perf script: Add dlfilter__filter_event_early()

filter_event_early() can be more than 30% faster than filter_event()
because it is called before internal filtering. In other respects it
is the same as filter_event(), except that it will be passed events
that have yet to be filtered out.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210627131818.810-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 32 insertions, 4 deletions

diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 03c4bf150656..e93c49c07999 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -175,6 +175,7 @@ static int dlfilter__open(struct dlfilter *d)
 	}
 	d->start = dlsym(d->handle, "start");
 	d->filter_event = dlsym(d->handle, "filter_event");
+	d->filter_event_early = dlsym(d->handle, "filter_event_early");
 	d->stop = dlsym(d->handle, "stop");
 	d->fns = dlsym(d->handle, "perf_dlfilter_fns");
 	if (d->fns)
@@ -251,7 +252,8 @@ int dlfilter__do_filter_event(struct dlfilter *d,
 			      struct evsel *evsel,
 			      struct machine *machine,
 			      struct addr_location *al,
-			      struct addr_location *addr_al)
+			      struct addr_location *addr_al,
+			      bool early)
 {
 	struct perf_dlfilter_sample d_sample;
 	struct perf_dlfilter_al d_ip_al;
@@ -322,7 +324,10 @@ int dlfilter__do_filter_event(struct dlfilter *d,
 
 	d->ctx_valid = true;
 
-	ret = d->filter_event(d->data, &d_sample, d);
+	if (early)
+		ret = d->filter_event_early(d->data, &d_sample, d);
+	else
+		ret = d->filter_event(d->data, &d_sample, d);
 
 	d->ctx_valid = false;
 
diff --git a/tools/perf/util/dlfilter.h b/tools/perf/util/dlfilter.h
index 22b7636028dd..a994560e563d 100644
--- a/tools/perf/util/dlfilter.h
+++ b/tools/perf/util/dlfilter.h
@@ -40,6 +40,9 @@ struct dlfilter {
 	int (*filter_event)(void *data,
 			    const struct perf_dlfilter_sample *sample,
 			    void *ctx);
+	int (*filter_event_early)(void *data,
+				  const struct perf_dlfilter_sample *sample,
+				  void *ctx);
 
 	struct perf_dlfilter_fns *fns;
 };
@@ -54,7 +57,8 @@ int dlfilter__do_filter_event(struct dlfilter *d,
 			      struct evsel *evsel,
 			      struct machine *machine,
 			      struct addr_location *al,
-			      struct addr_location *addr_al);
+			      struct addr_location *addr_al,
+			      bool early);
 
 void dlfilter__cleanup(struct dlfilter *d);
 
@@ -68,7 +72,20 @@ static inline int dlfilter__filter_event(struct dlfilter *d,
 {
 	if (!d || !d->filter_event)
 		return 0;
-	return dlfilter__do_filter_event(d, event, sample, evsel, machine, al, addr_al);
+	return dlfilter__do_filter_event(d, event, sample, evsel, machine, al, addr_al, false);
+}
+
+static inline int dlfilter__filter_event_early(struct dlfilter *d,
+					       union perf_event *event,
+					       struct perf_sample *sample,
+					       struct evsel *evsel,
+					       struct machine *machine,
+					       struct addr_location *al,
+					       struct addr_location *addr_al)
+{
+	if (!d || !d->filter_event_early)
+		return 0;
+	return dlfilter__do_filter_event(d, event, sample, evsel, machine, al, addr_al, true);
 }
 
 #endif
diff --git a/tools/perf/util/perf_dlfilter.h b/tools/perf/util/perf_dlfilter.h
index 82833ee8680d..f7a847fdee59 100644
--- a/tools/perf/util/perf_dlfilter.h
+++ b/tools/perf/util/perf_dlfilter.h
@@ -120,4 +120,10 @@ int stop(void *data, void *ctx);
  */
 int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
 
+/*
+ * The same as 'filter_event' except it is called before internal
+ * filtering.
+ */
+int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+
 #endif