rcu: Support direct wake-up of synchronize_rcu() users

This patch introduces a small enhancement which allows to do a
direct wake-up of synchronize_rcu() callers. It occurs after a
completion of grace period, thus by the gp-kthread.

Number of clients is limited by the hard-coded maximum allowed
threshold. The remaining part, if still exists is deferred to
a main worker.

Link: https://lore.kernel.org/lkml/Zd0ZtNu+Rt0qXkfS@lothringen/Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>

kernel/rcu/tree.c

@@ -1645,7 +1645,8 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
  */
 static void rcu_sr_normal_gp_cleanup(void)
 {
-	struct llist_node *wait_tail;
+	struct llist_node *wait_tail, *next, *rcu;
+	int done = 0;
 
 	wait_tail = rcu_state.srs_wait_tail;
 	if (wait_tail == NULL)
@@ -1653,11 +1654,32 @@ static void rcu_sr_normal_gp_cleanup(void)
 
 	rcu_state.srs_wait_tail = NULL;
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail);
+	WARN_ON_ONCE(!rcu_sr_is_wait_head(wait_tail));
+
+	/*
+	 * Process (a) and (d) cases. See an illustration.
+	 */
+	llist_for_each_safe(rcu, next, wait_tail->next) {
+		if (rcu_sr_is_wait_head(rcu))
+			break;
+
+		rcu_sr_normal_complete(rcu);
+		// It can be last, update a next on this step.
+		wait_tail->next = next;
+
+		if (++done == SR_MAX_USERS_WAKE_FROM_GP)
+			break;
+	}
 
 	// concurrent sr_normal_gp_cleanup work might observe this update.
 	smp_store_release(&rcu_state.srs_done_tail, wait_tail);
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail);
 
+	/*
+	 * We schedule a work in order to perform a final processing
+	 * of outstanding users(if still left) and releasing wait-heads
+	 * added by rcu_sr_normal_gp_init() call.
+	 */
 	schedule_work(&rcu_state.srs_cleanup_work);
 }
 

kernel/rcu/tree.h

@@ -315,6 +315,12 @@ do {									\
 	__set_current_state(TASK_RUNNING);				\
 } while (0)
 
+/*
+ * A max threshold for synchronize_rcu() users which are
+ * awaken directly by the rcu_gp_kthread(). Left part is
+ * deferred to the main worker.
+ */
+#define SR_MAX_USERS_WAKE_FROM_GP 5
 #define SR_NORMAL_GP_WAIT_HEAD_MAX 5
 
 struct sr_wait_node {