x86.c

	if (!reported) {
		reported = 1;
		printk(KERN_WARNING "kvm: emulating exchange as write\n");
	}
#ifndef CONFIG_X86_64
	/* guests cmpxchg8b have to be emulated atomically */
	if (bytes == 8) {
		gpa_t gpa;
		struct page *page;
		char *kaddr;
		u64 val;

		gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);

		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;

		val = *(u64 *)new;

		down_read(&current->mm->mmap_sem);
		page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
		up_read(&current->mm->mmap_sem);

		kaddr = kmap_atomic(page, KM_USER0);
		set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
		kunmap_atomic(kaddr, KM_USER0);
		kvm_release_page_dirty(page);
	}
emul_write:
#endif

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

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)
{
	return X86EMUL_CONTINUE;
}

int emulate_clts(struct kvm_vcpu *vcpu)
{
	KVMTRACE_0D(CLTS, vcpu, handler);
	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
	return X86EMUL_CONTINUE;
}

int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
	struct kvm_vcpu *vcpu = ctxt->vcpu;

	switch (dr) {
	case 0 ... 3:
		*dest = kvm_x86_ops->get_dr(vcpu, dr);
		return X86EMUL_CONTINUE;
	default:
		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
		return X86EMUL_UNHANDLEABLE;
	}
}

int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
{
	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
	int exception;

	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
	if (exception) {
		/* FIXME: better handling */
		return X86EMUL_UNHANDLEABLE;
	}
	return X86EMUL_CONTINUE;
}

void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
{
	u8 opcodes[4];
	unsigned long rip = kvm_rip_read(vcpu);
	unsigned long rip_linear;

	if (!printk_ratelimit())
		return;

	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);

	emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu);

	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);

static struct x86_emulate_ops emulate_ops = {
	.read_std            = emulator_read_std,
	.read_emulated       = emulator_read_emulated,
	.write_emulated      = emulator_write_emulated,
	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
};

static void cache_all_regs(struct kvm_vcpu *vcpu)
{
	kvm_register_read(vcpu, VCPU_REGS_RAX);
	kvm_register_read(vcpu, VCPU_REGS_RSP);
	kvm_register_read(vcpu, VCPU_REGS_RIP);
	vcpu->arch.regs_dirty = ~0;
}

int emulate_instruction(struct kvm_vcpu *vcpu,
			struct kvm_run *run,
			unsigned long cr2,
			u16 error_code,
			int emulation_type)
{
	int r;
	struct decode_cache *c;

	kvm_clear_exception_queue(vcpu);
	vcpu->arch.mmio_fault_cr2 = cr2;
	/*
	 * TODO: fix x86_emulate.c to use guest_read/write_register
	 * instead of direct ->regs accesses, can save hundred cycles
	 * on Intel for instructions that don't read/change RSP, for
	 * for example.
	 */
	cache_all_regs(vcpu);

	vcpu->mmio_is_write = 0;
	vcpu->arch.pio.string = 0;

	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
		int cs_db, cs_l;
		kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);

		vcpu->arch.emulate_ctxt.vcpu = vcpu;
		vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
		vcpu->arch.emulate_ctxt.mode =
			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
			? X86EMUL_MODE_REAL : cs_l
			? X86EMUL_MODE_PROT64 :	cs_db
			? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;

		r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);

		/* Reject the instructions other than VMCALL/VMMCALL when
		 * try to emulate invalid opcode */
		c = &vcpu->arch.emulate_ctxt.decode;
		if ((emulation_type & EMULTYPE_TRAP_UD) &&
		    (!(c->twobyte && c->b == 0x01 &&
		      (c->modrm_reg == 0 || c->modrm_reg == 3) &&
		       c->modrm_mod == 3 && c->modrm_rm == 1)))
			return EMULATE_FAIL;

		++vcpu->stat.insn_emulation;
		if (r)  {
			++vcpu->stat.insn_emulation_fail;
			if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
				return EMULATE_DONE;
			return EMULATE_FAIL;
		}
	}

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

	if (vcpu->arch.pio.string)
		return EMULATE_DO_MMIO;

	if ((r || vcpu->mmio_is_write) && run) {
		run->exit_reason = KVM_EXIT_MMIO;
		run->mmio.phys_addr = vcpu->mmio_phys_addr;
		memcpy(run->mmio.data, vcpu->mmio_data, 8);
		run->mmio.len = vcpu->mmio_size;
		run->mmio.is_write = vcpu->mmio_is_write;
	}

	if (r) {
		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
			return EMULATE_DONE;
		if (!vcpu->mmio_needed) {
			kvm_report_emulation_failure(vcpu, "mmio");
			return EMULATE_FAIL;
		}
		return EMULATE_DO_MMIO;
	}

