perf tools: Print lost samples due to BPF filter

Print the actual dropped sample count in the event stat.

$ sudo perf record -o- -e cycles --filter 'period < 10000' \
-e instructions --filter 'ip > 0x8000000000000000' perf test -w noploop | \
perf report --stat -i-
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.058 MB - ]

Aggregated stats:
TOTAL events: 469
MMAP events: 268 (57.1%)
COMM events: 2 ( 0.4%)
EXIT events: 1 ( 0.2%)
SAMPLE events: 16 ( 3.4%)
MMAP2 events: 22 ( 4.7%)
LOST_SAMPLES events: 2 ( 0.4%)
KSYMBOL events: 89 (19.0%)
BPF_EVENT events: 39 ( 8.3%)
ATTR events: 2 ( 0.4%)
FINISHED_ROUND events: 1 ( 0.2%)
ID_INDEX events: 1 ( 0.2%)
THREAD_MAP events: 1 ( 0.2%)
CPU_MAP events: 1 ( 0.2%)
EVENT_UPDATE events: 2 ( 0.4%)
TIME_CONV events: 1 ( 0.2%)
FEATURE events: 20 ( 4.3%)
FINISHED_INIT events: 1 ( 0.2%)
cycles stats:
SAMPLE events: 2
LOST_SAMPLES (BPF) events: 4010
instructions stats:
SAMPLE events: 14
LOST_SAMPLES (BPF) events: 3990

Signed-off-by: Namhyung Kim <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: KP Singh <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Song Liu <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-report.c

···
 
 	evsel = evlist__id2evsel(rep->session->evlist, sample->id);
 	if (evsel) {
-		hists__inc_nr_lost_samples(evsel__hists(evsel),
-					   event->lost_samples.lost);
+		struct hists *hists = evsel__hists(evsel);
+		u32 count = event->lost_samples.lost;
+
+		if (event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)
+			hists__inc_nr_dropped_samples(hists, count);
+		else
+			hists__inc_nr_lost_samples(hists, count);
 	}
 	return 0;
 }

tools/perf/ui/stdio/hist.c

···
 			continue;
 
 		if (i && total) {
-			ret += fprintf(fp, "%16s events: %10d  (%4.1f%%)\n",
+			ret += fprintf(fp, "%20s events: %10d  (%4.1f%%)\n",
 				       name, stats->nr_events[i],
 				       100.0 * stats->nr_events[i] / total);
 		} else {
-			ret += fprintf(fp, "%16s events: %10d\n",
+			ret += fprintf(fp, "%20s events: %10d\n",
 				       name, stats->nr_events[i]);
 		}
 	}

tools/perf/util/events_stats.h

···
  * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
  * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
  * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
- * all struct perf_record_lost_samples.lost fields reported.
+ * all struct perf_record_lost_samples.lost fields reported without setting the
+ * misc field in the header.
+ *
+ * The BPF program can discard samples according to the filter expressions given
+ * by the user.  This number is kept in a BPF map and dumped at the end of perf
+ * record in a PERF_RECORD_LOST_SAMPLES event.  To differentiate it from other
+ * lost samples, perf tools sets PERF_RECORD_MISC_LOST_SAMPLES_BPF flag in the
+ * header.misc field.  The number of dropped-samples events is stored in
+ * .nr_events[PERF_RECORD_LOST_SAMPLES] while total_dropped_samples tells
+ * exactly how many samples the BPF program in fact dropped, i.e. it is the sum
+ * of all struct perf_record_lost_samples.lost fields reported with the misc
+ * field set in the header.
  *
  * The total_period is needed because by default auto-freq is used, so
  * multiplying nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
···
 struct events_stats {
 	u64 total_lost;
 	u64 total_lost_samples;
+	u64 total_dropped_samples;
 	u64 total_aux_lost;
 	u64 total_aux_partial;
 	u64 total_aux_collision;
···
 	u32 nr_samples;
 	u32 nr_non_filtered_samples;
 	u32 nr_lost_samples;
+	u32 nr_dropped_samples;
 };
 
 void events_stats__inc(struct events_stats *stats, u32 type);

tools/perf/util/hist.c

···
 	hists->stats.nr_lost_samples += lost;
 }
 
+void hists__inc_nr_dropped_samples(struct hists *hists, u32 lost)
+{
+	hists->stats.nr_dropped_samples += lost;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
···
 
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
+		u64 total_samples = hists->stats.nr_samples;
 
-		if (symbol_conf.skip_empty && !hists->stats.nr_samples &&
-		    !hists->stats.nr_lost_samples)
+		total_samples += hists->stats.nr_lost_samples;
+		total_samples += hists->stats.nr_dropped_samples;
+
+		if (symbol_conf.skip_empty && total_samples == 0)
 			continue;
 
 		ret += fprintf(fp, "%s stats:\n", evsel__name(pos));
 		if (hists->stats.nr_samples)
-			ret += fprintf(fp, "%16s events: %10d\n",
+			ret += fprintf(fp, "%20s events: %10d\n",
 				       "SAMPLE", hists->stats.nr_samples);
 		if (hists->stats.nr_lost_samples)
-			ret += fprintf(fp, "%16s events: %10d\n",
+			ret += fprintf(fp, "%20s events: %10d\n",
 				       "LOST_SAMPLES", hists->stats.nr_lost_samples);
+		if (hists->stats.nr_dropped_samples)
+			ret += fprintf(fp, "%20s events: %10d\n",
+				       "LOST_SAMPLES (BPF)", hists->stats.nr_dropped_samples);
 	}
 
 	return ret;

tools/perf/util/hist.h

···
 void hists__inc_nr_events(struct hists *hists);
 void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void hists__inc_nr_lost_samples(struct hists *hists, u32 lost);
+void hists__inc_nr_dropped_samples(struct hists *hists, u32 lost);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,

tools/perf/util/machine.c

···
 int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 					union perf_event *event, struct perf_sample *sample)
 {
-	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n",
-		    sample->id, event->lost_samples.lost);
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "%s\n",
+		    sample->id, event->lost_samples.lost,
+		    event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF ? " (BPF)" : "");
 	return 0;
 }
 

tools/perf/util/session.c

···
 			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
 	case PERF_RECORD_LOST_SAMPLES:
-		if (tool->lost_samples == perf_event__process_lost_samples &&
-		    !(event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF))
+		if (event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)
+			evlist->stats.total_dropped_samples += event->lost_samples.lost;
+		else if (tool->lost_samples == perf_event__process_lost_samples)
 			evlist->stats.total_lost_samples += event->lost_samples.lost;
 		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ: