linux/arch/x86/kvm/cpuid.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 * cpuid support routines
 *
 * derived from arch/x86/kvm/x86.c
 *
 * Copyright 2011 Red Hat, Inc. and/or its affiliates.
 * Copyright IBM Corporation, 2008
 */

#include <linux/kvm_host.h>
#include <linux/export.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <linux/sched/stat.h>

#include <asm/processor.h>
#include <asm/user.h>
#include <asm/fpu/xstate.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
#include "trace.h"
#include "pmu.h"

/*
 * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be
 * aligned to sizeof(unsigned long) because it's not accessed via bitops.
 */
u32 kvm_cpu_caps[NCAPINTS] __read_mostly;
EXPORT_SYMBOL_GPL(kvm_cpu_caps);

static u32 xstate_required_size(u64 xstate_bv, bool compacted)
{
	int feature_bit = 0;
	u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;

	xstate_bv &= XFEATURE_MASK_EXTEND;
	while (xstate_bv) {
		if (xstate_bv & 0x1) {
		        u32 eax, ebx, ecx, edx, offset;
		        cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
			offset = compacted ? ret : ebx;
			ret = max(ret, offset + eax);
		}

		xstate_bv >>= 1;
		feature_bit++;
	}

	return ret;
}

#define F feature_bit

int kvm_update_cpuid(struct kvm_vcpu *vcpu)
{
	struct kvm_cpuid_entry2 *best;
	struct kvm_lapic *apic = vcpu->arch.apic;

	best = kvm_find_cpuid_entry(vcpu, 1, 0);
	if (!best)
		return 0;

	/* Update OSXSAVE bit */
	if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1)
		cpuid_entry_change(best, X86_FEATURE_OSXSAVE,
				   kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE));

	cpuid_entry_change(best, X86_FEATURE_APIC,
			   vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE);

	if (apic) {
		if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER))
			apic->lapic_timer.timer_mode_mask = 3 << 17;
		else
			apic->lapic_timer.timer_mode_mask = 1 << 17;
	}

	best = kvm_find_cpuid_entry(vcpu, 7, 0);
	if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7)
		cpuid_entry_change(best, X86_FEATURE_OSPKE,
				   kvm_read_cr4_bits(vcpu, X86_CR4_PKE));

	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
	if (!best) {
		vcpu->arch.guest_supported_xcr0 = 0;
		vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
	} else {
		vcpu->arch.guest_supported_xcr0 =
			(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
		vcpu->arch.guest_xstate_size = best->ebx =
			xstate_required_size(vcpu->arch.xcr0, false);
	}

	best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
	if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) ||
		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);

	/*
	 * The existing code assumes virtual address is 48-bit or 57-bit in the
	 * canonical address checks; exit if it is ever changed.
	 */
	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
	if (best) {
		int vaddr_bits = (best->eax & 0xff00) >> 8;

		if (vaddr_bits != 48 && vaddr_bits != 57 && vaddr_bits != 0)
			return -EINVAL;
	}

	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);

	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
		if (best)
			cpuid_entry_change(best, X86_FEATURE_MWAIT,
					   vcpu->arch.ia32_misc_enable_msr &
					   MSR_IA32_MISC_ENABLE_MWAIT);
	}

	/* Update physical-address width */
	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
	kvm_mmu_reset_context(vcpu);

	kvm_pmu_refresh(vcpu);
	return 0;
}

static int is_efer_nx(void)
{
	unsigned long long efer = 0;

	rdmsrl_safe(MSR_EFER, &efer);
	return efer & EFER_NX;
}

static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
{
	int i;
	struct kvm_cpuid_entry2 *e, *entry;

	entry = NULL;
	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		e = &vcpu->arch.cpuid_entries[i];
		if (e->function == 0x80000001) {
			entry = e;
			break;
		}
	}
	if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) {
		cpuid_entry_clear(entry, X86_FEATURE_NX);
		printk(KERN_INFO "kvm: guest NX capability removed\n");
	}
}

int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
{
	struct kvm_cpuid_entry2 *best;

	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
	if (!best || best->eax < 0x80000008)
		goto not_found;
	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
	if (best)
		return best->eax & 0xff;
not_found:
	return 36;
}
EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr);

