x86.c

	get_cpu();
	do_cpuid_1_ent(entry, function, index);
	++*nent;

	switch (function) {
	case 0:
		entry->eax = min(entry->eax, (u32)0xd);
		break;
	case 1:
		entry->edx &= kvm_supported_word0_x86_features;
		entry->ecx &= kvm_supported_word4_x86_features;
		/* we support x2apic emulation even if host does not support
		 * it since we emulate x2apic in software */
		entry->ecx |= F(X2APIC);
		break;
	/* function 2 entries are STATEFUL. That is, repeated cpuid commands
	 * may return different values. This forces us to get_cpu() before
	 * issuing the first command, and also to emulate this annoying behavior
	 * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
	case 2: {
		int t, times = entry->eax & 0xff;

		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
		for (t = 1; t < times && *nent < maxnent; ++t) {
			do_cpuid_1_ent(&entry[t], function, 0);
			entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
			++*nent;
		}
		break;
	}
	/* function 4 and 0xb have additional index. */
	case 4: {
		int i, cache_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until cache_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			cache_type = entry[i - 1].eax & 0x1f;
			if (!cache_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 0xb: {
		int i, level_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until level_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			level_type = entry[i - 1].ecx & 0xff00;
			if (!level_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 0xd: {
		int i;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		for (i = 1; *nent < maxnent; ++i) {
			if (entry[i - 1].eax == 0 && i != 2)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case KVM_CPUID_SIGNATURE: {
		char signature[12] = "KVMKVMKVM\0\0";
		u32 *sigptr = (u32 *)signature;
		entry->eax = 0;
		entry->ebx = sigptr[0];
		entry->ecx = sigptr[1];
		entry->edx = sigptr[2];
		break;
	}
	case KVM_CPUID_FEATURES:
		entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	case 0x80000000:
		entry->eax = min(entry->eax, 0x8000001a);
		break;
	case 0x80000001:
		entry->edx &= kvm_supported_word1_x86_features;
		entry->ecx &= kvm_supported_word6_x86_features;
		break;
	}

	kvm_x86_ops->set_supported_cpuid(function, entry);

	put_cpu();
}

#undef F

static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
				     struct kvm_cpuid_entry2 __user *entries)
{
	struct kvm_cpuid_entry2 *cpuid_entries;
	int limit, nent = 0, r = -E2BIG;
	u32 func;

	if (cpuid->nent < 1)
		goto out;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
	r = -ENOMEM;
	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
	if (!cpuid_entries)
		goto out;

	do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent);
	limit = cpuid_entries[0].eax;
	for (func = 1; func <= limit && nent < cpuid->nent; ++func)
		do_cpuid_ent(&cpuid_entries[nent], func, 0,
			     &nent, cpuid->nent);
	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent);
	limit = cpuid_entries[nent - 1].eax;
	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
		do_cpuid_ent(&cpuid_entries[nent], func, 0,
			     &nent, cpuid->nent);



	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
		     cpuid->nent);

	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
		     cpuid->nent);

	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	r = -EFAULT;
	if (copy_to_user(entries, cpuid_entries,
			 nent * sizeof(struct kvm_cpuid_entry2)))
		goto out_free;
	cpuid->nent = nent;
	r = 0;

out_free:
	vfree(cpuid_entries);
out:
	return r;
}

static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);

	return 0;
}

static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
	kvm_apic_post_state_restore(vcpu);
	update_cr8_intercept(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
				    struct kvm_interrupt *irq)
{
	if (irq->irq < 0 || irq->irq >= 256)
		return -EINVAL;
	if (irqchip_in_kernel(vcpu->kvm))
		return -ENXIO;

	kvm_queue_interrupt(vcpu, irq->irq, false);

	return 0;
}

static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
{
	kvm_inject_nmi(vcpu);

	return 0;
}

static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
					   struct kvm_tpr_access_ctl *tac)
{
	if (tac->flags)
		return -EINVAL;
	vcpu->arch.tpr_access_reporting = !!tac->enabled;
	return 0;
}

