rcu: Initialize and destroy rcu_synchronize only when necessary

The __wait_rcu_gp() function unconditionally initializes and cleans up
each element of rs_array[], whether used or not.  This is slightly
wasteful and rather confusing, so this commit skips both initialization
and cleanup for duplicate callback functions.
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/update.c

@@ -390,14 +390,15 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 			might_sleep();
 			continue;
 		}
-		init_rcu_head_on_stack(&rs_array[i].head);
-		init_completion(&rs_array[i].completion);
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
+			init_rcu_head_on_stack(&rs_array[i].head);
+			init_completion(&rs_array[i].completion);
 			(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
 		}
+	}
 
 	/* Wait for all callbacks to be invoked. */
 	for (i = 0; i < n; i++) {
@@ -407,10 +408,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
 			wait_for_completion(&rs_array[i].completion);
 			destroy_rcu_head_on_stack(&rs_array[i].head);
 		}
+	}
 }
 EXPORT_SYMBOL_GPL(__wait_rcu_gp);