[PATCH v2] xfrm: optimize ipv4 selector matching

[Alexey Dobriyan <adobriyan@gmail.com>]

Current addr_match() is errh, under-optimized.

Compiler doesn't know that memcmp() branch doesn't trigger for IPv4.
Also, pass addresses by value -- they fit into register.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---

 include/net/xfrm.h     |    8 ++++++++
 net/xfrm/xfrm_policy.c |    4 ++--
 2 files changed, 10 insertions(+), 2 deletions(-)

--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -827,6 +827,14 @@ static inline bool addr_match(const void *token1, const void *token2,
 	return true;
 }
 
+static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen)
+{
+	/* C99 6.5.7 (3): u32 << 32 is undefined behaviour */
+	if (prefixlen == 0)
+		return true;
+	return !((a1 ^ a2) & htonl(0xFFFFFFFFu << (32 - prefixlen)));
+}
+
 static __inline__
 __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli)
 {
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -61,8 +61,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	const struct flowi4 *fl4 = &fl->u.ip4;
 
-	return  addr_match(&fl4->daddr, &sel->daddr, sel->prefixlen_d) &&
-		addr_match(&fl4->saddr, &sel->saddr, sel->prefixlen_s) &&
+	return  addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
+		addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
 		!((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
 		!((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
 		(fl4->flowi4_proto == sel->proto || !sel->proto) &&