x86.c

void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u64 offset, ns, elapsed;
	unsigned long flags;
	s64 sdiff;

	spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
	offset = data - native_read_tsc();
	ns = get_kernel_ns();
	elapsed = ns - kvm->arch.last_tsc_nsec;
	sdiff = data - kvm->arch.last_tsc_write;
	if (sdiff < 0)
		sdiff = -sdiff;

	/*
	 * Special case: close write to TSC within 5 seconds of
	 * another CPU is interpreted as an attempt to synchronize
	 * The 5 seconds is to accomodate host load / swapping as
	 * well as any reset of TSC during the boot process.
	 *
	 * In that case, for a reliable TSC, we can match TSC offsets,
	 * or make a best guest using elapsed value.
	 */
	if (sdiff < nsec_to_cycles(5ULL * NSEC_PER_SEC) &&
	    elapsed < 5ULL * NSEC_PER_SEC) {
		if (!check_tsc_unstable()) {
			offset = kvm->arch.last_tsc_offset;
			pr_debug("kvm: matched tsc offset for %llu\n", data);
		} else {
			u64 delta = nsec_to_cycles(elapsed);
			offset += delta;
			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
		}
		ns = kvm->arch.last_tsc_nsec;
	}
	kvm->arch.last_tsc_nsec = ns;
	kvm->arch.last_tsc_write = data;
	kvm->arch.last_tsc_offset = offset;
	kvm_x86_ops->write_tsc_offset(vcpu, offset);
	spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);

	/* Reset of TSC must disable overshoot protection below */
	vcpu->arch.hv_clock.tsc_timestamp = 0;
	vcpu->arch.last_tsc_write = data;
	vcpu->arch.last_tsc_nsec = ns;
}
EXPORT_SYMBOL_GPL(kvm_write_tsc);

static int kvm_guest_time_update(struct kvm_vcpu *v)
{
	unsigned long flags;
	struct kvm_vcpu_arch *vcpu = &v->arch;
	void *shared_kaddr;
	unsigned long this_tsc_khz;
	s64 kernel_ns, max_kernel_ns;
	u64 tsc_timestamp;

	/* Keep irq disabled to prevent changes to the clock */
	local_irq_save(flags);
	kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
	kernel_ns = get_kernel_ns();
	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);

	if (unlikely(this_tsc_khz == 0)) {
		local_irq_restore(flags);
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
		return 1;
	}

	/*
	 * We may have to catch up the TSC to match elapsed wall clock
	 * time for two reasons, even if kvmclock is used.
	 *   1) CPU could have been running below the maximum TSC rate
	 *   2) Broken TSC compensation resets the base at each VCPU
	 *      entry to avoid unknown leaps of TSC even when running
	 *      again on the same CPU.  This may cause apparent elapsed
	 *      time to disappear, and the guest to stand still or run
	 *	very slowly.
	 */
	if (vcpu->tsc_catchup) {
		u64 tsc = compute_guest_tsc(v, kernel_ns);
		if (tsc > tsc_timestamp) {
			kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp);
			tsc_timestamp = tsc;
		}
	}

	local_irq_restore(flags);

	if (!vcpu->time_page)
		return 0;

	/*
	 * Time as measured by the TSC may go backwards when resetting the base
	 * tsc_timestamp.  The reason for this is that the TSC resolution is
	 * higher than the resolution of the other clock scales.  Thus, many
	 * possible measurments of the TSC correspond to one measurement of any
	 * other clock, and so a spread of values is possible.  This is not a
	 * problem for the computation of the nanosecond clock; with TSC rates
	 * around 1GHZ, there can only be a few cycles which correspond to one
	 * nanosecond value, and any path through this code will inevitably
	 * take longer than that.  However, with the kernel_ns value itself,
	 * the precision may be much lower, down to HZ granularity.  If the
	 * first sampling of TSC against kernel_ns ends in the low part of the
	 * range, and the second in the high end of the range, we can get:
	 *
	 * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
	 *
	 * As the sampling errors potentially range in the thousands of cycles,
	 * it is possible such a time value has already been observed by the
	 * guest.  To protect against this, we must compute the system time as
	 * observed by the guest and ensure the new system time is greater.
	 */
	max_kernel_ns = 0;
	if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
		max_kernel_ns = vcpu->last_guest_tsc -
				vcpu->hv_clock.tsc_timestamp;
		max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
				    vcpu->hv_clock.tsc_to_system_mul,
				    vcpu->hv_clock.tsc_shift);
		max_kernel_ns += vcpu->last_kernel_ns;
	}

	if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
				   &vcpu->hv_clock.tsc_shift,
				   &vcpu->hv_clock.tsc_to_system_mul);
		vcpu->hw_tsc_khz = this_tsc_khz;
	}

	if (max_kernel_ns > kernel_ns)
		kernel_ns = max_kernel_ns;

