KVM: x86: Replace (almost) all guest CPUID feature queries with cpu_caps

Switch all queries (except XSAVES) of guest features from guest CPUID to
guest capabilities, i.e. replace all calls to guest_cpuid_has() with calls
to guest_cpu_cap_has().

Keep guest_cpuid_has() around for XSAVES, but subsume its helper
guest_cpuid_get_register() and add a compile-time assertion to prevent
using guest_cpuid_has() for any other feature.  Add yet another comment
for XSAVE to explain why KVM is allowed to query its raw guest CPUID.

Opportunistically drop the unused guest_cpuid_clear(), as there should be
no circumstance in which KVM needs to _clear_ a guest CPUID feature now
that everything is tracked via cpu_caps.  E.g. KVM may need to _change_
a feature to emulate dynamic CPUID flags, but KVM should never need to
clear a feature in guest CPUID to prevent it from being used by the guest.

Delete the last remnants of the governed features framework, as the lone
holdout was vmx_adjust_secondary_exec_control()'s divergent behavior for
governed vs. ungoverned features.

Note, replacing guest_cpuid_has() checks with guest_cpu_cap_has() when
computing reserved CR4 bits is a nop when viewed as a whole, as KVM's
capabilities are already incorporated into the calculation, i.e. if a
feature is present in guest CPUID but unsupported by KVM, its CR4 bit
was already being marked as reserved, checking guest_cpu_cap_has() simply
double-stamps that it's a reserved bit.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20241128013424.4096668-51-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/kvm/cpuid.c

@@ -437,7 +437,7 @@ void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * and can install smaller shadow pages if the host lacks 1GiB support.
 	 */
 	allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
-				      guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
+				      guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES);
 	guest_cpu_cap_change(vcpu, X86_FEATURE_GBPAGES, allow_gbpages);
 
 	best = kvm_find_cpuid_entry(vcpu, 1);
@@ -462,7 +462,7 @@ void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 #define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f)
 	vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_) |
-					 __cr4_reserved_bits(guest_cpuid_has, vcpu);
+					 __cr4_reserved_bits(guest_cpu_cap_has, vcpu);
 #undef __kvm_cpu_cap_has
 
 	kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu));

arch/x86/kvm/cpuid.h

@@ -67,41 +67,40 @@ static __always_inline void cpuid_entry_override(struct kvm_cpuid_entry2 *entry,
 	*reg = kvm_cpu_caps[leaf];
 }
 
-static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu,
-						     unsigned int x86_feature)
+static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu,
+					    unsigned int x86_feature)
 {
 	const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature);
 	struct kvm_cpuid_entry2 *entry;
+	u32 *reg;
+
+	/*
+	 * XSAVES is a special snowflake.  Due to lack of a dedicated intercept
+	 * on SVM, KVM must assume that XSAVES (and thus XRSTORS) is usable by
+	 * the guest if the host supports XSAVES and *XSAVE* is exposed to the
+	 * guest.  Because the guest can execute XSAVES and XRSTORS, i.e. can
+	 * indirectly consume XSS, KVM must ensure XSS is zeroed when running
+	 * the guest, i.e. must set XSAVES in vCPU capabilities.  But to reject
+	 * direct XSS reads and writes (to minimize the virtualization hole and
+	 * honor userspace's CPUID), KVM needs to check the raw guest CPUID,
+	 * not KVM's view of guest capabilities.
+	 *
+	 * For all other features, guest capabilities are accurate.  Expand
+	 * this allowlist with extreme vigilance.
+	 */
+	BUILD_BUG_ON(x86_feature != X86_FEATURE_XSAVES);
 
 	entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index);
 	if (!entry)
 		return NULL;
 
-	return __cpuid_entry_get_reg(entry, cpuid.reg);
-}
-
-static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu,
-					    unsigned int x86_feature)
-{
-	u32 *reg;
-
-	reg = guest_cpuid_get_register(vcpu, x86_feature);
+	reg = __cpuid_entry_get_reg(entry, cpuid.reg);
 	if (!reg)
 		return false;
 
 	return *reg & __feature_bit(x86_feature);
 }
 
-static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu,
-					      unsigned int x86_feature)
-{
-	u32 *reg;
-
-	reg = guest_cpuid_get_register(vcpu, x86_feature);
-	if (reg)
-		*reg &= ~__feature_bit(x86_feature);
-}
-
 static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.is_amd_compatible;
@@ -202,27 +201,6 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu,
 	return vcpu->arch.pv_cpuid.features & (1u << kvm_feature);
 }
 
-enum kvm_governed_features {
-#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x,
-#include "governed_features.h"
-	KVM_NR_GOVERNED_FEATURES
-};
-
-static __always_inline int kvm_governed_feature_index(unsigned int x86_feature)
-{
-	switch (x86_feature) {
-#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x;
-#include "governed_features.h"
-	default:
-		return -1;
-	}
-}
-
-static __always_inline bool kvm_is_governed_feature(unsigned int x86_feature)
-{
-	return kvm_governed_feature_index(x86_feature) >= 0;
-}
-
 static __always_inline void guest_cpu_cap_set(struct kvm_vcpu *vcpu,
 					      unsigned int x86_feature)
 {
@@ -267,17 +245,17 @@ static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr
 
 static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu)
 {
-	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
-		guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) ||
-		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) ||
-		guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD));
+	return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_STIBP) ||
+		guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS) ||
+		guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_SSBD));
 }
 
 static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu)
 {
-	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
-		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) ||
-		guest_cpuid_has(vcpu, X86_FEATURE_SBPB));
+	return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB) ||
+		guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB));
 }
 
