perf stat: Make read_counter work over the thread dimension

The read function will be used later for both aggr and cpu counters, so
we need to make it work over threads as well.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Matt Fleming <matt.fleming@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1416562275-12404-6-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9cc0db1..2511d3a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -444,11 +444,18 @@
  */
 static int read_counter(struct perf_evsel *counter)
 {
-	int cpu;
+	int nthreads = thread_map__nr(evsel_list->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		if (perf_evsel__read_cb(counter, cpu, 0, read_cb))
-			return -1;
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+				return -1;
+		}
 	}
 
 	return 0;