	/* With all the info we got, fill in the values */
	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	vcpu->last_kernel_ns = kernel_ns;
	vcpu->last_guest_tsc = tsc_timestamp;
	vcpu->hv_clock.flags = 0;

	/*
	 * The interface expects us to write an even number signaling that the
	 * update is finished. Since the guest won't see the intermediate
	 * state, we just increase by 2 at the end.
	 */
	vcpu->hv_clock.version += 2;

	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);

	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
	       sizeof(vcpu->hv_clock));

	kunmap_atomic(shared_kaddr, KM_USER0);

	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
	return 0;
}

static bool msr_mtrr_valid(unsigned msr)
{
	switch (msr) {
	case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
	case MSR_MTRRfix64K_00000:
	case MSR_MTRRfix16K_80000:
	case MSR_MTRRfix16K_A0000:
	case MSR_MTRRfix4K_C0000:
	case MSR_MTRRfix4K_C8000:
	case MSR_MTRRfix4K_D0000:
	case MSR_MTRRfix4K_D8000:
	case MSR_MTRRfix4K_E0000:
	case MSR_MTRRfix4K_E8000:
	case MSR_MTRRfix4K_F0000:
	case MSR_MTRRfix4K_F8000:
	case MSR_MTRRdefType:
	case MSR_IA32_CR_PAT:
		return true;
	case 0x2f8:
		return true;
	}
	return false;
}

static bool valid_pat_type(unsigned t)
{
	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
}

static bool valid_mtrr_type(unsigned t)
{
	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
}

static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	int i;

	if (!msr_mtrr_valid(msr))
		return false;

	if (msr == MSR_IA32_CR_PAT) {
		for (i = 0; i < 8; i++)
			if (!valid_pat_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	} else if (msr == MSR_MTRRdefType) {
		if (data & ~0xcff)
			return false;
		return valid_mtrr_type(data & 0xff);
	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
		for (i = 0; i < 8 ; i++)
			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	}

	/* variable MTRRs */
	return valid_mtrr_type(data & 0xff);
}

static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

	if (!mtrr_valid(vcpu, msr, data))
		return 1;

	if (msr == MSR_MTRRdefType) {
		vcpu->arch.mtrr_state.def_type = data;
		vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
	} else if (msr == MSR_MTRRfix64K_00000)
		p[0] = data;
	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
		p[1 + msr - MSR_MTRRfix16K_80000] = data;
	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
		p[3 + msr - MSR_MTRRfix4K_C0000] = data;
	else if (msr == MSR_IA32_CR_PAT)
		vcpu->arch.pat = data;
	else {	/* Variable MTRRs */
		int idx, is_mtrr_mask;
		u64 *pt;

		idx = (msr - 0x200) / 2;
		is_mtrr_mask = msr - 0x200 - 2 * idx;
		if (!is_mtrr_mask)
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
		else
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
		*pt = data;
	}

	kvm_mmu_reset_context(vcpu);
	return 0;
}

static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;

	switch (msr) {
	case MSR_IA32_MCG_STATUS:
		vcpu->arch.mcg_status = data;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P))
			return 1;
		if (data != 0 && data != ~(u64)0)
			return -1;
		vcpu->arch.mcg_ctl = data;
		break;
	default:
		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
			u32 offset = msr - MSR_IA32_MC0_CTL;
			/* only 0 or all 1s can be written to IA32_MCi_CTL
			 * some Linux kernels though clear bit 10 in bank 4 to
			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
			 * this to avoid an uncatched #GP in the guest
			 */
			if ((offset & 0x3) == 0 &&
			    data != 0 && (data | (1 << 10)) != ~(u64)0)
				return -1;
			vcpu->arch.mce_banks[offset] = data;
			break;
		}
		return 1;
	}
	return 0;
}

