-#define writeb(v,a) __arch_putb(v,a)
-#define writew(v,a) __arch_putw(v,a)
-#define writel(v,a) __arch_putl(v,a)
+/*
+ * TODO: The kernel offers some more advanced versions of barriers, it might
+ * have some advantages to use them instead of the simple one here.
+ */
+#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define __iormb() dmb()
+#define __iowmb() dmb()
+
+#define writeb(v,c) ({ u8 __v = v; __iowmb(); __arch_putb(__v,c); __v; })
+#define writew(v,c) ({ u16 __v = v; __iowmb(); __arch_putw(__v,c); __v; })
+#define writel(v,c) ({ u32 __v = v; __iowmb(); __arch_putl(__v,c); __v; })