perf stat: Support metrics in --per-core/socket mode

Enable metrics printing in --per-core / --per-socket mode. We need to
save the shadow metrics in a unique place. Always use the first CPU in
the aggregation. Then use the same CPU to retrieve the shadow value
later.

Example output:

  % perf stat --per-core -a ./BC1s

   Performance counter stats for 'system wide':

  S0-C0 2   2966.020381 task-clock (msec) #   2.004 CPUs utilized  (100.00%)
  S0-C0 2            49 context-switches  #   0.017 K/sec          (100.00%)
  S0-C0 2             4 cpu-migrations    #   0.001 K/sec          (100.00%)
  S0-C0 2           467 page-faults       #   0.157 K/sec
  S0-C0 2 4,599,061,773 cycles            #   1.551 GHz            (100.00%)
  S0-C0 2 9,755,886,883 instructions      #   2.12  insn per cycle (100.00%)
  S0-C0 2 1,906,272,125 branches          # 642.704 M/sec          (100.00%)
  S0-C0 2    81,180,867 branch-misses     #   4.26% of all branches
  S0-C1 2   2965.995373 task-clock (msec) #   2.003 CPUs utilized  (100.00%)
  S0-C1 2            62 context-switches  #   0.021 K/sec          (100.00%)
  S0-C1 2             8 cpu-migrations    #   0.003 K/sec          (100.00%)
  S0-C1 2           281 page-faults       #   0.095 K/sec
  S0-C1 2     6,347,290 cycles            #   0.002 GHz            (100.00%)
  S0-C1 2     4,654,156 instructions      #   0.73  insn per cycle (100.00%)
  S0-C1 2       947,121 branches          #   0.319 M/sec          (100.00%)
  S0-C1 2        37,322 branch-misses     #   3.94% of all branches

         1.480409747 seconds time elapsed

v2: Rebase to older patches
v3: Document shadow cpus. Fix aggr_get_id argument. Fix -A shadows (Jiri)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1456785386-19481-4-git-send-email-andi@firstfloor.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 2ffb822..9b5089c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -740,6 +740,8 @@
 	bool newline;
 	const char *prefix;
 	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
 };
 
 #define METRIC_LEN  35
@@ -755,12 +757,9 @@
 {
 	fputc('\n', os->fh);
 	fputs(os->prefix, os->fh);
+	aggr_printout(os->evsel, os->id, os->nr);
 	if (stat_config.aggr_mode == AGGR_NONE)
 		fprintf(os->fh, "        ");
-	if (stat_config.aggr_mode == AGGR_CORE)
-		fprintf(os->fh, "                  ");
-	if (stat_config.aggr_mode == AGGR_SOCKET)
-		fprintf(os->fh, "            ");
 	fprintf(os->fh, "                                                 ");
 }
 
@@ -798,6 +797,7 @@
 	fputc('\n', os->fh);
 	if (os->prefix)
 		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	aggr_printout(os->evsel, os->id, os->nr);
 	for (i = 0; i < os->nfields; i++)
 		fputs(csv_sep, os->fh);
 }
@@ -855,6 +855,28 @@
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+{
+	int i;
+
+	if (!aggr_get_id)
+		return 0;
+
+	if (stat_config.aggr_mode == AGGR_NONE)
+		return id;
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -891,7 +913,10 @@
 	struct perf_stat_output_ctx out;
 	struct outstate os = {
 		.fh = stat_config.output,
-		.prefix = prefix ? prefix : ""
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
 	};
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
@@ -958,16 +983,37 @@
 	}
 
 	perf_stat__print_shadow_stats(counter, uval,
-				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
-				cpu_map__id_to_cpu(id),
+				first_shadow_cpu(counter, id),
 				&out);
-
 	if (!csv_output) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
 }
 
+static void aggr_update_shadow(void)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
+		evlist__for_each(evsel_list, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			val = val * counter->scale;
+			perf_stat__update_shadow_stats(counter, &val,
+						       first_shadow_cpu(counter, id));
+		}
+	}
+}
+
 static void print_aggr(char *prefix)
 {
 	FILE *output = stat_config.output;
@@ -979,6 +1025,8 @@
 	if (!(aggr_map || aggr_get_id))
 		return;
 
+	aggr_update_shadow();
+
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
 		evlist__for_each(evsel_list, counter) {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 367e220..5e2d2e3 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -14,6 +14,13 @@
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];