rcu: Reduce synchronize_rcu_expedited() latency

The synchronize_rcu_expedited() function disables interrupts across a
scan of all leaf rcu_node structures, which is not good for real-time
scheduling latency on large systems (hundreds or especially thousands
of CPUs).  This commit therefore holds off CPU-hotplug operations using
get_online_cpus(), and removes the prior acquisiion of the ->onofflock
(which required disabling interrupts).

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

kernel/rcutree_plugin.h

@@ -799,34 +799,48 @@ void synchronize_rcu_expedited(void)
 	snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
 	smp_mb(); /* Above access cannot bleed into critical section. */
 
+	/*
+	 * Block CPU-hotplug operations.  This means that any CPU-hotplug
+	 * operation that finds an rcu_node structure with tasks in the
+	 * process of being boosted will know that all tasks blocking
+	 * this expedited grace period will already be in the process of
+	 * being boosted.  This simplifies the process of moving tasks
+	 * from leaf to root rcu_node structures.
+	 */
+	get_online_cpus();
+
 	/*
 	 * Acquire lock, falling back to synchronize_rcu() if too many
 	 * lock-acquisition failures.  Of course, if someone does the
 	 * expedited grace period for us, just leave.
 	 */
 	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
+		if (ULONG_CMP_LT(snap,
+		    ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+			put_online_cpus();
+			goto mb_ret; /* Others did our work for us. */
+		}
 		if (trycount++ < 10) {
 			udelay(trycount * num_online_cpus());
 		} else {
+			put_online_cpus();
 			synchronize_rcu();
 			return;
 		}
-		if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count)))
-			goto mb_ret; /* Others did our work for us. */
 	}
-	if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count)))
+	if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+		put_online_cpus();
 		goto unlock_mb_ret; /* Others did our work for us. */
+	}
 
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
-	raw_spin_lock_irqsave(&rsp->onofflock, flags);
-
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rnp->expmask = rnp->qsmaskinit;
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
 	/* Snapshot current state of ->blkd_tasks lists. */
@@ -835,7 +849,7 @@ void synchronize_rcu_expedited(void)
 	if (NUM_RCU_NODES > 1)
 		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
 
-	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+	put_online_cpus();
 
 	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);