powerpc: Reduce csum_add() complexity for PPC64

PPC64 does everything in C, gcc is able to skip calculation
when one of the operands in zero.

Move the constant folding in PPC32 part.

This helps GCC and reduces ppc64_defconfig by 170 bytes.

Signed-off-by: Christophe Leroy <[e-mail]>
Signed-off-by: Michael Ellerman <[e-mail]>
Link: https://lore.kernel.org/r/a4ca63dd[e-mail]

arch/powerpc/include/asm/checksum.h

···
 {
 #ifdef __powerpc64__
 	u64 res = (__force u64)csum;
-#endif
+
+	res += (__force u64)addend;
+	return (__force __wsum)((u32)res + (res >> 32));
+#else
 	if (__builtin_constant_p(csum) && csum == 0)
 		return addend;
 	if (__builtin_constant_p(addend) && addend == 0)
 		return csum;
 
-#ifdef __powerpc64__
-	res += (__force u64)addend;
-	return (__force __wsum)((u32)res + (res >> 32));
-#else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"
 	    : "+r" (csum) : "r" (addend) : "xer");