locking/lockdep: Avoid struct return in lock_stats()

Returning a large structure from the lock_stats() function causes clang
to have multiple copies of it on the stack and copy between them, which
can end up exceeding the frame size warning limit:

kernel/locking/lockdep.c:300:25: error: stack frame size (1464) exceeds limit (1280) in 'lock_stats' [-Werror,-Wframe-larger-than]
  300 | struct lock_class_stats lock_stats(struct lock_class *class)

Change the calling conventions to directly operate on the caller's copy,
which apparently is what gcc does already.

Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Boqun Feng <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: arndb

include/linux/lockdep_types.h

@@ -175,7 +175,7 @@ struct lock_class_stats {
 	unsigned long			bounces[nr_bounce_types];
 };
 
-struct lock_class_stats lock_stats(struct lock_class *class);
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats);
 void clear_lock_stats(struct lock_class *class);
 #endif
 

kernel/locking/lockdep.c

@@ -297,33 +297,30 @@ static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
 	dst->nr += src->nr;
 }
 
-struct lock_class_stats lock_stats(struct lock_class *class)
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats)
 {
-	struct lock_class_stats stats;
 	int cpu, i;
 
-	memset(&stats, 0, sizeof(struct lock_class_stats));
+	memset(stats, 0, sizeof(struct lock_class_stats));
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *pcs =
 			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
-			stats.contention_point[i] += pcs->contention_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contention_point); i++)
+			stats->contention_point[i] += pcs->contention_point[i];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
-			stats.contending_point[i] += pcs->contending_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contending_point); i++)
+			stats->contending_point[i] += pcs->contending_point[i];
 
-		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
-		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
+		lock_time_add(&pcs->read_waittime, &stats->read_waittime);
+		lock_time_add(&pcs->write_waittime, &stats->write_waittime);
 
-		lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
-		lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);
+		lock_time_add(&pcs->read_holdtime, &stats->read_holdtime);
+		lock_time_add(&pcs->write_holdtime, &stats->write_holdtime);
 
-		for (i = 0; i < ARRAY_SIZE(stats.bounces); i++)
-			stats.bounces[i] += pcs->bounces[i];
+		for (i = 0; i < ARRAY_SIZE(stats->bounces); i++)
+			stats->bounces[i] += pcs->bounces[i];
 	}
-
-	return stats;
 }
 
 void clear_lock_stats(struct lock_class *class)

kernel/locking/lockdep_proc.c

@@ -657,7 +657,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 			if (!test_bit(idx, lock_classes_in_use))
 				continue;
 			iter->class = class;
-			iter->stats = lock_stats(class);
+			lock_stats(class, &iter->stats);
 			iter++;
 		}