	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);

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

	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);

static void free_pio_guest_pages(struct kvm_vcpu *vcpu)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i)
		if (vcpu->arch.pio.guest_pages[i]) {
			kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]);
			vcpu->arch.pio.guest_pages[i] = NULL;
		}
}

static int pio_copy_data(struct kvm_vcpu *vcpu)
{
	void *p = vcpu->arch.pio_data;
	void *q;
	unsigned bytes;
	int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1;

	q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
		 PAGE_KERNEL);
	if (!q) {
		free_pio_guest_pages(vcpu);
		return -ENOMEM;
	}
	q += vcpu->arch.pio.guest_page_offset;
	bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
	if (vcpu->arch.pio.in)
		memcpy(q, p, bytes);
	else
		memcpy(p, q, bytes);
	q -= vcpu->arch.pio.guest_page_offset;
	vunmap(q);
	free_pio_guest_pages(vcpu);
	return 0;
}

int complete_pio(struct kvm_vcpu *vcpu)
{
	struct kvm_pio_request *io = &vcpu->arch.pio;
	long delta;
	int r;
	unsigned long val;

	if (!io->string) {
		if (io->in) {
			val = kvm_register_read(vcpu, VCPU_REGS_RAX);
			memcpy(&val, vcpu->arch.pio_data, io->size);
			kvm_register_write(vcpu, VCPU_REGS_RAX, val);
		}
	} else {
		if (io->in) {
			r = pio_copy_data(vcpu);
			if (r)
				return r;
		}

		delta = 1;
		if (io->rep) {
			delta *= io->cur_count;
			/*
			 * The size of the register should really depend on
			 * current address size.
			 */
			val = kvm_register_read(vcpu, VCPU_REGS_RCX);
			val -= delta;
			kvm_register_write(vcpu, VCPU_REGS_RCX, val);
		}
		if (io->down)
			delta = -delta;
		delta *= io->size;
		if (io->in) {
			val = kvm_register_read(vcpu, VCPU_REGS_RDI);
			val += delta;
			kvm_register_write(vcpu, VCPU_REGS_RDI, val);
		} else {
			val = kvm_register_read(vcpu, VCPU_REGS_RSI);
			val += delta;
			kvm_register_write(vcpu, VCPU_REGS_RSI, val);
		}
	}

	io->count -= io->cur_count;
	io->cur_count = 0;

	return 0;
}

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

	mutex_lock(&vcpu->kvm->lock);
	if (vcpu->arch.pio.in)
		kvm_iodevice_read(pio_dev, vcpu->arch.pio.port,
				  vcpu->arch.pio.size,
				  pd);
	else
		kvm_iodevice_write(pio_dev, vcpu->arch.pio.port,
				   vcpu->arch.pio.size,
				   pd);
	mutex_unlock(&vcpu->kvm->lock);
}

static void pio_string_write(struct kvm_io_device *pio_dev,
			     struct kvm_vcpu *vcpu)
{
	struct kvm_pio_request *io = &vcpu->arch.pio;
	void *pd = vcpu->arch.pio_data;
	int i;

	mutex_lock(&vcpu->kvm->lock);
	for (i = 0; i < io->cur_count; i++) {
		kvm_iodevice_write(pio_dev, io->port,
				   io->size,
				   pd);
		pd += io->size;
	}
	mutex_unlock(&vcpu->kvm->lock);
}

static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
					       gpa_t addr, int len,
					       int is_write)
{
	return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr, len, is_write);
}

int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
		  int size, unsigned port)
{
	struct kvm_io_device *pio_dev;
	unsigned long val;

	vcpu->run->exit_reason = KVM_EXIT_IO;
	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
	vcpu->run->io.size = vcpu->arch.pio.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
	vcpu->run->io.port = vcpu->arch.pio.port = port;
	vcpu->arch.pio.in = in;
	vcpu->arch.pio.string = 0;
	vcpu->arch.pio.down = 0;
	vcpu->arch.pio.guest_page_offset = 0;
	vcpu->arch.pio.rep = 0;

