rcu: Move grace-period pre-init delay after pre-init

The main race with the early part of grace-period initialization appears
to be with CPU hotplug.  To more fully open this race window, this commit
moves the rcu_gp_slow() from the beginning of the early initialization
loop to follow that loop, thus widening the race window, especially for
the rcu_node structures that are initialized last.  This commit also
expands rcutree.gp_preinit_delay from 3 to 12, giving the same overall
delay in the grace period, but concentrated in the spot where it will
do the most good.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.c

@@ -1900,7 +1900,6 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * will handle subsequent offline CPUs.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
-		rcu_gp_slow(rsp, gp_preinit_delay);
 		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -1945,6 +1944,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		raw_spin_unlock_irq_rcu_node(rnp);
 		spin_unlock(&rsp->ofl_lock);
 	}
+	rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node

tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot

 rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2