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.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-dlfilter.txt

@@ -36,16 +36,17 @@ const struct perf_dlfilter_fns perf_dlfilter_fns;
 int start(void **data, void *ctx);
 int stop(void *data, void *ctx);
 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);
 ----
 
 If implemented, 'start' will be called at the beginning, before any
-calls to 'filter_event' . Return 0 to indicate success,
+calls to 'filter_event' or 'filter_event_early'. Return 0 to indicate success,
 or return a negative error code. '*data' can be assigned for use by other
 functions. 'ctx' is needed for calls to perf_dlfilter_fns, but most
 perf_dlfilter_fns are not valid when called from 'start'.
 
 If implemented, 'stop' will be called at the end, after any calls to
-'filter_event'. Return 0 to indicate success, or
+'filter_event' or 'filter_event_early'. Return 0 to indicate success, or
 return a negative error code. 'data' is set by 'start'. 'ctx' is needed
 for calls to perf_dlfilter_fns, but most perf_dlfilter_fns are not valid
 when called from 'stop'.
@@ -55,10 +56,13 @@ Return 0 to keep the sample event, 1 to filter it out, or return a negative
 error code. 'data' is set by 'start'. 'ctx' is needed for calls to
 'perf_dlfilter_fns'.
 
+'filter_event_early' is the same as 'filter_event' except it is called before
+internal filtering.
+
 The perf_dlfilter_sample structure
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-'filter_event' is passed a perf_dlfilter_sample
+'filter_event' and 'filter_event_early' are passed a perf_dlfilter_sample
 structure, which contains the following fields:
 [source,c]
 ----
@@ -105,7 +109,8 @@ The perf_dlfilter_fns structure
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 The 'perf_dlfilter_fns' structure is populated with function pointers when the
-file is loaded. The functions can be called by 'filter_event'.
+file is loaded. The functions can be called by 'filter_event' or
+'filter_event_early'.
 
 [source,c]
 ----

tools/perf/builtin-script.c

@@ -2179,9 +2179,20 @@ static int process_sample_event(struct perf_tool *tool,
 	struct addr_location addr_al;
 	int ret = 0;
 
+	/* Set thread to NULL to indicate addr_al and al are not initialized */
+	addr_al.thread = NULL;
+	al.thread = NULL;
+
+	ret = dlfilter__filter_event_early(dlfilter, event, sample, evsel, machine, &al, &addr_al);
+	if (ret) {
+		if (ret > 0)
+			ret = 0;
+		goto out_put;
+	}
+
 	if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num,
 					  sample->time)) {
-		return 0;
+		goto out_put;
 	}
 
 	if (debug_mode) {
@@ -2192,24 +2203,22 @@ static int process_sample_event(struct perf_tool *tool,
 			nr_unordered++;
 		}
 		last_timestamp = sample->time;
-		return 0;
+		goto out_put;
 	}
 
 	if (filter_cpu(sample))
-		return 0;
+		goto out_put;
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
-		return -1;
+		ret = -1;
+		goto out_put;
 	}
 
 	if (al.filtered)
 		goto out_put;
 
-	/* Set thread to NULL to indicate addr_al is not initialized */
-	addr_al.thread = NULL;
-
 	if (!show_event(sample, evsel, al.thread, &al, &addr_al))
 		goto out_put;
 
@@ -2238,6 +2247,7 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 out_put:
+	if (al.thread)
 		addr_location__put(&al);
 	return ret;
 }

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;
@@ -322,6 +324,9 @@ int dlfilter__do_filter_event(struct dlfilter *d,
 
 	d->ctx_valid = true;
 
+	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;

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

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