powerpc/64: optimises from64to32()

The current implementation of from64to32() gives a poor result:

0000000000000270 <.from64to32>:
 270:	38 00 ff ff 	li      r0,-1
 274:	78 69 00 22 	rldicl  r9,r3,32,32
 278:	78 00 00 20 	clrldi  r0,r0,32
 27c:	7c 60 00 38 	and     r0,r3,r0
 280:	7c 09 02 14 	add     r0,r9,r0
 284:	78 09 00 22 	rldicl  r9,r0,32,32
 288:	7c 00 4a 14 	add     r0,r0,r9
 28c:	78 03 00 20 	clrldi  r3,r0,32
 290:	4e 80 00 20 	blr

This patch modifies from64to32() to operate in the same
spirit as csum_fold()

It swaps the two 32-bit halves of sum then it adds it with the
unswapped sum. If there is a carry from adding the two 32-bit halves,
it will carry from the lower half into the upper half, giving us the
correct sum in the upper half.

The resulting code is:

0000000000000260 <.from64to32>:
 260:	78 60 00 02 	rotldi  r0,r3,32
 264:	7c 60 1a 14 	add     r3,r0,r3
 268:	78 63 00 22 	rldicl  r3,r3,32,32
 26c:	4e 80 00 20 	blr
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/checksum.h

@@ -12,6 +12,7 @@
 #ifdef CONFIG_GENERIC_CSUM
 #include <asm-generic/checksum.h>
 #else
+#include <linux/bitops.h>
 /*
  * Computes the checksum of a memory block at src, length len,
  * and adds in "sum" (32-bit), while copying the block to dst.
@@ -55,11 +56,7 @@ static inline __sum16 csum_fold(__wsum sum)
 
 static inline u32 from64to32(u64 x)
 {
-	/* add up 32-bit and 32-bit for 32+c bit */
-	x = (x & 0xffffffff) + (x >> 32);
-	/* add up carry.. */
-	x = (x & 0xffffffff) + (x >> 32);
-	return (u32)x;
+	return (x + ror64(x, 32)) >> 32;
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,