On 7/31/2024 9:58 PM, Mingwei Zhang wrote:
> From: Xiong Zhang <xiong.y.zhang@xxxxxxxxxxxxxxx>
>
> Add correct PMU context switch at VM_entry/exit boundary.
>
> Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
> Signed-off-by: Xiong Zhang <xiong.y.zhang@xxxxxxxxxxxxxxx>
> Tested-by: Yongwei Ma <yongwei.ma@xxxxxxxxx>
> Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
> ---
> 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