static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
					u64 mcg_cap)
{
	int r;
	unsigned bank_num = mcg_cap & 0xff, bank;

	r = -EINVAL;
	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
		goto out;
	if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
		goto out;
	r = 0;
	vcpu->arch.mcg_cap = mcg_cap;
	/* Init IA32_MCG_CTL to all 1s */
	if (mcg_cap & MCG_CTL_P)
		vcpu->arch.mcg_ctl = ~(u64)0;
	/* Init IA32_MCi_CTL to all 1s */
	for (bank = 0; bank < bank_num; bank++)
		vcpu->arch.mce_banks[bank*4] = ~(u64)0;
out:
	return r;
}

static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
				      struct kvm_x86_mce *mce)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;
	u64 *banks = vcpu->arch.mce_banks;

	if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL))
		return -EINVAL;
	/*
	 * if IA32_MCG_CTL is not all 1s, the uncorrected error
	 * reporting is disabled
	 */
	if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) &&
	    vcpu->arch.mcg_ctl != ~(u64)0)
		return 0;
	banks += 4 * mce->bank;
	/*
	 * if IA32_MCi_CTL is not all 1s, the uncorrected error
	 * reporting is disabled for the bank
	 */
	if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0)
		return 0;
	if (mce->status & MCI_STATUS_UC) {
		if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
		    !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
			printk(KERN_DEBUG "kvm: set_mce: "
			       "injects mce exception while "
			       "previous one is in progress!\n");
			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
			return 0;
		}
		if (banks[1] & MCI_STATUS_VAL)
			mce->status |= MCI_STATUS_OVER;
		banks[2] = mce->addr;
		banks[3] = mce->misc;
		vcpu->arch.mcg_status = mce->mcg_status;
		banks[1] = mce->status;
		kvm_queue_exception(vcpu, MC_VECTOR);
	} else if (!(banks[1] & MCI_STATUS_VAL)
		   || !(banks[1] & MCI_STATUS_UC)) {
		if (banks[1] & MCI_STATUS_VAL)
			mce->status |= MCI_STATUS_OVER;
		banks[2] = mce->addr;
		banks[3] = mce->misc;
		banks[1] = mce->status;
	} else
		banks[1] |= MCI_STATUS_OVER;
	return 0;
}

static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
					       struct kvm_vcpu_events *events)
{
	events->exception.injected =
		vcpu->arch.exception.pending &&
		!kvm_exception_is_soft(vcpu->arch.exception.nr);
	events->exception.nr = vcpu->arch.exception.nr;
	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
	events->exception.error_code = vcpu->arch.exception.error_code;

	events->interrupt.injected =
		vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
	events->interrupt.nr = vcpu->arch.interrupt.nr;
	events->interrupt.soft = 0;
	events->interrupt.shadow =
		kvm_x86_ops->get_interrupt_shadow(vcpu,
			KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);

	events->nmi.injected = vcpu->arch.nmi_injected;
	events->nmi.pending = vcpu->arch.nmi_pending;
	events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);

	events->sipi_vector = vcpu->arch.sipi_vector;

	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR
			 | KVM_VCPUEVENT_VALID_SHADOW);
}

static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
					      struct kvm_vcpu_events *events)
{
	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
			      | KVM_VCPUEVENT_VALID_SHADOW))
		return -EINVAL;

	vcpu->arch.exception.pending = events->exception.injected;
	vcpu->arch.exception.nr = events->exception.nr;
	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
	vcpu->arch.exception.error_code = events->exception.error_code;

	vcpu->arch.interrupt.pending = events->interrupt.injected;
	vcpu->arch.interrupt.nr = events->interrupt.nr;
	vcpu->arch.interrupt.soft = events->interrupt.soft;
	if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
		kvm_pic_clear_isr_ack(vcpu->kvm);
	if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
		kvm_x86_ops->set_interrupt_shadow(vcpu,
						  events->interrupt.shadow);

	vcpu->arch.nmi_injected = events->nmi.injected;
	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
		vcpu->arch.nmi_pending = events->nmi.pending;
	kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);

	if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
		vcpu->arch.sipi_vector = events->sipi_vector;

	return 0;
}

static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
					     struct kvm_debugregs *dbgregs)
{
	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
	dbgregs->dr6 = vcpu->arch.dr6;
	dbgregs->dr7 = vcpu->arch.dr7;
	dbgregs->flags = 0;
}

static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
					    struct kvm_debugregs *dbgregs)
{
	if (dbgregs->flags)
		return -EINVAL;

	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
	vcpu->arch.dr6 = dbgregs->dr6;
	vcpu->arch.dr7 = dbgregs->dr7;

	return 0;
}

static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
					 struct kvm_xsave *guest_xsave)
{
	if (cpu_has_xsave)
		memcpy(guest_xsave->region,
			&vcpu->arch.guest_fpu.state->xsave,
			sizeof(struct xsave_struct));
	else {
		memcpy(guest_xsave->region,
			&vcpu->arch.guest_fpu.state->fxsave,
			sizeof(struct i387_fxsave_struct));
		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
			XSTATE_FPSSE;
	}
}

static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
					struct kvm_xsave *guest_xsave)
{
	u64 xstate_bv =
		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];

	if (cpu_has_xsave)
		memcpy(&vcpu->arch.guest_fpu.state->xsave,
			guest_xsave->region, sizeof(struct xsave_struct));
	else {
		if (xstate_bv & ~XSTATE_FPSSE)
			return -EINVAL;
		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
			guest_xsave->region, sizeof(struct i387_fxsave_struct));
	}
	return 0;
}

static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
					struct kvm_xcrs *guest_xcrs)
{
	if (!cpu_has_xsave) {
		guest_xcrs->nr_xcrs = 0;
		return;
	}

	guest_xcrs->nr_xcrs = 1;
	guest_xcrs->flags = 0;
	guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
	guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
}

static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
				       struct kvm_xcrs *guest_xcrs)
{
	int i, r = 0;

	if (!cpu_has_xsave)
		return -EINVAL;

	if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
		return -EINVAL;

	for (i = 0; i < guest_xcrs->nr_xcrs; i++)
		/* Only support XCR0 currently */
		if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
			r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
				guest_xcrs->xcrs[0].value);
			break;
		}
	if (r)
		r = -EINVAL;
	return r;
}

long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;
	union {
		struct kvm_lapic_state *lapic;
		struct kvm_xsave *xsave;
		struct kvm_xcrs *xcrs;
		void *buffer;
	} u;

	u.buffer = NULL;
	switch (ioctl) {
	case KVM_GET_LAPIC: {
		r = -EINVAL;
		if (!vcpu->arch.apic)
			goto out;
		u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);

		r = -ENOMEM;
		if (!u.lapic)
			goto out;
		r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state)))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_LAPIC: {
		r = -EINVAL;
		if (!vcpu->arch.apic)
			goto out;
		u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.lapic)
			goto out;
		r = -EFAULT;
		if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state)))
			goto out;
		r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_INTERRUPT: {
		struct kvm_interrupt irq;

		r = -EFAULT;
		if (copy_from_user(&irq, argp, sizeof irq))
			goto out;
		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_NMI: {
		r = kvm_vcpu_ioctl_nmi(vcpu);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_CPUID: {
		struct kvm_cpuid __user *cpuid_arg = argp;
		struct kvm_cpuid cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
			goto out;
		r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
		if (r)
			goto out;
		break;
	}
	case KVM_SET_CPUID2: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
			goto out;
		r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
					      cpuid_arg->entries);
		if (r)
			goto out;
		break;
	}
	case KVM_GET_CPUID2: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
			goto out;
		r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
					      cpuid_arg->entries);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_MSRS:
		r = msr_io(vcpu, argp, kvm_get_msr, 1);
		break;
	case KVM_SET_MSRS:
		r = msr_io(vcpu, argp, do_set_msr, 0);
		break;
	case KVM_TPR_ACCESS_REPORTING: {
		struct kvm_tpr_access_ctl tac;

