perf stat: Hide invalid uncore event output for aggr mode

The current display code for perf stat iterates given cpus and build the
aggr map to collect the event data for the aggregation mode.

But uncore events have their own cpu maps and it won't guarantee that
it'd match to the aggr map.  For example, per-package uncore events
would generate a single value for each socket.  When user asks per-core
aggregation mode, the output would contain 0 values for other cores.

Thus it needs to check the uncore PMU's cpumask and if it matches to the
current aggregation id.

Before:
  $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1

   Performance counter stats for 'system wide':

  S0-D0-C0              1               3.73 Joules power/energy-pkg/
  S0-D0-C1              0      <not counted> Joules power/energy-pkg/
  S0-D0-C2              0      <not counted> Joules power/energy-pkg/
  S0-D0-C3              0      <not counted> Joules power/energy-pkg/

         1.001404046 seconds time elapsed

  Some events weren't counted. Try disabling the NMI watchdog:
  	echo 0 > /proc/sys/kernel/nmi_watchdog
  	perf stat ...
  	echo 1 > /proc/sys/kernel/nmi_watchdog

The core 1, 2 and 3 should not be printed because the event is handled
in a cpu in the core 0 only.  With this change, the output becomes like
below.

After:
  $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1

   Performance counter stats for 'system wide':

  S0-D0-C0              1               2.09 Joules power/energy-pkg/

Fixes: b8976135 ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Ian Rogers <irogers@google.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/stat-display.c

@@ -787,6 +787,51 @@ static void uniquify_counter(struct perf_stat_config *config, struct evsel *coun
 		uniquify_event_name(counter);
 }
 
+/**
+ * should_skip_zero_count() - Check if the event should print 0 values.
+ * @config: The perf stat configuration (including aggregation mode).
+ * @counter: The evsel with its associated cpumap.
+ * @id: The aggregation id that is being queried.
+ *
+ * Due to mismatch between the event cpumap or thread-map and the
+ * aggregation mode, sometimes it'd iterate the counter with the map
+ * which does not contain any values.
+ *
+ * For example, uncore events have dedicated CPUs to manage them,
+ * result for other CPUs should be zero and skipped.
+ *
+ * Return: %true if the value should NOT be printed, %false if the value
+ * needs to be printed like "<not counted>" or "<not supported>".
+ */
+static bool should_skip_zero_counter(struct perf_stat_config *config,
+				     struct evsel *counter,
+				     const struct aggr_cpu_id *id)
+{
+	struct perf_cpu cpu;
+	int idx;
+
+	/*
+	 * Skip value 0 when enabling --per-thread globally,
+	 * otherwise it will have too many 0 output.
+	 */
+	if (config->aggr_mode == AGGR_THREAD && config->system_wide)
+		return true;
+	/*
+	 * Skip value 0 when it's an uncore event and the given aggr id
+	 * does not belong to the PMU cpumask.
+	 */
+	if (!counter->pmu || !counter->pmu->is_uncore)
+		return false;
+
+	perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) {
+		struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu);
+
+		if (aggr_cpu_id__equal(id, &own_id))
+			return false;
+	}
+	return true;
+}
+
 static void print_counter_aggrdata(struct perf_stat_config *config,
 				   struct evsel *counter, int s,
 				   struct outstate *os)
@@ -814,11 +859,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 	ena = aggr->counts.ena;
 	run = aggr->counts.run;
 
-	/*
-	 * Skip value 0 when enabling --per-thread globally, otherwise it will
-	 * have too many 0 output.
-	 */
-	if (val == 0 && config->aggr_mode == AGGR_THREAD && config->system_wide)
+	if (val == 0 && should_skip_zero_counter(config, counter, &id))
 		return;
 
 	if (!metric_only) {