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 <[e-mail]>
Cc: Mike Galbraith <[e-mail]>
Cc: Paul E. McKenney <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: [e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

fs/autofs4/autofs_i.h

···
 #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

include/linux/dcache.h

···
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 #include <linux/stringhash.h>
+#include <linux/wait.h>
 
 struct path;
 struct vfsmount;

include/linux/rcupdate.h

···
 #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>
···
 		    rcu_callback_t func);
 
 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

include/linux/rcupdate_wait.h

···
+#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 */

include/linux/rcutiny.h

···
 	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)
 {

kernel/rcu/srcu.c

···
 #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>

kernel/rcu/tiny.c

···
 #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>
···
 		       struct rcu_ctrlblk *rcp);
 
 #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)
 

kernel/rcu/tree.c

···
 #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>

kernel/rcu/update.c

···
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_wait.h>
 
 #define CREATE_TRACE_POINTS
 

kernel/sched/core.c

···
 #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>