		r = -EFAULT;
		if (copy_from_user(&tac, argp, sizeof tac))
			goto out;
		r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &tac, sizeof tac))
			goto out;
		r = 0;
		break;
	};
	case KVM_SET_VAPIC_ADDR: {
		struct kvm_vapic_addr va;

		r = -EINVAL;
		if (!irqchip_in_kernel(vcpu->kvm))
			goto out;
		r = -EFAULT;
		if (copy_from_user(&va, argp, sizeof va))
			goto out;
		r = 0;
		kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
		break;
	}
	case KVM_X86_SETUP_MCE: {
		u64 mcg_cap;

		r = -EFAULT;
		if (copy_from_user(&mcg_cap, argp, sizeof mcg_cap))
			goto out;
		r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap);
		break;
	}
	case KVM_X86_SET_MCE: {
		struct kvm_x86_mce mce;

		r = -EFAULT;
		if (copy_from_user(&mce, argp, sizeof mce))
			goto out;
		r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
		break;
	}
	case KVM_GET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events);

		r = -EFAULT;
		if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_VCPU_EVENTS: {
		struct kvm_vcpu_events events;

		r = -EFAULT;
		if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
			break;

		r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
		break;
	}
	case KVM_GET_DEBUGREGS: {
		struct kvm_debugregs dbgregs;

		kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);

		r = -EFAULT;
		if (copy_to_user(argp, &dbgregs,
				 sizeof(struct kvm_debugregs)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_DEBUGREGS: {
		struct kvm_debugregs dbgregs;

		r = -EFAULT;
		if (copy_from_user(&dbgregs, argp,
				   sizeof(struct kvm_debugregs)))
			break;

		r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
		break;
	}
	case KVM_GET_XSAVE: {
		u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.xsave)
			break;

		kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);

		r = -EFAULT;
		if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_XSAVE: {
		u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.xsave)
			break;

		r = -EFAULT;
		if (copy_from_user(u.xsave, argp, sizeof(struct kvm_xsave)))
			break;

		r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
		break;
	}
	case KVM_GET_XCRS: {
		u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.xcrs)
			break;

		kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);

		r = -EFAULT;
		if (copy_to_user(argp, u.xcrs,
				 sizeof(struct kvm_xcrs)))
			break;
		r = 0;
		break;
	}
	case KVM_SET_XCRS: {
		u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
		r = -ENOMEM;
		if (!u.xcrs)
			break;

		r = -EFAULT;
		if (copy_from_user(u.xcrs, argp,
				   sizeof(struct kvm_xcrs)))
			break;

		r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
		break;
	}
	default:
		r = -EINVAL;
	}
out:
	kfree(u.buffer);
	return r;
}

static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
{
	int ret;

	if (addr > (unsigned int)(-3 * PAGE_SIZE))
		return -1;
	ret = kvm_x86_ops->set_tss_addr(kvm, addr);
	return ret;
}

static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
					      u64 ident_addr)
{
	kvm->arch.ept_identity_map_addr = ident_addr;
	return 0;
}

static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
					  u32 kvm_nr_mmu_pages)
{
	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
		return -EINVAL;

	mutex_lock(&kvm->slots_lock);
	spin_lock(&kvm->mmu_lock);

	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;

	spin_unlock(&kvm->mmu_lock);
	mutex_unlock(&kvm->slots_lock);
	return 0;
}

static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
	return kvm->arch.n_alloc_mmu_pages;
}

static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		memcpy(&chip->chip.pic,
			&pic_irqchip(kvm)->pics[0],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		memcpy(&chip->chip.pic,
			&pic_irqchip(kvm)->pics[1],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_IOAPIC:
		r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
		break;
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		raw_spin_lock(&pic_irqchip(kvm)->lock);
		memcpy(&pic_irqchip(kvm)->pics[0],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		raw_spin_unlock(&pic_irqchip(kvm)->lock);
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		raw_spin_lock(&pic_irqchip(kvm)->lock);
		memcpy(&pic_irqchip(kvm)->pics[1],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		raw_spin_unlock(&pic_irqchip(kvm)->lock);
		break;
	case KVM_IRQCHIP_IOAPIC:
		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
		break;
	default:
		r = -EINVAL;
		break;
	}
	kvm_pic_update_irq(pic_irqchip(kvm));
	return r;
}

static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
	int r = 0;

