On Tue, Jul 19, 2016 at 4:20 PM, Brendan Gregg <bgr...@netflix.com> wrote:
> When perf is performing hrtimer-based sampling, this tracepoint can be used
> by BPF to run additional logic on each sample. For example, BPF can fetch
> stack traces and frequency count them in kernel context, for an efficient
> profiler.
Any comments on this patch? Thanks,
Brendan
>
> Signed-off-by: Brendan Gregg <bgr...@netflix.com>
> Cc: Alexei Starovoitov <a...@kernel.org>
> Cc: Wang Nan <wangn...@huawei.com>
> ---
> include/trace/events/perf.h | 29 +++++++++++++++++++++++++++++
> kernel/events/core.c | 5 +++++
> 2 files changed, 34 insertions(+)
> create mode 100644 include/trace/events/perf.h
>
> diff --git a/include/trace/events/perf.h b/include/trace/events/perf.h
> new file mode 100644
> index 0000000..461770d
> --- /dev/null
> +++ b/include/trace/events/perf.h
> @@ -0,0 +1,29 @@
> +#undef TRACE_SYSTEM
> +#define TRACE_SYSTEM perf
> +
> +#if !defined(_TRACE_PERF_H) || defined(TRACE_HEADER_MULTI_READ)
> +#define _TRACE_PERF_H
> +
> +#include <linux/tracepoint.h>
> +
> +TRACE_EVENT(perf_hrtimer,
> + TP_PROTO(struct pt_regs *regs, struct perf_event *event),
> +
> + TP_ARGS(regs, event),
> +
> + TP_STRUCT__entry(
> + __field(struct pt_regs *, regs)
> + __field(struct perf_event *, event)
> + ),
> +
> + TP_fast_assign(
> + __entry->regs = regs;
> + __entry->event = event;
> + ),
> +
> + TP_printk("regs=%p evt=%p", __entry->regs, __entry->event)
> +);
> +#endif /* _TRACE_PERF_H */
> +
> +/* This part must be outside protection */
> +#include <trace/define_trace.h>
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 79dae18..0d843a7 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -51,6 +51,9 @@
>
> #include <asm/irq_regs.h>
>
> +#define CREATE_TRACE_POINTS
> +#include <trace/events/perf.h>
> +
> typedef int (*remote_function_f)(void *);
>
> struct remote_function_call {
> @@ -8036,6 +8039,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct
> hrtimer *hrtimer)
> perf_sample_data_init(&data, 0, event->hw.last_period);
> regs = get_irq_regs();
>
> + trace_perf_hrtimer(regs, event);
> +
> if (regs && !perf_exclude_event(event, regs)) {
> if (!(event->attr.exclude_idle && is_idle_task(current)))
> if (__perf_event_overflow(event, 1, &data, regs))
> --
> 2.7.4
>
