On 8/1/2024 12:58 PM, Mingwei Zhang wrote:
> If a guest PMI is delivered after VM-exit, the KVM maskable interrupt will
> be held pending until EFLAGS.IF is set. In the meantime, if the logical
> processor receives an NMI for any reason at all, perf_event_nmi_handler()
> will be invoked. If there is any active perf event anywhere on the system,
> x86_pmu_handle_irq() will be invoked, and it will clear
> IA32_PERF_GLOBAL_STATUS. By the time KVM's PMI handler is invoked, it will
> be a mystery which counter(s) overflowed.
>
> When LVTPC is using KVM PMI vecotr, PMU is owned by guest, Host NMI let
> x86_pmu_handle_irq() run, x86_pmu_handle_irq() restore PMU vector to NMI
> and clear IA32_PERF_GLOBAL_STATUS, this breaks guest vPMU passthrough
> environment.
>
> So modify perf_event_nmi_handler() to check perf_in_guest per cpu variable,
> and if so, to simply return without calling x86_pmu_handle_irq().
>
> Suggested-by: Jim Mattson <jmattson@xxxxxxxxxx>
> Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
> Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
> ---
> arch/x86/events/core.c | 27 +++++++++++++++++++++++++--
> 1 file changed, 25 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index b17ef8b6c1a6..cb5d8f5fd9ce 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -52,6 +52,8 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
> .pmu = &pmu,
> };
>
> +DEFINE_PER_CPU(bool, pmi_vector_is_nmi) = true;
> +
> DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key);
> DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key);
> DEFINE_STATIC_KEY_FALSE(perf_is_hybrid);
> @@ -1733,6 +1735,24 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
> u64 finish_clock;
> int ret;
>
> + /*
> + * When guest pmu context is loaded this handler should be forbidden from
> + * running, the reasons are:
> + * 1. After perf_guest_enter() is called, and before cpu enter into
> + * non-root mode, NMI could happen, but x86_pmu_handle_irq() restore PMU
> + * to use NMI vector, which destroy KVM PMI vector setting.
> + * 2. When VM is running, host NMI other than PMI causes VM exit, KVM will
> + * call host NMI handler (vmx_vcpu_enter_exit()) first before KVM save
> + * guest PMU context (kvm_pmu_save_pmu_context()), as x86_pmu_handle_irq()
> + * clear global_status MSR which has guest status now, then this destroy
> + * guest PMU status.
> + * 3. After VM exit, but before KVM save guest PMU context, host NMI other
> + * than PMI could happen, x86_pmu_handle_irq() clear global_status MSR
> + * which has guest status now, then this destroy guest PMU status.
> + */
> + if (!this_cpu_read(pmi_vector_is_nmi))
> + return 0;
0 -> NMI_DONE
> +
> /*
> * All PMUs/events that share this PMI handler should make sure to
> * increment active_events for their events.
> @@ -2675,11 +2695,14 @@ static bool x86_pmu_filter(struct pmu *pmu, int cpu)
>
> static void x86_pmu_switch_interrupt(bool enter, u32 guest_lvtpc)
> {
> - if (enter)
> + if (enter) {
> apic_write(APIC_LVTPC, APIC_DM_FIXED | KVM_GUEST_PMI_VECTOR |
> (guest_lvtpc & APIC_LVT_MASKED));
> - else
> + this_cpu_write(pmi_vector_is_nmi, false);
> + } else {
> apic_write(APIC_LVTPC, APIC_DM_NMI);
> + this_cpu_write(pmi_vector_is_nmi, true);
> + }
> }
>
> static struct pmu pmu = {