/* when an old userspace process fills a new kernel module */
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
			     struct kvm_cpuid *cpuid,
			     struct kvm_cpuid_entry __user *entries)
{
	int r, i;
	struct kvm_cpuid_entry *cpuid_entries = NULL;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -ENOMEM;
	if (cpuid->nent) {
		cpuid_entries =
			vmalloc(array_size(sizeof(struct kvm_cpuid_entry),
					   cpuid->nent));
		if (!cpuid_entries)
			goto out;
		r = -EFAULT;
		if (copy_from_user(cpuid_entries, entries,
				   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
			goto out;
	}
	for (i = 0; i < cpuid->nent; i++) {
		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
		vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
		vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
		vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
		vcpu->arch.cpuid_entries[i].index = 0;
		vcpu->arch.cpuid_entries[i].flags = 0;
		vcpu->arch.cpuid_entries[i].padding[0] = 0;
		vcpu->arch.cpuid_entries[i].padding[1] = 0;
		vcpu->arch.cpuid_entries[i].padding[2] = 0;
	}
	vcpu->arch.cpuid_nent = cpuid->nent;
	cpuid_fix_nx_cap(vcpu);
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);
	r = kvm_update_cpuid(vcpu);

out:
	vfree(cpuid_entries);
	return r;
}

int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
			      struct kvm_cpuid2 *cpuid,
			      struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -EFAULT;
	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	vcpu->arch.cpuid_nent = cpuid->nent;
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);
	r = kvm_update_cpuid(vcpu);
out:
	return r;
}

int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
			      struct kvm_cpuid2 *cpuid,
			      struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent < vcpu->arch.cpuid_nent)
		goto out;
	r = -EFAULT;
	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	return 0;

out:
	cpuid->nent = vcpu->arch.cpuid_nent;
	return r;
}

static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
{
	reverse_cpuid_check(leaf);
	kvm_cpu_caps[leaf] &= mask;
}

void kvm_set_cpu_caps(void)
{
	unsigned int f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
	unsigned int f_gbpages = F(GBPAGES);
	unsigned int f_lm = F(LM);
#else
	unsigned int f_gbpages = 0;
	unsigned int f_lm = 0;
#endif

	BUILD_BUG_ON(sizeof(kvm_cpu_caps) >
		     sizeof(boot_cpu_data.x86_capability));

	memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability,
	       sizeof(kvm_cpu_caps));

	kvm_cpu_cap_mask(CPUID_1_ECX,
		/*
		 * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not*
		 * advertised to guests via CPUID!
		 */
		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
		0 /* DS-CPL, VMX, SMX, EST */ |
		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
		F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ |
		F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) |
		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
		0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
		F(F16C) | F(RDRAND)
	);

	kvm_cpu_cap_mask(CPUID_1_EDX,
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) |
		0 /* Reserved, DS, ACPI */ | F(MMX) |
		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
		0 /* HTT, TM, Reserved, PBE */
	);

	kvm_cpu_cap_mask(CPUID_7_0_EBX,
		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
		F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/
	);

	kvm_cpu_cap_mask(CPUID_7_ECX,
		F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) |
		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/
	);
	/* Set LA57 based on hardware capability. */
	if (cpuid_ecx(7) & F(LA57))
		kvm_cpu_cap_set(X86_FEATURE_LA57);

	kvm_cpu_cap_mask(CPUID_7_EDX,
		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
		F(MD_CLEAR)
	);

	kvm_cpu_cap_mask(CPUID_7_1_EAX,
		F(AVX512_BF16)
	);

	kvm_cpu_cap_mask(CPUID_D_1_EAX,
		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES)
	);

	kvm_cpu_cap_mask(CPUID_8000_0001_ECX,
		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) |
		F(TOPOEXT) | F(PERFCTR_CORE)
	);

	kvm_cpu_cap_mask(CPUID_8000_0001_EDX,
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* Reserved */ |
		f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
		F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) |
		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW)
	);

	if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64))
		kvm_cpu_cap_set(X86_FEATURE_GBPAGES);

	kvm_cpu_cap_mask(CPUID_8000_0008_EBX,
		F(CLZERO) | F(XSAVEERPTR) |
		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON)
	);

