perf record: Record dropped sample count

When it uses bpf filters, event might drop some samples.  It'd be nice
if it can report how many samples it lost.  As LOST_SAMPLES event can
carry the similar information, let's use it for bpf filters.

To indicate it's from BPF filters, add a new misc flag for that and
do not display cpu load warnings.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Song Liu <song@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/lib/perf/include/perf/event.h

@@ -70,6 +70,8 @@ struct perf_record_lost {
 	__u64			 lost;
 };
 
+#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15)
+
 struct perf_record_lost_samples {
 	struct perf_event_header header;
 	__u64			 lost;

tools/perf/builtin-record.c

@@ -52,6 +52,7 @@
 #include "util/pmu-hybrid.h"
 #include "util/evlist-hybrid.h"
 #include "util/off_cpu.h"
+#include "util/bpf-filter.h"
 #include "asm/bug.h"
 #include "perf.h"
 #include "cputopo.h"
@@ -1856,24 +1857,16 @@ record__switch_output(struct record *rec, bool at_exit)
 	return fd;
 }
 
-static void __record__read_lost_samples(struct record *rec, struct evsel *evsel,
+static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
 					struct perf_record_lost_samples *lost,
-					int cpu_idx, int thread_idx)
+					int cpu_idx, int thread_idx, u64 lost_count,
+					u16 misc_flag)
 {
-	struct perf_counts_values count;
 	struct perf_sample_id *sid;
 	struct perf_sample sample = {};
 	int id_hdr_size;
 
-	if (perf_evsel__read(&evsel->core, cpu_idx, thread_idx, &count) < 0) {
-		pr_debug("read LOST count failed\n");
-		return;
-	}
-
-	if (count.lost == 0)
-		return;
-
-	lost->lost = count.lost;
+	lost->lost = lost_count;
 	if (evsel->core.ids) {
 		sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx);
 		sample.id = sid->id;
@@ -1882,6 +1875,7 @@ static void __record__read_lost_samples(struct record *rec, struct evsel *evsel,
 	id_hdr_size = perf_event__synthesize_id_sample((void *)(lost + 1),
 						       evsel->core.attr.sample_type, &sample);
 	lost->header.size = sizeof(*lost) + id_hdr_size;
+	lost->header.misc = misc_flag;
 	record__write(rec, NULL, lost, lost->header.size);
 }
 
@@ -1905,6 +1899,7 @@ static void record__read_lost_samples(struct record *rec)
 
 	evlist__for_each_entry(session->evlist, evsel) {
 		struct xyarray *xy = evsel->core.sample_id;
+		u64 lost_count;
 
 		if (xy == NULL || evsel->core.fd == NULL)
 			continue;
@@ -1916,12 +1911,27 @@ static void record__read_lost_samples(struct record *rec)
 
 		for (int x = 0; x < xyarray__max_x(xy); x++) {
 			for (int y = 0; y < xyarray__max_y(xy); y++) {
-				__record__read_lost_samples(rec, evsel, lost, x, y);
-			}
-		}
-	}
-	free(lost);
+				struct perf_counts_values count;
 
+				if (perf_evsel__read(&evsel->core, x, y, &count) < 0) {
+					pr_debug("read LOST count failed\n");
+					goto out;
+				}
+
+				if (count.lost) {
+					__record__save_lost_samples(rec, evsel, lost,
+								    x, y, count.lost, 0);
+				}
+			}
+		}
+
+		lost_count = perf_bpf_filter__lost_count(evsel);
+		if (lost_count)
+			__record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
+						    PERF_RECORD_MISC_LOST_SAMPLES_BPF);
+	}
+out:
+	free(lost);
 }
 
 static volatile sig_atomic_t workload_exec_errno;

tools/perf/util/bpf-filter.c

@@ -69,6 +69,13 @@ int perf_bpf_filter__destroy(struct evsel *evsel)
 	return 0;
 }
 
+u64 perf_bpf_filter__lost_count(struct evsel *evsel)
+{
+	struct sample_filter_bpf *skel = evsel->bpf_skel;
+
+	return skel ? skel->bss->dropped : 0;
+}
+
 struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags,
 						       enum perf_bpf_filter_op op,
 						       unsigned long val)

tools/perf/util/bpf-filter.h

@@ -22,6 +22,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag
 int perf_bpf_filter__parse(struct list_head *expr_head, const char *str);
 int perf_bpf_filter__prepare(struct evsel *evsel);
 int perf_bpf_filter__destroy(struct evsel *evsel);
+u64 perf_bpf_filter__lost_count(struct evsel *evsel);
 
 #else /* !HAVE_BPF_SKEL */
 
@@ -38,5 +39,9 @@ static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
 {
 	return -EOPNOTSUPP;
 }
+static inline u64 perf_bpf_filter__lost_count(struct evsel *evsel __maybe_unused)
+{
+	return 0;
+}
 #endif /* HAVE_BPF_SKEL*/
 #endif /* PERF_UTIL_BPF_FILTER_H */

tools/perf/util/session.c

@@ -1582,7 +1582,8 @@ static int machines__deliver_event(struct machines *machines,
 			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)
+		if (tool->lost_samples == perf_event__process_lost_samples &&
+		    !(event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF))
 			evlist->stats.total_lost_samples += event->lost_samples.lost;
 		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ: