As Segher pointed out, inline asm is better than the volatile casting all over
the place. From the PowerPC patch description:
 Also use inline functions instead of macros; this actually
 improves code generation (some code becomes a little smaller,
 probably because of improved alias information -- just a few
 hundred bytes total on a default kernel build, nothing shocking).

My config with march=k8 and gcc (GCC) 4.1.2 (Gentoo 4.1.2):
  text    data     bss     dec     hex filename
  4002473  385936  474440 4862849  4a3381 atomic_normal/vmlinux
  4002587  385936  474440 4862963  4a33f3 atomic_inlineasm/vmlinux
  4003911  385936  474440 4864287  4a391f atomic_volatile/vmlinux
  4003959  385936  474440 4864335  4a394f atomic_volatile_inline/vmlinux

Signed-off-by: Sebastian Siewior <sebastian@breakpoint.cc>
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -29,19 +29,34 @@ typedef struct { int counter; } atomic_t
 /**
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
- * 
+ *
  * Atomically reads the value of @v.
- */ 
-#define atomic_read(v)		((v)->counter)
+ */
+static __inline__ int atomic_read(const atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+			"movl %1, %0"
+			: "=r"(t)
+			: "m"(v->counter));
+	return t;
+}
 
 /**
  * atomic_set - set atomic variable
  * @v: pointer of type atomic_t
  * @i: required value
- * 
+ *
  * Atomically sets the value of @v to @i.
- */ 
-#define atomic_set(v,i)		(((v)->counter) = (i))
+ */
+static __inline__ void atomic_set(atomic_t *v, int i)
+{
+	__asm__ __volatile__(
+			"movl %1, %0"
+			: "=m"(v->counter)
+			: "ir"(i));
+}
 
 /**
  * atomic_add - add integer to atomic variable
@@ -206,7 +221,7 @@ static __inline__ int atomic_sub_return(
 
 /* An 64bit atomic type */
 
-typedef struct { volatile long counter; } atomic64_t;
+typedef struct { long counter; } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
@@ -217,7 +232,16 @@ typedef struct { volatile long counter; 
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-#define atomic64_read(v)		((v)->counter)
+static __inline__ long atomic64_read(const atomic64_t *v)
+{
+	long t;
+
+	__asm__ __volatile__(
+			"movq %1, %0"
+			: "=r"(t)
+			: "m"(v->counter));
+	return t;
+}
 
 /**
  * atomic64_set - set atomic64 variable
@@ -226,7 +250,13 @@ typedef struct { volatile long counter; 
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic64_set(v,i)		(((v)->counter) = (i))
+static __inline__ void atomic64_set(atomic64_t *v, long i)
+{
+	__asm__ __volatile__(
+			"movq %1, %0"
+			: "=m"(v->counter)
+			: "ir"(i));
+}
 
 /**
  * atomic64_add - add integer to atomic64 variable

-- 

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/