net: optimise csum_replace4()

csum_partial() is a generic function which is not optimised for small fixed
length calculations, and its use requires to store "from" and "to" values in
memory while we already have them available in registers. This also has impact,
especially on RISC processors. In the same spirit as the change done by
Eric Dumazet on csum_replace2(), this patch rewrites inet_proto_csum_replace4()
taking into account RFC1624.

I spotted during a NATted tcp transfert that csum_partial() is one of top 5
consuming functions (around 8%), and the second user of csum_partial() is
inet_proto_csum_replace4().

I have proposed the same modification to inet_proto_csum_replace4() in another
patch.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 1 insertions, 3 deletions

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 87cb1903640d..6465bae80a4f 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -122,9 +122,7 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
 
 static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
 {
-	__be32 diff[] = { ~from, to };
-
-	*sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum)));
+	*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to));
 }
 
 /* Implements RFC 1624 (Incremental Internet Checksum)