perf sched: Fixes for thread safety analysis

Add annotations to describe lock behavior. Add unlocks so that mutexes
aren't conditionally held on exit from perf_sched__replay. Add an exit
variable so that thread_func can terminate, rather than leaving the
threads blocked on mutexes.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Truong <alexandre.truong@arm.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andres Freund <andres@anarazel.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Colin Ian King <colin.king@intel.com>
Cc: Dario Petrillo <dario.pk1@gmail.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Dave Marchevsky <davemarchevsky@fb.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Fangrui Song <maskray@google.com>
Cc: Hewenliang <hewenliang4@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jason Wang <wangborong@cdjrlc.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin Liška <mliska@suse.cz>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Pavithra Gurushankar <gpavithrasha@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <quentin@isovalent.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Remi Bernon <rbernon@codeweavers.com>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Weiguo Li <liwg06@foxmail.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: William Cohen <wcohen@redhat.com>
Cc: Zechuan Chen <chenzechuan1@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Cc: yaowenbin <yaowenbin1@huawei.com>
Link: https://lore.kernel.org/r/20220826164242.43412-17-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-sched.c

@@ -246,6 +246,7 @@ struct perf_sched {
 	const char	*time_str;
 	struct perf_time_interval ptime;
 	struct perf_time_interval hist_time;
+	volatile bool   thread_funcs_exit;
 };
 
 /* per thread run time data */
@@ -633,31 +634,34 @@ static void *thread_func(void *ctx)
 	prctl(PR_SET_NAME, comm2);
 	if (fd < 0)
 		return NULL;
-again:
-	ret = sem_post(&this_task->ready_for_work);
-	BUG_ON(ret);
-	mutex_lock(&sched->start_work_mutex);
-	mutex_unlock(&sched->start_work_mutex);
 
-	cpu_usage_0 = get_cpu_usage_nsec_self(fd);
+	while (!sched->thread_funcs_exit) {
+		ret = sem_post(&this_task->ready_for_work);
+		BUG_ON(ret);
+		mutex_lock(&sched->start_work_mutex);
+		mutex_unlock(&sched->start_work_mutex);
 
-	for (i = 0; i < this_task->nr_events; i++) {
-		this_task->curr_event = i;
-		perf_sched__process_event(sched, this_task->atoms[i]);
-	}
+		cpu_usage_0 = get_cpu_usage_nsec_self(fd);
 
-	cpu_usage_1 = get_cpu_usage_nsec_self(fd);
-	this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
-	ret = sem_post(&this_task->work_done_sem);
-	BUG_ON(ret);
+		for (i = 0; i < this_task->nr_events; i++) {
+			this_task->curr_event = i;
+			perf_sched__process_event(sched, this_task->atoms[i]);
+		}
 
-	mutex_lock(&sched->work_done_wait_mutex);
-	mutex_unlock(&sched->work_done_wait_mutex);
+		cpu_usage_1 = get_cpu_usage_nsec_self(fd);
+		this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
+		ret = sem_post(&this_task->work_done_sem);
+		BUG_ON(ret);
 
-	goto again;
+		mutex_lock(&sched->work_done_wait_mutex);
+		mutex_unlock(&sched->work_done_wait_mutex);
+	}
+	return NULL;
 }
 
 static void create_tasks(struct perf_sched *sched)
+	EXCLUSIVE_LOCK_FUNCTION(sched->start_work_mutex)
+	EXCLUSIVE_LOCK_FUNCTION(sched->work_done_wait_mutex)
 {
 	struct task_desc *task;
 	pthread_attr_t attr;
@@ -687,6 +691,8 @@ static void create_tasks(struct perf_sched *sched)
 }
 
 static void wait_for_tasks(struct perf_sched *sched)
+	EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex)
+	EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex)
 {
 	u64 cpu_usage_0, cpu_usage_1;
 	struct task_desc *task;
@@ -738,6 +744,8 @@ static void wait_for_tasks(struct perf_sched *sched)
 }
 
 static void run_one_test(struct perf_sched *sched)
+	EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex)
+	EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex)
 {
 	u64 T0, T1, delta, avg_delta, fluct;
 
@@ -3309,11 +3317,15 @@ static int perf_sched__replay(struct perf_sched *sched)
 	print_task_traces(sched);
 	add_cross_task_wakeups(sched);
 
+	sched->thread_funcs_exit = false;
 	create_tasks(sched);
 	printf("------------------------------------------------------------\n");
 	for (i = 0; i < sched->replay_repeat; i++)
 		run_one_test(sched);
 
+	sched->thread_funcs_exit = true;
+	mutex_unlock(&sched->start_work_mutex);
+	mutex_unlock(&sched->work_done_wait_mutex);
 	return 0;
 }