static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	int lm = is_long_mode(vcpu);
	u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
		: (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
	u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
		: kvm->arch.xen_hvm_config.blob_size_32;
	u32 page_num = data & ~PAGE_MASK;
	u64 page_addr = data & PAGE_MASK;
	u8 *page;
	int r;

	r = -E2BIG;
	if (page_num >= blob_size)
		goto out;
	r = -ENOMEM;
	page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (!page)
		goto out;
	r = -EFAULT;
	if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
		goto out_free;
	if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
		goto out_free;
	r = 0;
out_free:
	kfree(page);
out:
	return r;
}

static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
}

static bool kvm_hv_msr_partition_wide(u32 msr)
{
	bool r = false;
	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
	case HV_X64_MSR_HYPERCALL:
		r = true;
		break;
	}

	return r;
}

static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	struct kvm *kvm = vcpu->kvm;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		kvm->arch.hv_guest_os_id = data;
		/* setting guest os id to zero disables hypercall page */
		if (!kvm->arch.hv_guest_os_id)
			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
		break;
	case HV_X64_MSR_HYPERCALL: {
		u64 gfn;
		unsigned long addr;
		u8 instructions[4];

		/* if guest os id is not set hypercall should remain disabled */
		if (!kvm->arch.hv_guest_os_id)
			break;
		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
			kvm->arch.hv_hypercall = data;
			break;
		}
		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
		addr = gfn_to_hva(kvm, gfn);
		if (kvm_is_error_hva(addr))
			return 1;
		kvm_x86_ops->patch_hypercall(vcpu, instructions);
		((unsigned char *)instructions)[3] = 0xc3; /* ret */
		if (copy_to_user((void __user *)addr, instructions, 4))
			return 1;
		kvm->arch.hv_hypercall = data;
		break;
	}
	default:
		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
			  "data 0x%llx\n", msr, data);
		return 1;
	}
	return 0;
}

static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	switch (msr) {
	case HV_X64_MSR_APIC_ASSIST_PAGE: {
		unsigned long addr;

		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
			vcpu->arch.hv_vapic = data;
			break;
		}
		addr = gfn_to_hva(vcpu->kvm, data >>
				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
		if (kvm_is_error_hva(addr))
			return 1;
		if (clear_user((void __user *)addr, PAGE_SIZE))
			return 1;
		vcpu->arch.hv_vapic = data;
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
	default:
		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
			  "data 0x%llx\n", msr, data);
		return 1;
	}

	return 0;
}

int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	switch (msr) {
	case MSR_EFER:
		return set_efer(vcpu, data);
	case MSR_K7_HWCR:
		data &= ~(u64)0x40;	/* ignore flush filter disable */
		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
		if (data != 0) {
			pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
				data);
			return 1;
		}
		break;
	case MSR_FAM10H_MMIO_CONF_BASE:
		if (data != 0) {
			pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: "
				"0x%llx\n", data);
			return 1;
		}
		break;
	case MSR_AMD64_NB_CFG:
		break;
	case MSR_IA32_DEBUGCTLMSR:
		if (!data) {
			/* We support the non-activated case already */
			break;
		} else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) {
			/* Values other than LBR and BTF are vendor-specific,
			   thus reserved and should throw a #GP */
			return 1;
		}
		pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
			__func__, data);
		break;
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_UCODE_WRITE:
	case MSR_VM_HSAVE_PA:
	case MSR_AMD64_PATCH_LOADER:
		break;
	case 0x200 ... 0x2ff:
		return set_msr_mtrr(vcpu, msr, data);
	case MSR_IA32_APICBASE:
		kvm_set_apic_base(vcpu, data);
		break;
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
		return kvm_x2apic_msr_write(vcpu, msr, data);
	case MSR_IA32_MISC_ENABLE:
		vcpu->arch.ia32_misc_enable_msr = data;
		break;
	case MSR_KVM_WALL_CLOCK_NEW:
	case MSR_KVM_WALL_CLOCK:
		vcpu->kvm->arch.wall_clock = data;
		kvm_write_wall_clock(vcpu->kvm, data);
		break;
	case MSR_KVM_SYSTEM_TIME_NEW:
	case MSR_KVM_SYSTEM_TIME: {
		if (vcpu->arch.time_page) {
			kvm_release_page_dirty(vcpu->arch.time_page);
			vcpu->arch.time_page = NULL;
		}

		vcpu->arch.time = data;
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

		/* we verify if the enable bit is set... */
		if (!(data & 1))
			break;

