x86.c

			mutex_lock(&kvm->lock);
			if (irq_event.irq < 16)
				kvm_pic_set_irq(pic_irqchip(kvm),
					irq_event.irq,
					irq_event.level);
			kvm_ioapic_set_irq(kvm->vioapic,
					irq_event.irq,
					irq_event.level);
			mutex_unlock(&kvm->lock);
			r = 0;
		}
		break;
	}
	case KVM_GET_IRQCHIP: {
		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
		struct kvm_irqchip chip;

		r = -EFAULT;
		if (copy_from_user(&chip, argp, sizeof chip))
			goto out;
		r = -ENXIO;
		if (!irqchip_in_kernel(kvm))
			goto out;
		r = kvm_vm_ioctl_get_irqchip(kvm, &chip);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &chip, sizeof chip))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_IRQCHIP: {
		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
		struct kvm_irqchip chip;

		r = -EFAULT;
		if (copy_from_user(&chip, argp, sizeof chip))
			goto out;
		r = -ENXIO;
		if (!irqchip_in_kernel(kvm))
			goto out;
		r = kvm_vm_ioctl_set_irqchip(kvm, &chip);
		if (r)
			goto out;
		r = 0;
		break;
	}
	default:
		;
	}
out:
	return r;
}

static void kvm_init_msr_list(void)
{
	u32 dummy[2];
	unsigned i, j;

	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
			continue;
		if (j < i)
			msrs_to_save[j] = msrs_to_save[i];
		j++;
	}
	num_msrs_to_save = j;
}

/*
 * Only apic need an MMIO device hook, so shortcut now..
 */
static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
						gpa_t addr)
{
	struct kvm_io_device *dev;

	if (vcpu->apic) {
		dev = &vcpu->apic->dev;
		if (dev->in_range(dev, addr))
			return dev;
	}
	return NULL;
}


static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
						gpa_t addr)
{
	struct kvm_io_device *dev;

	dev = vcpu_find_pervcpu_dev(vcpu, addr);
	if (dev == NULL)
		dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
	return dev;
}

int emulator_read_std(unsigned long addr,
			     void *val,
			     unsigned int bytes,
			     struct kvm_vcpu *vcpu)
{
	void *data = val;

	while (bytes) {
		gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
		unsigned offset = addr & (PAGE_SIZE-1);
		unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
		int ret;

		if (gpa == UNMAPPED_GVA)
			return X86EMUL_PROPAGATE_FAULT;
		ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy);
		if (ret < 0)
			return X86EMUL_UNHANDLEABLE;

		bytes -= tocopy;
		data += tocopy;
		addr += tocopy;
	}

	return X86EMUL_CONTINUE;
}
EXPORT_SYMBOL_GPL(emulator_read_std);

static int emulator_write_std(unsigned long addr,
			      const void *val,
			      unsigned int bytes,
			      struct kvm_vcpu *vcpu)
{
	pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes);
	return X86EMUL_UNHANDLEABLE;
}

static int emulator_read_emulated(unsigned long addr,
				  void *val,
				  unsigned int bytes,
				  struct kvm_vcpu *vcpu)
{
	struct kvm_io_device *mmio_dev;
	gpa_t                 gpa;

	if (vcpu->mmio_read_completed) {
		memcpy(val, vcpu->mmio_data, bytes);
		vcpu->mmio_read_completed = 0;
		return X86EMUL_CONTINUE;
	}

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

	/* For APIC access vmexit */
	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
		goto mmio;

	if (emulator_read_std(addr, val, bytes, vcpu)
			== X86EMUL_CONTINUE)
		return X86EMUL_CONTINUE;
	if (gpa == UNMAPPED_GVA)
		return X86EMUL_PROPAGATE_FAULT;

mmio:
	/*
	 * Is this MMIO handled locally?
	 */
	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
	if (mmio_dev) {
		kvm_iodevice_read(mmio_dev, gpa, bytes, val);
		return X86EMUL_CONTINUE;
	}

	vcpu->mmio_needed = 1;
	vcpu->mmio_phys_addr = gpa;
	vcpu->mmio_size = bytes;
	vcpu->mmio_is_write = 0;

	return X86EMUL_UNHANDLEABLE;
}

static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
			       const void *val, int bytes)
{
	int ret;

	ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
	if (ret < 0)
		return 0;
	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
	return 1;
}

static int emulator_write_emulated_onepage(unsigned long addr,
					   const void *val,
					   unsigned int bytes,
					   struct kvm_vcpu *vcpu)
{
	struct kvm_io_device *mmio_dev;
	gpa_t                 gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);

	if (gpa == UNMAPPED_GVA) {
		kvm_x86_ops->inject_page_fault(vcpu, addr, 2);
		return X86EMUL_PROPAGATE_FAULT;
	}

	/* For APIC access vmexit */
	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
		goto mmio;

	if (emulator_write_phys(vcpu, gpa, val, bytes))
		return X86EMUL_CONTINUE;

mmio:
	/*
	 * Is this MMIO handled locally?
	 */
	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
	if (mmio_dev) {
		kvm_iodevice_write(mmio_dev, gpa, bytes, val);
		return X86EMUL_CONTINUE;
	}

	vcpu->mmio_needed = 1;
	vcpu->mmio_phys_addr = gpa;
	vcpu->mmio_size = bytes;
	vcpu->mmio_is_write = 1;
	memcpy(vcpu->mmio_data, val, bytes);

	return X86EMUL_CONTINUE;
}

int emulator_write_emulated(unsigned long addr,
				   const void *val,
				   unsigned int bytes,
				   struct kvm_vcpu *vcpu)
{
	/* Crossing a page boundary? */
	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
		int rc, now;

		now = -addr & ~PAGE_MASK;
		rc = emulator_write_emulated_onepage(addr, val, now, vcpu);
		if (rc != X86EMUL_CONTINUE)
			return rc;
		addr += now;
		val += now;
		bytes -= now;
	}
	return emulator_write_emulated_onepage(addr, val, bytes, vcpu);
}
EXPORT_SYMBOL_GPL(emulator_write_emulated);

static int emulator_cmpxchg_emulated(unsigned long addr,
				     const void *old,
				     const void *new,
				     unsigned int bytes,
				     struct kvm_vcpu *vcpu)
{
	static int reported;

	if (!reported) {
		reported = 1;
		printk(KERN_WARNING "kvm: emulating exchange as write\n");
	}
	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)
{
	kvm_x86_ops->set_cr0(vcpu, vcpu->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", __FUNCTION__, 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)
{
	static int reported;
	u8 opcodes[4];
	unsigned long rip = vcpu->rip;
	unsigned long rip_linear;

	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);

	if (reported)
		return;

	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]);
	reported = 1;
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);

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

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

	vcpu->mmio_fault_cr2 = cr2;
	kvm_x86_ops->cache_regs(vcpu);

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

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

		vcpu->emulate_ctxt.vcpu = vcpu;
		vcpu->emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
		vcpu->emulate_ctxt.cr2 = cr2;
		vcpu->emulate_ctxt.mode =
			(vcpu->emulate_ctxt.eflags & X86_EFLAGS_VM)
			? X86EMUL_MODE_REAL : cs_l
			? X86EMUL_MODE_PROT64 :	cs_db
			? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;

		if (vcpu->emulate_ctxt.mode == X86EMUL_MODE_PROT64) {
			vcpu->emulate_ctxt.cs_base = 0;
			vcpu->emulate_ctxt.ds_base = 0;
			vcpu->emulate_ctxt.es_base = 0;
			vcpu->emulate_ctxt.ss_base = 0;
		} else {
			vcpu->emulate_ctxt.cs_base =
					get_segment_base(vcpu, VCPU_SREG_CS);
			vcpu->emulate_ctxt.ds_base =
					get_segment_base(vcpu, VCPU_SREG_DS);
			vcpu->emulate_ctxt.es_base =
					get_segment_base(vcpu, VCPU_SREG_ES);
			vcpu->emulate_ctxt.ss_base =
					get_segment_base(vcpu, VCPU_SREG_SS);
		}

		vcpu->emulate_ctxt.gs_base =
					get_segment_base(vcpu, VCPU_SREG_GS);
		vcpu->emulate_ctxt.fs_base =
					get_segment_base(vcpu, VCPU_SREG_FS);

