rcu-tasks: Make Tasks RCU wait idly for grace-period delays

Currently, all waits for grace periods sleep at TASK_UNINTERRUPTIBLE,
regardless of RCU flavor. This has worked well, but there have been
cases where a longer-than-average Tasks RCU grace period has triggered
softlockup splats, many of them, before the Tasks RCU CPU stall warning
appears. These softlockup splats unnecessarily consume console bandwidth
and complicate diagnosis of the underlying problem. Plus a long but not
pathologically long Tasks RCU grace period might trigger a few softlockup
splats before completing normally, which generates noise for no good
reason.

This commit therefore causes Tasks RCU grace periods to sleep at TASK_IDLE
priority. If there really is a persistent problem, the eventual Tasks
RCU CPU stall warning will flag it, and without the extra noise.

Reported-by: Breno Leitao <[e-mail]>
Signed-off-by: Paul E. McKenney <[e-mail]>
Signed-off-by: Uladzislau Rezki (Sony) <[e-mail]>

include/linux/rcupdate_wait.h

···
 };
 void wakeme_after_rcu(struct rcu_head *head);
 
-void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array,
 		   struct rcu_synchronize *rs_array);
 
-#define _wait_rcu_gp(checktiny, ...) \
-do {									\
-	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
-	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
-	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
-			__crcu_array, __rs_array);			\
+#define _wait_rcu_gp(checktiny, state, ...) \
+do {												\
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };					\
+	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];				\
+	__wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array);	\
 } while (0)
 
-#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
+#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__)
+#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__)
 
 /**
  * synchronize_rcu_mult - Wait concurrently for multiple grace periods
···
  * grace period.
  */
 #define synchronize_rcu_mult(...) \
-	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__)
 
 static inline void cond_resched_rcu(void)
 {

kernel/rcu/tasks.h

···
  * @holdouts_func: This flavor's holdout-list scan function (optional).
  * @postgp_func: This flavor's post-grace-period function (optional).
  * @call_func: This flavor's call_rcu()-equivalent function.
+ * @wait_state: Task state for synchronous grace-period waits (default TASK_UNINTERRUPTIBLE).
  * @rtpcpu: This flavor's rcu_tasks_percpu structure.
  * @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks.
  * @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing.
···
 	holdouts_func_t holdouts_func;
 	postgp_func_t postgp_func;
 	call_rcu_func_t call_func;
+	unsigned int wait_state;
 	struct rcu_tasks_percpu __percpu *rtpcpu;
 	int percpu_enqueue_shift;
 	int percpu_enqueue_lim;
···
 	.tasks_gp_mutex = __MUTEX_INITIALIZER(rt_name.tasks_gp_mutex),			\
 	.gp_func = gp,									\
 	.call_func = call,								\
+	.wait_state = TASK_UNINTERRUPTIBLE,						\
 	.rtpcpu = &rt_name ## __percpu,							\
 	.lazy_jiffies = DIV_ROUND_UP(HZ, 4),						\
 	.name = n,									\
···
 
 	// If the grace-period kthread is running, use it.
 	if (READ_ONCE(rtp->kthread_ptr)) {
-		wait_rcu_gp(rtp->call_func);
+		wait_rcu_gp_state(rtp->wait_state, rtp->call_func);
 		return;
 	}
 	rcu_tasks_one_gp(rtp, true);
···
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
 	rcu_tasks.holdouts_func = check_all_holdout_tasks;
 	rcu_tasks.postgp_func = rcu_tasks_postgp;
+	rcu_tasks.wait_state = TASK_IDLE;
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
 	return 0;
 }

kernel/rcu/update.c

···
 }
 EXPORT_SYMBOL_GPL(wakeme_after_rcu);
 
-void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array,
 		   struct rcu_synchronize *rs_array)
 {
 	int i;
···
 			if (crcu_array[j] == crcu_array[i])
 				break;
 		if (j == i) {
-			wait_for_completion(&rs_array[i].completion);
+			wait_for_completion_state(&rs_array[i].completion, state);
 			destroy_rcu_head_on_stack(&rs_array[i].head);
 		}
 	}