		/* ...but clean it before doing the actual write */
		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);

		vcpu->arch.time_page =
				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);

		if (is_error_page(vcpu->arch.time_page)) {
			kvm_release_page_clean(vcpu->arch.time_page);
			vcpu->arch.time_page = NULL;
		}
		break;
	}
	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
		return set_msr_mce(vcpu, msr, data);

	/* Performance counters are not protected by a CPUID bit,
	 * so we should check all of them in the generic path for the sake of
	 * cross vendor migration.
	 * Writing a zero into the event select MSRs disables them,
	 * which we perfectly emulate ;-). Any other value should be at least
	 * reported, some guests depend on them.
	 */
	case MSR_P6_EVNTSEL0:
	case MSR_P6_EVNTSEL1:
	case MSR_K7_EVNTSEL0:
	case MSR_K7_EVNTSEL1:
	case MSR_K7_EVNTSEL2:
	case MSR_K7_EVNTSEL3:
		if (data != 0)
			pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
				"0x%x data 0x%llx\n", msr, data);
		break;
	/* at least RHEL 4 unconditionally writes to the perfctr registers,
	 * so we ignore writes to make it happy.
	 */
	case MSR_P6_PERFCTR0:
	case MSR_P6_PERFCTR1:
	case MSR_K7_PERFCTR0:
	case MSR_K7_PERFCTR1:
	case MSR_K7_PERFCTR2:
	case MSR_K7_PERFCTR3:
		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
			"0x%x data 0x%llx\n", msr, data);
		break;
	case MSR_K7_CLK_CTL:
		/*
		 * Ignore all writes to this no longer documented MSR.
		 * Writes are only relevant for old K7 processors,
		 * all pre-dating SVM, but a recommended workaround from
		 * AMD for these chips. It is possible to speicify the
		 * affected processor models on the command line, hence
		 * the need to ignore the workaround.
		 */
		break;
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
		if (kvm_hv_msr_partition_wide(msr)) {
			int r;
			mutex_lock(&vcpu->kvm->lock);
			r = set_msr_hyperv_pw(vcpu, msr, data);
			mutex_unlock(&vcpu->kvm->lock);
			return r;
		} else
			return set_msr_hyperv(vcpu, msr, data);
		break;
	default:
		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
			return xen_hvm_config(vcpu, data);
		if (!ignore_msrs) {
			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
				msr, data);
			return 1;
		} else {
			pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
				msr, data);
			break;
		}
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);


/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
}

static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

	if (!msr_mtrr_valid(msr))
		return 1;

	if (msr == MSR_MTRRdefType)
		*pdata = vcpu->arch.mtrr_state.def_type +
			 (vcpu->arch.mtrr_state.enabled << 10);
	else if (msr == MSR_MTRRfix64K_00000)
		*pdata = p[0];
	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
		*pdata = p[1 + msr - MSR_MTRRfix16K_80000];
	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
		*pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
	else if (msr == MSR_IA32_CR_PAT)
		*pdata = vcpu->arch.pat;
	else {	/* Variable MTRRs */
		int idx, is_mtrr_mask;
		u64 *pt;

		idx = (msr - 0x200) / 2;
		is_mtrr_mask = msr - 0x200 - 2 * idx;
		if (!is_mtrr_mask)
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
		else
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
		*pdata = *pt;
	}

	return 0;
}

static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data;
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;

	switch (msr) {
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
		data = 0;
		break;
	case MSR_IA32_MCG_CAP:
		data = vcpu->arch.mcg_cap;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P))
			return 1;
		data = vcpu->arch.mcg_ctl;
		break;
	case MSR_IA32_MCG_STATUS:
		data = vcpu->arch.mcg_status;
		break;
	default:
		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
			u32 offset = msr - MSR_IA32_MC0_CTL;
			data = vcpu->arch.mce_banks[offset];
			break;
		}
		return 1;
	}
	*pdata = data;
	return 0;
}

static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;
	struct kvm *kvm = vcpu->kvm;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		data = kvm->arch.hv_guest_os_id;
		break;
	case HV_X64_MSR_HYPERCALL:
		data = kvm->arch.hv_hypercall;
		break;
	default:
		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}

