rcu: Separate the RCU synchronization types and APIs into <linux/rcupdate_wait.h>

So rcupdate.h is a pretty complex header, in particular it includes
<linux/completion.h> which includes <linux/wait.h> - creating a
dependency that includes <linux/wait.h> in <linux/sched.h>,
which prevents the isolation of <linux/sched.h> from the derived
<linux/wait.h> header.

Solve part of the problem by decoupling rcupdate.h from completions:
this can be done by separating out the rcu_synchronize types and APIs,
and updating their usage sites.

Since this is a mostly RCU-internal types this will not just simplify
<linux/sched.h>'s dependencies, but will make all the hundreds of
.c files that include rcupdate.h but not completions or wait.h build
faster.

( For rcutiny this means that two dependent APIs have to be uninlined,
  but that shouldn't be much of a problem as they are rare variants. )

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e773129..ef3bcfb 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -30,7 +30,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index fa6a48d..6ad330d 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -25,7 +25,7 @@
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
@@ -47,6 +47,18 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "tiny_plugin.h"
 
+void rcu_barrier_bh(void)
+{
+	wait_rcu_gp(call_rcu_bh);
+}
+EXPORT_SYMBOL(rcu_barrier_bh);
+
+void rcu_barrier_sched(void)
+{
+	wait_rcu_gp(call_rcu_sched);
+}
+EXPORT_SYMBOL(rcu_barrier_sched);
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d80e0d2..cb62ce2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -32,7 +32,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9e03db9..a0e90e0 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -49,6 +49,7 @@
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_wait.h>
 
 #define CREATE_TRACE_POINTS