From:   Leonardo Bras <leobras@redhat.com>
To:     Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Leonardo Bras <leobras@redhat.com>, Guo Ren <guoren@kernel.org>
Cc:     linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [RESEND RFC PATCH v2 1/6] riscv/cmpxchg: Deduplicate cmpxchg() asm functions
Date:   Tue, 21 Mar 2023 04:42:44 -0300
Message-Id: <20230321074249.2221674-2-leobras@redhat.com>
In-Reply-To: <20230321074249.2221674-1-leobras@redhat.com>
References: <20230321074249.2221674-1-leobras@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In this header every cmpxchg define (_relaxed, _acquire, _release,
vanilla) contain it's own asm file, both for 4-byte variables an 8-byte
variables, on a total of 8 versions of mostly the same asm.

This is usually bad, as it means any change may be done in up to 8
different places.

Unify those versions by creating a new define with enough parameters to
generate any version of the previous 8.

(This did not cause any change in generated asm)

Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 arch/riscv/include/asm/cmpxchg.h | 102 ++++++++-----------------------
 1 file changed, 24 insertions(+), 78 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 12debce235e52..21984d24cbfe7 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -163,6 +163,22 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
+
+#define ___cmpxchg(lr_sfx, sc_sfx, prepend, append)			\
+{									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"0:	lr" lr_sfx " %0, %2\n"				\
+		"	bne  %0, %z3, 1f\n"				\
+		"	sc" sc_sfx " %1, %z4, %2\n"			\
+		"	bnez %1, 0b\n"					\
+		append							\
+		"1:\n"							\
+		: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)		\
+		: "rJ" ((long)__old), "rJ" (__new)			\
+		: "memory");						\
+}
+
 #define __cmpxchg_relaxed(ptr, old, new, size)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
@@ -172,26 +188,10 @@
 	register unsigned int __rc;					\
 	switch (size) {							\
 	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
-			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
+		___cmpxchg(".w", ".w", "", "");				\
 		break;							\
 	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
-			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
+		___cmpxchg(".d", ".d", "", "");				\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -216,28 +216,10 @@
 	register unsigned int __rc;					\
 	switch (size) {							\
 	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %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)		\
-			: "memory");					\
+		___cmpxchg(".w", ".w", "", RISCV_ACQUIRE_BARRIER);	\
 		break;							\
 	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %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)			\
-			: "memory");					\
+		___cmpxchg(".d", ".d", "", RISCV_ACQUIRE_BARRIER);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -262,28 +244,10 @@
 	register unsigned int __rc;					\
 	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"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
+		___cmpxchg(".w", ".w", RISCV_RELEASE_BARRIER, "");	\
 		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"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
+		___cmpxchg(".d", ".d", RISCV_RELEASE_BARRIER, "");	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -308,28 +272,10 @@
 	register unsigned int __rc;					\
 	switch (size) {							\
 	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %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)		\
-			: "memory");					\
+		___cmpxchg(".w", ".w.rl", "", "	fence rw, rw\n");	\
 		break;							\
 	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %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)			\
-			: "memory");					\
+		___cmpxchg(".d", ".d.rl", "", "	fence rw, rw\n");	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
-- 
2.40.0