diff options
| author | Like Xu <likexu@tencent.com> | 2022-01-11 15:38:23 +0800 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2022-01-17 12:56:03 -0500 |
| commit | 4732f2444acd9b7eabc744f20eb5cc9694c0bfbd (patch) | |
| tree | 66dab7a1b1d173842630ce98a8e67a63f0fc2291 /arch/x86/kvm/x86.h | |
| parent | ecebb966acaab2466d9857d1cc435ee1fc9eee50 (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/x86.h')
| -rw-r--r-- | arch/x86/kvm/x86.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index da7031e80f23..1ebd5a7594da 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -336,6 +336,7 @@ extern u64 host_xcr0; extern u64 supported_xcr0; extern u64 host_xss; extern u64 supported_xss; +extern bool enable_pmu; static inline bool kvm_mpx_supported(void) { |