[PATCH tip/locking/core v5 0/6] atomics: powerpc: Implement relaxed/acquire/release variants of some atomics

@@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");

@@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stdcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");

@@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 	unsigned int prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
 	cmpw	0,%0,%3\n\
 	bne-	2f\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)

@@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 	unsigned long prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
 	cmpd	0,%0,%3\n\
 	bne-	2f\n\
 	stdcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)

@@ -44,7 +44,7 @@ static inline void isync(void)
 	MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
 #define PPC_ACQUIRE_BARRIER	 "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
 #define PPC_RELEASE_BARRIER	 stringify_in_c(LWSYNC) "\n"
-#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n"
 #define PPC_ATOMIC_EXIT_BARRIER	 "\n" stringify_in_c(sync) "\n"
 #else
 #define PPC_ACQUIRE_BARRIER

@@ -27,6 +27,65 @@ do {								\
 		(unsigned long long)r);				\
 } while (0)
 
+/*
+ * Test for a atomic operation family,
+ * @test should be a macro accepting parameters (bit, op, ...)
+ */
+
+#define FAMILY_TEST(test, bit, op, args...)	\
+do {						\
+	test(bit, op, ##args);		\
+	test(bit, op##_acquire, ##args);	\
+	test(bit, op##_release, ##args);	\
+	test(bit, op##_relaxed, ##args);	\
+} while (0)
+
+#define TEST_RETURN(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != r);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
+#define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
+} while (0)
+
+#define TEST_ARGS(bit, op, init, ret, expect, args...)		\
+do {								\
+	atomic##bit##_set(&v, init);				\
+	BUG_ON(atomic##bit##_##op(&v, ##args) != ret);		\
+	BUG_ON(atomic##bit##_read(&v) != expect);		\
+} while (0)
+
+#define XCHG_FAMILY_TEST(bit, init, new)				\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, xchg, init, init, new, new);	\
+} while (0)
+
+#define CMPXCHG_FAMILY_TEST(bit, init, new, wrong)			\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg, 				\
+			init, init, new, init, new);			\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg,				\
+			init, init, init, wrong, new);			\
+} while (0)
+
+#define INC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, inc_return,		\
+			i, (i) + one, (i) + one);	\
+} while (0)
+
+#define DEC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, dec_return,		\
+			i, (i) - one, (i) - one);	\
+} while (0)
+
 static __init void test_atomic(void)
 {
 	int v0 = 0xaaa31337;

@@ -45,6 +104,18 @@ static __init void test_atomic(void)
 	TEST(, and, &=, v1);
 	TEST(, xor, ^=, v1);
 	TEST(, andnot, &= ~, v1);
+
+	RETURN_FAMILY_TEST(, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(, add_return, +=, -one);
+	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(, sub_return, -=, -one);
+
+	INC_RETURN_FAMILY_TEST(, v0);
+	DEC_RETURN_FAMILY_TEST(, v0);
+
+	XCHG_FAMILY_TEST(, v0, v1);
+	CMPXCHG_FAMILY_TEST(, v0, v1, onestwos);
+
 }
 
 #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)

@@ -74,25 +145,10 @@ static __init void test_atomic64(void)
 	TEST(64, xor, ^=, v1);
 	TEST(64, andnot, &= ~, v1);
 
-	INIT(v0);
-	r += onestwos;
-	BUG_ON(atomic64_add_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r += -one;
-	BUG_ON(atomic64_add_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= onestwos;
-	BUG_ON(atomic64_sub_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= -one;
-	BUG_ON(atomic64_sub_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
+	RETURN_FAMILY_TEST(64, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(64, add_return, +=, -one);
+	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
 	INIT(v0);
 	atomic64_inc(&v);

@@ -100,33 +156,15 @@ static __init void test_atomic64(void)
 	BUG_ON(v.counter != r);
 
 	INIT(v0);
-	r += one;
-	BUG_ON(atomic64_inc_return(&v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
 	atomic64_dec(&v);
 	r -= one;
 	BUG_ON(v.counter != r);
 
-	INIT(v0);
-	r -= one;
-	BUG_ON(atomic64_dec_return(&v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_xchg(&v, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
+	INC_RETURN_FAMILY_TEST(64, v0);
+	DEC_RETURN_FAMILY_TEST(64, v0);
 
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0);
-	BUG_ON(v.counter != r);
+	XCHG_FAMILY_TEST(64, v0, v1);
+	CMPXCHG_FAMILY_TEST(64, v0, v1, v2);
 
 	INIT(v0);
 	BUG_ON(atomic64_add_unless(&v, one, v0));

