rcu: Introduce proper blocking to no-CBs kthreads GP waits

Currently, the no-CBs kthreads do repeated timed waits for grace periods
to elapse.  This is crude and energy inefficient, so this commit allows
no-CBs kthreads to specify exactly which grace period they are waiting
for and also allows them to block for the entire duration until the
desired grace period completes.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 6ad0716..433f426 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -310,7 +310,7 @@
 
 	if (rcu_gp_in_progress(rsp))
 		return 0;  /* No, a grace period is already in progress. */
-	if (rcu_nocb_needs_gp(rdp))
+	if (rcu_nocb_needs_gp(rsp))
 		return 1;  /* Yes, a no-CBs CPU needs one. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL])
 		return 0;  /* No, this is a no-CBs (or offline) CPU. */
@@ -1364,6 +1364,7 @@
 static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
+	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1394,11 +1395,13 @@
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
 		rnp->completed = rsp->gpnum;
+		nocb += rcu_nocb_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
 	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
@@ -3084,6 +3087,7 @@
 			}
 			rnp->level = i;
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
+			rcu_init_one_nocb(rnp);
 		}
 	}