perf stat: Remove --per-thread pid/tid limitation

Currently, if we execute 'perf stat --per-thread' without specifying
pid/tid, perf will return error.

root@skl:/tmp# perf stat --per-thread
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

This patch removes this limitation. If no pid/tid specified, it returns
all threads (get threads from /proc).

Note that it doesn't support cpu_list yet so if it's a cpu_list case,
then skip.

Signed-off-by: Jin Yao <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-stat.c

···
 			attr->enable_on_exec = 1;
 	}
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
···
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		ncpus = perf_evsel__nr_cpus(counter);
 	else
 		ncpus = 1;
···
 		run_count = 1;
 	}
 
-	if ((stat_config.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, stat_options, "p", 1);
-		parse_options_usage(NULL, stat_options, "t", 1);
-		goto out;
+	if ((stat_config.aggr_mode == AGGR_THREAD) &&
+		!target__has_task(&target)) {
+		if (!target.system_wide || target.cpu_list) {
+			fprintf(stderr, "The --per-thread option is only "
+				"available when monitoring via -p -t -a "
+				"options or only --per-thread.\n");
+			parse_options_usage(NULL, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
+			goto out;
+		}
 	}
 
 	/*
···
 		goto out;
 
 	target__validate(&target);
+
+	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+		target.per_thread = true;
 
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {

tools/perf/util/target.h

···
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__has_per_thread(struct target *target)
+{
+	return target->system_wide && target->per_thread;
+}
+
 static inline bool target__uses_dummy_map(struct target *target)
 {
 	bool use_dummy = false;
···
 		use_dummy = target->per_thread ? true : false;
 	else if (target__has_task(target) ||
 	         (!target__has_cpu(target) && !target->uses_mmap))
+		use_dummy = true;
+	else if (target__has_per_thread(target))
 		use_dummy = true;
 
 	return use_dummy;