu_load(vcpu);

	if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
		kvm_vcpu_block(vcpu);
		vcpu_put(vcpu);
		return -EAGAIN;
	}

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

	/* re-sync apic's tpr */
	if (!irqchip_in_kernel(vcpu->kvm))
		set_cr8(vcpu, kvm_run->cr8);

	if (vcpu->pio.cur_count) {
		r = complete_pio(vcpu);
		if (r)
			goto out;
	}
#if CONFIG_HAS_IOMEM
	if (vcpu->mmio_needed) {
		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
		vcpu->mmio_read_completed = 1;
		vcpu->mmio_needed = 0;
		r = emulate_instruction(vcpu, kvm_run,
					vcpu->mmio_fault_cr2, 0, 1);
		if (r == EMULATE_DO_MMIO) {
			/*
			 * Read-modify-write.  Back to userspace.
			 */
			r = 0;
			goto out;
		}
	}
#endif
	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) {
		kvm_x86_ops->cache_regs(vcpu);
		vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret;
		kvm_x86_ops->decache_regs(vcpu);
	}

	r = __vcpu_run(vcpu, kvm_run);

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

	vcpu_put(vcpu);
	return r;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);

	kvm_x86_ops->cache_regs(vcpu);

	regs->rax = vcpu->regs[VCPU_REGS_RAX];
	regs->rbx = vcpu->regs[VCPU_REGS_RBX];
	regs->rcx = vcpu->regs[VCPU_REGS_RCX];
	regs->rdx = vcpu->regs[VCPU_REGS_RDX];
	regs->rsi = vcpu->regs[VCPU_REGS_RSI];
	regs->rdi = vcpu->regs[VCPU_REGS_RDI];
	regs->rsp = vcpu->regs[VCPU_REGS_RSP];
	regs->rbp = vcpu->regs[VCPU_REGS_RBP];
#ifdef CONFIG_X86_64
	regs->r8 = vcpu->regs[VCPU_REGS_R8];
	regs->r9 = vcpu->regs[VCPU_REGS_R9];
	regs->r10 = vcpu->regs[VCPU_REGS_R10];
	regs->r11 = vcpu->regs[VCPU_REGS_R11];
	regs->r12 = vcpu->regs[VCPU_REGS_R12];
	regs->r13 = vcpu->regs[VCPU_REGS_R13];
	regs->r14 = vcpu->regs[VCPU_REGS_R14];
	regs->r15 = vcpu->regs[VCPU_REGS_R15];
#endif

	regs->rip = vcpu->rip;
	regs->rflags = kvm_x86_ops->get_rflags(vcpu);

	/*
	 * Don't leak debug flags in case they were set for guest debugging
	 */
	if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep)
		regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);

	vcpu_put(vcpu);

	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);

	vcpu->regs[VCPU_REGS_RAX] = regs->rax;
	vcpu->regs[VCPU_REGS_RBX] = regs->rbx;
	vcpu->regs[VCPU_REGS_RCX] = regs->rcx;
	vcpu->regs[VCPU_REGS_RDX] = regs->rdx;
	vcpu->regs[VCPU_REGS_RSI] = regs->rsi;
	vcpu->regs[VCPU_REGS_RDI] = regs->rdi;
	vcpu->regs[VCPU_REGS_RSP] = regs->rsp;
	vcpu->regs[VCPU_REGS_RBP] = regs->rbp;
#ifdef CONFIG_X86_64
	vcpu->regs[VCPU_REGS_R8] = regs->r8;
	vcpu->regs[VCPU_REGS_R9] = regs->r9;
	vcpu->regs[VCPU_REGS_R10] = regs->r10;
	vcpu->regs[VCPU_REGS_R11] = regs->r11;
	vcpu->regs[VCPU_REGS_R12] = regs->r12;
	vcpu->regs[VCPU_REGS_R13] = regs->r13;
	vcpu->regs[VCPU_REGS_R14] = regs->r14;
	vcpu->regs[VCPU_REGS_R15] = regs->r15;
#endif

	vcpu->rip = regs->rip;
	kvm_x86_ops->set_rflags(vcpu, regs->rflags);

	kvm_x86_ops->decache_regs(vcpu);

	vcpu_put(vcpu);

	return 0;
}

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

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

	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 descriptor_table dt;
	int pending_vec;

	vcpu_load(vcpu);

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

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

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

	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
	sregs->cr0 = vcpu->cr0;
	sregs->cr2 = vcpu->cr2;
	sregs->cr3 = vcpu->cr3;
	sregs->cr4 = vcpu->cr4;
	sregs->cr8 = get_cr8(vcpu);
	sregs->efer = vcpu->shadow_efer;
	sregs->apic_base = kvm_get_apic_base(vcpu);

	if (irqchip_in_kernel(vcpu->kvm)) {
		memset(sregs->interrupt_bitmap, 0,
		       sizeof sregs->interrupt_bitmap);
		pending_vec = kvm_x86_ops->get_irq(vcpu);
		if (pending_vec >= 0)
			set_bit(pending_vec,
				(unsigned long *)sregs->interrupt_bitmap);
	} else
		memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
		       sizeof sregs->interrupt_bitmap);

	vcpu_put(vcpu);

	return 0;
}

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

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

	vcpu_load(vcpu);

