[RFC 3/5] powerpc: atomic: implement atomic{, 64}_{add, sub}_return_* variants

[Boqun Feng]

On powerpc, we don't need a general memory barrier to achieve acquire and
release semantics, so arch_atomic_op_{acquire,release} can be implemented
using "lwsync" and "isync".

For release semantics, since we only need to ensure all memory accesses
that issue before must take effects before the -store- part of the
atomics, "lwsync" is what we only need. On the platform without
"lwsync", "sync" should be used. Therefore, smp_lwsync() is used here.

For acquire semantics, "lwsync" is what we only need for the similar
reason.  However on the platform without "lwsync", we can use "isync"
rather than "sync" as an acquire barrier. So a new kind of barrier
smp_acquire_barrier__after_atomic() is introduced, which is barrier() on
UP, "lwsync" if available and "isync" otherwise.

For full ordered semantics, like the original ones, smp_lwsync() is put
before relaxed variants and smp_mb__after_atomic() is put after.

Signed-off-by: Boqun Feng <boqun.feng at gmail.com>
---
 arch/powerpc/include/asm/atomic.h | 88 ++++++++++++++++++++++++++++-----------
 1 file changed, 64 insertions(+), 24 deletions(-)

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 55f106e..806ce50 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -12,6 +12,39 @@
 
 #define ATOMIC_INIT(i)		{ (i) }
 
+/*
+ * Since {add,sub}_return_relaxed and 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.
+ */
+#ifdef CONFIG_SMP
+#define smp_acquire_barrier__after_atomic() \
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER : : : "memory")
+#else
+#define smp_acquire_barrier__after_atomic() barrier()
+#endif
+#define arch_atomic_op_acquire(op, args...)				\
+({									\
+	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
+	smp_acquire_barrier__after_atomic();				\
+	__ret;								\
+})
+
+#define arch_atomic_op_release(op, args...)				\
+({									\
+	smp_lwsync();							\
+	op##_relaxed(args);						\
+})
+
+#define arch_atomic_op_fence(op, args...)				\
+({									\
+	typeof(op##_relaxed(args)) __ret;				\
+	smp_lwsync();							\
+	__ret = op##_relaxed(args);					\
+	smp_mb__after_atomic();						\
+	__ret;								\
+})
+
 static __inline__ int atomic_read(const atomic_t *v)
 {
 	int t;
@@ -42,27 +75,27 @@ 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 +104,11 @@ 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)
@@ -285,26 +321,27 @@ 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 +349,11 @@ 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)
-- 
2.5.0