[PATCH v4 07/10] riscv: Apply acquire/release semantics to arch_atomic operations

[Xu Lu]

The existing arch_atomic operations are implemented by inserting fence
instrucitons before or after atomic instructions. This commit replaces
them with real acquire/release semantics.

|-----------------------------------------------|
|    | arch_atomic(64)_{add|sub}_return_release |
| rl |------------------------------------------|
|    |                amoadd.rl                 |
|-----------------------------------------------|
|    | arch_atomic(64)_{add|sub}_return_acquire |
| aq |------------------------------------------|
|    |                amoadd.aq                 |
|-----------------------------------------------|

|---------------------------------------------------------|
|    | arch_atomic(64)_fetch_{add|sub|and|or|xor}_release |
| rl |----------------------------------------------------|
|    |               amo{add|and|or|xor}.rl               |
|---------------------------------------------------------|
|    | arch_atomic(64)_fetch_{add|sub|and|or|xor}_acquire |
| aq |----------------------------------------------------|
|    |               amo{add|and|or|xor}.aq               |
|---------------------------------------------------------|

Signed-off-by: Xu Lu <luxu.kernel at bytedance.com>
---
 arch/riscv/include/asm/atomic.h | 64 +++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 5b96c2f61adb5..86291de07de62 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -98,6 +98,30 @@ c_type arch_atomic##prefix##_fetch_##op##_relaxed(c_type i,		\
 	return ret;							\
 }									\
 static __always_inline							\
+c_type arch_atomic##prefix##_fetch_##op##_acquire(c_type i,		\
+						  atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type ".aq %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
+}									\
+static __always_inline							\
+c_type arch_atomic##prefix##_fetch_##op##_release(c_type i,		\
+						  atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type ".rl %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
+}									\
+static __always_inline							\
 c_type arch_atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v)	\
 {									\
 	register c_type ret;						\
@@ -117,6 +141,18 @@ c_type arch_atomic##prefix##_##op##_return_relaxed(c_type i,		\
         return arch_atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I;	\
 }									\
 static __always_inline							\
+c_type arch_atomic##prefix##_##op##_return_acquire(c_type i,		\
+						   atomic##prefix##_t *v)	\
+{									\
+	return arch_atomic##prefix##_fetch_##op##_acquire(i, v) c_op I;	\
+}									\
+static __always_inline							\
+c_type arch_atomic##prefix##_##op##_return_release(c_type i,		\
+						   atomic##prefix##_t *v)	\
+{									\
+	return arch_atomic##prefix##_fetch_##op##_release(i, v) c_op I;	\
+}									\
+static __always_inline							\
 c_type arch_atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v)	\
 {									\
         return arch_atomic##prefix##_fetch_##op(i, v) c_op I;		\
@@ -139,22 +175,38 @@ ATOMIC_OPS(sub, add, +, -i)
 
 #define arch_atomic_add_return_relaxed	arch_atomic_add_return_relaxed
 #define arch_atomic_sub_return_relaxed	arch_atomic_sub_return_relaxed
+#define arch_atomic_add_return_acquire	arch_atomic_add_return_acquire
+#define arch_atomic_sub_return_acquire	arch_atomic_sub_return_acquire
+#define arch_atomic_add_return_release	arch_atomic_add_return_release
+#define arch_atomic_sub_return_release	arch_atomic_sub_return_release
 #define arch_atomic_add_return		arch_atomic_add_return
 #define arch_atomic_sub_return		arch_atomic_sub_return
 
