[PATCH tip/core/rcu 1/2] rcu: Make expedited grace period use direct call on last leaf

[Paul E. McKenney]

During expedited grace-period initialization, a work item is scheduled
for each leaf rcu_node structure.  However, that initialization code
is itself (normally) executing from a workqueue, so one of the leaf
rcu_node structures could just as well be handled by that pre-existing
workqueue, and with less overhead.  This commit therefore uses a
shiny new rcu_is_leaf_node() macro to execute the last leaf rcu_node
structure's initialization directly from the pre-existing workqueue.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
---
 kernel/rcu/rcu.h      | 3 +++
 kernel/rcu/tree_exp.h | 5 +++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 40cea6735c2d..db0870acfdff 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -276,6 +276,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 /* Is this rcu_node a leaf? */
 #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
 
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
 /*
  * Do a full breadth-first scan of the rcu_node structures for the
  * specified rcu_state structure.
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..c6385ee1af65 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -486,8 +486,9 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		rnp->rew.rew_func = func;
 		rnp->rew.rew_rsp = rsp;
 		if (!READ_ONCE(rcu_par_gp_wq) ||
-		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
-			/* No workqueues yet. */
+		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+		    rcu_is_last_leaf_node(rsp, rnp)) {
+			/* No workqueues yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
 		}
-- 
2.17.1