KVM: x86: Introduce "struct kvm_caps" to track misc caps/settings

Add kvm_caps to hold a variety of capabilites and defaults that aren't
handled by kvm_cpu_caps because they aren't CPUID bits in order to reduce
the amount of boilerplate code required to add a new feature.  The vast
majority (all?) of the caps interact with vendor code and are written
only during initialization, i.e. should be tagged __read_mostly, declared
extern in x86.h, and exported.

No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220524135624.22988-4-chenyi.qiang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -1664,21 +1664,6 @@ extern bool tdp_enabled;
 
 u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
 
-/* control of guest tsc rate supported? */
-extern bool kvm_has_tsc_control;
-/* maximum supported tsc_khz for guests */
-extern u32  kvm_max_guest_tsc_khz;
-/* number of bits of the fractional part of the TSC scaling ratio */
-extern u8   kvm_tsc_scaling_ratio_frac_bits;
-/* maximum allowed value of TSC scaling ratio */
-extern u64  kvm_max_tsc_scaling_ratio;
-/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
-extern u64  kvm_default_tsc_scaling_ratio;
-/* bus lock detection supported? */
-extern bool kvm_has_bus_lock_exit;
-
-extern u64 kvm_mce_cap_supported;
-
 /*
  * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing
  *			userspace I/O) to indicate that the emulation context

arch/x86/kvm/cpuid.c

@@ -200,7 +200,7 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
 
 /*
  * Calculate guest's supported XCR0 taking into account guest CPUID data and
- * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0).
+ * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0).
  */
 static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent)
 {
@@ -210,7 +210,7 @@ static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent)
 	if (!best)
 		return 0;
 
-	return (best->eax | ((u64)best->edx << 32)) & supported_xcr0;
+	return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0;
 }
 
 static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
@@ -912,8 +912,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		}
 		break;
 	case 0xd: {
-		u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm();
-		u64 permitted_xss = supported_xss;
+		u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
+		u64 permitted_xss = kvm_caps.supported_xss;
 
 		entry->eax &= permitted_xcr0;
 		entry->ebx = xstate_required_size(permitted_xcr0, false);

arch/x86/kvm/debugfs.c

@@ -48,7 +48,7 @@ DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_fops, vcpu_get_tsc_scaling_ratio, NULL,
 
 static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val)
 {
-	*val = kvm_tsc_scaling_ratio_frac_bits;
+	*val = kvm_caps.tsc_scaling_ratio_frac_bits;
 	return 0;
 }
 
@@ -66,7 +66,7 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_
 				    debugfs_dentry, vcpu,
 				    &vcpu_timer_advance_ns_fops);
 
-	if (kvm_has_tsc_control) {
+	if (kvm_caps.has_tsc_control) {
 		debugfs_create_file("tsc-scaling-ratio", 0444,
 				    debugfs_dentry, vcpu,
 				    &vcpu_tsc_scaling_fops);

arch/x86/kvm/lapic.c

@@ -1603,7 +1603,7 @@ static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
 	 * that __delay() uses delay_tsc whenever the hardware has TSC, thus
 	 * always for VMX enabled hardware.
 	 */
-	if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+	if (vcpu->arch.tsc_scaling_ratio == kvm_caps.default_tsc_scaling_ratio) {
 		__delay(min(guest_cycles,
 			nsec_to_cycles(vcpu, timer_advance_ns)));
 	} else {

arch/x86/kvm/svm/nested.c

@@ -674,7 +674,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 
 	vmcb02->control.tsc_offset = vcpu->arch.tsc_offset;
 
-	if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) {
+	if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
 		WARN_ON(!svm->tsc_scaling_enabled);
 		nested_svm_update_tsc_ratio_msr(vcpu);
 	}
@@ -1031,7 +1031,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
 	}
 
-	if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) {
+	if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
 		WARN_ON(!svm->tsc_scaling_enabled);
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);

arch/x86/kvm/svm/svm.c

@@ -1285,7 +1285,7 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	svm_init_osvw(vcpu);
 	vcpu->arch.microcode_version = 0x01000065;
-	svm->tsc_ratio_msr = kvm_default_tsc_scaling_ratio;
+	svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio;
 
 	if (sev_es_guest(vcpu->kvm))
 		sev_es_vcpu_reset(svm);
@@ -4868,7 +4868,7 @@ static __init void svm_set_cpu_caps(void)
 {
 	kvm_set_cpu_caps();
 
-	supported_xss = 0;
+	kvm_caps.supported_xss = 0;
 
 	/* CPUID 0x80000001 and 0x8000000A (SVM features) */
 	if (nested) {
@@ -4944,7 +4944,8 @@ static __init int svm_hardware_setup(void)
 
 	init_msrpm_offsets();
 
-	supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
+	kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
+				     XFEATURE_MASK_BNDCSR);
 
 	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
 		kvm_enable_efer_bits(EFER_FFXSR);
@@ -4954,11 +4955,11 @@ static __init int svm_hardware_setup(void)
 			tsc_scaling = false;
 		} else {
 			pr_info("TSC scaling supported\n");
-			kvm_has_tsc_control = true;
+			kvm_caps.has_tsc_control = true;
 		}
 	}
-	kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX;
-	kvm_tsc_scaling_ratio_frac_bits = 32;
+	kvm_caps.max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX;
+	kvm_caps.tsc_scaling_ratio_frac_bits = 32;
 
 	tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
 

arch/x86/kvm/vmx/nested.c

@@ -2548,7 +2548,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			vmx_get_l2_tsc_multiplier(vcpu));
 
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-	if (kvm_has_tsc_control)
+	if (kvm_caps.has_tsc_control)
 		vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);
 
 	nested_vmx_transition_tlb_flush(vcpu, vmcs12, true);
@@ -4610,7 +4610,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-	if (kvm_has_tsc_control)
+	if (kvm_caps.has_tsc_control)
 		vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);
 
 	if (vmx->nested.l1_tpr_threshold != -1)

arch/x86/kvm/vmx/vmx.c

@@ -1717,7 +1717,7 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
 	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING))
 		return vmcs12->tsc_multiplier;
 
-	return kvm_default_tsc_scaling_ratio;
+	return kvm_caps.default_tsc_scaling_ratio;
 }
 
 static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
@@ -7544,7 +7544,7 @@ static __init void vmx_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_UMIP);
 
 	/* CPUID 0xD.1 */
-	supported_xss = 0;
+	kvm_caps.supported_xss = 0;
 	if (!cpu_has_vmx_xsaves())
 		kvm_cpu_cap_clear(X86_FEATURE_XSAVES);
 
@@ -7685,9 +7685,9 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
 		delta_tsc = 0;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
-	if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
+	if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio &&
 	    delta_tsc && u64_shl_div_u64(delta_tsc,
-				kvm_tsc_scaling_ratio_frac_bits,
+				kvm_caps.tsc_scaling_ratio_frac_bits,
 				vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc))
 		return -ERANGE;
 
@@ -8064,7 +8064,7 @@ static __init int hardware_setup(void)
 	}
 
 	if (!cpu_has_vmx_mpx())
-		supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
+		kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
 					     XFEATURE_MASK_BNDCSR);
 
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
@@ -8132,11 +8132,11 @@ static __init int hardware_setup(void)
 		enable_ipiv = false;
 
 	if (cpu_has_vmx_tsc_scaling())
-		kvm_has_tsc_control = true;
+		kvm_caps.has_tsc_control = true;
 
-	kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
-	kvm_tsc_scaling_ratio_frac_bits = 48;
-	kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection();
+	kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
+	kvm_caps.tsc_scaling_ratio_frac_bits = 48;
+	kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection();
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
@@ -8193,7 +8193,7 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit;
 	}
 
-	kvm_mce_cap_supported |= MCG_LMCE_P;
+	kvm_caps.supported_mce_cap |= MCG_LMCE_P;
 
 	if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST)
 		return -EINVAL;

arch/x86/kvm/x86.h

@@ -8,6 +8,25 @@
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
 
+struct kvm_caps {
+	/* control of guest tsc rate supported? */
+	bool has_tsc_control;
+	/* maximum supported tsc_khz for guests */
+	u32  max_guest_tsc_khz;
+	/* number of bits of the fractional part of the TSC scaling ratio */
+	u8   tsc_scaling_ratio_frac_bits;
+	/* maximum allowed value of TSC scaling ratio */
+	u64  max_tsc_scaling_ratio;
+	/* 1ull << kvm_caps.tsc_scaling_ratio_frac_bits */
+	u64  default_tsc_scaling_ratio;
+	/* bus lock detection supported? */
+	bool has_bus_lock_exit;
+
+	u64 supported_mce_cap;
+	u64 supported_xcr0;
+	u64 supported_xss;
+};
+
 void kvm_spurious_fault(void);
 
 #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check)		\
@@ -283,14 +302,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 
 extern u64 host_xcr0;
-extern u64 supported_xcr0;
 extern u64 host_xss;
-extern u64 supported_xss;
+
+extern struct kvm_caps kvm_caps;
+
 extern bool enable_pmu;
 
 static inline bool kvm_mpx_supported(void)
 {
-	return (supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
+	return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
 		== (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
 }