[NETFILTER]: nf_conntrack: avoid duplicate protocol comparison in nf_ct_tuple_equal()

nf_ct_tuple_src_equal() and nf_ct_tuple_dst_equal() both compare the protocol
numbers. Unfortunately gcc doesn't optimize out the second comparison, so
remove it and prefix both functions with __ to indicate that they should not
be used directly.

Saves another 16 byte of text in __nf_conntrack_find() on x86_64:

  nf_conntrack_tuple_taken |  -20 # 320 -> 300, size inlines: 181 -> 161
  __nf_conntrack_find      |  -16 # 267 -> 251, size inlines: 127 -> 115
  __nf_conntrack_confirm   |  -40 # 875 -> 835, size inlines: 570 -> 537
 3 functions changed, 76 bytes removed
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/netfilter/nf_conntrack_tuple.h

@@ -132,34 +132,33 @@ struct nf_conntrack_tuple_hash
 
 #endif /* __KERNEL__ */
 
-static inline int nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1,
-				        const struct nf_conntrack_tuple *t2)
+static inline int __nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1,
+					  const struct nf_conntrack_tuple *t2)
 { 
 	return (t1->src.u3.all[0] == t2->src.u3.all[0] &&
 		t1->src.u3.all[1] == t2->src.u3.all[1] &&
 		t1->src.u3.all[2] == t2->src.u3.all[2] &&
 		t1->src.u3.all[3] == t2->src.u3.all[3] &&
 		t1->src.u.all == t2->src.u.all &&
-		t1->src.l3num == t2->src.l3num &&
-		t1->dst.protonum == t2->dst.protonum);
+		t1->src.l3num == t2->src.l3num);
 }
 
-static inline int nf_ct_tuple_dst_equal(const struct nf_conntrack_tuple *t1,
-				        const struct nf_conntrack_tuple *t2)
+static inline int __nf_ct_tuple_dst_equal(const struct nf_conntrack_tuple *t1,
+					  const struct nf_conntrack_tuple *t2)
 {
 	return (t1->dst.u3.all[0] == t2->dst.u3.all[0] &&
 		t1->dst.u3.all[1] == t2->dst.u3.all[1] &&
 		t1->dst.u3.all[2] == t2->dst.u3.all[2] &&
 		t1->dst.u3.all[3] == t2->dst.u3.all[3] &&
 		t1->dst.u.all == t2->dst.u.all &&
-		t1->src.l3num == t2->src.l3num &&
 		t1->dst.protonum == t2->dst.protonum);
 }
 
 static inline int nf_ct_tuple_equal(const struct nf_conntrack_tuple *t1,
 				    const struct nf_conntrack_tuple *t2)
 {
-	return nf_ct_tuple_src_equal(t1, t2) && nf_ct_tuple_dst_equal(t1, t2);
+	return __nf_ct_tuple_src_equal(t1, t2) &&
+	       __nf_ct_tuple_dst_equal(t1, t2);
 }
 
 static inline int nf_ct_tuple_mask_equal(const struct nf_conntrack_tuple_mask *m1,
@@ -199,7 +198,7 @@ static inline int nf_ct_tuple_mask_cmp(const struct nf_conntrack_tuple *t,
 				       const struct nf_conntrack_tuple_mask *mask)
 {
 	return nf_ct_tuple_src_mask_cmp(t, tuple, mask) &&
-	       nf_ct_tuple_dst_equal(t, tuple);
+	       __nf_ct_tuple_dst_equal(t, tuple);
 }
 
 #endif /* _NF_CONNTRACK_TUPLE_H */