perf lock: Add -t/--thread option for report

The -t option is to show per-thread lock stat like below:

  $ perf lock report -t -F acquired,contended,avg_wait

                Name   acquired  contended   avg wait (ns)

                perf     240569          9            5784
             swapper     106610         19             543
              :15789      17370          2           14538
        ContainerMgr       8981          6             874
               sleep       5275          1           11281
     ContainerThread       4416          4             944
     RootPressureThr       3215          5            1215
         rcu_preempt       2954          0               0
        ContainerMgr       2560          0               0
             unnamed       1873          0               0
     EventManager_De       1845          1             636
     futex-default-S       1609          0               0
  ...

Committer notes:

Add that option to the 'perf lock report' man page.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220521010811.932703-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-lock.txt

@@ -64,6 +64,27 @@ REPORT OPTIONS
 --combine-locks::
 	Merge lock instances in the same class (based on name).
 
+-t::
+--threads::
+    The -t option is to show per-thread lock stat like below:
+
+      $ perf lock report -t -F acquired,contended,avg_wait
+
+                    Name   acquired  contended   avg wait (ns)
+
+                    perf     240569          9            5784
+                 swapper     106610         19             543
+                  :15789      17370          2           14538
+            ContainerMgr       8981          6             874
+                   sleep       5275          1           11281
+         ContainerThread       4416          4             944
+         RootPressureThr       3215          5            1215
+             rcu_preempt       2954          0               0
+            ContainerMgr       2560          0               0
+                 unnamed       1873          0               0
+         EventManager_De       1845          1             636
+         futex-default-S       1609          0               0
+
 INFO OPTIONS
 ------------
 

tools/perf/builtin-lock.c

@@ -118,6 +118,7 @@ struct thread_stat {
 static struct rb_root		thread_stats;
 
 static bool combine_locks;
+static bool show_thread_stats;
 
 static struct thread_stat *thread_stat_find(u32 tid)
 {
@@ -542,6 +543,10 @@ static int report_lock_acquire_event(struct evsel *evsel,
 	u64 addr = evsel__intval(evsel, sample, "lockdep_addr");
 	int flag = evsel__intval(evsel, sample, "flags");
 
+	/* abuse ls->addr for tid */
+	if (show_thread_stats)
+		addr = sample->tid;
+
 	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -ENOMEM;
@@ -611,6 +616,9 @@ static int report_lock_acquired_event(struct evsel *evsel,
 	const char *name = evsel__strval(evsel, sample, "name");
 	u64 addr = evsel__intval(evsel, sample, "lockdep_addr");
 
+	if (show_thread_stats)
+		addr = sample->tid;
+
 	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -ENOMEM;
@@ -670,6 +678,9 @@ static int report_lock_contended_event(struct evsel *evsel,
 	const char *name = evsel__strval(evsel, sample, "name");
 	u64 addr = evsel__intval(evsel, sample, "lockdep_addr");
 
+	if (show_thread_stats)
+		addr = sample->tid;
+
 	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -ENOMEM;
@@ -722,6 +733,9 @@ static int report_lock_release_event(struct evsel *evsel,
 	const char *name = evsel__strval(evsel, sample, "name");
 	u64 addr = evsel__intval(evsel, sample, "lockdep_addr");
 
+	if (show_thread_stats)
+		addr = sample->tid;
+
 	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -ENOMEM;
@@ -848,7 +862,17 @@ static void print_result(void)
 
 		if (strlen(st->name) < 20) {
 			/* output raw name */
-			pr_info("%20s ", st->name);
+			const char *name = st->name;
+
+			if (show_thread_stats) {
+				struct thread *t;
+
+				/* st->addr contains tid of thread */
+				t = perf_session__findnew(session, st->addr);
+				name = thread__comm_str(t);
+			}
+
+			pr_info("%20s ", name);
 		} else {
 			strncpy(cut_name, st->name, 16);
 			cut_name[16] = '.';
@@ -1125,6 +1149,8 @@ int cmd_lock(int argc, const char **argv)
 	/* TODO: type */
 	OPT_BOOLEAN('c', "combine-locks", &combine_locks,
 		    "combine locks in the same class"),
+	OPT_BOOLEAN('t', "threads", &show_thread_stats,
+		    "show per-thread lock stats"),
 	OPT_PARENT(lock_options)
 	};