diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c885daae68c8ee9687ea6be1fdb17ce3d3bf603b..beef981aa54f34f40478b019f2afe7e0d81d4c7b 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/completion.h>
 
 /* This is the range of ioctl() numbers we claim as ours */
 #define AUTOFS_IOC_FIRST     AUTOFS_IOC_READY
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 591b6c16f9c12e08c6e91c51f6309fb3d73b8533..d2e38dc6172c0670472e654103f2f0bfa0d1b2ba 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -11,6 +11,7 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 #include <linux/stringhash.h>
+#include <linux/wait.h>
 
 struct path;
 struct vfsmount;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6ade6a52d9d42b731fef1b68c9f44dd91928f26c..de88b33c0974877bdaac25c0759f8f4d0ea3808b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,7 +40,6 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
-#include <linux/completion.h>
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
@@ -226,45 +225,6 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
-/*
- * Structure allowing asynchronous waiting on RCU.
- */
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
-};
-void wakeme_after_rcu(struct rcu_head *head);
-
-void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
-		   struct rcu_synchronize *rs_array);
-
-#define _wait_rcu_gp(checktiny, ...) \
-do {									\
-	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
-	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
-	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
-			__crcu_array, __rs_array);			\
-} while (0)
-
-#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
-
-/**
- * synchronize_rcu_mult - Wait concurrently for multiple grace periods
- * @...: List of call_rcu() functions for the flavors to wait on.
- *
- * This macro waits concurrently for multiple flavors of RCU grace periods.
- * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
- * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
- * domain requires you to write a wrapper function for that SRCU domain's
- * call_srcu() function, supplying the corresponding srcu_struct.
- *
- * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
- * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
- * is automatically a grace period.
- */
-#define synchronize_rcu_mult(...) \
-	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
-
 /**
  * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
  * @head: structure to be used for queueing the RCU updates.
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
new file mode 100644
index 0000000000000000000000000000000000000000..e774b4f5f220da5407eabe14e9fe7777481d7574
--- /dev/null
+++ b/include/linux/rcupdate_wait.h
@@ -0,0 +1,50 @@
+#ifndef _LINUX_SCHED_RCUPDATE_WAIT_H
+#define _LINUX_SCHED_RCUPDATE_WAIT_H
+
+/*
+ * RCU synchronization types and methods:
+ */
+
+#include <linux/rcupdate.h>
+#include <linux/completion.h>
+
+/*
+ * Structure allowing asynchronous waiting on RCU.
+ */
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+void wakeme_after_rcu(struct rcu_head *head);
+
+void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+		   struct rcu_synchronize *rs_array);
+
+#define _wait_rcu_gp(checktiny, ...) \
+do {									\
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
+	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
+	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
+			__crcu_array, __rs_array);			\
+} while (0)
+
+#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
+
+/**
+ * synchronize_rcu_mult - Wait concurrently for multiple grace periods
+ * @...: List of call_rcu() functions for the flavors to wait on.
+ *
+ * This macro waits concurrently for multiple flavors of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
+ * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
+ * domain requires you to write a wrapper function for that SRCU domain's
+ * call_srcu() function, supplying the corresponding srcu_struct.
+ *
+ * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
+ * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
+ * is automatically a grace period.
+ */
+#define synchronize_rcu_mult(...) \
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+
+#endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 4f9b2fa2173d692aac0ec3b4011456a3823105d4..b452953e21c8ae0b311a29d2af46a2a4d3036ce7 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -53,15 +53,8 @@ static inline void cond_synchronize_sched(unsigned long oldstate)
 	might_sleep();
 }
 
-static inline void rcu_barrier_bh(void)
-{
-	wait_rcu_gp(call_rcu_bh);
-}
-
-static inline void rcu_barrier_sched(void)
-{
-	wait_rcu_gp(call_rcu_sched);
-}
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 static inline void synchronize_rcu_expedited(void)
 {
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e773129c8b08d29d0ce81cbdbc195bed905b2562..ef3bcfb15b39ec4815275077d3e79825db740a27 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 fa6a48d3917bf26ce12f18aa2c94de0c65854323..6ad330dbbae2ec3fa4f74fdc1cc1a2ff1154bc9d 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 d80e0d2f68c675de3d95a89ad22a09465a2a995b..cb62ce23ffc7da2c81fcb259aade7ecc53b65a25 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 9e03db9ea9c09c422625537c80a16a020fe0bda0..a0e90e0afc755e4ba3db2037c7ed47bf0a12c294 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
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d51ec65dc73496476dfb11a173c5eccc86c7459..1bd317db98108ace615b174d16537bd1a0295215 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10,6 +10,7 @@
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
 #include <linux/context_tracking.h>
+#include <linux/rcupdate_wait.h>
 
 #include <linux/blkdev.h>
 #include <linux/kprobes.h>