locking/xchg/alpha: Remove superfluous memory barriers from the _local() variants

The following two commits:

  79d442461df74 ("locking/xchg/alpha: Clean up barrier usage by using smp_mb() in place of __ASM__MB")
  472e8c55cf662 ("locking/xchg/alpha: Fix xchg() and cmpxchg() memory ordering bugs")

... ended up adding unnecessary barriers to the _local() variants on Alpha,
which the previous code took care to avoid.

Fix them by adding the smp_mb() into the cmpxchg() macro rather than into the
____cmpxchg() variants.

Reported-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-alpha@vger.kernel.org
Fixes: 472e8c55cf662 ("locking/xchg/alpha: Fix xchg() and cmpxchg() memory ordering bugs")
Fixes: 79d442461df74 ("locking/xchg/alpha: Clean up barrier usage by using smp_mb() in place of __ASM__MB")
Link: http://lkml.kernel.org/r/1519704058-13430-1-git-send-email-parri.andrea@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 8a2b331..6c7c394 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -38,19 +38,31 @@
 #define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
 #include <asm/xchg.h>
 
+/*
+ * The leading and the trailing memory barriers guarantee that these
+ * operations are fully ordered.
+ */
 #define xchg(ptr, x)							\
 ({									\
+	__typeof__(*(ptr)) __ret;					\
 	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
-				 sizeof(*(ptr)));			\
+	smp_mb();							\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
+	smp_mb();							\
+	__ret;								\
 })
 
 #define cmpxchg(ptr, o, n)						\
 ({									\
+	__typeof__(*(ptr)) __ret;					\
 	__typeof__(*(ptr)) _o_ = (o);					\
 	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
-				    (unsigned long)_n_,	sizeof(*(ptr)));\
+	smp_mb();							\
+	__ret = (__typeof__(*(ptr))) __cmpxchg((ptr),			\
+		(unsigned long)_o_, (unsigned long)_n_, sizeof(*(ptr)));\
+	smp_mb();							\
+	__ret;								\
 })
 
 #define cmpxchg64(ptr, o, n)						\