	*pdata = data;
	return 0;
}

static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;

	switch (msr) {
	case HV_X64_MSR_VP_INDEX: {
		int r;
		struct kvm_vcpu *v;
		kvm_for_each_vcpu(r, v, vcpu->kvm)
			if (v == vcpu)
				data = r;
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
	default:
		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}
	*pdata = data;
	return 0;
}

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data;

	switch (msr) {
	case MSR_IA32_PLATFORM_ID:
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_EBL_CR_POWERON:
	case MSR_IA32_DEBUGCTLMSR:
	case MSR_IA32_LASTBRANCHFROMIP:
	case MSR_IA32_LASTBRANCHTOIP:
	case MSR_IA32_LASTINTFROMIP:
	case MSR_IA32_LASTINTTOIP:
	case MSR_K8_SYSCFG:
	case MSR_K7_HWCR:
	case MSR_VM_HSAVE_PA:
	case MSR_P6_PERFCTR0:
	case MSR_P6_PERFCTR1:
	case MSR_P6_EVNTSEL0:
	case MSR_P6_EVNTSEL1:
	case MSR_K7_EVNTSEL0:
	case MSR_K7_PERFCTR0:
	case MSR_K8_INT_PENDING_MSG:
	case MSR_AMD64_NB_CFG:
	case MSR_FAM10H_MMIO_CONF_BASE:
		data = 0;
		break;
	case MSR_MTRRcap:
		data = 0x500 | KVM_NR_VAR_MTRR;
		break;
	case 0x200 ... 0x2ff:
		return get_msr_mtrr(vcpu, msr, pdata);
	case 0xcd: /* fsb frequency */
		data = 3;
		break;
		/*
		 * MSR_EBC_FREQUENCY_ID
		 * Conservative value valid for even the basic CPU models.
		 * Models 0,1: 000 in bits 23:21 indicating a bus speed of
		 * 100MHz, model 2 000 in bits 18:16 indicating 100MHz,
		 * and 266MHz for model 3, or 4. Set Core Clock
		 * Frequency to System Bus Frequency Ratio to 1 (bits
		 * 31:24) even though these are only valid for CPU
		 * models > 2, however guests may end up dividing or
		 * multiplying by zero otherwise.
		 */
	case MSR_EBC_FREQUENCY_ID:
		data = 1 << 24;
		break;
	case MSR_IA32_APICBASE:
		data = kvm_get_apic_base(vcpu);
		break;
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
		return kvm_x2apic_msr_read(vcpu, msr, pdata);
		break;
	case MSR_IA32_MISC_ENABLE:
		data = vcpu->arch.ia32_misc_enable_msr;
		break;
	case MSR_IA32_PERF_STATUS:
		/* TSC increment by tick */
		data = 1000ULL;
		/* CPU multiplier */
		data |= (((uint64_t)4ULL) << 40);
		break;
	case MSR_EFER:
		data = vcpu->arch.efer;
		break;
	case MSR_KVM_WALL_CLOCK:
	case MSR_KVM_WALL_CLOCK_NEW:
		data = vcpu->kvm->arch.wall_clock;
		break;
	case MSR_KVM_SYSTEM_TIME:
	case MSR_KVM_SYSTEM_TIME_NEW:
		data = vcpu->arch.time;
		break;
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
	case MSR_IA32_MCG_CAP:
	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
		return get_msr_mce(vcpu, msr, pdata);
	case MSR_K7_CLK_CTL:
		/*
		 * Provide expected ramp-up count for K7. All other
		 * are set to zero, indicating minimum divisors for
		 * every field.
		 *
		 * This prevents guest kernels on AMD host with CPU
		 * type 6, model 8 and higher from exploding due to
		 * the rdmsr failing.
		 */
		data = 0x20000000;
		break;
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
		if (kvm_hv_msr_partition_wide(msr)) {
			int r;
			mutex_lock(&vcpu->kvm->lock);
			r = get_msr_hyperv_pw(vcpu, msr, pdata);
			mutex_unlock(&vcpu->kvm->lock);
			return r;
		} else
			return get_msr_hyperv(vcpu, msr, pdata);
		break;
	default:
		if (!ignore_msrs) {
			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
			return 1;
		} else {
			pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
			data = 0;
		}
		break;
	}
	*pdata = data;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);

/*
 * Read or write a bunch of msrs. All parameters are kernel addresses.
 *
 * @return number of msrs set successfully.
 */
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
		    struct kvm_msr_entry *entries,
		    int (*do_msr)(struct kvm_vcpu *vcpu,
				  unsigned index, u64 *data))
{
	int i, idx;

