path: root/arch/x86/kvm/svm/pmu.c
diff options
authorLike Xu <likexu@tencent.com>2022-01-11 15:38:23 +0800
committerPaolo Bonzini <pbonzini@redhat.com>2022-01-17 12:56:03 -0500
commit4732f2444acd9b7eabc744f20eb5cc9694c0bfbd (patch)
tree66dab7a1b1d173842630ce98a8e67a63f0fc2291 /arch/x86/kvm/svm/pmu.c
parentecebb966acaab2466d9857d1cc435ee1fc9eee50 (diff)
KVM: x86: Making the module parameter of vPMU more common
The new module parameter to control PMU virtualization should apply to Intel as well as AMD, for situations where userspace is not trusted. If the module parameter allows PMU virtualization, there could be a new KVM_CAP or guest CPUID bits whereby userspace can enable/disable PMU virtualization on a per-VM basis. If the module parameter does not allow PMU virtualization, there should be no userspace override, since we have no precedent for authorizing that kind of override. If it's false, other counter-based profiling features (such as LBR including the associated CPUID bits if any) will not be exposed. Change its name from "pmu" to "enable_pmu" as we have temporary variables with the same name in our code like "struct kvm_pmu *pmu". Fixes: b1d66dad65dc ("KVM: x86/svm: Add module param to control PMU virtualization") Suggested-by : Jim Mattson <jmattson@google.com> Signed-off-by: Like Xu <likexu@tencent.com> Message-Id: <20220111073823.21885-1-likexu@tencent.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kvm/svm/pmu.c')
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 12d8b301065a..5aa45f13b16d 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/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 (!pmu)
+ if (!enable_pmu)
return NULL;
switch (msr) {