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

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

	set_cr8(vcpu, sregs->cr8);

	mmu_reset_needed |= vcpu->shadow_efer != sregs->efer;
#ifdef CONFIG_X86_64
	kvm_x86_ops->set_efer(vcpu, sregs->efer);
#endif
	kvm_set_apic_base(vcpu, sregs->apic_base);

	kvm_x86_ops->decache_cr4_guest_bits(vcpu);

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

	mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
	if (!is_long_mode(vcpu) && is_pae(vcpu))
		load_pdptrs(vcpu, vcpu->cr3);

	if (mmu_reset_needed)
		kvm_mmu_reset_context(vcpu);

	if (!irqchip_in_kernel(vcpu->kvm)) {
		memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
		       sizeof vcpu->irq_pending);
		vcpu->irq_summary = 0;
		for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
			if (vcpu->irq_pending[i])
				__set_bit(i, &vcpu->irq_summary);
	} else {
		max_bits = (sizeof sregs->interrupt_bitmap) << 3;
		pending_vec = find_first_bit(
			(const unsigned long *)sregs->interrupt_bitmap,
			max_bits);
		/* Only pending external irq is handled here */
		if (pending_vec < max_bits) {
			kvm_x86_ops->set_irq(vcpu, pending_vec);
			pr_debug("Set back pending irq %d\n",
				 pending_vec);
		}
	}

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

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

	vcpu_put(vcpu);

	return 0;
}

int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
				    struct kvm_debug_guest *dbg)
{
	int r;

	vcpu_load(vcpu);

	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);

	vcpu_put(vcpu);

	return r;
}

/*
 * fxsave fpu state.  Taken from x86_64/processor.h.  To be killed when
 * we have asm/x86/processor.h
 */
struct fxsave {
	u16	cwd;
	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;

	vcpu_load(vcpu);
	mutex_lock(&vcpu->kvm->lock);
	gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
	tr->physical_address = gpa;
	tr->valid = gpa != UNMAPPED_GVA;
	tr->writeable = 1;
	tr->usermode = 0;
	mutex_unlock(&vcpu->kvm->lock);
	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->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->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;

	/* Initialize guest FPU by resetting ours and saving into guest's */
	preempt_disable();
	fx_save(&vcpu->host_fx_image);
	fpu_init();
	fx_save(&vcpu->guest_fx_image);
	fx_restore(&vcpu->host_fx_image);
	preempt_enable();

	vcpu->cr0 |= X86_CR0_ET;
	after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
	vcpu->guest_fx_image.mxcsr = 0x1f80;
	memset((void *)&vcpu->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->fpu_active || vcpu->guest_fpu_loaded)
		return;

	vcpu->guest_fpu_loaded = 1;
	fx_save(&vcpu->host_fx_image);
	fx_restore(&vcpu->guest_fx_image);
}
EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);

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

	vcpu->guest_fpu_loaded = 0;
	fx_save(&vcpu->guest_fx_image);
	fx_restore(&vcpu->host_fx_image);
	++vcpu->stat.fpu_reload;
}
EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
	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->host_fx_image & 0xF);

	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)
{
	return kvm_x86_ops->vcpu_reset(vcpu);
}

void kvm_arch_hardware_enable(void *garbage)
{
	kvm_x86_ops->hardware_enable(garbage);
}

void kvm_arch_hardware_disable(void *garbage)
{
	kvm_x86_ops->hardware_disable(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->mmu.root_hpa = INVALID_PAGE;
	if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
		vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
	else
		vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED;

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

	return 0;

fail_mmu_destroy:
	kvm_mmu_destroy(vcpu);
fail_free_pio_data:
	free_page((unsigned long)vcpu->pio_data);
fail:
	return r;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	kvm_free_lapic(vcpu);
	kvm_mmu_destroy(vcpu);
	free_page((unsigned long)vcpu->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->active_mmu_pages);

	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;

	/*
	 * Unpin any mmu pages first.
	 */
	for (i = 0; i < KVM_MAX_VCPUS; ++i)
		if (kvm->vcpus[i])
			kvm_unload_vcpu_mmu(kvm->vcpus[i]);
	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
		if (kvm->vcpus[i]) {
			kvm_arch_vcpu_free(kvm->vcpus[i]);
			kvm->vcpus[i] = NULL;
		}
	}

}

void kvm_arch_destroy_vm(struct kvm *kvm)
{
	kfree(kvm->vpic);
	kfree(kvm->vioapic);
	kvm_free_vcpus(kvm);
	kvm_free_physmem(kvm);
	kfree(kvm);
}

int kvm_arch_set_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;
	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];

	/*To keep backward compatibility with older userspace,
	 *x86 needs to hanlde !user_alloc case.
	 */
	if (!user_alloc) {
		if (npages && !old.rmap) {
			down_write(&current->mm->mmap_sem);
			memslot->userspace_addr = do_mmap(NULL, 0,
						     npages * PAGE_SIZE,
						     PROT_READ | PROT_WRITE,
						     MAP_SHARED | MAP_ANONYMOUS,
						     0);
			up_write(&current->mm->mmap_sem);

			if (IS_ERR((void *)memslot->userspace_addr))
				return PTR_ERR((void *)memslot->userspace_addr);
		} else {
			if (!old.user_alloc && old.rmap) {
				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");
			}
		}
	}

	if (!kvm->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);
	kvm_flush_remote_tlbs(kvm);

	return 0;
}