powerpc: optimise csum_partial() call when len is constant

csum_partial is often called for small fixed length packets
for which it is suboptimal to use the generic csum_partial()
function.

For instance, in my configuration, I got:
* One place calling it with constant len 4
* Seven places calling it with constant len 8
* Three places calling it with constant len 14
* One place calling it with constant len 20
* One place calling it with constant len 24
* One place calling it with constant len 32

This patch renames csum_partial() to __csum_partial() and
implements csum_partial() as a wrapper inline function which
* uses csum_add() for small 16bits multiple constant length
* uses ip_fast_csum() for other 32bits multiple constant
* uses __csum_partial() in all other cases

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 0d34f47..d90870a 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -24,9 +24,9 @@
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
  *
- * csum_partial(buff, len, sum)
+ * __csum_partial(buff, len, sum)
  */
-_GLOBAL(csum_partial)
+_GLOBAL(__csum_partial)
 	subi	r3,r3,4
 	srawi.	r6,r4,2		/* Divide len by 4 and also clear carry */
 	beq	3f		/* if we're doing < 4 bytes */
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index f53f4ab..8e6e510 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -21,9 +21,9 @@
  * Computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit).
  *
- * csum_partial(r3=buff, r4=len, r5=sum)
+ * __csum_partial(r3=buff, r4=len, r5=sum)
  */
-_GLOBAL(csum_partial)
+_GLOBAL(__csum_partial)
 	addic	r0,r5,0			/* clear carry */
 
 	srdi.	r6,r4,3			/* less than 8 bytes? */
diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c
index 8cd5c0b..c422812 100644
--- a/arch/powerpc/lib/ppc_ksyms.c
+++ b/arch/powerpc/lib/ppc_ksyms.c
@@ -17,7 +17,7 @@
 EXPORT_SYMBOL(strncmp);
 
 #ifndef CONFIG_GENERIC_CSUM
-EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(__csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_generic);
 #endif