KVM: x86: Provide per VM capability for disabling PMU virtualization

Add a new capability, KVM_CAP_PMU_CAPABILITY, that takes a bitmask of
settings/features to allow userspace to configure PMU virtualization on
a per-VM basis.  For now, support a single flag, KVM_PMU_CAP_DISABLE,
to allow disabling PMU virtualization for a VM even when KVM is configured
with enable_pmu=true a module level.

To keep KVM simple, disallow changing VM's PMU configuration after vCPUs
have been created.
Signed-off-by: David Dunn <daviddunn@google.com>
Message-Id: <20220223225743.2703915-2-daviddunn@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -7643,3 +7643,25 @@ The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
 of the result of KVM_CHECK_EXTENSION.  KVM will forward to userspace
 the hypercalls whose corresponding bit is in the argument, and return
 ENOSYS for the others.
+
+8.35 KVM_CAP_PMU_CAPABILITY
+---------------------------
+
+:Capability KVM_CAP_PMU_CAPABILITY
+:Architectures: x86
+:Type: vm
+:Parameters: arg[0] is bitmask of PMU virtualization capabilities.
+:Returns 0 on success, -EINVAL when arg[0] contains invalid bits
+
+This capability alters PMU virtualization in KVM.
+
+Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
+PMU virtualization capabilities that can be adjusted on a VM.
+
+The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
+PMU virtualization capabilities to be applied to the VM.  This can
+only be invoked on a VM prior to the creation of VCPUs.
+
+At this time, KVM_PMU_CAP_DISABLE is the only capability.  Setting
+this capability will disable PMU virtualization for that VM.  Usermode
+should adjust CPUID leaf 0xA to reflect that the PMU is disabled.

arch/x86/include/asm/kvm_host.h

@@ -1147,6 +1147,7 @@ struct kvm_arch {
 	bool exception_payload_enabled;
 
 	bool bus_lock_detection_enabled;
+	bool enable_pmu;
 	/*
 	 * If exit_on_emulation_error is set, and the in-kernel instruction
 	 * emulator fails to emulate an instruction, allow userspace

arch/x86/kvm/svm/pmu.c

@@ -101,7 +101,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 {
 	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
 
-	if (!enable_pmu)
+	if (!vcpu->kvm->arch.enable_pmu)
 		return NULL;
 
 	switch (msr) {

arch/x86/kvm/vmx/pmu_intel.c

@@ -487,7 +487,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
-	if (!entry || !enable_pmu)
+	if (!entry || !vcpu->kvm->arch.enable_pmu)
 		return;
 	eax.full = entry->eax;
 	edx.full = entry->edx;

arch/x86/kvm/x86.c

@@ -110,6 +110,8 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
 #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE)
 
+#define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE
+
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
 
@@ -4330,6 +4332,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		if (r < sizeof(struct kvm_xsave))
 			r = sizeof(struct kvm_xsave);
 		break;
+	case KVM_CAP_PMU_CAPABILITY:
+		r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0;
+		break;
 	}
 	default:
 		break;
@@ -6004,6 +6009,18 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		kvm->arch.exit_on_emulation_error = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_PMU_CAPABILITY:
+		r = -EINVAL;
+		if (!enable_pmu || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK))
+			break;
+
+		mutex_lock(&kvm->lock);
+		if (!kvm->created_vcpus) {
+			kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE);
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -11586,6 +11603,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 	kvm->arch.guest_can_read_msr_platform_info = true;
+	kvm->arch.enable_pmu = enable_pmu;
 
 #if IS_ENABLED(CONFIG_HYPERV)
 	spin_lock_init(&kvm->arch.hv_root_tdp_lock);

include/uapi/linux/kvm.h

@@ -1142,6 +1142,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SYS_ATTRIBUTES 209
 #define KVM_CAP_PPC_AIL_MODE_3 210
 #define KVM_CAP_S390_MEM_OP_EXTENSION 211
+#define KVM_CAP_PMU_CAPABILITY 212
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1978,6 +1979,8 @@ struct kvm_dirty_gfn {
 #define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
 #define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
 
+#define KVM_PMU_CAP_DISABLE                    (1 << 0)
+
 /**
  * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
  * @flags: Some extra information for header, always 0 for now.

tools/include/uapi/linux/kvm.h

@@ -1135,6 +1135,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_XSAVE2 208
 #define KVM_CAP_SYS_ATTRIBUTES 209
 #define KVM_CAP_PPC_AIL_MODE_3 210
+#define KVM_CAP_S390_MEM_OP_EXTENSION 211
+#define KVM_CAP_PMU_CAPABILITY 212
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1971,6 +1973,8 @@ struct kvm_dirty_gfn {
 #define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
 #define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
 
+#define KVM_PMU_CAP_DISABLE                    (1 << 0)
+
 /**
  * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
  * @flags: Some extra information for header, always 0 for now.