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 <[e-mail]>
Signed-off-by: Andrea Parri <[e-mail]>
Cc: Alan Stern <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Ivan Kokshaysky <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Matt Turner <[e-mail]>
Cc: Paul E. McKenney <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Richard Henderson <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: [e-mail]
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/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

arch/alpha/include/asm/cmpxchg.h

···
 #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)						\

arch/alpha/include/asm/xchg.h

···
  * Atomic exchange.
  * Since it can be used to implement critical sections
  * it must clobber "memory" (also for interrupts in UP).
- *
- * The leading and the trailing memory barriers guarantee that these
- * operations are fully ordered.
- *
  */
 
 static inline unsigned long
···
 {
 	unsigned long ret, tmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	insbl	%1,%4,%1\n"
···
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
-	smp_mb();
 
 	return ret;
 }
···
 {
 	unsigned long ret, tmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	inswl	%1,%4,%1\n"
···
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
-	smp_mb();
 
 	return ret;
 }
···
 {
 	unsigned long dummy;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%4\n"
 	"	bis $31,%3,%1\n"
···
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
-	smp_mb();
 
 	return val;
 }
···
 {
 	unsigned long dummy;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%4\n"
 	"	bis $31,%3,%1\n"
···
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
-	smp_mb();
 
 	return val;
 }
···
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
- *
- * The leading and the trailing memory barriers guarantee that these
- * operations are fully ordered.
- *
- * The trailing memory barrier is placed in SMP unconditionally, in
- * order to guarantee that dependency ordering is preserved when a
- * dependency is headed by an unsuccessful operation.
  */
 
 static inline unsigned long
···
 {
 	unsigned long prev, tmp, cmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	insbl	%1,%5,%1\n"
···
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-	smp_mb();
 
 	return prev;
 }
···
 {
 	unsigned long prev, tmp, cmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	inswl	%1,%5,%1\n"
···
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-	smp_mb();
 
 	return prev;
 }
···
 {
 	unsigned long prev, cmp;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
···
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-	smp_mb();
 
 	return prev;
 }
···
 {
 	unsigned long prev, cmp;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
···
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-	smp_mb();
 
 	return prev;
 }