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

	if (vcpu->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->decache_regs(vcpu);
	kvm_x86_ops->set_rflags(vcpu, vcpu->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->pio.guest_pages); ++i)
		if (vcpu->pio.guest_pages[i]) {
			kvm_release_page(vcpu->pio.guest_pages[i]);
			vcpu->pio.guest_pages[i] = NULL;
		}
}

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

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

	kvm_x86_ops->cache_regs(vcpu);

	if (!io->string) {
		if (io->in)
			memcpy(&vcpu->regs[VCPU_REGS_RAX], vcpu->pio_data,
			       io->size);
	} else {
		if (io->in) {
			r = pio_copy_data(vcpu);
			if (r) {
				kvm_x86_ops->cache_regs(vcpu);
				return r;
			}
		}

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

	kvm_x86_ops->decache_regs(vcpu);

	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->pio.in)
		kvm_iodevice_read(pio_dev, vcpu->pio.port,
				  vcpu->pio.size,
				  pd);
	else
		kvm_iodevice_write(pio_dev, vcpu->pio.port,
				   vcpu->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->pio;
	void *pd = vcpu->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)
{
	return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr);
}

int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
		  int size, unsigned port)
{
	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->pio.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = 1;
	vcpu->run->io.port = vcpu->pio.port = port;
	vcpu->pio.in = in;
	vcpu->pio.string = 0;
	vcpu->pio.down = 0;
	vcpu->pio.guest_page_offset = 0;
	vcpu->pio.rep = 0;

	kvm_x86_ops->cache_regs(vcpu);
	memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
	kvm_x86_ops->decache_regs(vcpu);

	kvm_x86_ops->skip_emulated_instruction(vcpu);

	pio_dev = vcpu_find_pio_dev(vcpu, port);
	if (pio_dev) {
		kernel_pio(pio_dev, vcpu, vcpu->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->pio.size = size;
	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
	vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = count;
	vcpu->run->io.port = vcpu->pio.port = port;
	vcpu->pio.in = in;
	vcpu->pio.string = 1;
	vcpu->pio.down = down;
	vcpu->pio.guest_page_offset = offset_in_page(address);
	vcpu->pio.rep = rep;

	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");
		inject_gp(vcpu);
		return 1;
	}
	vcpu->run->io.count = now;
	vcpu->pio.cur_count = now;

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

	for (i = 0; i < nr_pages; ++i) {
		mutex_lock(&vcpu->kvm->lock);
		page = gva_to_page(vcpu, address + i * PAGE_SIZE);
		vcpu->pio.guest_pages[i] = page;
		mutex_unlock(&vcpu->kvm->lock);
		if (!page) {
			inject_gp(vcpu);
			free_pio_guest_pages(vcpu);
			return 1;
		}
	}

	pio_dev = vcpu_find_pio_dev(vcpu, port);
	if (!vcpu->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->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)
{
	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;

	kvm_init_msr_list();

	if (kvm_x86_ops) {
		printk(KERN_ERR "kvm: already loaded the other module\n");
		return -EEXIST;
	}

	if (!ops->cpu_has_kvm_support()) {
		printk(KERN_ERR "kvm: no hardware support\n");
		return -EOPNOTSUPP;
	}
	if (ops->disabled_by_bios()) {
		printk(KERN_ERR "kvm: disabled by bios\n");
		return -EOPNOTSUPP;
	}

	kvm_x86_ops = ops;

	return 0;
}

void kvm_arch_exit(void)
{
	kvm_x86_ops = NULL;
 }

int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.halt_exits;
	if (irqchip_in_kernel(vcpu->kvm)) {
		vcpu->mp_state = VCPU_MP_STATE_HALTED;
		kvm_vcpu_block(vcpu);
		if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE)
			return -EINTR;
		return 1;
	} else {
		vcpu->run->exit_reason = KVM_EXIT_HLT;
		return 0;
	}
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);

