powerpc: atomic: Implement acquire/release/relaxed variants for xchg

Implement xchg{,64}_relaxed and atomic{,64}_xchg_relaxed, based on these
_relaxed variants, release/acquire variants and fully ordered versions
can be built.

Note that xchg{,64}_relaxed and atomic_{,64}_xchg_relaxed are not
compiler barriers.
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/atomic.h

@@ -177,6 +177,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
  * __atomic_add_unless - add unless the number is a given value
@@ -444,6 +445,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+#define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
  * atomic64_add_unless - add unless the number is a given value

arch/powerpc/include/asm/cmpxchg.h

@@ -9,21 +9,20 @@
 /*
  * Atomic exchange
  *
- * Changes the memory location '*ptr' to be val and returns
+ * Changes the memory location '*p' to be val and returns
  * the previous value stored there.
  */
+
 static __always_inline unsigned long
-__xchg_u32(volatile void *p, unsigned long val)
+__xchg_u32_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -31,42 +30,34 @@ __xchg_u32(volatile void *p, unsigned long val)
 	return prev;
 }
 
-/*
- * Atomic exchange
- *
- * Changes the memory location '*ptr' to be val and returns
- * the previous value stored there.
- */
 static __always_inline unsigned long
-__xchg_u32_local(volatile void *p, unsigned long val)
+__xchg_u32_relaxed(u32 *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+"1:	lwarx	%0,0,%2\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
 	: "r" (p), "r" (val)
-	: "cc", "memory");
+	: "cc");
 
 	return prev;
 }
 
 #ifdef CONFIG_PPC64
 static __always_inline unsigned long
-__xchg_u64(volatile void *p, unsigned long val)
+__xchg_u64_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stdcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -75,18 +66,18 @@ __xchg_u64(volatile void *p, unsigned long val)
 }
 
 static __always_inline unsigned long
-__xchg_u64_local(volatile void *p, unsigned long val)
+__xchg_u64_relaxed(u64 *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-"1:	ldarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stdcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+"1:	ldarx	%0,0,%2\n"
+	PPC405_ERR77(0, %2)
+"	stdcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
 	: "r" (p), "r" (val)
-	: "cc", "memory");
+	: "cc");
 
 	return prev;
 }
@@ -99,14 +90,14 @@ __xchg_u64_local(volatile void *p, unsigned long val)
 extern void __xchg_called_with_bad_pointer(void);
 
 static __always_inline unsigned long
-__xchg(volatile void *ptr, unsigned long x, unsigned int size)
+__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
 	case 4:
-		return __xchg_u32(ptr, x);
+		return __xchg_u32_local(ptr, x);
 #ifdef CONFIG_PPC64
 	case 8:
-		return __xchg_u64(ptr, x);
+		return __xchg_u64_local(ptr, x);
 #endif
 	}
 	__xchg_called_with_bad_pointer();
@@ -114,25 +105,19 @@ __xchg(volatile void *ptr, unsigned long x, unsigned int size)
 }
 
 static __always_inline unsigned long
-__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
+__xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
 	case 4:
-		return __xchg_u32_local(ptr, x);
+		return __xchg_u32_relaxed(ptr, x);
 #ifdef CONFIG_PPC64
 	case 8:
-		return __xchg_u64_local(ptr, x);
+		return __xchg_u64_relaxed(ptr, x);
 #endif
 	}
 	__xchg_called_with_bad_pointer();
 	return x;
 }
-#define xchg(ptr,x)							     \
-  ({									     \
-     __typeof__(*(ptr)) _x_ = (x);					     \
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
-  })
-
 #define xchg_local(ptr,x)						     \
   ({									     \
      __typeof__(*(ptr)) _x_ = (x);					     \
@@ -140,6 +125,12 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
      		(unsigned long)_x_, sizeof(*(ptr))); 			     \
   })
 
+#define xchg_relaxed(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
+			(unsigned long)_x_, sizeof(*(ptr)));		\
+})
 /*
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.