perf stat: Report summary for interval mode

Currently 'perf stat' supports to print counts at regular interval (-I),
but it's not very easy for user to get the overall statistics.

The patch uses 'evsel->prev_raw_counts' to get counts for summary.  Copy
the counts to 'evsel->counts' after printing the interval results.
Next, we just follow the non-interval processing.

Let's see some examples,

 root@kbl-ppc:~# perf stat -e cycles -I1000 --interval-count 2
 #           time             counts unit events
      1.000412064          2,281,114      cycles
      2.001383658          2,547,880      cycles

  Performance counter stats for 'system wide':

          4,828,994      cycles

        2.002860349 seconds time elapsed

 root@kbl-ppc:~# perf stat -e cycles,instructions -I1000 --interval-count 2
 #           time             counts unit events
      1.000389902          1,536,093      cycles
      1.000389902            420,226      instructions              #    0.27  insn per cycle
      2.001433453          2,213,952      cycles
      2.001433453            735,465      instructions              #    0.33  insn per cycle

  Performance counter stats for 'system wide':

          3,750,045      cycles
          1,155,691      instructions              #    0.31  insn per cycle

        2.003023361 seconds time elapsed

 root@kbl-ppc:~# perf stat -M CPI,IPC -I1000 --interval-count 2
 #           time             counts unit events
      1.000435121            905,303      inst_retired.any          #      2.9 CPI
      1.000435121          2,663,333      cycles
      1.000435121            914,702      inst_retired.any          #      0.3 IPC
      1.000435121          2,676,559      cpu_clk_unhalted.thread
      2.001615941          1,951,092      inst_retired.any          #      1.8 CPI
      2.001615941          3,551,357      cycles
      2.001615941          1,950,837      inst_retired.any          #      0.5 IPC
      2.001615941          3,551,044      cpu_clk_unhalted.thread

  Performance counter stats for 'system wide':

          2,856,395      inst_retired.any          #      2.2 CPI
          6,214,690      cycles
          2,865,539      inst_retired.any          #      0.5 IPC
          6,227,603      cpu_clk_unhalted.thread

        2.003403078 seconds time elapsed

Committer testing:

Before:

  # perf stat -e cycles -I1000 --interval-count 2
  #           time             counts unit events
       1.000618627         26,877,408      cycles
       2.001417968        233,672,829      cycles
  #

After:

  # perf stat -e cycles -I1000 --interval-count 2
  #           time             counts unit events
       1.001531815      5,341,388,792      cycles
       2.002936530        100,073,912      cycles

   Performance counter stats for 'system wide':

       5,441,462,704      cycles

         2.004893794 seconds time elapsed

  #

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200520042737.24160-6-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -314,14 +314,14 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 	return 0;
 }
 
-static void read_counters(struct timespec *rs)
+static int read_affinity_counters(struct timespec *rs)
 {
 	struct evsel *counter;
 	struct affinity affinity;
 	int i, ncpus, cpu;
 
 	if (affinity__setup(&affinity) < 0)
-		return;
+		return -1;
 
 	ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
 	if (!target__has_cpu(&target) || target__has_per_thread(&target))
@@ -341,6 +341,15 @@ static void read_counters(struct timespec *rs)
 		}
 	}
 	affinity__cleanup(&affinity);
+	return 0;
+}
+
+static void read_counters(struct timespec *rs)
+{
+	struct evsel *counter;
+
+	if (!stat_config.summary && (read_affinity_counters(rs) < 0))
+		return;
 
 	evlist__for_each_entry(evsel_list, counter) {
 		if (counter->err)
@@ -763,7 +772,21 @@ try_again_reset:
 	if (stat_config.walltime_run_table)
 		stat_config.walltime_run[run_idx] = t1 - t0;
 
-	update_stats(&walltime_nsecs_stats, t1 - t0);
+	if (interval) {
+		stat_config.interval = 0;
+		stat_config.summary = true;
+		init_stats(&walltime_nsecs_stats);
+		update_stats(&walltime_nsecs_stats, t1 - t0);
+
+		if (stat_config.aggr_mode == AGGR_GLOBAL)
+			perf_evlist__save_aggr_prev_raw_counts(evsel_list);
+
+		perf_evlist__copy_prev_raw_counts(evsel_list);
+		perf_evlist__reset_prev_raw_counts(evsel_list);
+		runtime_stat_reset(&stat_config);
+		perf_stat__reset_shadow_per_stat(&rt_stat);
+	} else
+		update_stats(&walltime_nsecs_stats, t1 - t0);
 
 	/*
 	 * Closing a group leader splits the group, and as we only disable
@@ -2159,7 +2182,7 @@ int cmd_stat(int argc, const char **argv)
 		}
 	}
 
-	if (!forever && status != -1 && !interval)
+	if (!forever && status != -1 && (!interval || stat_config.summary))
 		print_counters(NULL, argc, argv);
 
 	if (STAT_RECORD) {

tools/perf/util/stat.c

@@ -408,7 +408,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	 * interval mode, otherwise overall avg running
 	 * averages will be shown for each interval.
 	 */
-	if (config->interval) {
+	if (config->interval || config->summary) {
 		for (i = 0; i < 3; i++)
 			init_stats(&ps->res_stats[i]);
 	}

tools/perf/util/stat.h

@@ -110,6 +110,7 @@ struct perf_stat_config {
 	bool			 all_kernel;
 	bool			 all_user;
 	bool			 percore_show_thread;
+	bool			 summary;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;