	/*
	 * Hide all SVM features by default, SVM will set the cap bits for
	 * features it emulates and/or exposes for L1.
	 */
	kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0);

	kvm_cpu_cap_mask(CPUID_C000_0001_EDX,
		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
		F(PMM) | F(PMM_EN)
	);
}
EXPORT_SYMBOL_GPL(kvm_set_cpu_caps);

struct kvm_cpuid_array {
	struct kvm_cpuid_entry2 *entries;
	const int maxnent;
	int nent;
};

static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
					      u32 function, u32 index)
{
	struct kvm_cpuid_entry2 *entry;

	if (array->nent >= array->maxnent)
		return NULL;

	entry = &array->entries[array->nent++];

	entry->function = function;
	entry->index = index;
	entry->flags = 0;

	cpuid_count(entry->function, entry->index,
		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);

	switch (function) {
	case 2:
		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
		break;
	case 4:
	case 7:
	case 0xb:
	case 0xd:
	case 0xf:
	case 0x10:
	case 0x12:
	case 0x14:
	case 0x17:
	case 0x18:
	case 0x1f:
	case 0x8000001d:
		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		break;
	}

	return entry;
}

static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func)
{
	struct kvm_cpuid_entry2 *entry = &array->entries[array->nent];

	entry->function = func;
	entry->index = 0;
	entry->flags = 0;

	switch (func) {
	case 0:
		entry->eax = 7;
		++array->nent;
		break;
	case 1:
		entry->ecx = F(MOVBE);
		++array->nent;
		break;
	case 7:
		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		entry->eax = 0;
		entry->ecx = F(RDPID);
		++array->nent;
	default:
		break;
	}

	return 0;
}

static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry)
{
	switch (entry->index) {
	case 0:
		entry->eax = min(entry->eax, 1u);
		cpuid_entry_mask(entry, CPUID_7_0_EBX);
		/* TSC_ADJUST is emulated */
		cpuid_entry_set(entry, X86_FEATURE_TSC_ADJUST);
		cpuid_entry_mask(entry, CPUID_7_ECX);
		cpuid_entry_mask(entry, CPUID_7_EDX);
		if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS))
			cpuid_entry_set(entry, X86_FEATURE_SPEC_CTRL);
		if (boot_cpu_has(X86_FEATURE_STIBP))
			cpuid_entry_set(entry, X86_FEATURE_INTEL_STIBP);
		if (boot_cpu_has(X86_FEATURE_AMD_SSBD))
			cpuid_entry_set(entry, X86_FEATURE_SPEC_CTRL_SSBD);
		/*
		 * We emulate ARCH_CAPABILITIES in software even
		 * if the host doesn't support it.
		 */
		cpuid_entry_set(entry, X86_FEATURE_ARCH_CAPABILITIES);
		break;
	case 1:
		cpuid_entry_mask(entry, CPUID_7_1_EAX);
		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	default:
		WARN_ON_ONCE(1);
		entry->eax = 0;
		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	}
}

static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
{
	struct kvm_cpuid_entry2 *entry;
	int r, i, max_idx;
	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;

	/* all calls to cpuid_count() should be made on the same cpu */
	get_cpu();

	r = -E2BIG;

	entry = do_host_cpuid(array, function, 0);
	if (WARN_ON(!entry))
		goto out;

	switch (function) {
	case 0:
		/* Limited to the highest leaf implemented in KVM. */
		entry->eax = min(entry->eax, 0x1fU);
		break;
	case 1:
		cpuid_entry_mask(entry, CPUID_1_EDX);
		cpuid_entry_mask(entry, CPUID_1_ECX);
		/* we support x2apic emulation even if host does not support
		 * it since we emulate x2apic in software */
		cpuid_entry_set(entry, X86_FEATURE_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:
		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;

		for (i = 1, max_idx = entry->eax & 0xff; i < max_idx; ++i) {
			entry = do_host_cpuid(array, function, 0);
			if (!entry)
				goto out;
		}
		break;
	/* functions 4 and 0x8000001d have additional index. */
	case 4:
	case 0x8000001d:
		/*
		 * Read entries until the cache type in the previous entry is
		 * zero, i.e. indicates an invalid entry.
		 */
		for (i = 1; entry->eax & 0x1f; ++i) {
			entry = do_host_cpuid(array, function, i);
			if (!entry)
				goto out;
		}
		break;
	case 6: /* Thermal management */
		entry->eax = 0x4; /* allow ARAT */
		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	/* function 7 has additional index. */
	case 7:
		do_cpuid_7_mask(entry);

		for (i = 1, max_idx = entry->eax; i <= max_idx; i++) {
			entry = do_host_cpuid(array, function, i);
			if (!entry)
				goto out;

			do_cpuid_7_mask(entry);
		}
		break;
	case 9:
		break;
	case 0xa: { /* Architectural Performance Monitoring */
		struct x86_pmu_capability cap;
		union cpuid10_eax eax;
		union cpuid10_edx edx;

		perf_get_x86_pmu_capability(&cap);

		/*
		 * Only support guest architectural pmu on a host
		 * with architectural pmu.
		 */
		if (!cap.version)
			memset(&cap, 0, sizeof(cap));

		eax.split.version_id = min(cap.version, 2);
		eax.split.num_counters = cap.num_counters_gp;
		eax.split.bit_width = cap.bit_width_gp;
		eax.split.mask_length = cap.events_mask_len;

		edx.split.num_counters_fixed = cap.num_counters_fixed;
		edx.split.bit_width_fixed = cap.bit_width_fixed;
		edx.split.reserved = 0;

		entry->eax = eax.full;
		entry->ebx = cap.events_mask;
		entry->ecx = 0;
		entry->edx = edx.full;
		break;
	}
	/*
	 * Per Intel's SDM, the 0x1f is a superset of 0xb,
	 * thus they can be handled by common code.
	 */
	case 0x1f:
	case 0xb:
		/*
		 * Populate entries until the level type (ECX[15:8]) of the
		 * previous entry is zero.  Note, CPUID EAX.{0x1f,0xb}.0 is
		 * the starting entry, filled by the primary do_host_cpuid().
		 */
		for (i = 1; entry->ecx & 0xff00; ++i) {
			entry = do_host_cpuid(array, function, i);
			if (!entry)
				goto out;
		}
		break;
	case 0xd:
		entry->eax &= supported_xcr0;
		entry->ebx = xstate_required_size(supported_xcr0, false);
		entry->ecx = entry->ebx;
		entry->edx &= supported_xcr0 >> 32;
		if (!supported_xcr0)
			break;

		entry = do_host_cpuid(array, function, 1);
		if (!entry)
			goto out;

		cpuid_entry_mask(entry, CPUID_D_1_EAX);
		if (entry->eax & (F(XSAVES)|F(XSAVEC)))
			entry->ebx = xstate_required_size(supported_xcr0, true);
		else
			entry->ebx = 0;
		/* Saving XSS controlled state via XSAVES isn't supported. */
		entry->ecx = 0;
		entry->edx = 0;

		for (i = 2; i < 64; ++i) {
			if (!(supported_xcr0 & BIT_ULL(i)))
				continue;

			entry = do_host_cpuid(array, function, i);
			if (!entry)
				goto out;

			/*
			 * The supported check above should have filtered out
			 * invalid sub-leafs as well as sub-leafs managed by
			 * IA32_XSS MSR.  Only XCR0-managed sub-leafs should
			 * reach this point, and they should have a non-zero
			 * save state size.
			 */
			if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 1))) {
				--array->nent;
				continue;
			}

			entry->ecx = 0;
			entry->edx = 0;
		}
		break;
	/* Intel PT */
	case 0x14:
		if (!f_intel_pt) {
			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
			break;
		}

		for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) {
			if (!do_host_cpuid(array, function, i))
				goto out;
		}
		break;
	case KVM_CPUID_SIGNATURE: {
		static const char signature[12] = "KVMKVMKVM\0\0";
		const u32 *sigptr = (const u32 *)signature;
		entry->eax = KVM_CPUID_FEATURES;
		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_ASYNC_PF) |
			     (1 << KVM_FEATURE_PV_EOI) |
			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
			     (1 << KVM_FEATURE_PV_UNHALT) |
			     (1 << KVM_FEATURE_PV_TLB_FLUSH) |
			     (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) |
			     (1 << KVM_FEATURE_PV_SEND_IPI) |
			     (1 << KVM_FEATURE_POLL_CONTROL) |
			     (1 << KVM_FEATURE_PV_SCHED_YIELD);

		if (sched_info_on())
			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);

		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	case 0x80000000:
		entry->eax = min(entry->eax, 0x8000001f);
		break;
	case 0x80000001:
		cpuid_entry_mask(entry, CPUID_8000_0001_EDX);
		/* Add it manually because it may not be in host CPUID.  */
		if (!tdp_enabled)
			cpuid_entry_set(entry, X86_FEATURE_GBPAGES);
		cpuid_entry_mask(entry, CPUID_8000_0001_ECX);
		break;
	case 0x80000007: /* Advanced power management */
		/* invariant TSC is CPUID.80000007H:EDX[8] */
		entry->edx &= (1 << 8);
		/* mask against host */
		entry->edx &= boot_cpu_data.x86_power;
		entry->eax = entry->ebx = entry->ecx = 0;
		break;
	case 0x80000008: {
		unsigned g_phys_as = (entry->eax >> 16) & 0xff;
		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
		unsigned phys_as = entry->eax & 0xff;

		if (!g_phys_as)
			g_phys_as = phys_as;
		entry->eax = g_phys_as | (virt_as << 8);
		entry->edx = 0;
		cpuid_entry_mask(entry, CPUID_8000_0008_EBX);
		/*
		 * AMD has separate bits for each SPEC_CTRL bit.
		 * arch/x86/kernel/cpu/bugs.c is kind enough to
		 * record that in cpufeatures so use them.
		 */
		if (boot_cpu_has(X86_FEATURE_IBPB))
			cpuid_entry_set(entry, X86_FEATURE_AMD_IBPB);
		if (boot_cpu_has(X86_FEATURE_IBRS))
			cpuid_entry_set(entry, X86_FEATURE_AMD_IBRS);
		if (boot_cpu_has(X86_FEATURE_STIBP))
			cpuid_entry_set(entry, X86_FEATURE_AMD_STIBP);
		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
			cpuid_entry_set(entry, X86_FEATURE_AMD_SSBD);
		if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
			cpuid_entry_set(entry, X86_FEATURE_AMD_SSB_NO);
		/*
		 * The preference is to use SPEC CTRL MSR instead of the
		 * VIRT_SPEC MSR.
		 */
		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
		    !boot_cpu_has(X86_FEATURE_AMD_SSBD))
			cpuid_entry_set(entry, X86_FEATURE_VIRT_SSBD);
		break;
	}
	case 0x80000019:
		entry->ecx = entry->edx = 0;
		break;
	case 0x8000001a:
	case 0x8000001e:
		break;
	/* Support memory encryption cpuid if host supports it */
	case 0x8000001F:
		if (!boot_cpu_has(X86_FEATURE_SEV))
			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
		break;
	/*Add support for Centaur's CPUID instruction*/
	case 0xC0000000:
		/*Just support up to 0xC0000004 now*/
		entry->eax = min(entry->eax, 0xC0000004);
		break;
	case 0xC0000001:
		cpuid_entry_mask(entry, CPUID_C000_0001_EDX);
		break;
	case 3: /* Processor serial number */
	case 5: /* MONITOR/MWAIT */
	case 0xC0000002:
	case 0xC0000003:
	case 0xC0000004:
	default:
		entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
		break;
	}

	kvm_x86_ops->set_supported_cpuid(entry);

	r = 0;

out:
	put_cpu();

	return r;
}

static int do_cpuid_func(struct kvm_cpuid_array *array, u32 func,
			 unsigned int type)
{
	if (array->nent >= array->maxnent)
		return -E2BIG;

	if (type == KVM_GET_EMULATED_CPUID)
		return __do_cpuid_func_emulated(array, func);

	return __do_cpuid_func(array, func);
}

#define CENTAUR_CPUID_SIGNATURE 0xC0000000

static int get_cpuid_func(struct kvm_cpuid_array *array, u32 func,
			  unsigned int type)
{
	u32 limit;
	int r;

	if (func == CENTAUR_CPUID_SIGNATURE &&
	    boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR)
		return 0;

	r = do_cpuid_func(array, func, type);
	if (r)
		return r;

	limit = array->entries[array->nent - 1].eax;
	for (func = func + 1; func <= limit; ++func) {
		r = do_cpuid_func(array, func, type);
		if (r)
			break;
	}

	return r;
}

static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
				 __u32 num_entries, unsigned int ioctl_type)
{
	int i;
	__u32 pad[3];

	if (ioctl_type != KVM_GET_EMULATED_CPUID)
		return false;

