[PATCH v4 2/4] tools/perf: Track where perf_sample_ids need per-thread periods
From: Ben Gainey
Date: Fri Mar 22 2024 - 12:43:22 EST
perf_sample_ids and related evlist/evsel code are modified to track
which events combine inherit+inherit_stat+PERF_SAMPLE_READ.
Events with this combination of properties must be handled differently
when tracking each streams sample period, as their stream-id is now only
unique per thread, rather than globally unique.
Signed-off-by: Ben Gainey <ben.gainey@xxxxxxx>
---
tools/lib/perf/evlist.c | 1 +
tools/lib/perf/evsel.c | 7 +++++++
tools/lib/perf/include/internal/evsel.h | 9 +++++++++
3 files changed, 17 insertions(+)
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 058e3ff10f9b..c585c49491a5 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -255,6 +255,7 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist,
sid->id = id;
sid->evsel = evsel;
+ sid->period_per_thread = perf_evsel__attr_has_per_thread_sample_period(evsel);
hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
hlist_add_head(&sid->node, &evlist->heads[hash]);
}
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c07160953224..dd60ee0557d8 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -537,6 +537,13 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
evsel->ids = 0;
}
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
+{
+ return (evsel->attr.sample_type & PERF_SAMPLE_READ)
+ && evsel->attr.inherit
+ && evsel->attr.inherit_stat;
+}
+
void perf_counts_values__scale(struct perf_counts_values *count,
bool scale, __s8 *pscaled)
{
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 5cd220a61962..8dd58149986c 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -36,6 +36,13 @@ struct perf_sample_id {
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
u64 period;
+
+ /*
+ * When inherit+inherit_stat is combined with PERF_SAMPLE_READ, the
+ * period value is per (sample_id, thread) tuple, rather than per
+ * sample_id.
+ */
+ bool period_per_thread;
};
struct perf_evsel {
@@ -88,4 +95,6 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
void perf_evsel__free_id(struct perf_evsel *evsel);
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
+
#endif /* __LIBPERF_INTERNAL_EVSEL_H */
--
2.44.0