Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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>,
        Andrea Parri <parri.andrea@gmail.com>,
        Conor Dooley <conor.dooley@microchip.com>
Cc:     linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [RFC PATCH v1 1/2] riscv/cmpxchg: Deduplicate cmpxchg() asm and macros
Date:   Thu,  6 Apr 2023 05:20:18 -0300
Message-Id: <20230406082018.70367-2-leobras@redhat.com>
In-Reply-To: <20230406082018.70367-1-leobras@redhat.com>
References: <20230406082018.70367-1-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.

Then unify the result under a more general define, and simplify
arch_cmpxchg* generation

(This did not cause any change in generated asm)

Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 arch/riscv/include/asm/cmpxchg.h | 184 ++++++-------------------------
 1 file changed, 36 insertions(+), 148 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 12debce235e52..f88fae357071c 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -163,51 +163,23 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-#define __cmpxchg_relaxed(ptr, old, new, size)				\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	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");					\
-		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");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
 
-#define arch_cmpxchg_relaxed(ptr, o, n)					\
+#define ____cmpxchg(lr_sfx, sc_sfx, prepend, append, r, rc, p, co, o, n)\
 ({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
+	__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" (r), "=&r" (rc), "+A" (*(p))			\
+		: "rJ" (co o), "rJ" (n)					\
+		: "memory");						\
 })
 
-#define __cmpxchg_acquire(ptr, old, new, size)				\
+#define ___cmpxchg(ptr, old, new, size, sc_sfx, prepend, append)	\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(ptr)) __old = (old);				\
@@ -216,28 +188,12 @@
 	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" sc_sfx, prepend, append,		\
+			    __ret, __rc, __ptr, (long), __old, __new);	\
 		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" sc_sfx, prepend, append,		\
+			    __ret, __rc, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -245,105 +201,37 @@
 	__ret;								\
 })
 
-#define arch_cmpxchg_acquire(ptr, o, n)					\
+#define __cmpxchg_relaxed(ptr, old, new, size)				\
+	___cmpxchg(ptr, old, new, size, "", "", "")
+
+#define _arch_cmpxchg(order, ptr, o, n)					\
 ({									\
 	__typeof__(*(ptr)) _o_ = (o);					\
 	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
+	(__typeof__(*(ptr))) __cmpxchg ## order((ptr), _o_, _n_,	\
+						sizeof(*(ptr)));	\
 })
 
+#define arch_cmpxchg_relaxed(ptr, o, n)					\
+	_arch_cmpxchg(_relaxed, ptr, o, n)
+
+#define __cmpxchg_acquire(ptr, old, new, size)				\
+	___cmpxchg(ptr, old, new, size, "", "", RISCV_ACQUIRE_BARRIER)
+
+#define arch_cmpxchg_acquire(ptr, o, n)					\
+	_arch_cmpxchg(_acquire, ptr, o, n)
+
 #define __cmpxchg_release(ptr, old, new, size)				\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	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");					\
-		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");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	___cmpxchg(ptr, old, new, size, "", RISCV_RELEASE_BARRIER, "")
 
 #define arch_cmpxchg_release(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_release((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
-})
+	_arch_cmpxchg(_release, ptr, o, n)
 
 #define __cmpxchg(ptr, old, new, size)					\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	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");					\
-		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");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	___cmpxchg(ptr, old, new, size, ".rl", "", "	fence rw, rw\n")
 
 #define arch_cmpxchg(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg((ptr),				\
-				       _o_, _n_, sizeof(*(ptr)));	\
-})
+	_arch_cmpxchg(, ptr, o, n)
 
 #define arch_cmpxchg_local(ptr, o, n)					\
 	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
-- 
2.40.0