	/*
	 * We want to make sure that ->padding is being passed clean from
	 * userspace in case we want to use it for something in the future.
	 *
	 * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
	 * have to give ourselves satisfied only with the emulated side. /me
	 * sheds a tear.
	 */
	for (i = 0; i < num_entries; i++) {
		if (copy_from_user(pad, entries[i].padding, sizeof(pad)))
			return true;

		if (pad[0] || pad[1] || pad[2])
			return true;
	}
	return false;
}

int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
			    struct kvm_cpuid_entry2 __user *entries,
			    unsigned int type)
{
	static const u32 funcs[] = {
		0, 0x80000000, CENTAUR_CPUID_SIGNATURE, KVM_CPUID_SIGNATURE,
	};

	struct kvm_cpuid_array array = {
		.nent = 0,
		.maxnent = cpuid->nent,
	};
	int r, i;

	if (cpuid->nent < 1)
		return -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		cpuid->nent = KVM_MAX_CPUID_ENTRIES;

	if (sanity_check_entries(entries, cpuid->nent, type))
		return -EINVAL;

	array.entries = vzalloc(array_size(sizeof(struct kvm_cpuid_entry2),
					   cpuid->nent));
	if (!array.entries)
		return -ENOMEM;

	for (i = 0; i < ARRAY_SIZE(funcs); i++) {
		r = get_cpuid_func(&array, funcs[i], type);
		if (r)
			goto out_free;
	}
	cpuid->nent = array.nent;

	if (copy_to_user(entries, array.entries,
			 array.nent * sizeof(struct kvm_cpuid_entry2)))
		r = -EFAULT;

out_free:
	vfree(array.entries);
	return r;
}

static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
	struct kvm_cpuid_entry2 *ej;
	int j = i;
	int 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 */
	do {
		j = (j + 1) % nent;
		ej = &vcpu->arch.cpuid_entries[j];
	} while (ej->function != e->function);

	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;

	return j;
}

/* 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;
}

struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
					      u32 function, u32 index)
{
	int i;
	struct kvm_cpuid_entry2 *best = NULL;

	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		struct kvm_cpuid_entry2 *e;

		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;
		}
	}
	return best;
}
EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);

/*
 * If the basic or extended CPUID leaf requested is higher than the
 * maximum supported basic or extended leaf, respectively, then it is
 * out of range.
 */
static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
{
	struct kvm_cpuid_entry2 *max;

	max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
	return max && function <= max->eax;
}

bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
	       u32 *ecx, u32 *edx, bool check_limit)
{
	u32 function = *eax, index = *ecx;
	struct kvm_cpuid_entry2 *entry;
	struct kvm_cpuid_entry2 *max;
	bool found;

	entry = kvm_find_cpuid_entry(vcpu, function, index);
	found = entry;
	/*
	 * Intel CPUID semantics treats any query for an out-of-range
	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
	 * requested. AMD CPUID semantics returns all zeroes for any
	 * undefined leaf, whether or not the leaf is in range.
	 */
	if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
	    !cpuid_function_in_range(vcpu, function)) {
		max = kvm_find_cpuid_entry(vcpu, 0, 0);
		if (max) {
			function = max->eax;
			entry = kvm_find_cpuid_entry(vcpu, function, index);
		}
	}
	if (entry) {
		*eax = entry->eax;
		*ebx = entry->ebx;
		*ecx = entry->ecx;
		*edx = entry->edx;
		if (function == 7 && index == 0) {
			u64 data;
		        if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
			    (data & TSX_CTRL_CPUID_CLEAR))
				*ebx &= ~(F(RTM) | F(HLE));
		}
	} else {
		*eax = *ebx = *ecx = *edx = 0;
		/*
		 * When leaf 0BH or 1FH is defined, CL is pass-through
		 * and EDX is always the x2APIC ID, even for undefined
		 * subleaves. Index 1 will exist iff the leaf is
		 * implemented, so we pass through CL iff leaf 1
		 * exists. EDX can be copied from any existing index.
		 */
		if (function == 0xb || function == 0x1f) {
			entry = kvm_find_cpuid_entry(vcpu, function, 1);
			if (entry) {
				*ecx = index & 0xff;
				*edx = entry->edx;
			}
		}
	}
	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
	return found;
}
EXPORT_SYMBOL_GPL(kvm_cpuid);

int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	u32 eax, ebx, ecx, edx;

	if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0))
		return 1;

	eax = kvm_rax_read(vcpu);
	ecx = kvm_rcx_read(vcpu);
	kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
	kvm_rax_write(vcpu, eax);
	kvm_rbx_write(vcpu, ebx);
	kvm_rcx_write(vcpu, ecx);
	kvm_rdx_write(vcpu, edx);
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);