rcu: Extend expedited funnel locking to rcu_data structure

The strictly rcu_node based funnel-locking scheme works well in many
cases, but systems with CONFIG_RCU_FANOUT_LEAF=64 won't necessarily get
all that much concurrency.  This commit therefore extends the funnel
locking into the per-CPU rcu_data structure, providing concurrency equal
to the number of CPUs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 5c1042d..efee84c 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -364,11 +364,12 @@
 	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
-	/* 6) _rcu_barrier() and OOM callbacks. */
+	/* 6) _rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+	struct mutex exp_funnel_mutex;
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
@@ -494,6 +495,7 @@
 	atomic_long_t expedited_tryfail;	/* # acquisition failures. */
 	atomic_long_t expedited_workdone1;	/* # done by others #1. */
 	atomic_long_t expedited_workdone2;	/* # done by others #2. */
+	atomic_long_t expedited_workdone3;	/* # done by others #3. */
 	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */