On Wed, Mar 06, 2024, Sean Christopherson wrote:
> Snapshot VMX's LBR capabilities once during module initialization instead
> of calling into perf every time a vCPU reconfigures its vPMU. This will
> allow massaging the LBR capabilities, e.g. if the CPU doesn't support
> callstacks, without having to remember to update multiple locations.
>
> Opportunistically tag vmx_get_perf_capabilities() with __init, as it's
> only called from vmx_set_cpu_caps().
>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> ---
Reviewed-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
> arch/x86/kvm/vmx/pmu_intel.c | 2 +-
> arch/x86/kvm/vmx/vmx.c | 9 +++++----
> arch/x86/kvm/vmx/vmx.h | 2 ++
> 3 files changed, 8 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> index 12ade343a17e..be40474de6e4 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -535,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
> perf_capabilities = vcpu_get_perf_capabilities(vcpu);
> if (cpuid_model_is_consistent(vcpu) &&
> (perf_capabilities & PMU_CAP_LBR_FMT))
> - x86_perf_get_lbr(&lbr_desc->records);
> + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps));
> else
> lbr_desc->records.nr = 0;
>
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 7a74388f9ecf..2a7cd66988a5 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -217,6 +217,8 @@ module_param(ple_window_max, uint, 0444);
> int __read_mostly pt_mode = PT_MODE_SYSTEM;
> module_param(pt_mode, int, S_IRUGO);
>
> +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps;
> +
> static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
> static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
> static DEFINE_MUTEX(vmx_l1d_flush_mutex);
> @@ -7844,10 +7846,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
> vmx_update_exception_bitmap(vcpu);
> }
>
> -static u64 vmx_get_perf_capabilities(void)
> +static __init u64 vmx_get_perf_capabilities(void)
> {
> u64 perf_cap = PMU_CAP_FW_WRITES;
> - struct x86_pmu_lbr lbr;
> u64 host_perf_cap = 0;
>
> if (!enable_pmu)
> @@ -7857,8 +7858,8 @@ static u64 vmx_get_perf_capabilities(void)
> rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
>
> if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
> - x86_perf_get_lbr(&lbr);
> - if (lbr.nr)
> + x86_perf_get_lbr(&vmx_lbr_caps);
> + if (vmx_lbr_caps.nr)
> perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
> }
>
> diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
> index 65786dbe7d60..cc10df53966e 100644
> --- a/arch/x86/kvm/vmx/vmx.h
> +++ b/arch/x86/kvm/vmx/vmx.h
> @@ -109,6 +109,8 @@ struct lbr_desc {
> bool msr_passthrough;
> };
>
> +extern struct x86_pmu_lbr vmx_lbr_caps;
> +
> /*
> * The nested_vmx structure is part of vcpu_vmx, and holds information we need
> * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
> --
> 2.44.0.278.ge034bb2e1d-goog
>
