arm64: move percpu cmpxchg implementation from cmpxchg.h to percpu.h

We want to avoid pulling linux/preempt.h into cmpxchg.h, since that can
introduce a circular dependency on linux/bitops.h. linux/preempt.h is
only needed by the per-cpu cmpxchg implementation, which is better off
alongside the per-cpu xchg implementation in percpu.h, so move it there
and add the missing #include.
Reported-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/cmpxchg.h

@@ -196,32 +196,6 @@ __CMPXCHG_GEN(_mb)
 	__ret; \
 })
 
-/* this_cpu_cmpxchg */
-#define _protect_cmpxchg_local(pcp, o, n)			\
-({								\
-	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
-	preempt_disable();					\
-	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
-	preempt_enable();					\
-	__ret;							\
-})
-
-#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-
-#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
-({									\
-	int __ret;							\
-	preempt_disable();						\
-	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
-					raw_cpu_ptr(&(ptr2)),		\
-					o1, o2, n1, n2);		\
-	preempt_enable();						\
-	__ret;								\
-})
-
 #define __CMPWAIT_CASE(w, sz, name)					\
 static inline void __cmpwait_case_##name(volatile void *ptr,		\
 					 unsigned long val)		\

arch/arm64/include/asm/percpu.h

@@ -16,7 +16,10 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#include <linux/preempt.h>
+
 #include <asm/alternative.h>
+#include <asm/cmpxchg.h>
 #include <asm/stack_pointer.h>
 
 static inline void set_my_cpu_offset(unsigned long off)
@@ -197,6 +200,32 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	return ret;
 }
 
+/* this_cpu_cmpxchg */
+#define _protect_cmpxchg_local(pcp, o, n)			\
+({								\
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
+	preempt_disable();					\
+	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
+	preempt_enable();					\
+	__ret;							\
+})
+
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
+({									\
+	int __ret;							\
+	preempt_disable();						\
+	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
+					raw_cpu_ptr(&(ptr2)),		\
+					o1, o2, n1, n2);		\
+	preempt_enable();						\
+	__ret;								\
+})
+
 #define _percpu_read(pcp)						\
 ({									\
 	typeof(pcp) __retval;						\