Received-SPF: pass (google.com: domain of linux-kernel+bounces-67882-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240214173950.18570-1-khuey@kylehuey.com> <20240214173950.18570-2-khuey@kylehuey.com>
In-Reply-To: <20240214173950.18570-2-khuey@kylehuey.com>
From: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Date: Thu, 15 Feb 2024 16:11:42 -0800
Message-ID: <CAEf4BzZu_7XRqKcJnM7qwaG=RPDv6fq8=qP4q-gVTkAP=uV=UQ@mail.gmail.com>
Subject: Re: [RESEND PATCH v5 1/4] perf/bpf: Call bpf handler directly, not
 through overflow machinery
To: Kyle Huey <me@kylehuey.com>
Cc: Kyle Huey <khuey@kylehuey.com>, linux-kernel@vger.kernel.org, 
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>, Marco Elver <elver@google.com>, 
	Yonghong Song <yonghong.song@linux.dev>, Peter Zijlstra <peterz@infradead.org>, 
	Ingo Molnar <mingo@redhat.com>, Arnaldo Carvalho de Melo <acme@kernel.org>, 
	"Robert O'Callahan" <robert@ocallahan.org>, Song Liu <song@kernel.org>, 
	Mark Rutland <mark.rutland@arm.com>, 
	Alexander Shishkin <alexander.shishkin@linux.intel.com>, Ian Rogers <irogers@google.com>, 
	Adrian Hunter <adrian.hunter@intel.com>, linux-perf-users@vger.kernel.org, 
	bpf@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Feb 14, 2024 at 9:40=E2=80=AFAM Kyle Huey <me@kylehuey.com> wrote:
>
> To ultimately allow bpf programs attached to perf events to completely
> suppress all of the effects of a perf event overflow (rather than just th=
e
> sample output, as they do today), call bpf_overflow_handler() from
> __perf_event_overflow() directly rather than modifying struct perf_event'=
s
> overflow_handler. Return the bpf program's return value from
> bpf_overflow_handler() so that __perf_event_overflow() knows how to
> proceed. Remove the now unnecessary orig_overflow_handler from struct
> perf_event.
>
> This patch is solely a refactoring and results in no behavior change.
>
> Signed-off-by: Kyle Huey <khuey@kylehuey.com>
> Suggested-by: Namhyung Kim <namhyung@kernel.org>
> Acked-by: Song Liu <song@kernel.org>
> Acked-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  include/linux/perf_event.h |  6 +-----
>  kernel/events/core.c       | 28 +++++++++++++++-------------
>  2 files changed, 16 insertions(+), 18 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index d2a15c0c6f8a..c7f54fd74d89 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -810,7 +810,6 @@ struct perf_event {
>         perf_overflow_handler_t         overflow_handler;
>         void                            *overflow_handler_context;
>  #ifdef CONFIG_BPF_SYSCALL
> -       perf_overflow_handler_t         orig_overflow_handler;
>         struct bpf_prog                 *prog;
>         u64                             bpf_cookie;
>  #endif
> @@ -1357,10 +1356,7 @@ __is_default_overflow_handler(perf_overflow_handle=
r_t overflow_handler)
>  #ifdef CONFIG_BPF_SYSCALL
>  static inline bool uses_default_overflow_handler(struct perf_event *even=
t)
>  {
> -       if (likely(is_default_overflow_handler(event)))
> -               return true;
> -
> -       return __is_default_overflow_handler(event->orig_overflow_handler=
);
> +       return is_default_overflow_handler(event);
>  }
>  #else
>  #define uses_default_overflow_handler(event) \

and so in both cases uses_default_overflow_handler() is now just
is_default_overflow_handler(), right? So we can clean all this up
quite a bit?

> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index f0f0f71213a1..24a718e7eb98 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -9548,6 +9548,12 @@ static inline bool sample_is_allowed(struct perf_e=
vent *event, struct pt_regs *r
>         return true;
>  }
>
> +#ifdef CONFIG_BPF_SYSCALL
> +static int bpf_overflow_handler(struct perf_event *event,
> +                               struct perf_sample_data *data,
> +                               struct pt_regs *regs);
> +#endif
> +
>  /*
>   * Generic event overflow handling, sampling.
>   */
> @@ -9617,7 +9623,10 @@ static int __perf_event_overflow(struct perf_event=
 *event,
>                 irq_work_queue(&event->pending_irq);
>         }
>
> -       READ_ONCE(event->overflow_handler)(event, data, regs);
> +#ifdef CONFIG_BPF_SYSCALL
> +       if (!(event->prog && !bpf_overflow_handler(event, data, regs)))
> +#endif
> +               READ_ONCE(event->overflow_handler)(event, data, regs);

This is quite hard to follow... And that CONFIG_BPF_SYSCALL check
breaking apart that if statement is not great. Maybe something like:


bool skip_def_handler =3D false;

#ifdef CONFIG_BPF_SYSCALL
    if (event->prog)
        skip =3D bpf_overflow_handler(event, data, regs) =3D=3D 0;
#endif
    if (!skip_def_handler)
        READ_ONCE(event->overflow_handler)(event, data, regs);

we can of course invert "skip" to be "run" and invert conditions, if
that's easier to follow

>
>         if (*perf_event_fasync(event) && event->pending_kill) {
>                 event->pending_wakeup =3D 1;
> @@ -10427,9 +10436,9 @@ static void perf_event_free_filter(struct perf_ev=
ent *event)
>  }
>
>  #ifdef CONFIG_BPF_SYSCALL
> -static void bpf_overflow_handler(struct perf_event *event,
> -                                struct perf_sample_data *data,
> -                                struct pt_regs *regs)
> +static int bpf_overflow_handler(struct perf_event *event,
> +                               struct perf_sample_data *data,
> +                               struct pt_regs *regs)
>  {
>         struct bpf_perf_event_data_kern ctx =3D {
>                 .data =3D data,

[...]