mutex: speed up generic mutex implementations

[pandora-kernel.git] / include / asm-generic / mutex-dec.h

diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
index 29c6ac3..f104af7 100644 (file)
--- a/include/asm-generic/mutex-dec.h
+++ b/include/asm-generic/mutex-dec.h
@@ -1,5 +1,5 @@
 /*
- * asm-generic/mutex-dec.h
+ * include/asm-generic/mutex-dec.h
  *
  * Generic implementation of the mutex fastpath, based on atomic
  * decrement/increment.
@@ -18,12 +18,10 @@
  * 1 even when the "1" assertion wasn't true.
  */
 static inline void
-__mutex_fastpath_lock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
        if (unlikely(atomic_dec_return(count) < 0))
                fail_fn(count);
-       else
-               smp_mb();
 }
 
 /**
@@ -37,14 +35,11 @@ __mutex_fastpath_lock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
  * or anything the slow path function returns.
  */
 static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, fastcall int (*fail_fn)(atomic_t *))
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
        if (unlikely(atomic_dec_return(count) < 0))
                return fail_fn(count);
-       else {
-               smp_mb();
-               return 0;
-       }
+       return 0;
 }
 
 /**
@@ -61,9 +56,8 @@ __mutex_fastpath_lock_retval(atomic_t *count, fastcall int (*fail_fn)(atomic_t *
  * to return 0 otherwise.
  */
 static inline void
-__mutex_fastpath_unlock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
-       smp_mb();
        if (unlikely(atomic_inc_return(count) <= 0))
                fail_fn(count);
 }
@@ -88,25 +82,9 @@ __mutex_fastpath_unlock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-       /*
-        * We have two variants here. The cmpxchg based one is the best one
-        * because it never induce a false contention state.  It is included
-        * here because architectures using the inc/dec algorithms over the
-        * xchg ones are much more likely to support cmpxchg natively.
-        *
-        * If not we fall back to the spinlock based variant - that is
-        * just as efficient (and simpler) as a 'destructive' probing of
-        * the mutex state would be.
-        */
-#ifdef __HAVE_ARCH_CMPXCHG
-       if (likely(atomic_cmpxchg(count, 1, 0) == 1)) {
-               smp_mb();
+       if (likely(atomic_cmpxchg(count, 1, 0) == 1))
                return 1;
-       }
        return 0;
-#else
-       return fail_fn(count);
-#endif
 }
 
 #endif