 #endif

arch/x86/kvm/governed_features.h

@@ -1352,7 +1352,7 @@ static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
 		return;
 
 	if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
-	    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+	    !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVEC))
 		return;
 
 	pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "

arch/x86/kvm/hyperv.c

@@ -598,7 +598,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	 * version first and level-triggered interrupts never get EOIed in
 	 * IOAPIC.
 	 */
-	if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) &&
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) &&
 	    !ioapic_in_kernel(vcpu->kvm))
 		v |= APIC_LVR_DIRECTED_EOI;
 	kvm_lapic_set_reg(apic, APIC_LVR, v);
@@ -2634,7 +2634,7 @@ int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated)
 		return 0;
 
 	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
-		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
+		(guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
 
 	if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
 		return 1;

arch/x86/kvm/lapic.c

@@ -283,7 +283,7 @@ void enter_smm(struct kvm_vcpu *vcpu)
 	memset(smram.bytes, 0, sizeof(smram.bytes));
 
 #ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, &smram.smram64);
 	else
 #endif
@@ -353,7 +353,7 @@ void enter_smm(struct kvm_vcpu *vcpu)
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
 #ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		if (kvm_x86_call(set_efer)(vcpu, 0))
 			goto error;
 #endif
@@ -586,7 +586,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 	 * supports long mode.
 	 */
 #ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) {
 		struct kvm_segment cs_desc;
 		unsigned long cr4;
 
@@ -609,7 +609,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 		kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
 
 #ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) {
 		unsigned long cr4, efer;
 
 		/* Clear CR4.PAE before clearing EFER.LME. */
@@ -634,7 +634,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 		return X86EMUL_UNHANDLEABLE;
 
 #ifdef CONFIG_X86_64
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		ret = rsm_load_state_64(ctxt, &smram.smram64);
 	else
 #endif

arch/x86/kvm/smm.c

@@ -46,7 +46,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 
 	switch (msr) {
 	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
-		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+		if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE))
 			return NULL;
 		/*
 		 * Each PMU counter has a pair of CTL and CTR MSRs. CTLn
@@ -109,7 +109,7 @@ static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3:
 		return pmu->version > 0;
 	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
-		return guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE);
+		return guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE);
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
@@ -179,7 +179,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 	union cpuid_0x80000022_ebx ebx;
 
 	pmu->version = 1;
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFMON_V2)) {
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFMON_V2)) {
 		pmu->version = 2;
 		/*
 		 * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest
@@ -189,7 +189,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 			     x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index);
 		ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx;
 		pmu->nr_arch_gp_counters = ebx.split.num_core_pmc;
-	} else if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
+	} else if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE;
 	} else {
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;

arch/x86/kvm/svm/pmu.c

@@ -4435,8 +4435,8 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
-		bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
-				 guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+		bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) ||
+				 guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID);
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
 	}

arch/x86/kvm/svm/sev.c

@@ -1187,14 +1187,14 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 	 */
 	if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
 		if (!npt_enabled ||
-		    !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID))
+		    !guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_INVPCID))
 			svm_set_intercept(svm, INTERCEPT_INVPCID);
 		else
 			svm_clr_intercept(svm, INTERCEPT_INVPCID);
 	}
 
 	if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) {
-		if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP))
 			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
 		else
 			svm_set_intercept(svm, INTERCEPT_RDTSCP);
@@ -2940,7 +2940,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+		    !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD))
 			return 1;
 
 		msr_info->data = svm->virt_spec_ctrl;
@@ -3091,7 +3091,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+		    !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD))
 			return 1;
 
 		if (data & ~SPEC_CTRL_SSBD)
@@ -3272,7 +3272,7 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	unsigned long type;
 	gva_t gva;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -4404,7 +4404,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	guest_cpu_cap_change(vcpu, X86_FEATURE_XSAVES,
 			     boot_cpu_has(X86_FEATURE_XSAVE) &&
 			     boot_cpu_has(X86_FEATURE_XSAVES) &&
-			     guest_cpuid_has(vcpu, X86_FEATURE_XSAVE));
+			     guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE));
 
 	/*
 	 * Intercept VMLOAD if the vCPU model is Intel in order to emulate that
@@ -4422,7 +4422,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
-				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
+				     !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
 	if (sev_guest(vcpu->kvm))
 		sev_vcpu_after_set_cpuid(svm);
@@ -4673,7 +4673,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
 	 * responsible for ensuring nested SVM and SMIs are mutually exclusive.
 	 */
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		return 1;
 
 	smram->smram64.svm_guest_flag = 1;
@@ -4720,14 +4720,14 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 
 	const struct kvm_smram_state_64 *smram64 = &smram->smram64;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		return 0;
 
 	/* Non-zero if SMI arrived while vCPU was in guest mode. */
 	if (!smram64->svm_guest_flag)
 		return 0;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SVM))
 		return 1;
 
 	if (!(smram64->efer & EFER_SVME))

arch/x86/kvm/svm/svm.c

@@ -42,7 +42,7 @@ static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx)
 	return vmx->nested.hv_evmcs;
 }
 
-static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
+static inline bool guest_cpu_cap_has_evmcs(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and