To ultimately allow bpf programs attached to perf events to completely
suppress all of the effects of a perf event overflow (rather than just the
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_handler_t overflow_handler)
 #ifdef CONFIG_BPF_SYSCALL
 static inline bool uses_default_overflow_handler(struct perf_event *event)
 {
-	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) \
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_event *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);
 
 	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
@@ -10427,9 +10436,9 @@ static void perf_event_free_filter(struct perf_event *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 = {
 		.data = data,
@@ -10450,10 +10459,8 @@ static void bpf_overflow_handler(struct perf_event *event,
 	rcu_read_unlock();
 out:
 	__this_cpu_dec(bpf_prog_active);
-	if (!ret)
-		return;
 
-	event->orig_overflow_handler(event, data, regs);
+	return ret;
 }
 
 static int perf_event_set_bpf_handler(struct perf_event *event,
@@ -10489,8 +10496,6 @@ static int perf_event_set_bpf_handler(struct perf_event *event,
 
 	event->prog = prog;
 	event->bpf_cookie = bpf_cookie;
-	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
-	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
 	return 0;
 }
 
@@ -10501,7 +10506,6 @@ static void perf_event_free_bpf_handler(struct perf_event *event)
 	if (!prog)
 		return;
 
-	WRITE_ONCE(event->overflow_handler, event->orig_overflow_handler);
 	event->prog = NULL;
 	bpf_prog_put(prog);
 }
@@ -11975,13 +11979,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		overflow_handler = parent_event->overflow_handler;
 		context = parent_event->overflow_handler_context;
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING)
-		if (overflow_handler == bpf_overflow_handler) {
+		if (parent_event->prog) {
 			struct bpf_prog *prog = parent_event->prog;
 
 			bpf_prog_inc(prog);
 			event->prog = prog;
-			event->orig_overflow_handler =
-				parent_event->orig_overflow_handler;
 		}
 #endif
 	}
-- 
2.34.1

* 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 the
> 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

Could we reduce the #ifdeffery please?

On distros CONFIG_BPF_SYSCALL is almost always enabled, so it's not like 
this truly saves anything on real systems.

I'd suggest making the perf_event::prog and perf_event::bpf_cookie fields 
unconditional.

> +#ifdef CONFIG_BPF_SYSCALL
> +static int bpf_overflow_handler(struct perf_event *event,
> +				struct perf_sample_data *data,
> +				struct pt_regs *regs);
> +#endif

If the function definitions are misordered then first do a patch that moves 
the function earlier in the file, instead of slapping a random prototype 
into a random place.

> -	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 #ifdef would go away too - on !CONFIG_BPF_SYSCALL event->prog should 
always be NULL.

Please keep the #ifdeffery reduction and function-moving patches separate 
from these other changes.

Thanks,

	Ingo

On Wed, Apr 10, 2024 at 12:32 AM Ingo Molnar <mingo@kernel.org> wrote:
>
>
> * 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 the
> > 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
>
> Could we reduce the #ifdeffery please?

Not easily.

> On distros CONFIG_BPF_SYSCALL is almost always enabled, so it's not like
> this truly saves anything on real systems.
>
> I'd suggest making the perf_event::prog and perf_event::bpf_cookie fields
> unconditional.

That's not sufficient. See below.

> > +#ifdef CONFIG_BPF_SYSCALL
> > +static int bpf_overflow_handler(struct perf_event *event,
> > +                             struct perf_sample_data *data,
> > +                             struct pt_regs *regs);
> > +#endif
>
> If the function definitions are misordered then first do a patch that moves
> the function earlier in the file, instead of slapping a random prototype
> into a random place.

Ok.

> > -     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 #ifdef would go away too - on !CONFIG_BPF_SYSCALL event->prog should
> always be NULL.

bpf_overflow_handler() is also #ifdef CONFIG_BPF_SYSCALL. It uses
bpf_prog_active, so that would need to be moved out of the ifdef,
which would require moving the DEFINE_PER_CPU out of bpf/syscall.c ...
or I'd have to add a !CONFIG_BPF_SYSCALL definition of
bpf_overflow_handler() that only returns 1 and never actually gets
called because the condition short-circuits on event->prog. Neither
seems like it makes my patch or the code simpler, especially since
this weird ifdef-that-applies-only-to-the-condition goes away in Part
3 where I actually change the behavior.

It feels like the root of your objection is that CONFIG_BPF_SYSCALL
exists at all. I could remove it in a separate patch if there's
consensus about that.




> Please keep the #ifdeffery reduction and function-moving patches separate
> from these other changes.
>
> Thanks,
>
>         Ingo

- Kyle

On Thu, Apr 11, 2024 at 8:11 AM Kyle Huey <me@kylehuey.com> wrote:
>
> On Wed, Apr 10, 2024 at 12:32 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> >
> > * 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 the
> > > 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
> >
> > Could we reduce the #ifdeffery please?
>
> Not easily.
>
> > On distros CONFIG_BPF_SYSCALL is almost always enabled, so it's not like
> > this truly saves anything on real systems.
> >
> > I'd suggest making the perf_event::prog and perf_event::bpf_cookie fields
> > unconditional.
>
> That's not sufficient. See below.
>
> > > +#ifdef CONFIG_BPF_SYSCALL
> > > +static int bpf_overflow_handler(struct perf_event *event,
> > > +                             struct perf_sample_data *data,
> > > +                             struct pt_regs *regs);
> > > +#endif
> >
> > If the function definitions are misordered then first do a patch that moves
> > the function earlier in the file, instead of slapping a random prototype
> > into a random place.
>
> Ok.
>
> > > -     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 #ifdef would go away too - on !CONFIG_BPF_SYSCALL event->prog should
> > always be NULL.
>
> bpf_overflow_handler() is also #ifdef CONFIG_BPF_SYSCALL. It uses
> bpf_prog_active, so that would need to be moved out of the ifdef,
> which would require moving the DEFINE_PER_CPU out of bpf/syscall.c ...
> or I'd have to add a !CONFIG_BPF_SYSCALL definition of
> bpf_overflow_handler() that only returns 1 and never actually gets
> called because the condition short-circuits on event->prog. Neither
> seems like it makes my patch or the code simpler, especially since
> this weird ifdef-that-applies-only-to-the-condition goes away in Part
> 3 where I actually change the behavior.

After fiddling with this I think the stub definition of
bpf_overflow_handler() is fine. The other CONFIG_BPF_SYSCALL functions
in this file already have similar stubs. I'll send a new patch set.

- Kyle

> It feels like the root of your objection is that CONFIG_BPF_SYSCALL
> exists at all. I could remove it in a separate patch if there's
> consensus about that.
>
>
>
>
> > Please keep the #ifdeffery reduction and function-moving patches separate
> > from these other changes.
> >
> > Thanks,
> >
> >         Ingo
>
> - Kyle

On Wed, Feb 14, 2024 at 9:40 AM 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 the
> 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_handler_t overflow_handler)
>  #ifdef CONFIG_BPF_SYSCALL
>  static inline bool uses_default_overflow_handler(struct perf_event *event)
>  {
> -       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_event *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 = false;

#ifdef CONFIG_BPF_SYSCALL
    if (event->prog)
        skip = bpf_overflow_handler(event, data, regs) == 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 = 1;
> @@ -10427,9 +10436,9 @@ static void perf_event_free_filter(struct perf_event *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 = {
>                 .data = data,

[...]