perf record: Read and inject LOST_SAMPLES events

When there are lost samples, it can read the number of PERF_FORMAT_LOST and
convert it to PERF_RECORD_LOST_SAMPLES and write to the data file at the end.

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220901195739.668604-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a91ead72fd413e39dd646d2412d156491e9e05e7..741e763436cafb107b8ae01d2c240c781ee65a6d 100644 (file)
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -10,6 +10,7 @@
 
 #include "util/build-id.h"
 #include <subcmd/parse-options.h>
+#include <internal/xyarray.h>
 #include "util/parse-events.h"
 #include "util/config.h"
 
@@ -1852,6 +1853,68 @@ record__switch_output(struct record *rec, bool at_exit)
        return fd;
 }
 
+static void __record__read_lost_samples(struct record *rec, struct evsel *evsel,
+                                       struct perf_record_lost_samples *lost,
+                                       int cpu_idx, int thread_idx)
+{
+       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_err("read LOST count failed\n");
+               return;
+       }
+
+       if (count.lost == 0)
+               return;
+
+       lost->lost = count.lost;
+       if (evsel->core.ids) {
+               sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx);
+               sample.id = sid->id;
+       }
+
+       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;
+       record__write(rec, NULL, lost, lost->header.size);
+}
+
+static void record__read_lost_samples(struct record *rec)
+{
+       struct perf_session *session = rec->session;
+       struct perf_record_lost_samples *lost;
+       struct evsel *evsel;
+
+       lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+       if (lost == NULL) {
+               pr_debug("Memory allocation failed\n");
+               return;
+       }
+
+       lost->header.type = PERF_RECORD_LOST_SAMPLES;
+
+       evlist__for_each_entry(session->evlist, evsel) {
+               struct xyarray *xy = evsel->core.sample_id;
+
+               if (xyarray__max_x(evsel->core.fd) != xyarray__max_x(xy) ||
+                   xyarray__max_y(evsel->core.fd) != xyarray__max_y(xy)) {
+                       pr_debug("Unmatched FD vs. sample ID: skip reading LOST count\n");
+                       continue;
+               }
+
+               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);
+
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -2714,6 +2777,7 @@ out_free_threads:
        if (rec->off_cpu)
                rec->bytes_written += off_cpu_write(rec->session);
 
+       record__read_lost_samples(rec);
        record__synthesize(rec, true);
        /* this will be recalculated during process_buildids() */
        rec->samples = 0;