perf lock: Support -t option for 'contention' subcommand

Like perf lock report, it can report lock contention stat of each task.

  $ perf lock contention -t
   contended   total wait     max wait     avg wait          pid   comm

           5    945.20 us    902.08 us    189.04 us       316167   EventManager_De
          33     98.17 us      6.78 us      2.97 us       766063   kworker/0:1-get
           7     92.47 us     61.26 us     13.21 us       316170   EventManager_De
          14     76.31 us     12.87 us      5.45 us        12949   timedcall
          24     76.15 us     12.27 us      3.17 us       767992   sched-pipe
          15     75.62 us     11.93 us      5.04 us        15127   switchto-defaul
          24     71.84 us      5.59 us      2.99 us       629168   kworker/u513:2-
          17     67.41 us      7.94 us      3.96 us        13504   coroner-
           1     59.56 us     59.56 us     59.56 us       316165   EventManager_De
          14     56.21 us      6.89 us      4.01 us            0   swapper

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20220725183124.368304-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-lock.txt

@@ -119,6 +119,10 @@ CONTENTION OPTIONS
 	and users can customize that using this.  Possible values:
 	contended, wait_total, wait_max, wait_min, avg_wait.
 
+-t::
+--threads::
+	Show per-thread lock contention stat
+
 
 SEE ALSO
 --------

tools/perf/builtin-lock.c

@@ -1560,7 +1560,10 @@ static void print_contention_result(void)
 	list_for_each_entry(key, &lock_keys, list)
 		pr_info("%*s ", key->len, key->header);
 
-	pr_info("  %10s   %s\n\n", "type", "caller");
+	if (show_thread_stats)
+		pr_info("  %10s   %s\n\n", "pid", "comm");
+	else
+		pr_info("  %10s   %s\n\n", "type", "caller");
 
 	bad = total = 0;
 	while ((st = pop_from_result())) {
@@ -1573,6 +1576,16 @@ static void print_contention_result(void)
 			pr_info(" ");
 		}
 
+		if (show_thread_stats) {
+			struct thread *t;
+			int pid = st->addr;
+
+			/* st->addr contains tid of thread */
+			t = perf_session__findnew(session, pid);
+			pr_info("  %10d   %s\n", pid, thread__comm_str(t));
+			continue;
+		}
+
 		pr_info("  %10s   %s\n", get_type_str(st), st->name);
 	}
 
@@ -1703,7 +1716,10 @@ static int __cmd_contention(void)
 	if (select_key(true))
 		goto out_delete;
 
-	aggr_mode = LOCK_AGGR_CALLER;
+	if (show_thread_stats)
+		aggr_mode = LOCK_AGGR_TASK;
+	else
+		aggr_mode = LOCK_AGGR_CALLER;
 
 	err = perf_session__process_events(session);
 	if (err)
@@ -1843,6 +1859,8 @@ int cmd_lock(int argc, const char **argv)
 		    "key for sorting (contended / wait_total / wait_max / wait_min / avg_wait)"),
 	OPT_STRING('F', "field", &output_fields, "contended,wait_total,wait_max,avg_wait",
 		    "output fields (contended / wait_total / wait_max / wait_min / avg_wait)"),
+	OPT_BOOLEAN('t', "threads", &show_thread_stats,
+		    "show per-thread lock stats"),
 	OPT_PARENT(lock_options)
 	};