	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
		KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
			    handler);
	else
		KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
			    handler);

	val = kvm_register_read(vcpu, VCPU_REGS_RAX);
	memcpy(vcpu->arch.pio_data, &val, 4);

	kvm_x86_ops->skip_emulated_instruction(vcpu);

	pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
	if (pio_dev) {
		kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
		complete_pio(vcpu);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_emulate_pio);

int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
		  int size, unsigned long count, int down,
		  gva_t address, int rep, unsigned port)
{
	unsigned now, in_page;
	int i, ret = 0;
	int nr_pages = 1;
	struct page *page;
	struct kvm_io_device *pio_dev;

	vcpu->run->exit_reason = KVM_EXIT_IO;
	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
	vcpu->run->io.size = vcpu->arch.pio.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
	vcpu->run->io.port = vcpu->arch.pio.port = port;
	vcpu->arch.pio.in = in;
	vcpu->arch.pio.string = 1;
	vcpu->arch.pio.down = down;
	vcpu->arch.pio.guest_page_offset = offset_in_page(address);
	vcpu->arch.pio.rep = rep;

	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
		KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
			    handler);
	else
		KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
			    handler);

	if (!count) {
		kvm_x86_ops->skip_emulated_instruction(vcpu);
		return 1;
	}

	if (!down)
		in_page = PAGE_SIZE - offset_in_page(address);
	else
		in_page = offset_in_page(address) + size;
	now = min(count, (unsigned long)in_page / size);
	if (!now) {
		/*
		 * String I/O straddles page boundary.  Pin two guest pages
		 * so that we satisfy atomicity constraints.  Do just one
		 * transaction to avoid complexity.
		 */
		nr_pages = 2;
		now = 1;
	}
	if (down) {
		/*
		 * String I/O in reverse.  Yuck.  Kill the guest, fix later.
		 */
		pr_unimpl(vcpu, "guest string pio down\n");
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
	vcpu->run->io.count = now;
	vcpu->arch.pio.cur_count = now;

	if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
		kvm_x86_ops->skip_emulated_instruction(vcpu);

	for (i = 0; i < nr_pages; ++i) {
		page = gva_to_page(vcpu, address + i * PAGE_SIZE);
		vcpu->arch.pio.guest_pages[i] = page;
		if (!page) {
			kvm_inject_gp(vcpu, 0);
			free_pio_guest_pages(vcpu);
			return 1;
		}
	}

	pio_dev = vcpu_find_pio_dev(vcpu, port,
				    vcpu->arch.pio.cur_count,
				    !vcpu->arch.pio.in);
	if (!vcpu->arch.pio.in) {
		/* string PIO write */
		ret = pio_copy_data(vcpu);
		if (ret >= 0 && pio_dev) {
			pio_string_write(pio_dev, vcpu);
			complete_pio(vcpu);
			if (vcpu->arch.pio.count == 0)
				ret = 1;
		}
	} else if (pio_dev)
		pr_unimpl(vcpu, "no string pio read support yet, "
		       "port %x size %d count %ld\n",
			port, size, count);

	return ret;
}
EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);

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);
	return 0;

out:
	return r;
}

void kvm_arch_exit(void)
{
	kvm_x86_ops = NULL;
	kvm_mmu_module_exit();
}

int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.halt_exits;
	KVMTRACE_0D(HLT, vcpu, handler);
	if (irqchip_in_kernel(vcpu->kvm)) {
		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
		up_read(&vcpu->kvm->slots_lock);
		kvm_vcpu_block(vcpu);
		down_read(&vcpu->kvm->slots_lock);
		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
			return -EINTR;
		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_emulate_hypercall(struct kvm_vcpu *vcpu)
{
	unsigned long nr, a0, a1, a2, a3, ret;
	int r = 1;

	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);

	KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler);

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

	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;
	}
	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];
	int ret = 0;
	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);
	if (emulator_write_emulated(rip, instruction, 3, vcpu)
	    != X86EMUL_CONTINUE)
		ret = -EFAULT;

	return ret;
}

static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
}

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

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

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

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

void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
		   unsigned long *rflags)
{
	kvm_lmsw(vcpu, msw);
	*rflags = kvm_x86_ops->get_rflags(vcpu);
}

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
	unsigned long value;

	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
	switch (cr) {
	case 0:
		value = vcpu->arch.cr0;
		break;
	case 2:
		value = vcpu->arch.cr2;
		break;
	case 3:
		value = vcpu->arch.cr3;
		break;
	case 4:
		value = vcpu->arch.cr4;
		break;
	case 8:
		value = kvm_get_cr8(vcpu);
		break;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
		return 0;
	}
	KVMTRACE_3D(CR_READ, vcpu, (u32)cr, (u32)value,
		    (u32)((u64)value >> 32), handler);

	return value;
}

void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
		     unsigned long *rflags)
{
	KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)val,
		    (u32)((u64)val >> 32), handler);

	switch (cr) {
	case 0:
		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
		*rflags = kvm_x86_ops->get_rflags(vcpu);
		break;
	case 2:
		vcpu->arch.cr2 = val;
		break;
	case 3:
		kvm_set_cr3(vcpu, val);
		break;
	case 4:
		kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
		break;
	case 8:
		kvm_set_cr8(vcpu, val & 0xfUL);
		break;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
	}
}

