[PATCH] alpha: additional smp barriers

As stated in Documentation/atomic_ops.txt, atomic functions
returning values must have the memory barriers both before and after
the operation.

Thanks to DaveM for pointing that out.

Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/include/asm-alpha/atomic.h b/include/asm-alpha/atomic.h
index 1b383e3cb68c942454d3e8d049e3266a772eea52..0b40bad0028983de15b47a0b223016f582e8b859 100644 (file)
--- a/include/asm-alpha/atomic.h
+++ b/include/asm-alpha/atomic.h
@@ -100,18 +100,19 @@ static __inline__ void atomic64_sub(long i, atomic64_t * v)
 static __inline__ long atomic_add_return(int i, atomic_t * v)
 {
        long temp, result;
+       smp_mb();
        __asm__ __volatile__(
        "1:     ldl_l %0,%1\n"
        "       addl %0,%3,%2\n"
        "       addl %0,%3,%0\n"
        "       stl_c %0,%1\n"
        "       beq %0,2f\n"
-       "       mb\n"
        ".subsection 2\n"
        "2:     br 1b\n"
        ".previous"
        :"=&r" (temp), "=m" (v->counter), "=&r" (result)
        :"Ir" (i), "m" (v->counter) : "memory");
+       smp_mb();
        return result;
 }
 
@@ -120,54 +121,57 @@ static __inline__ long atomic_add_return(int i, atomic_t * v)
 static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 {
        long temp, result;
+       smp_mb();
        __asm__ __volatile__(
        "1:     ldq_l %0,%1\n"
        "       addq %0,%3,%2\n"
        "       addq %0,%3,%0\n"
        "       stq_c %0,%1\n"
        "       beq %0,2f\n"
-       "       mb\n"
        ".subsection 2\n"
        "2:     br 1b\n"
        ".previous"
        :"=&r" (temp), "=m" (v->counter), "=&r" (result)
        :"Ir" (i), "m" (v->counter) : "memory");
+       smp_mb();
        return result;
 }
 
 static __inline__ long atomic_sub_return(int i, atomic_t * v)
 {
        long temp, result;
+       smp_mb();
        __asm__ __volatile__(
        "1:     ldl_l %0,%1\n"
        "       subl %0,%3,%2\n"
        "       subl %0,%3,%0\n"
        "       stl_c %0,%1\n"
        "       beq %0,2f\n"
-       "       mb\n"
        ".subsection 2\n"
        "2:     br 1b\n"
        ".previous"
        :"=&r" (temp), "=m" (v->counter), "=&r" (result)
        :"Ir" (i), "m" (v->counter) : "memory");
+       smp_mb();
        return result;
 }
 
 static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 {
        long temp, result;
+       smp_mb();
        __asm__ __volatile__(
        "1:     ldq_l %0,%1\n"
        "       subq %0,%3,%2\n"
        "       subq %0,%3,%0\n"
        "       stq_c %0,%1\n"
        "       beq %0,2f\n"
-       "       mb\n"
        ".subsection 2\n"
        "2:     br 1b\n"
        ".previous"
        :"=&r" (temp), "=m" (v->counter), "=&r" (result)
        :"Ir" (i), "m" (v->counter) : "memory");
+       smp_mb();
        return result;
 }