rcu/nocb: Reduce contention at no-CBs registry-time CB advancement

Currently, __call_rcu_nocb_wake() conditionally acquires the leaf rcu_node
structure's ->lock, and only afterwards does rcu_advance_cbs_nowake()
check to see if it is possible to advance callbacks without potentially
needing to awaken the grace-period kthread.  Given that the no-awaken
check can be done locklessly, this commit reverses the order, so that
rcu_advance_cbs_nowake() is invoked without holding the leaf rcu_node
structure's ->lock and rcu_advance_cbs_nowake() checks the grace-period
state before conditionally acquiring that lock, thus reducing the number
of needless acquistions of the leaf rcu_node structure's ->lock.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>

kernel/rcu/tree.c

@@ -1341,10 +1341,11 @@ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
 static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
-	raw_lockdep_assert_held_rcu_node(rnp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
+	    !raw_spin_trylock_rcu_node(rnp))
 		return;
 	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	raw_spin_unlock_rcu_node(rnp);
 }
 
 /*

kernel/rcu/tree_plugin.h

@@ -1668,10 +1668,8 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		if (!rdp->nocb_cb_sleep &&
 		    rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			// Already going full tilt, so don't try to rewake.
-		} else if (rcu_segcblist_pend_cbs(&rdp->cblist) &&
-			   raw_spin_trylock_rcu_node(rdp->mynode)) {
+		} else if (rcu_segcblist_pend_cbs(&rdp->cblist)) {
 			rcu_advance_cbs_nowake(rdp->mynode, rdp);
-			raw_spin_unlock_rcu_node(rdp->mynode);
 		} else {
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE,
 					   TPS("WakeOvfIsDeferred"));