@@ -43,20 +43,29 @@ static inline int atomic_read_ctrl(const atomic_t *v)
  * The idea here is to build acquire/release variants by adding explicit
  * barriers on top of the relaxed variant. In the case where the relaxed
  * variant is already fully ordered, no additional barriers are needed.
+ *
+ * Besides, if an arch has a special barrier for acquire/release, it could
+ * implement its own __atomic_op_* and use the same framework for building
+ * variants
  */
+#ifndef __atomic_op_acquire
 #define __atomic_op_acquire(op, args...)				\
 ({									\
 	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
 	smp_mb__after_atomic();						\
 	__ret;								\
 })
+#endif
 
+#ifndef __atomic_op_release
 #define __atomic_op_release(op, args...)				\
 ({									\
 	smp_mb__before_atomic();					\
 	op##_relaxed(args);						\
 })
+#endif
 
+#ifndef __atomic_op_fence
 #define __atomic_op_fence(op, args...)					\
 ({									\
 	typeof(op##_relaxed(args)) __ret;				\

@@ -65,6 +74,7 @@ static inline int atomic_read_ctrl(const atomic_t *v)
 	smp_mb__after_atomic();						\
 	__ret;								\
 })
+#endif
 
 /* atomic_add_return_relaxed */
 #ifndef atomic_add_return_relaxed

@@ -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

@@ -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.

@@ -12,6 +12,24 @@
 
 #define ATOMIC_INIT(i)		{ (i) }
 
+/*
+ * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
+ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
+ * on the platform without lwsync.
+ */
+#define __atomic_op_acquire(op, args...)				\
+({									\
+	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
+	__ret;								\
+})
+
+#define __atomic_op_release(op, args...)				\
+({									\
+	smp_lwsync();							\
+	op##_relaxed(args);						\
+})
+
 static __inline__ int atomic_read(const atomic_t *v)
 {
 	int t;

@@ -42,27 +60,27 @@ static __inline__ void atomic_##op(int a, atomic_t *v)			\
 	: "cc");							\
 }									\
 
-#define ATOMIC_OP_RETURN(op, asm_op)					\
-static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
+#define ATOMIC_OP_RETURN_RELAXED(op, asm_op)				\
+static inline int atomic_##op##_return_relaxed(int a, atomic_t *v)	\
 {									\
 	int t;								\
 									\
 	__asm__ __volatile__(						\
-	PPC_ATOMIC_ENTRY_BARRIER					\
-"1:	lwarx	%0,0,%2		# atomic_" #op "_return\n"		\
-	#asm_op " %0,%1,%0\n"						\
-	PPC405_ERR77(0,%2)						\
-"	stwcx.	%0,0,%2 \n"						\
+"1:	lwarx	%0,0,%3		# atomic_" #op "_return_relaxed\n"	\
+	#asm_op " %0,%2,%0\n"						\
+	PPC405_ERR77(0, %3)						\
+"	stwcx.	%0,0,%3\n"						\
 "	bne-	1b\n"							\
-	PPC_ATOMIC_EXIT_BARRIER						\
-	: "=&r" (t)							\
+	: "=&r" (t), "+m" (v->counter)					\
 	: "r" (a), "r" (&v->counter)					\
-	: "cc", "memory");						\
+	: "cc");							\
 									\
 	return t;							\
 }
 
-#define ATOMIC_OPS(op, asm_op) ATOMIC_OP(op, asm_op) ATOMIC_OP_RETURN(op, asm_op)
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN_RELAXED(op, asm_op)
 
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)

@@ -71,8 +89,11 @@ ATOMIC_OP(and, and)
 ATOMIC_OP(or, or)
 ATOMIC_OP(xor, xor)
 
+#define atomic_add_return_relaxed atomic_add_return_relaxed
+#define atomic_sub_return_relaxed atomic_sub_return_relaxed
+
 #undef ATOMIC_OPS
-#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)

@@ -92,21 +113,19 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ int atomic_inc_return(atomic_t *v)
+static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
 	int t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# atomic_inc_return\n\
+"1:	lwarx	%0,0,%1		# atomic_inc_return_relaxed\n\
 	addic	%0,%0,1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }

@@ -136,25 +155,26 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ int atomic_dec_return(atomic_t *v)
+static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
 	int t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# atomic_dec_return\n\
+"1:	lwarx	%0,0,%1		# atomic_dec_return_relaxed\n\
 	addic	%0,%0,-1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
 
+#define atomic_inc_return_relaxed atomic_inc_return_relaxed
+#define atomic_dec_return_relaxed atomic_dec_return_relaxed
+
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 

@@ -285,26 +305,27 @@ static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
 	: "cc");							\
 }
 
-#define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
+#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+static inline long							\
+atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
 {									\
 	long t;								\
 									\
 	__asm__ __volatile__(						\
-	PPC_ATOMIC_ENTRY_BARRIER					\
-"1:	ldarx	%0,0,%2		# atomic64_" #op "_return\n"		\
-	#asm_op " %0,%1,%0\n"						\
-"	stdcx.	%0,0,%2 \n"						\
+"1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
+	#asm_op " %0,%2,%0\n"						\
+"	stdcx.	%0,0,%3\n"						\
 "	bne-	1b\n"							\
-	PPC_ATOMIC_EXIT_BARRIER						\
-	: "=&r" (t)							\
+	: "=&r" (t), "+m" (v->counter)					\
 	: "r" (a), "r" (&v->counter)					\
-	: "cc", "memory");						\
+	: "cc");							\
 									\
 	return t;							\
 }
 
-#define ATOMIC64_OPS(op, asm_op) ATOMIC64_OP(op, asm_op) ATOMIC64_OP_RETURN(op, asm_op)
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)

@@ -312,8 +333,11 @@ ATOMIC64_OP(and, and)
 ATOMIC64_OP(or, or)
 ATOMIC64_OP(xor, xor)
 
-#undef ATOMIC64_OPS
-#undef ATOMIC64_OP_RETURN
+#define atomic64_add_return_relaxed atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
+
+#undef ATOPIC64_OPS
+#undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)

@@ -332,20 +356,18 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ long atomic64_inc_return(atomic64_t *v)
+static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
 	long t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_inc_return\n\
 	addic	%0,%0,1\n\
 	stdcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }

@@ -374,24 +396,25 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ long atomic64_dec_return(atomic64_t *v)
+static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
 	long t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_dec_return\n\
 	addic	%0,%0,-1\n\
 	stdcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
 
+#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
+#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
+
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 

@@ -176,6 +176,11 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_dec_return_relaxed atomic_dec_return_relaxed
 
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+#define atomic_cmpxchg_relaxed(v, o, n) \
+	cmpxchg_relaxed(&((v)->counter), (o), (n))
+#define atomic_cmpxchg_acquire(v, o, n) \
+	cmpxchg_acquire(&((v)->counter), (o), (n))
+
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 

@@ -444,6 +449,11 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 }
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+#define atomic64_cmpxchg_relaxed(v, o, n) \
+	cmpxchg_relaxed(&((v)->counter), (o), (n))
+#define atomic64_cmpxchg_acquire(v, o, n) \
+	cmpxchg_acquire(&((v)->counter), (o), (n))
+
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 

@@ -181,6 +181,56 @@ __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
 	return prev;
 }
 
+static __always_inline unsigned long
+__cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+/*
+ * cmpxchg family don't have order guarantee if cmp part fails, therefore we
+ * can avoid superfluous barriers if we use assembly code to implement
+ * cmpxchg() and cmpxchg_acquire(), however we don't do the similar for
+ * cmpxchg_release() because that will result in putting a barrier in the
+ * middle of a ll/sc loop, which is probably a bad idea. For example, this
+ * might cause the conditional store more likely to fail.
+ */
+static __always_inline unsigned long
+__cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
 #ifdef CONFIG_PPC64
 static __always_inline unsigned long
 __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)

@@ -224,6 +274,46 @@ __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
 
 	return prev;
 }
+
+static __always_inline unsigned long
+__cmpxchg_u64_relaxed(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_relaxed\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_acquire\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
 #endif
 
 /* This function doesn't exist, so you'll get a linker error

@@ -262,6 +352,37 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 	return old;
 }
 
+static __always_inline unsigned long
+__cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_relaxed(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_relaxed(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_acquire(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_acquire(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
 #define cmpxchg(ptr, o, n)						 \
   ({									 \
      __typeof__(*(ptr)) _o_ = (o);					 \

@@ -279,6 +400,23 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 				    (unsigned long)_n_, sizeof(*(ptr))); \
   })
 
+#define cmpxchg_relaxed(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
+
+#define cmpxchg_acquire(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
 #ifdef CONFIG_PPC64
 #define cmpxchg64(ptr, o, n)						\
   ({									\

@@ -290,7 +428,16 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg_local((ptr), (o), (n));					\
   })
-#define cmpxchg64_relaxed	cmpxchg64_local
+#define cmpxchg64_relaxed(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_relaxed((ptr), (o), (n));				\
+})
+#define cmpxchg64_acquire(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_acquire((ptr), (o), (n));				\
+})
 #else
 #include <asm-generic/cmpxchg-local.h>
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))

@@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");

@@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stdcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");

@@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 	unsigned int prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
 	cmpw	0,%0,%3\n\
 	bne-	2f\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)

@@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 	unsigned long prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
 	cmpd	0,%0,%3\n\
 	bne-	2f\n\
 	stdcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)

@@ -44,7 +44,7 @@ static inline void isync(void)
 	MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
 #define PPC_ACQUIRE_BARRIER	 "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
 #define PPC_RELEASE_BARRIER	 stringify_in_c(LWSYNC) "\n"
-#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n"
 #define PPC_ATOMIC_EXIT_BARRIER	 "\n" stringify_in_c(sync) "\n"
 #else
 #define PPC_ACQUIRE_BARRIER