[ARM] 3239/1: Add ARM optimised swab32

Patch from Andre McCurdy

Replaces generic swab32 routine with a more ARM friendly version.
Reduces kernel text size by approx 1200 bytes when compiled with
3.4.4 and approx 2400 bytes with 4.0.2

Probably some performance benefit as well.
Signed-off-by: Andre McCurdy <armccurdy@yahoo.co.uk>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

include/asm-arm/byteorder.h

@@ -15,9 +15,22 @@
 #ifndef __ASM_ARM_BYTEORDER_H
 #define __ASM_ARM_BYTEORDER_H
 
-
 #include <asm/types.h>
 
+static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+	__u32 t;
+
+	t = x ^ ((x << 16) | (x >> 16));	/* eor r1,r0,r0,ror #16  */
+	x = (x << 24) | (x >> 8);		/* mov r0,r0,ror #8      */
+	t &= ~0x00FF0000;			/* bic r1,r1,#0x00FF0000 */
+	x ^= (t >> 8);				/* eor r0,r0,r1,lsr #8   */
+
+	return x;
+}
+
+#define __arch__swab32(x) ___arch__swab32(x)
+
 #if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
 #  define __BYTEORDER_HAS_U64__
 #  define __SWAB_64_THRU_32__