[SPARC64]: More fully work around Spitfire Errata 51.

It appears that a memory barrier soon after a mispredicted
branch, not just in the delay slot, can cause the hang
condition of this cpu errata.

So move them out-of-line, and explicitly put them into
a "branch always, predict taken" delay slot which should
fully kill this problem.

Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/asm-sparc64/bitops.h b/include/asm-sparc64/bitops.h
index 9c5e719..6388b83 100644
--- a/include/asm-sparc64/bitops.h
+++ b/include/asm-sparc64/bitops.h
@@ -72,8 +72,8 @@
 }
 
 #ifdef CONFIG_SMP
-#define smp_mb__before_clear_bit()	membar("#StoreLoad | #LoadLoad")
-#define smp_mb__after_clear_bit()	membar("#StoreLoad | #StoreStore")
+#define smp_mb__before_clear_bit()	membar_storeload_loadload()
+#define smp_mb__after_clear_bit()	membar_storeload_storestore()
 #else
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()