MIPS: cmpxchg: Omit redundant barriers for Loongson3

When building a kernel configured to support Loongson3 LL/SC workarounds
(ie. CONFIG_CPU_LOONGSON3_WORKAROUNDS=y) the inline assembly in
__xchg_asm() & __cmpxchg_asm() already emits completion barriers, and as
such we don't need to emit extra barriers from the xchg() or cmpxchg()
macros. Add compile-time constant checks causing us to omit the
redundant memory barriers.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-mips@vger.kernel.org
Cc: Huacai Chen <chenhc@lemote.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-kernel@vger.kernel.org

arch/mips/include/asm/cmpxchg.h

@@ -94,6 +94,12 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 ({									\
 	__typeof__(*(ptr)) __res;					\
 									\
+	/*								\
+	 * In the Loongson3 workaround case __xchg_asm() already	\
+	 * contains a completion barrier prior to the LL, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
 		smp_mb__before_llsc();					\
 									\
 	__res = (__typeof__(*(ptr)))					\
@@ -179,8 +185,22 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 ({									\
 	__typeof__(*(ptr)) __res;					\
 									\
+	/*								\
+	 * In the Loongson3 workaround case __cmpxchg_asm() already	\
+	 * contains a completion barrier prior to the LL, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
 		smp_mb__before_llsc();					\
+									\
 	__res = cmpxchg_local((ptr), (old), (new));			\
+									\
+	/*								\
+	 * In the Loongson3 workaround case __cmpxchg_asm() already	\
+	 * contains a completion barrier after the SC, so we don't	\
+	 * need to emit an extra one here.				\
+	 */								\
+	if (!__SYNC_loongson3_war)					\
 		smp_llsc_mb();						\
 									\
 	__res;								\