 #define arch_atomic_fetch_add_relaxed	arch_atomic_fetch_add_relaxed
 #define arch_atomic_fetch_sub_relaxed	arch_atomic_fetch_sub_relaxed
+#define arch_atomic_fetch_add_acquire	arch_atomic_fetch_add_acquire
+#define arch_atomic_fetch_sub_acquire	arch_atomic_fetch_sub_acquire
+#define arch_atomic_fetch_add_release	arch_atomic_fetch_add_release
+#define arch_atomic_fetch_sub_release	arch_atomic_fetch_sub_release
 #define arch_atomic_fetch_add		arch_atomic_fetch_add
 #define arch_atomic_fetch_sub		arch_atomic_fetch_sub
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 #define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
 #define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_add_return_acquire	arch_atomic64_add_return_acquire
+#define arch_atomic64_sub_return_acquire	arch_atomic64_sub_return_acquire
+#define arch_atomic64_add_return_release	arch_atomic64_add_return_release
+#define arch_atomic64_sub_return_release	arch_atomic64_sub_return_release
 #define arch_atomic64_add_return		arch_atomic64_add_return
 #define arch_atomic64_sub_return		arch_atomic64_sub_return
 
 #define arch_atomic64_fetch_add_relaxed	arch_atomic64_fetch_add_relaxed
 #define arch_atomic64_fetch_sub_relaxed	arch_atomic64_fetch_sub_relaxed
+#define arch_atomic64_fetch_add_acquire	arch_atomic64_fetch_add_acquire
+#define arch_atomic64_fetch_sub_acquire	arch_atomic64_fetch_sub_acquire
+#define arch_atomic64_fetch_add_release	arch_atomic64_fetch_add_release
+#define arch_atomic64_fetch_sub_release	arch_atomic64_fetch_sub_release
 #define arch_atomic64_fetch_add		arch_atomic64_fetch_add
 #define arch_atomic64_fetch_sub		arch_atomic64_fetch_sub
 #endif
@@ -177,6 +229,12 @@ ATOMIC_OPS(xor, xor, i)
 #define arch_atomic_fetch_and_relaxed	arch_atomic_fetch_and_relaxed
 #define arch_atomic_fetch_or_relaxed	arch_atomic_fetch_or_relaxed
 #define arch_atomic_fetch_xor_relaxed	arch_atomic_fetch_xor_relaxed
+#define arch_atomic_fetch_and_acquire	arch_atomic_fetch_and_acquire
+#define arch_atomic_fetch_or_acquire	arch_atomic_fetch_or_acquire
+#define arch_atomic_fetch_xor_acquire	arch_atomic_fetch_xor_acquire
+#define arch_atomic_fetch_and_release	arch_atomic_fetch_and_release
+#define arch_atomic_fetch_or_release	arch_atomic_fetch_or_release
+#define arch_atomic_fetch_xor_release	arch_atomic_fetch_xor_release
 #define arch_atomic_fetch_and		arch_atomic_fetch_and
 #define arch_atomic_fetch_or		arch_atomic_fetch_or
 #define arch_atomic_fetch_xor		arch_atomic_fetch_xor
@@ -185,6 +243,12 @@ ATOMIC_OPS(xor, xor, i)
 #define arch_atomic64_fetch_and_relaxed	arch_atomic64_fetch_and_relaxed
 #define arch_atomic64_fetch_or_relaxed	arch_atomic64_fetch_or_relaxed
 #define arch_atomic64_fetch_xor_relaxed	arch_atomic64_fetch_xor_relaxed
+#define arch_atomic64_fetch_and_acquire	arch_atomic64_fetch_and_acquire
+#define arch_atomic64_fetch_or_acquire	arch_atomic64_fetch_or_acquire
+#define arch_atomic64_fetch_xor_acquire	arch_atomic64_fetch_xor_acquire
+#define arch_atomic64_fetch_and_release	arch_atomic64_fetch_and_release
+#define arch_atomic64_fetch_or_release	arch_atomic64_fetch_or_release
+#define arch_atomic64_fetch_xor_release	arch_atomic64_fetch_xor_release
 #define arch_atomic64_fetch_and		arch_atomic64_fetch_and
 #define arch_atomic64_fetch_or		arch_atomic64_fetch_or
 #define arch_atomic64_fetch_xor		arch_atomic64_fetch_xor
-- 
2.20.1