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	for (i = 0; i < msrs->nmsrs; ++i)
		if (do_msr(vcpu, entries[i].index, &entries[i].data))
			break;
	srcu_read_unlock(&vcpu->kvm->srcu, idx);

	return i;
}

/*
 * Read or write a bunch of msrs. Parameters are user addresses.
 *
 * @return number of msrs set successfully.
 */
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
		  int (*do_msr)(struct kvm_vcpu *vcpu,
				unsigned index, u64 *data),
		  int writeback)
{
	struct kvm_msrs msrs;
	struct kvm_msr_entry *entries;
	int r, n;
	unsigned size;

	r = -EFAULT;
	if (copy_from_user(&msrs, user_msrs, sizeof msrs))
		goto out;

	r = -E2BIG;
	if (msrs.nmsrs >= MAX_IO_MSRS)
		goto out;

	r = -ENOMEM;
	size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
	entries = kmalloc(size, GFP_KERNEL);
	if (!entries)
		goto out;

	r = -EFAULT;
	if (copy_from_user(entries, user_msrs->entries, size))
		goto out_free;

	r = n = __msr_io(vcpu, &msrs, entries, do_msr);
	if (r < 0)
		goto out_free;

	r = -EFAULT;
	if (writeback && copy_to_user(user_msrs->entries, entries, size))
		goto out_free;

	r = n;

out_free:
	kfree(entries);
out:
	return r;
}

int kvm_dev_ioctl_check_extension(long ext)
{
	int r;

	switch (ext) {
	case KVM_CAP_IRQCHIP:
	case KVM_CAP_HLT:
	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
	case KVM_CAP_SET_TSS_ADDR:
	case KVM_CAP_EXT_CPUID:
	case KVM_CAP_CLOCKSOURCE:
	case KVM_CAP_PIT:
	case KVM_CAP_NOP_IO_DELAY:
	case KVM_CAP_MP_STATE:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_REINJECT_CONTROL:
	case KVM_CAP_IRQ_INJECT_STATUS:
	case KVM_CAP_ASSIGN_DEV_IRQ:
	case KVM_CAP_IRQFD:
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_PIT2:
	case KVM_CAP_PIT_STATE2:
	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
	case KVM_CAP_XEN_HVM:
	case KVM_CAP_ADJUST_CLOCK:
	case KVM_CAP_VCPU_EVENTS:
	case KVM_CAP_HYPERV:
	case KVM_CAP_HYPERV_VAPIC:
	case KVM_CAP_HYPERV_SPIN:
	case KVM_CAP_PCI_SEGMENT:
	case KVM_CAP_DEBUGREGS:
	case KVM_CAP_X86_ROBUST_SINGLESTEP:
	case KVM_CAP_XSAVE:
		r = 1;
		break;
	case KVM_CAP_COALESCED_MMIO:
		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
		break;
	case KVM_CAP_VAPIC:
		r = !kvm_x86_ops->cpu_has_accelerated_tpr();
		break;
	case KVM_CAP_NR_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_MEMORY_SLOTS;
		break;
	case KVM_CAP_PV_MMU:	/* obsolete */
		r = 0;
		break;
	case KVM_CAP_IOMMU:
		r = iommu_found();
		break;
	case KVM_CAP_MCE:
		r = KVM_MAX_MCE_BANKS;
		break;
	case KVM_CAP_XCRS:
		r = cpu_has_xsave;
		break;
	default:
		r = 0;
		break;
	}
	return r;

}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	long r;

	switch (ioctl) {
	case KVM_GET_MSR_INDEX_LIST: {
		struct kvm_msr_list __user *user_msr_list = argp;
		struct kvm_msr_list msr_list;
		unsigned n;

		r = -EFAULT;
		if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
			goto out;
		n = msr_list.nmsrs;
		msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
			goto out;
		r = -E2BIG;
		if (n < msr_list.nmsrs)
			goto out;
		r = -EFAULT;
		if (copy_to_user(user_msr_list->indices, &msrs_to_save,
				 num_msrs_to_save * sizeof(u32)))
			goto out;
		if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
				 &emulated_msrs,
				 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_SUPPORTED_CPUID: {
		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_dev_ioctl_get_supported_cpuid(&cpuid,
						      cpuid_arg->entries);
		if (r)