| Message ID | 20240801045907.4010984-42-mizhang@google.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Mediated Passthrough vPMU 3.0 for x86 | expand |
On 7/31/2024 9:58 PM, Mingwei Zhang wrote: > From: Xiong Zhang <xiong.y.zhang@linux.intel.com> > > Add correct PMU context switch at VM_entry/exit boundary. > > Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com> > Signed-off-by: Xiong Zhang <xiong.y.zhang@linux.intel.com> > Tested-by: Yongwei Ma <yongwei.ma@intel.com> > Signed-off-by: Mingwei Zhang <mizhang@google.com> > --- > arch/x86/kvm/x86.c | 6 ++++++ > 1 file changed, 6 insertions(+) > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index dd6d2c334d90..70274c0da017 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -11050,6 +11050,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) > set_debugreg(0, 7); > } > > + if (is_passthrough_pmu_enabled(vcpu)) > + kvm_pmu_restore_pmu_context(vcpu); Suggest to move is_passthrough_pmu_enabled() into the PMU restore API to keep x86.c clean. It's up to PMU to decide in what scenarios it needs to do context switch. > + > guest_timing_enter_irqoff(); > > for (;;) { > @@ -11078,6 +11081,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) > ++vcpu->stat.exits; > } > > + if (is_passthrough_pmu_enabled(vcpu)) > + kvm_pmu_save_pmu_context(vcpu); ditto. > /* > * Do this here before restoring debug registers on the host. And > * since we do this before handling the vmexit, a DR access vmexit
On 10/25/2024 3:57 AM, Chen, Zide wrote: > > On 7/31/2024 9:58 PM, Mingwei Zhang wrote: >> From: Xiong Zhang <xiong.y.zhang@linux.intel.com> >> >> Add correct PMU context switch at VM_entry/exit boundary. >> >> Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com> >> Signed-off-by: Xiong Zhang <xiong.y.zhang@linux.intel.com> >> Tested-by: Yongwei Ma <yongwei.ma@intel.com> >> Signed-off-by: Mingwei Zhang <mizhang@google.com> >> --- >> arch/x86/kvm/x86.c | 6 ++++++ >> 1 file changed, 6 insertions(+) >> >> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c >> index dd6d2c334d90..70274c0da017 100644 >> --- a/arch/x86/kvm/x86.c >> +++ b/arch/x86/kvm/x86.c >> @@ -11050,6 +11050,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) >> set_debugreg(0, 7); >> } >> >> + if (is_passthrough_pmu_enabled(vcpu)) >> + kvm_pmu_restore_pmu_context(vcpu); > Suggest to move is_passthrough_pmu_enabled() into the PMU restore API to > keep x86.c clean. It's up to PMU to decide in what scenarios it needs to > do context switch. Agree. > >> + >> guest_timing_enter_irqoff(); >> >> for (;;) { >> @@ -11078,6 +11081,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) >> ++vcpu->stat.exits; >> } >> >> + if (is_passthrough_pmu_enabled(vcpu)) >> + kvm_pmu_save_pmu_context(vcpu); > ditto. > >> /* >> * Do this here before restoring debug registers on the host. And >> * since we do this before handling the vmexit, a DR access vmexit
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index dd6d2c334d90..70274c0da017 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11050,6 +11050,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(0, 7); } + if (is_passthrough_pmu_enabled(vcpu)) + kvm_pmu_restore_pmu_context(vcpu); + guest_timing_enter_irqoff(); for (;;) { @@ -11078,6 +11081,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) ++vcpu->stat.exits; } + if (is_passthrough_pmu_enabled(vcpu)) + kvm_pmu_save_pmu_context(vcpu); + /* * Do this here before restoring debug registers on the host. And * since we do this before handling the vmexit, a DR access vmexit