net: optimize csum_replace2()

When changing one 16bit value by another in IP header, we can adjust
the IP checksum by doing a simple operation described in RFC 1624, as
reminded by David.

csum_partial() is a complex function on x86_64, not really suited for
small number of checksummed bytes.

I spotted csum_partial() being in the top 20 most consuming functions
(more than 1 %) in a GRO workload, which was rather unexpected.

The caller was inet_gro_complete() doing a csum_replace2() when
building the new IP header for the GRO packet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/checksum.h

@@ -69,6 +69,19 @@ static inline __wsum csum_sub(__wsum csum, __wsum addend)
 	return csum_add(csum, ~addend);
 }
 
+static inline __sum16 csum16_add(__sum16 csum, __be16 addend)
+{
+	u16 res = (__force u16)csum;
+
+	res += (__force u16)addend;
+	return (__force __sum16)(res + (res < (__force u16)addend));
+}
+
+static inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
+{
+	return csum16_add(csum, ~addend);
+}
+
 static inline __wsum
 csum_block_add(__wsum csum, __wsum csum2, int offset)
 {
@@ -112,9 +125,15 @@ static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
 	*sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum)));
 }
 
-static inline void csum_replace2(__sum16 *sum, __be16 from, __be16 to)
+/* Implements RFC 1624 (Incremental Internet Checksum)
+ * 3. Discussion states :
+ *     HC' = ~(~HC + ~m + m')
+ *  m : old value of a 16bit field
+ *  m' : new value of a 16bit field
+ */
+static inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
 {
-	csum_replace4(sum, (__force __be32)from, (__force __be32)to);
+	*sum = ~csum16_add(csum16_sub(~(*sum), old), new);
 }
 
 struct sk_buff;