Received-SPF: pass (google.com: domain of linux-kernel+bounces-135126-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
From: Uros Bizjak <ubizjak@gmail.com>
To: x86@kernel.org,
	linux-kernel@vger.kernel.org
Cc: Uros Bizjak <ubizjak@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@kernel.org>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH 2/3] locking/atomic/x86: Modernize x86_32 arch_{,try_}_cmpxchg64{,_local}()
Date: Mon,  8 Apr 2024 11:13:57 +0200
Message-ID: <20240408091547.90111-3-ubizjak@gmail.com>
In-Reply-To: <20240408091547.90111-1-ubizjak@gmail.com>
References: <20240408091547.90111-1-ubizjak@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Commit:

  b23e139d0b66 ("arch: Introduce arch_{,try_}_cmpxchg128{,_local}()")

introduced arch_{,try_}_cmpxchg128{,_local}() for x86_64 targets.

Modernize existing x86_32 arch_{,try_}_cmpxchg64{,_local}() definitions
to follow the same structure as the definitions introduced by the
above commit.

No functional changes intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 arch/x86/include/asm/cmpxchg_32.h | 179 +++++++++++++++++-------------
 1 file changed, 100 insertions(+), 79 deletions(-)

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index b5731c51f0f4..fe40d0681ea8 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -3,103 +3,124 @@
 #define _ASM_X86_CMPXCHG_32_H
 
 /*
- * Note: if you use set64_bit(), __cmpxchg64(), or their variants,
+ * Note: if you use __cmpxchg64(), or their variants,
  *       you need to test for the feature in boot_cpu_data.
  */
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define arch_cmpxchg64(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
-					 (unsigned long long)(n)))
-#define arch_cmpxchg64_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
-					       (unsigned long long)(n)))
-#define arch_try_cmpxchg64(ptr, po, n)					\
-	__try_cmpxchg64((ptr), (unsigned long long *)(po), \
-			(unsigned long long)(n))
-#endif
+union __u64_halves {
+	u64 full;
+	struct {
+		u32 low, high;
+	};
+};
+
+#define __arch_cmpxchg64(_ptr, _old, _new, _lock)			\
+({									\
+	union __u64_halves o = { .full = (_old), },			\
+			   n = { .full = (_new), };			\
+									\
+	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	o.full;								\
+})
 
-static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+
+static __always_inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
 {
-	u64 prev;
-	asm volatile(LOCK_PREFIX "cmpxchg8b %1"
-		     : "=A" (prev),
-		       "+m" (*ptr)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32)),
-		       "0" (old)
-		     : "memory");
-	return prev;
+	return __arch_cmpxchg64(ptr, old, new, LOCK_PREFIX);
 }
 
-static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 {
-	u64 prev;
-	asm volatile("cmpxchg8b %1"
-		     : "=A" (prev),
-		       "+m" (*ptr)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32)),
-		       "0" (old)
-		     : "memory");
-	return prev;
+	return __arch_cmpxchg64(ptr, old, new,);
 }
 
-static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
+#define __arch_try_cmpxchg64(_ptr, _oldp, _new, _lock)			\
+({									\
+	union __u64_halves o = { .full = *(_oldp), },			\
+			   n = { .full = (_new), };			\
+	bool ret;							\
+									\
+	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+		     CC_SET(e)						\
+		     : CC_OUT(e) (ret),					\
+		       [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	if (unlikely(!ret))						\
+		*(_oldp) = o.full;					\
+									\
+	likely(ret);							\
+})
+
+static __always_inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	bool success;
-	u64 old = *pold;
-	asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]"
-		     CC_SET(z)
-		     : CC_OUT(z) (success),
-		       [ptr] "+m" (*ptr),
-		       "+A" (old)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32))
-		     : "memory");
-
-	if (unlikely(!success))
-		*pold = old;
-	return success;
+	return __arch_try_cmpxchg64(ptr, oldp, new, LOCK_PREFIX);
 }
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CMPXCHG64
+
+#define arch_cmpxchg64 __cmpxchg64
+
+#define arch_cmpxchg64_local __cmpxchg64_local
+
+#define arch_try_cmpxchg64 __try_cmpxchg64
+
+#else
+
 /*
  * Building a kernel capable running on 80386 and 80486. It may be necessary
  * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
  */
 
-#define arch_cmpxchg64(ptr, o, n)				\
-({								\
-	__typeof__(*(ptr)) __ret;				\
-	__typeof__(*(ptr)) __old = (o);				\
-	__typeof__(*(ptr)) __new = (n);				\
-	alternative_io(LOCK_PREFIX_HERE				\
-			"call cmpxchg8b_emu",			\
-			"lock; cmpxchg8b (%%esi)" ,		\
-		       X86_FEATURE_CX8,				\
-		       "=A" (__ret),				\
-		       "S" ((ptr)), "0" (__old),		\
-		       "b" ((unsigned int)__new),		\
-		       "c" ((unsigned int)(__new>>32))		\
-		       : "memory");				\
-	__ret; })
-
-
-#define arch_cmpxchg64_local(ptr, o, n)				\
-({								\
-	__typeof__(*(ptr)) __ret;				\
-	__typeof__(*(ptr)) __old = (o);				\
-	__typeof__(*(ptr)) __new = (n);				\
-	alternative_io("call cmpxchg8b_emu",			\
-		       "cmpxchg8b (%%esi)" ,			\
-		       X86_FEATURE_CX8,				\
-		       "=A" (__ret),				\
-		       "S" ((ptr)), "0" (__old),		\
-		       "b" ((unsigned int)__new),		\
-		       "c" ((unsigned int)(__new>>32))		\
-		       : "memory");				\
-	__ret; })
+#define __arch_cmpxchg64_emu(_ptr, _old, _new)				\
+({									\
+	union __u64_halves o = { .full = (_old), },			\
+			   n = { .full = (_new), };			\
+									\
+	asm volatile(ALTERNATIVE(LOCK_PREFIX_HERE			\
+				 "call cmpxchg8b_emu",			\
+				 "lock; cmpxchg8b %[ptr]", X86_FEATURE_CX8) \
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
+		     : "memory");					\
+									\
+	o.full;								\
+})
+
+static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+	return __arch_cmpxchg64_emu(ptr, old, new);
+}
+#define arch_cmpxchg64 arch_cmpxchg64
+
+#define __arch_cmpxchg64_emu_local(_ptr, _old, _new)			\
+({									\
+	union __u64_halves o = { .full = (_old), },			\
+			   n = { .full = (_new), };			\
+									\
+	asm volatile(ALTERNATIVE("call cmpxchg8b_emu",			\
+				 "cmpxchg8b %[ptr]", X86_FEATURE_CX8)	\
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
+		     : "memory");					\
+									\
+	o.full;								\
+})
+
+static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+{
+	return __arch_cmpxchg64_emu_local(ptr, old, new);
+}
+#define arch_cmpxchg64_local arch_cmpxchg64_local
 
 #endif
 
-- 
2.44.0