From: Kan Liang <[email protected]> On x86, NMI handler is the most important part which brings overhead for sampling. Adding a pmu specific overhead type PERF_PMU_SAMPLE_OVERHEAD for it.
For other architectures which may don't have NMI, the overhead type can be reused. Signed-off-by: Kan Liang <[email protected]> --- arch/x86/events/core.c | 8 +++++++- include/uapi/linux/perf_event.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 09ab36a..1e57ccf 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1478,8 +1478,10 @@ void perf_events_lapic_init(void) static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu.pmu_cpu_context); u64 start_clock; u64 finish_clock; + u64 clock; int ret; /* @@ -1492,8 +1494,12 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) start_clock = sched_clock(); ret = x86_pmu.handle_irq(regs); finish_clock = sched_clock(); + clock = finish_clock - start_clock; + perf_sample_event_took(clock); - perf_sample_event_took(finish_clock - start_clock); + /* calculate NMI overhead */ + cpuctx->overhead[PERF_PMU_SAMPLE_OVERHEAD].nr++; + cpuctx->overhead[PERF_PMU_SAMPLE_OVERHEAD].time += clock; return ret; } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7ba6d30..954b116 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1004,6 +1004,7 @@ enum perf_record_overhead_type { PERF_CORE_MUX_OVERHEAD = 0, PERF_CORE_SB_OVERHEAD, /* PMU specific */ + PERF_PMU_SAMPLE_OVERHEAD, PERF_OVERHEAD_MAX, }; -- 2.4.3
