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>
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.
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
{
struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
- if (!enable_pmu)
+ if (!vcpu->kvm->arch.enable_pmu)
return NULL;
switch (msr) {
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;
#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)
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;
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;
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);
#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
#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.
#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
#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.