perf stat: Add per-core aggregation

This patch adds the --per-core option to perf stat.

This option is used to aggregate system-wide counts
on a per physical core basis. On processors with
hyperthreading, this means counts of all HT threads
running on a physical core are aggregated.

This mode is useful to find imblance between physical
cores running an uniform workload. Cores are identified
by socket: S0-C1, means physical core 1 on socket 0. Note
that cores are identified using their physical core id,
thus their numbering may not be continuous.

Per core aggregation can be combined with interval printing:

 # perf stat -a --per-core -I 1000 -e cycles sleep 1000
 #           time core         cpus             counts events
      1.000090030 S0-C0           1          4,765,747 cycles
      1.000090030 S0-C1           1          5,580,647 cycles
      1.000090030 S0-C2           1            221,181 cycles
      1.000090030 S0-C3           1            266,092 cycles

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1360846649-6411-4-git-send-email-eranian@google.com
[ committer note: Remove parts already applied on 86ee6e1 to keep bisectability ]
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 6f6ea931..7e910ba 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -80,6 +80,7 @@
 	AGGR_NONE,
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
+	AGGR_CORE,
 };
 
 static int			run_count			=  1;
@@ -384,6 +385,9 @@
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts events\n");
 			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts events\n");
+			break;
 		case AGGR_NONE:
 			fprintf(output, "#           time CPU                 counts events\n");
 			break;
@@ -397,6 +401,7 @@
 		num_print_interval = 0;
 
 	switch (aggr_mode) {
+	case AGGR_CORE:
 	case AGGR_SOCKET:
 		print_aggr(prefix);
 		break;
@@ -566,13 +571,23 @@
 	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void aggr_printout(struct perf_evsel *evsel, int cpu, int nr)
+static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 {
 	switch (aggr_mode) {
+	case AGGR_CORE:
+		fprintf(output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+		break;
 	case AGGR_SOCKET:
 		fprintf(output, "S%*d%s%*d%s",
 			csv_output ? 0 : -5,
-			cpu,
+			id,
 			csv_sep,
 			csv_output ? 0 : 4,
 			nr,
@@ -581,7 +596,7 @@
 	case AGGR_NONE:
 		fprintf(output, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
+			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
 	case AGGR_GLOBAL:
 	default:
@@ -1095,6 +1110,7 @@
 	}
 
 	switch (aggr_mode) {
+	case AGGR_CORE:
 	case AGGR_SOCKET:
 		print_aggr(NULL);
 		break;
@@ -1163,6 +1179,13 @@
 		}
 		aggr_get_id = cpu_map__get_socket;
 		break;
+	case AGGR_CORE:
+		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+			perror("cannot build core map");
+			return -1;
+		}
+		aggr_get_id = cpu_map__get_core;
+		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
 	default:
@@ -1372,6 +1395,8 @@
 		    "print counts at regular interval in ms (>= 100)"),
 	OPT_SET_UINT(0, "per-socket", &aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {