diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 564096e6e141..ee40d7eba741 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -34,16 +34,14 @@
 #define __LINUX_RCUPDATE_H
 
 #include <linux/types.h>
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-#include <linux/lockdep.h>
-#include <linux/bug.h>
 #include <linux/compiler.h>
-#include <linux/ktime.h>
+#include <linux/atomic.h>
 #include <linux/irqflags.h>
+#include <linux/preempt.h>
+#include <linux/bottom_half.h>
+#include <linux/lockdep.h>
+#include <asm/processor.h>
+#include <linux/cpumask.h>
 
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
@@ -856,14 +854,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
-#ifdef CONFIG_TINY_RCU
-static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	*nextevt = KTIME_MAX;
-	return 0;
-}
-#endif /* #ifdef CONFIG_TINY_RCU */
-
 /* Only for use by adaptive-ticks code. */
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 bool rcu_sys_is_idle(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 2bfe48bc0e3b..c869785f16bd 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -25,7 +25,7 @@
 #ifndef __LINUX_TINY_H
 #define __LINUX_TINY_H
 
-#include <linux/cache.h>
+#include <linux/ktime.h>
 
 struct rcu_dynticks;
 static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
@@ -96,6 +96,12 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 		rcu_note_voluntary_context_switch_lite(current); \
 	} while (0)
 
+static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+{
+	*nextevt = KTIME_MAX;
+	return 0;
+}
+
 /*
  * Take advantage of the fact that there is only one CPU, which
  * allows us to ignore virtualization-based context switches.