	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return r;
}

static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
	int r = 0;

	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return r;
}

static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	int r = 0;

	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
		sizeof(ps->channels));
	ps->flags = kvm->arch.vpit->pit_state.flags;
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return r;
}

static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
{
	int r = 0, start = 0;
	u32 prev_legacy, cur_legacy;
	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
	cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
	if (!prev_legacy && cur_legacy)
		start = 1;
	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
	       sizeof(kvm->arch.vpit->pit_state.channels));
	kvm->arch.vpit->pit_state.flags = ps->flags;
	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return r;
}

static int kvm_vm_ioctl_reinject(struct kvm *kvm,
				 struct kvm_reinject_control *control)
{
	if (!kvm->arch.vpit)
		return -ENXIO;
	mutex_lock(&kvm->arch.vpit->pit_state.lock);
	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
	return 0;
}

/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				      struct kvm_dirty_log *log)
{
	int r, i;
	struct kvm_memory_slot *memslot;
	unsigned long n;
	unsigned long is_dirty = 0;

	mutex_lock(&kvm->slots_lock);

	r = -EINVAL;
	if (log->slot >= KVM_MEMORY_SLOTS)
		goto out;

	memslot = &kvm->memslots->memslots[log->slot];
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	n = kvm_dirty_bitmap_bytes(memslot);

	for (i = 0; !is_dirty && i < n/sizeof(long); i++)
		is_dirty = memslot->dirty_bitmap[i];

	/* If nothing is dirty, don't bother messing with page tables. */
	if (is_dirty) {
		struct kvm_memslots *slots, *old_slots;
		unsigned long *dirty_bitmap;

		spin_lock(&kvm->mmu_lock);
		kvm_mmu_slot_remove_write_access(kvm, log->slot);
		spin_unlock(&kvm->mmu_lock);

		r = -ENOMEM;
		dirty_bitmap = vmalloc(n);
		if (!dirty_bitmap)
			goto out;
		memset(dirty_bitmap, 0, n);

		r = -ENOMEM;
		slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
		if (!slots) {
			vfree(dirty_bitmap);
			goto out;
		}
		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
		slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;

		old_slots = kvm->memslots;
		rcu_assign_pointer(kvm->memslots, slots);
		synchronize_srcu_expedited(&kvm->srcu);
		dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap;
		kfree(old_slots);

		r = -EFAULT;
		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) {
			vfree(dirty_bitmap);
			goto out;
		}
		vfree(dirty_bitmap);
	} else {
		r = -EFAULT;
		if (clear_user(log->dirty_bitmap, n))
			goto out;
	}

	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
}

long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r = -ENOTTY;
	/*
	 * This union makes it completely explicit to gcc-3.x
	 * that these two variables' stack usage should be
	 * combined, not added together.
	 */
	union {
		struct kvm_pit_state ps;
		struct kvm_pit_state2 ps2;
		struct kvm_pit_config pit_config;
	} u;

	switch (ioctl) {
	case KVM_SET_TSS_ADDR:
		r = kvm_vm_ioctl_set_tss_addr(kvm, arg);
		if (r < 0)
			goto out;
		break;
	case KVM_SET_IDENTITY_MAP_ADDR: {
		u64 ident_addr;

		r = -EFAULT;
		if (copy_from_user(&ident_addr, argp, sizeof ident_addr))
			goto out;
		r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr);
		if (r < 0)
			goto out;
		break;
	}
	case KVM_SET_NR_MMU_PAGES:
		r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
		if (r)
			goto out;
		break;
	case KVM_GET_NR_MMU_PAGES:
		r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
		break;
	case KVM_CREATE_IRQCHIP: {
		struct kvm_pic *vpic;