| Message ID | 20220422075509.353942-16-weijiang.yang@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Introduce Architectural LBR for vPMU | expand |
On 4/22/2022 3:55 AM, Yang Weijiang wrote: > Arch LBR MSRs are xsave-supported, but they're operated as "independent" > xsave feature by PMU code, i.e., during thread/process context switch, > the MSRs are saved/restored with PMU specific code instead of generic > kernel fpu XSAVES/XRSTORS operation. During thread/process context switch, Linux perf still uses the XSAVES/XRSTORS operation to save/restore the LBR MSRs. Linux perf only manipulates these MSRs only when the xsave feature is not supported. Thanks, Kan > When vcpu guest/host fpu state swap > happens, Arch LBR MSRs won't be touched so access them directly. > > Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> > --- > arch/x86/kvm/vmx/pmu_intel.c | 10 ++++++++++ > 1 file changed, 10 insertions(+) > > diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c > index 79eecbffa07b..5f81644c4612 100644 > --- a/arch/x86/kvm/vmx/pmu_intel.c > +++ b/arch/x86/kvm/vmx/pmu_intel.c > @@ -431,6 +431,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) > case MSR_ARCH_LBR_CTL: > msr_info->data = vmcs_read64(GUEST_IA32_LBR_CTL); > return 0; > + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: > + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: > + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: > + rdmsrl(msr_info->index, msr_info->data); > + return 0; > default: > if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || > (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { > @@ -512,6 +517,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) > (data & ARCH_LBR_CTL_LBREN)) > intel_pmu_create_guest_lbr_event(vcpu); > return 0; > + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: > + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: > + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: > + wrmsrl(msr_info->index, msr_info->data); > + return 0; > default: > if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || > (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
On 4/28/2022 11:05 PM, Liang, Kan wrote: > > On 4/22/2022 3:55 AM, Yang Weijiang wrote: >> Arch LBR MSRs are xsave-supported, but they're operated as "independent" >> xsave feature by PMU code, i.e., during thread/process context switch, >> the MSRs are saved/restored with PMU specific code instead of generic >> kernel fpu XSAVES/XRSTORS operation. > During thread/process context switch, Linux perf still uses the > XSAVES/XRSTORS operation to save/restore the LBR MSRs. I meant Arch LBR MSRs are switched with perf_event_task_sched_out()/ perf_event_task_sched_in() instead of save_fpregs_to_fpstate()/ restore_fpregs_from_fpstate(). sorry for the confusion, will modify it a bit. > > Linux perf only manipulates these MSRs only when the xsave feature is > not supported. Exactly. > > Thanks, > Kan > >> When vcpu guest/host fpu state swap >> happens, Arch LBR MSRs won't be touched so access them directly. >> >> Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> >> --- >> arch/x86/kvm/vmx/pmu_intel.c | 10 ++++++++++ >> 1 file changed, 10 insertions(+) >> >> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c >> index 79eecbffa07b..5f81644c4612 100644 >> --- a/arch/x86/kvm/vmx/pmu_intel.c >> +++ b/arch/x86/kvm/vmx/pmu_intel.c >> @@ -431,6 +431,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) >> case MSR_ARCH_LBR_CTL: >> msr_info->data = vmcs_read64(GUEST_IA32_LBR_CTL); >> return 0; >> + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: >> + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: >> + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: >> + rdmsrl(msr_info->index, msr_info->data); >> + return 0; >> default: >> if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || >> (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { >> @@ -512,6 +517,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) >> (data & ARCH_LBR_CTL_LBREN)) >> intel_pmu_create_guest_lbr_event(vcpu); >> return 0; >> + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: >> + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: >> + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: >> + wrmsrl(msr_info->index, msr_info->data); >> + return 0; >> default: >> if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || >> (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 79eecbffa07b..5f81644c4612 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -431,6 +431,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_ARCH_LBR_CTL: msr_info->data = vmcs_read64(GUEST_IA32_LBR_CTL); return 0; + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: + rdmsrl(msr_info->index, msr_info->data); + return 0; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { @@ -512,6 +517,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (data & ARCH_LBR_CTL_LBREN)) intel_pmu_create_guest_lbr_event(vcpu); return 0; + case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31: + case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31: + case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31: + wrmsrl(msr_info->index, msr_info->data); + return 0; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
Arch LBR MSRs are xsave-supported, but they're operated as "independent" xsave feature by PMU code, i.e., during thread/process context switch, the MSRs are saved/restored with PMU specific code instead of generic kernel fpu XSAVES/XRSTORS operation. When vcpu guest/host fpu state swap happens, Arch LBR MSRs won't be touched so access them directly. Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> --- arch/x86/kvm/vmx/pmu_intel.c | 10 ++++++++++ 1 file changed, 10 insertions(+)