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 == i; 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;
}

void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	int i;
	u32 function, index;
	struct kvm_cpuid_entry2 *e, *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 = NULL;
	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		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;
	}
	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);
	KVMTRACE_5D(CPUID, vcpu, function,
		    (u32)kvm_register_read(vcpu, VCPU_REGS_RAX),
		    (u32)kvm_register_read(vcpu, VCPU_REGS_RBX),
		    (u32)kvm_register_read(vcpu, VCPU_REGS_RCX),
		    (u32)kvm_register_read(vcpu, VCPU_REGS_RDX), handler);
}
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,
					  struct kvm_run *kvm_run)
{
	return (!vcpu->arch.irq_summary &&
		kvm_run->request_interrupt_window &&
		vcpu->arch.interrupt_window_open &&
		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
}

static void post_kvm_run_save(struct kvm_vcpu *vcpu,
			      struct kvm_run *kvm_run)
{
	kvm_run->if_flag = (kvm_x86_ops->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 =
					(vcpu->arch.interrupt_window_open &&
					 vcpu->arch.irq_summary == 0);
}

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

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

	down_read(&current->mm->mmap_sem);
	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
	up_read(&current->mm->mmap_sem);

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

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

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

	down_read(&vcpu->kvm->slots_lock);
	kvm_release_page_dirty(apic->vapic_page);
	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
	up_read(&vcpu->kvm->slots_lock);
}

static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	int r;

	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_x86_ops->vcpu_reset(vcpu);
		if (r)
			return r;
		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
	}

	down_read(&vcpu->kvm->slots_lock);
	vapic_enter(vcpu);

preempted:
	if (vcpu->guest_debug.enabled)
		kvm_x86_ops->guest_debug_pre(vcpu);

again:
	if (vcpu->requests)
		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
			kvm_mmu_unload(vcpu);

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

	if (vcpu->requests) {
		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
			__kvm_migrate_timers(vcpu);
		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
			kvm_x86_ops->tlb_flush(vcpu);
		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
				       &vcpu->requests)) {
			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
			r = 0;
			goto out;
		}
		if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
			kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
			r = 0;
			goto out;
		}
	}

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

	preempt_disable();

	kvm_x86_ops->prepare_guest_switch(vcpu);
	kvm_load_guest_fpu(vcpu);

	local_irq_disable();

	if (vcpu->requests || need_resched()) {
		local_irq_enable();
		preempt_enable();
		r = 1;
		goto out;
	}

	if (signal_pending(current)) {
		local_irq_enable();
		preempt_enable();
		r = -EINTR;
		kvm_run->exit_reason = KVM_EXIT_INTR;
		++vcpu->stat.signal_exits;
		goto out;
	}

	vcpu->guest_mode = 1;
	/*
	 * Make sure that guest_mode assignment won't happen after
	 * testing the pending IRQ vector bitmap.
	 */
	smp_wmb();

	if (vcpu->arch.exception.pending)
		__queue_exception(vcpu);
	else if (irqchip_in_kernel(vcpu->kvm))
		kvm_x86_ops->inject_pending_irq(vcpu);
	else
		kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);

	kvm_lapic_sync_to_vapic(vcpu);

	up_read(&vcpu->kvm->slots_lock);

	kvm_guest_enter();


	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
	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();

	down_read(&vcpu->kvm->slots_lock);

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

	if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu))
		vcpu->arch.exception.pending = false;

	kvm_lapic_sync_from_vapic(vcpu);

	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:
	up_read(&vcpu->kvm->slots_lock);
	if (r > 0) {
		kvm_resched(vcpu);
		down_read(&vcpu->kvm->slots_lock);
		goto preempted;
	}

	post_kvm_run_save(vcpu, kvm_run);

	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;

	vcpu_load(vcpu);

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

	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
		kvm_vcpu_block(vcpu);
		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.cur_count) {
		r = complete_pio(vcpu);
		if (r)
			goto out;
	}
#if CONFIG_HAS_IOMEM
	if (vcpu->mmio_needed) {