diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index ff1518eb0d..3886f15899 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -117,21 +117,29 @@ extern inline void __raw_readsl(unsigned int addr, void *data, int longlen)
 		*buf++ = __arch_getl(addr);
 }
 
-#define __raw_writeb(v,a)		__arch_putb(v,a)
-#define __raw_writew(v,a)		__arch_putw(v,a)
-#define __raw_writel(v,a)		__arch_putl(v,a)
+#define __raw_writeb(v,a)	__arch_putb(v,a)
+#define __raw_writew(v,a)	__arch_putw(v,a)
+#define __raw_writel(v,a)	__arch_putl(v,a)
 
-#define __raw_readb(a)			__arch_getb(a)
-#define __raw_readw(a)			__arch_getw(a)
-#define __raw_readl(a)			__arch_getl(a)
+#define __raw_readb(a)		__arch_getb(a)
+#define __raw_readw(a)		__arch_getw(a)
+#define __raw_readl(a)		__arch_getl(a)
 
-#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 readb(a)			__arch_getb(a)
-#define readw(a)			__arch_getw(a)
-#define readl(a)			__arch_getl(a)
+#define writeb(v,c)	({ __iowmb(); __arch_putb(v,c); v; })
+#define writew(v,c)	({ __iowmb(); __arch_putw(v,c); v; })
+#define writel(v,c)	({ __iowmb(); __arch_putl(v,c); v; })
+
+#define readb(c)	({ u8  __v = __arch_getb(c); __iormb(); __v; })
+#define readw(c)	({ u16 __v = __arch_getw(c); __iormb(); __v; })
+#define readl(c)	({ u32 __v = __arch_getl(c); __iormb(); __v; })
 
 /*
  * The compiler seems to be incapable of optimising constants