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

	kvm_x86_ops->cache_regs(vcpu);

	nr = vcpu->regs[VCPU_REGS_RAX];
	a0 = vcpu->regs[VCPU_REGS_RBX];
	a1 = vcpu->regs[VCPU_REGS_RCX];
	a2 = vcpu->regs[VCPU_REGS_RDX];
	a3 = vcpu->regs[VCPU_REGS_RSI];

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

	switch (nr) {
	default:
		ret = -KVM_ENOSYS;
		break;
	}
	vcpu->regs[VCPU_REGS_RAX] = ret;
	kvm_x86_ops->decache_regs(vcpu);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);

int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
{
	char instruction[3];
	int ret = 0;

	mutex_lock(&vcpu->kvm->lock);

	/*
	 * 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->cache_regs(vcpu);
	kvm_x86_ops->patch_hypercall(vcpu, instruction);
	if (emulator_write_emulated(vcpu->rip, instruction, 3, vcpu)
	    != X86EMUL_CONTINUE)
		ret = -EFAULT;

	mutex_unlock(&vcpu->kvm->lock);

	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)
{
	lmsw(vcpu, msw);
	*rflags = kvm_x86_ops->get_rflags(vcpu);
}

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
	switch (cr) {
	case 0:
		return vcpu->cr0;
	case 2:
		return vcpu->cr2;
	case 3:
		return vcpu->cr3;
	case 4:
		return vcpu->cr4;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
		return 0;
	}
}

void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
		     unsigned long *rflags)
{
	switch (cr) {
	case 0:
		set_cr0(vcpu, mk_cr_64(vcpu->cr0, val));
		*rflags = kvm_x86_ops->get_rflags(vcpu);
		break;
	case 2:
		vcpu->cr2 = val;
		break;
	case 3:
		set_cr3(vcpu, val);
		break;
	case 4:
		set_cr4(vcpu, mk_cr_64(vcpu->cr4, val));
		break;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
	}
}

void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	int i;
	u32 function;
	struct kvm_cpuid_entry *e, *best;

	kvm_x86_ops->cache_regs(vcpu);
	function = vcpu->regs[VCPU_REGS_RAX];
	vcpu->regs[VCPU_REGS_RAX] = 0;
	vcpu->regs[VCPU_REGS_RBX] = 0;
	vcpu->regs[VCPU_REGS_RCX] = 0;
	vcpu->regs[VCPU_REGS_RDX] = 0;
	best = NULL;
	for (i = 0; i < vcpu->cpuid_nent; ++i) {
		e = &vcpu->cpuid_entries[i];
		if (e->function == function) {
			best = e;
			break;
		}
		/*
		 * Both basic or both extended?
		 */
		if (((e->function ^ function) & 0x80000000) == 0)
			if (!best || e->function > best->function)
				best = e;
	}
	if (best) {
		vcpu->regs[VCPU_REGS_RAX] = best->eax;
		vcpu->regs[VCPU_REGS_RBX] = best->ebx;
		vcpu->regs[VCPU_REGS_RCX] = best->ecx;
		vcpu->regs[VCPU_REGS_RDX] = best->edx;
	}
	kvm_x86_ops->decache_regs(vcpu);
	kvm_x86_ops->skip_emulated_instruction(vcpu);
}
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->irq_summary &&
		kvm_run->request_interrupt_window &&
		vcpu->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 = 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->interrupt_window_open &&
					 vcpu->irq_summary == 0);
}

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

	if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
		pr_debug("vcpu %d received sipi with vector # %x\n",
		       vcpu->vcpu_id, vcpu->sipi_vector);
		kvm_lapic_reset(vcpu);
		r = kvm_x86_ops->vcpu_reset(vcpu);
		if (r)
			return r;
		vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
	}

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

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

	kvm_inject_pending_timer_irqs(vcpu);

	preempt_disable();

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

	local_irq_disable();

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

	if (irqchip_in_kernel(vcpu->kvm))
		kvm_x86_ops->inject_pending_irq(vcpu);
	else if (!vcpu->mmio_read_completed)
		kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);

	vcpu->guest_mode = 1;
	kvm_guest_enter();

	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;
	}