[PATCH v2] perf util: Use target->per_thread and target->system_wide flags

[Jin Yao]

Mathieu Poirier reports issue in commit ("73c0ca1eee3d 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.

v2:
---
According to Jiri's comment, add description to explain why the patch
uses 'target->per_thread && target->system_wide'.

v2 doesn't have functional change.

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
 tools/perf/util/evlist.c     | 20 +++++++++++++++++++-
 tools/perf/util/thread_map.c |  4 ++--
 tools/perf/util/thread_map.h |  2 +-
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ac35cd2..3eea0f8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1106,8 +1106,26 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	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);
+				      target->per_thread && target->system_wide);
 
 	if (!threads)
 		return -1;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 3e1038f..729dad8 100644
--- a/tools/perf/util/thread_map.c
+++ b/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);
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0a806b9..5ec91cf 100644
--- a/tools/perf/util/thread_map.h
+++ b/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);
 
-- 
2.7.4