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_guest_context_loaded, 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 | 19 ++++++++++++++++++- include/linux/perf_event.h | 5 +++++ kernel/events/core.c | 5 +++++ 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 8167f2230d3a..c0f6e294fcad 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -726,7 +726,7 @@ EXPORT_SYMBOL_GPL(x86_perf_guest_exit); * It will not be re-enabled in the NMI handler again, because enabled=0. After * handling the NMI, disable_all will be called, which will not change the * state either. If PMI hits after disable_all, the PMU is already disabled - * before entering NMI handler. The NMI handler will not change the state + * before entering NMI handler. The NMI handler will no change the state * either. * * So either situation is harmless. @@ -1749,6 +1749,23 @@ 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 x86_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 (perf_is_guest_context_loaded()) + return 0; /* * All PMUs/events that share this PMI handler should make sure to * increment active_events for their events. diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index acf16676401a..5da7de42954e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1736,6 +1736,7 @@ extern int perf_get_mediated_pmu(void); extern void perf_put_mediated_pmu(void); void perf_guest_enter(void); void perf_guest_exit(void); +bool perf_is_guest_context_loaded(void); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, @@ -1830,6 +1831,10 @@ static inline int perf_get_mediated_pmu(void) static inline void perf_put_mediated_pmu(void) { } static inline void perf_guest_enter(void) { } static inline void perf_guest_exit(void) { } +static inline bool perf_is_guest_context_loaded(void) +{ + return false; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c6daf5cc923..184d06c23391 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5895,6 +5895,11 @@ void perf_guest_exit(void) perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } +bool perf_is_guest_context_loaded(void) +{ + return __this_cpu_read(perf_in_guest); +} + /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block -- 2.45.0.rc1.225.g2a3ae87e7f-goog