[v4,09/35] perf evlist: Propagate user CPU maps intersecting core PMU maps

Commit Message

Ian Rogers May 26, 2023, 9:53 p.m. UTC

The CPU map for a non-core PMU gives a default CPU value for
perf_event_open. For core PMUs the CPU map lists all CPUs the evsel
may be opened on. If there are >1 core PMU, the CPU maps will list the
CPUs for that core PMU, but the user_requested_cpus may contain CPUs
that are invalid for the PMU and cause perf_event_open to fail. To
avoid this, when propagating the CPU map for core PMUs intersect it
with the CPU map of the PMU (the evsel's "own_cpus").

Add comments to __perf_evlist__propagate_maps to explain its somewhat
complex behavior. Fix the related comments for system_wide in struct
perf_evsel.

Signed-off-by: Ian Rogers <[e-mail]>
Reviewed-by: Kan Liang <[e-mail]>
---
 tools/lib/perf/evlist.c                 | 25 ++++++++++++++++++++-----
 tools/lib/perf/include/internal/evsel.h |  6 +++---
 2 files changed, 23 insertions(+), 8 deletions(-)

Patch

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 81e8b5fcd8ba..b8b066d0dc5e 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -36,18 +36,33 @@  void perf_evlist__init(struct perf_evlist *evlist)
 static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 					  struct perf_evsel *evsel)
 {
-	/*
-	 * We already have cpus for evsel (via PMU sysfs) so
-	 * keep it, if there's no target cpu list defined.
-	 */
 	if (evsel->system_wide) {
+		/* System wide: set the cpu map of the evsel to all online CPUs. */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__new(NULL);
+	} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
+		/*
+		 * User requested CPUs on a core PMU, ensure the requested CPUs
+		 * are valid by intersecting with those of the PMU.
+		 */
+		perf_cpu_map__put(evsel->cpus);
+		evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
 	} else if (!evsel->own_cpus || evlist->has_user_cpus ||
-		   (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) {
+		(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
+		/*
+		 * The PMU didn't specify a default cpu map, this isn't a core
+		 * event and the user requested CPUs or the evlist user
+		 * requested CPUs have the "any CPU" (aka dummy) CPU value. In
+		 * which case use the user requested CPUs rather than the PMU
+		 * ones.
+		 */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
+		/*
+		 * No user requested cpu map but the PMU cpu map doesn't match
+		 * the evsel's. Reset it back to the PMU cpu map.
+		 */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
 	}
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 4d6f2a032f45..5cd220a61962 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -62,9 +62,9 @@  struct perf_evsel {
 	int			 nr_members;
 	/*
 	 * system_wide is for events that need to be on every CPU, irrespective
-	 * of user requested CPUs or threads. Map propagation will set cpus to
-	 * this event's own_cpus, whereby they will contribute to evlist
-	 * all_cpus.
+	 * of user requested CPUs or threads. Tha main example of this is the
+	 * dummy event. Map propagation will set cpus for this event to all CPUs
+	 * as software PMU events like dummy, have a CPU map that is empty.
 	 */
 	bool			 system_wide;
 	/*