rcu: Refactor code a bit in rcu_nocb_do_flush_bypass()

This consolidates the code a bit and makes it cleaner. Functionally it
is the same.
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree_nocb.h

@@ -327,10 +327,11 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
  *
  * Note that this function always returns true if rhp is NULL.
  */
-static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp_in,
 				     unsigned long j, bool lazy)
 {
 	struct rcu_cblist rcl;
+	struct rcu_head *rhp = rhp_in;
 
 	WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp));
 	rcu_lockdep_assert_cblist_protected(rdp);
@@ -345,16 +346,16 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 
 	/*
 	 * If the new CB requested was a lazy one, queue it onto the main
-	 * ->cblist so we can take advantage of a sooner grade period.
+	 * ->cblist so that we can take advantage of the grace-period that will
+	 * happen regardless. But queue it onto the bypass list first so that
+	 * the lazy CB is ordered with the existing CBs in the bypass list.
 	 */
 	if (lazy && rhp) {
-		rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, NULL);
-		rcu_cblist_enqueue(&rcl, rhp);
-		WRITE_ONCE(rdp->lazy_len, 0);
-	} else {
-		rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
-		WRITE_ONCE(rdp->lazy_len, 0);
+		rcu_cblist_enqueue(&rdp->nocb_bypass, rhp);
+		rhp = NULL;
 	}
+	rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
+	WRITE_ONCE(rdp->lazy_len, 0);
 
 	rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl);
 	WRITE_ONCE(rdp->nocb_bypass_first, j);