perf stat: Read tool events last

When reading a metric like memory bandwidth on multiple sockets, the
additional sockets will be on CPUS > 0. Because of the affinity
reading, the counters are read on CPU 0 along with the time, then the
later sockets are read. This can lead to the later sockets having a
bandwidth larger than is possible for the period of time. To avoid
this move the reading of tool events to occur after all other events
are read.

Signed-off-by: Ian Rogers <[e-mail]>
Signed-off-by: Namhyung Kim <[e-mail]>

tools/perf/builtin-stat.c

···
 	return 0;
 }
 
-static int read_affinity_counters(void)
+static int read_counters_with_affinity(void)
 {
 	struct evlist_cpu_iterator evlist_cpu_itr;
 	struct affinity saved_affinity, *affinity;
···
 		struct evsel *counter = evlist_cpu_itr.evsel;
 
 		if (evsel__is_bpf(counter))
+			continue;
+
+		if (evsel__is_tool(counter))
 			continue;
 
 		if (!counter->err)
···
 	return 0;
 }
 
-static int read_counters(void)
+static int read_tool_counters(void)
 {
-	if (!stat_config.stop_read_counter) {
-		if (read_bpf_map_counters() ||
-		    read_affinity_counters())
-			return -1;
+	struct evsel *counter;
+
+	evlist__for_each_entry(evsel_list, counter) {
+		int idx;
+
+		if (!evsel__is_tool(counter))
+			continue;
+
+		perf_cpu_map__for_each_idx(idx, counter->core.cpus) {
+			if (!counter->err)
+				counter->err = read_counter_cpu(counter, idx);
+		}
 	}
 	return 0;
+}
+
+static int read_counters(void)
+{
+	int ret;
+
+	if (stat_config.stop_read_counter)
+		return 0;
+
+	// Read all BPF counters first.
+	ret = read_bpf_map_counters();
+	if (ret)
+		return ret;
+
+	// Read non-BPF and non-tool counters next.
+	ret = read_counters_with_affinity();
+	if (ret)
+		return ret;
+
+	// Read the tool counters last. This way the duration_time counter
+	// should always be greater than any other counter's enabled time.
+	return read_tool_counters();
 }
 
 static void process_counters(void)