rcu: Clear .exp_hint only when deferred quiescent state has been reported

Currently, the .exp_hint flag is cleared in rcu_read_unlock_special(),
which works, but which can also prevent subsequent rcu_read_unlock() calls
from helping expedite the quiescent state needed by an ongoing expedited
RCU grace period.  This commit therefore defers clearing of .exp_hint
from rcu_read_unlock_special() to rcu_preempt_deferred_qs_irqrestore(),
thus ensuring that intervening calls to rcu_read_unlock() have a chance
to help end the expedited grace period.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree_plugin.h

@@ -444,6 +444,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		local_irq_restore(flags);
 		return;
 	}
+	t->rcu_read_unlock_special.b.exp_hint = false;
 	t->rcu_read_unlock_special.b.deferred_qs = false;
 	if (special.b.need_qs) {
 		rcu_qs();
@@ -610,7 +611,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		t->rcu_read_unlock_special.b.exp_hint = false;
 		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
 		      (rdp->grpmask & rnp->expmask) ||
 		      tick_nohz_full_cpu(rdp->cpu);
@@ -640,7 +640,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		local_irq_restore(flags);
 		return;
 	}
-	WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
 }