rcu: optimize rcutiny

rcu_sched_qs() currently calls local_irq_save()/local_irq_restore() up
to three times.

Remove irq masking from rcu_qsctr_help() / invoke_rcu_kthread()
and do it once in rcu_sched_qs() / rcu_bh_qs()

This generates smaller code as well.

   text	   data	    bss	    dec	    hex	filename
   2314	    156	     24	   2494	    9be	kernel/rcutiny.old.o
   2250	    156	     24	   2430	    97e	kernel/rcutiny.new.o

Fix an outdated comment for rcu_qsctr_help()
Move invoke_rcu_kthread() definition before its use.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

kernel/rcutiny.c

@@ -40,10 +40,10 @@
 static struct task_struct *rcu_kthread_task;
 static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
 static unsigned long have_rcu_kthread_work;
-static void invoke_rcu_kthread(void);
 
 /* Forward declarations for rcutiny_plugin.h. */
 struct rcu_ctrlblk;
+static void invoke_rcu_kthread(void);
 static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
 static int rcu_kthread(void *arg);
 static void __call_rcu(struct rcu_head *head,
@@ -79,26 +79,31 @@ void rcu_exit_nohz(void)
 #endif /* #ifdef CONFIG_NO_HZ */
 
 /*
- * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
- * Also disable irqs to avoid confusion due to interrupt handlers
+ * Helper function for rcu_sched_qs() and rcu_bh_qs().
+ * Also irqs are disabled to avoid confusion due to interrupt handlers
  * invoking call_rcu().
  */
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	if (rcp->rcucblist != NULL &&
 	    rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
-		local_irq_restore(flags);
 		return 1;
 	}
-	local_irq_restore(flags);
 
 	return 0;
 }
 
+/*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+	have_rcu_kthread_work = 1;
+	wake_up(&rcu_kthread_wq);
+}
+
 /*
  * Record an rcu quiescent state.  And an rcu_bh quiescent state while we
  * are at it, given that any rcu quiescent state is also an rcu_bh
@@ -106,9 +111,13 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  */
 void rcu_sched_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
 	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -116,8 +125,12 @@ void rcu_sched_qs(int cpu)
  */
 void rcu_bh_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -207,20 +220,6 @@ static int rcu_kthread(void *arg)
 	return 0;  /* Not reached, but needed to shut gcc up. */
 }
 
-/*
- * Wake up rcu_kthread() to process callbacks now eligible for invocation
- * or to boost readers.
- */
-static void invoke_rcu_kthread(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	have_rcu_kthread_work = 1;
-	wake_up(&rcu_kthread_wq);
-	local_irq_restore(flags);
-}
-
 /*
  * Wait for a grace period to elapse.  But it is illegal to invoke
  * synchronize_sched() from within an RCU read-side critical section.