perf tools: Use target->per_thread and target->system_wide flags

Mathieu Poirier reports issue in commit ("73c0ca1e perf thread_map:
Enumerate all threads from /proc") that it has negative impact on 'perf
record --per-thread'. It has the effect of creating a kernel event for
each thread in the system for 'perf record --per-thread'.

Mathieu Poirier's patch ("perf util: Do not reuse target->per_thread flag")
can fix this issue by creating a new target->all_threads flag.

This patch is based on Mathieu Poirier's patch but it doesn't use a new
target->all_threads flag. This patch just uses 'target->per_thread &&
target->system_wide' as a condition to check for all threads case.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-arm-kernel@lists.infradead.org
Fixes: 73c0ca1e ("perf thread_map: Enumerate all threads from /proc")
Link: http://lkml.kernel.org/r/1518467557-18505-3-git-send-email-mathieu.poirier@linaro.orgSigned-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
[Fixed checkpatch warning about line over 80 characters]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/evlist.c

@@ -1086,11 +1086,30 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
+	bool all_threads = (target->per_thread && target->system_wide);
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 
+	/*
+	 * If specify '-a' and '--per-thread' to perf record, perf record
+	 * will override '--per-thread'. target->per_thread = false and
+	 * target->system_wide = true.
+	 *
+	 * If specify '--per-thread' only to perf record,
+	 * target->per_thread = true and target->system_wide = false.
+	 *
+	 * So target->per_thread && target->system_wide is false.
+	 * For perf record, thread_map__new_str doesn't call
+	 * thread_map__new_all_cpus. That will keep perf record's
+	 * current behavior.
+	 *
+	 * For perf stat, it allows the case that target->per_thread and
+	 * target->system_wide are all true. It means to collect system-wide
+	 * per-thread data. thread_map__new_str will call
+	 * thread_map__new_all_cpus to enumerate all threads.
+	 */
 	threads = thread_map__new_str(target->pid, target->tid, target->uid,
-				      target->per_thread);
+				      all_threads);
 
 	if (!threads)
 		return -1;

tools/perf/util/thread_map.c

@@ -323,7 +323,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-				       uid_t uid, bool per_thread)
+				       uid_t uid, bool all_threads)
 {
 	if (pid)
 		return thread_map__new_by_pid_str(pid);
@@ -331,7 +331,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	if (!tid && uid != UINT_MAX)
 		return thread_map__new_by_uid(uid);
 
-	if (per_thread)
+	if (all_threads)
 		return thread_map__new_all_cpus();
 
 	return thread_map__new_by_tid_str(tid);

tools/perf/util/thread_map.h

@@ -31,7 +31,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-		const char *tid, uid_t uid, bool per_thread);
+		const char *tid, uid_t uid, bool all_threads);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);