[PATCH] riscv: Optimize AMO acquire/release usage

guoren at kernel.org guoren at kernel.org
Wed Apr 6 05:04:05 PDT 2022


From: Guo Ren <guoren at linux.alibaba.com>

Using RISCV_ACQUIRE/RELEASE_BARRIER is over expensive for
xchg/cmpxchg_acquire/release than nature instructions' .aq/rl.
The patch fixed these issues under RISC-V Instruction Set Manual,
Volume I: RISC-V User-Level ISA “A” Standard Extension for Atomic
Instructions, Version 2.1.

Signed-off-by: Guo Ren <guoren at linux.alibaba.com>
Signed-off-by: Guo Ren <guoren at kernel.org>
Cc: Palmer Dabbelt <palmer at dabbelt.com>
---
 arch/riscv/include/asm/atomic.h  | 70 ++++++++++++++++++++++++++++++--
 arch/riscv/include/asm/cmpxchg.h | 30 +++++---------
 2 files changed, 76 insertions(+), 24 deletions(-)

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index ac9bdf4fc404..364df773a36a 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -99,6 +99,30 @@ 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;						\
@@ -118,6 +142,18 @@ 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;		\
@@ -140,22 +176,38 @@ 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
@@ -178,6 +230,12 @@ 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
@@ -186,6 +244,12 @@ 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
@@ -315,12 +379,11 @@ static __always_inline int arch_atomic_sub_if_positive(atomic_t *v, int offset)
        int prev, rc;
 
 	__asm__ __volatile__ (
-		"0:	lr.w     %[p],  %[c]\n"
+		"0:	lr.w.aq  %[p],  %[c]\n"
 		"	sub      %[rc], %[p], %[o]\n"
 		"	bltz     %[rc], 1f\n"
 		"	sc.w.rl  %[rc], %[rc], %[c]\n"
 		"	bnez     %[rc], 0b\n"
-		"	fence    rw, rw\n"
 		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [o]"r" (offset)
@@ -337,12 +400,11 @@ static __always_inline s64 arch_atomic64_sub_if_positive(atomic64_t *v, s64 offs
        long rc;
 
 	__asm__ __volatile__ (
-		"0:	lr.d     %[p],  %[c]\n"
+		"0:	lr.d.aq  %[p],  %[c]\n"
 		"	sub      %[rc], %[p], %[o]\n"
 		"	bltz     %[rc], 1f\n"
 		"	sc.d.rl  %[rc], %[rc], %[c]\n"
 		"	bnez     %[rc], 0b\n"
-		"	fence    rw, rw\n"
 		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [o]"r" (offset)
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 36dc962f6343..8ff1cd8162ba 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -52,16 +52,14 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			"	amoswap.w %0, %2, %1\n"			\
-			RISCV_ACQUIRE_BARRIER				\
+			"	amoswap.w.aq %0, %2, %1\n"		\
 			: "=r" (__ret), "+A" (*__ptr)			\
 			: "r" (__new)					\
 			: "memory");					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			"	amoswap.d %0, %2, %1\n"			\
-			RISCV_ACQUIRE_BARRIER				\
+			"	amoswap.d.aq %0, %2, %1\n"		\
 			: "=r" (__ret), "+A" (*__ptr)			\
 			: "r" (__new)					\
 			: "memory");					\
@@ -87,16 +85,14 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"	amoswap.w %0, %2, %1\n"			\
+			"	amoswap.w.rl %0, %2, %1\n"		\
 			: "=r" (__ret), "+A" (*__ptr)			\
 			: "r" (__new)					\
 			: "memory");					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"	amoswap.d %0, %2, %1\n"			\
+			"	amoswap.d.rl %0, %2, %1\n"		\
 			: "=r" (__ret), "+A" (*__ptr)			\
 			: "r" (__new)					\
 			: "memory");					\
@@ -217,11 +213,10 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
+			"0:	lr.w.aq %0, %2\n"			\
 			"	bne  %0, %z3, 1f\n"			\
 			"	sc.w %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" ((long)__old), "rJ" (__new)		\
@@ -229,11 +224,10 @@
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
+			"0:	lr.d.aq %0, %2\n"			\
 			"	bne %0, %z3, 1f\n"			\
 			"	sc.d %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\
@@ -263,10 +257,9 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
 			"0:	lr.w %0, %2\n"				\
 			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
+			"	sc.w.rl %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
@@ -275,10 +268,9 @@
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
 			"0:	lr.d %0, %2\n"				\
 			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
+			"	sc.d.rl %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
@@ -309,11 +301,10 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
+			"0:	lr.w.aq %0, %2\n"			\
 			"	bne  %0, %z3, 1f\n"			\
 			"	sc.w.rl %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" ((long)__old), "rJ" (__new)		\
@@ -321,11 +312,10 @@
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
+			"0:	lr.d.aq %0, %2\n"			\
 			"	bne %0, %z3, 1f\n"			\
 			"	sc.d.rl %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\
-- 
2.25.1




More information about the linux-riscv mailing list