perf stat: Introduce --per-thread option

Currently all the -p option PID arguments tasks values get aggregated
and printed as single values.

Adding --per-tasks option to print values per task.

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242
  ^C
   Performance counter stats for process id '30190,30242':

               cat-30190                     0      cycles
               yes-30242         3,842,525,421      cycles
               cat-30190                     0      instructions
               yes-30242        10,370,817,010      instructions

         1.143155657 seconds time elapsed

Also works under interval mode:

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242 -I 1000
  #           time             comm-pid                  counts unit events
       1.000073435              cat-30190                89,058      cycles
       1.000073435              yes-30242         3,360,786,902      cycles                     (100.00%)
       1.000073435              cat-30190                14,066      instructions
       1.000073435              yes-30242         9,069,937,462      instructions
       2.000204830              cat-30190                     0      cycles
       2.000204830              yes-30242         3,351,667,626      cycles
       2.000204830              cat-30190                     0      instructions
       2.000204830              yes-30242         9,045,796,885      instructions
  ^C     2.771286639              cat-30190                     0      cycles
       2.771286639              yes-30242         2,593,884,166      cycles
       2.771286639              cat-30190                     0      instructions
       2.771286639              yes-30242         7,001,171,191      instructions

It works only with -t and -p options, otherwise following error is
printed:

  $ perf stat  -e cycles --per-thread  -I 1000 ls
  The --per-thread option is only available when monitoring via -p -t options.
      -p, --pid <pid>       stat events on existing process id
      -t, --tid <tid>       stat events on existing thread id

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1435310967-14570-23-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-stat.txt

@@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to

tools/perf/builtin-stat.c

@@ -231,6 +231,7 @@ process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_THREAD:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
@@ -602,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_THREAD:
+		fprintf(output, "%*s-%*d%s",
+			csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -750,6 +759,40 @@ static void print_aggr(char *prefix)
 	}
 }
 
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -876,6 +919,9 @@ static void print_interval(char *prefix, struct timespec *ts)
 		case AGGR_NONE:
 			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
 			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			break;
 		case AGGR_GLOBAL:
 		default:
 			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
@@ -944,6 +990,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_SOCKET:
 		print_aggr(prefix);
 		break;
+	case AGGR_THREAD:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_thread(counter, prefix);
+		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
@@ -1031,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void)
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_THREAD:
 	default:
 		break;
 	}
@@ -1255,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_END()
@@ -1346,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
+		fprintf(stderr, "The --per-thread option is only available "
+			"when monitoring via -p -t options.\n");
+		parse_options_usage(NULL, options, "p", 1);
+		parse_options_usage(NULL, options, "t", 1);
+		goto out;
+	}
+
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
@@ -1375,6 +1439,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		goto out;
 	}
+
+	/*
+	 * Initialize thread_map with comm names,
+	 * so we could print it out on output.
+	 */
+	if (aggr_mode == AGGR_THREAD)
+		thread_map__read_comms(evsel_list->threads);
+
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
 		parse_options_usage(stat_usage, options, "I", 1);

tools/perf/util/stat.h

@@ -30,6 +30,7 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_THREAD,
 };
 
 struct perf_counts_values {