1 files changed, 120 insertions, 46 deletions

diff --git a/include/net/route.h b/include/net/route.h
index 93e10c453f6b..8fce0621cad1 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -49,36 +49,44 @@
 
 struct fib_nh;
 struct inet_peer;
+struct fib_info;
 struct rtable {
         struct dst_entry        dst;
 
-        /* Cache lookup keys */
-        struct flowi            fl;
+        /* Lookup key. */
+        __be32                  rt_key_dst;
+        __be32                  rt_key_src;
 
         int                     rt_genid;
         unsigned                rt_flags;
         __u16                   rt_type;
+        __u8                    rt_tos;
 
         __be32                  rt_dst; /* Path destination     */
         __be32                  rt_src; /* Path source          */
+        int                     rt_route_iif;
         int                     rt_iif;
+        int                     rt_oif;
+        __u32                   rt_mark;
 
         /* Info on neighbour */
         __be32                  rt_gateway;
 
         /* Miscellaneous cached information */
         __be32                  rt_spec_dst; /* RFC1122 specific destination */
+        u32                     rt_peer_genid;
         struct inet_peer        *peer; /* long-living peer info */
+        struct fib_info         *fi; /* for client ref to shared metrics */
 };
 
 static inline bool rt_is_input_route(struct rtable *rt)
 {
-        return rt->fl.iif != 0;
+        return rt->rt_route_iif != 0;
 }
 
 static inline bool rt_is_output_route(struct rtable *rt)
 {
-        return rt->fl.iif == 0;
+        return rt->rt_route_iif == 0;
 }
 
 struct ip_rt_acct {
@@ -115,9 +123,63 @@ extern void		ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
                                        __be32 src, struct net_device *dev);
 extern void             rt_cache_flush(struct net *net, int how);
 extern void             rt_cache_flush_batch(struct net *net);
-extern int              __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
-extern int              ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
-extern int              ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
+extern struct rtable *__ip_route_output_key(struct net *, const struct flowi4 *flp);
+extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
+                                           struct sock *sk);
+extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
+
+static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp)
+{
+        return ip_route_output_flow(net, flp, NULL);
+}
+
+static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
+                                             __be32 saddr, u8 tos, int oif)
+{
+        struct flowi4 fl4 = {
+                .flowi4_oif = oif,
+                .daddr = daddr,
+                .saddr = saddr,
+                .flowi4_tos = tos,
+        };
+        return ip_route_output_key(net, &fl4);
+}
+
+static inline struct rtable *ip_route_output_ports(struct net *net, struct sock *sk,
+                                                   __be32 daddr, __be32 saddr,
+                                                   __be16 dport, __be16 sport,
+                                                   __u8 proto, __u8 tos, int oif)
+{
+        struct flowi4 fl4 = {
+                .flowi4_oif = oif,
+                .flowi4_flags = sk ? inet_sk_flowi_flags(sk) : 0,
+                .flowi4_mark = sk ? sk->sk_mark : 0,
+                .daddr = daddr,
+                .saddr = saddr,
+                .flowi4_tos = tos,
+                .flowi4_proto = proto,
+                .fl4_dport = dport,
+                .fl4_sport = sport,
+        };
+        if (sk)
+                security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+        return ip_route_output_flow(net, &fl4, sk);
+}
+
+static inline struct rtable *ip_route_output_gre(struct net *net,
+                                                 __be32 daddr, __be32 saddr,
+                                                 __be32 gre_key, __u8 tos, int oif)
+{
+        struct flowi4 fl4 = {
+                .flowi4_oif = oif,
+                .daddr = daddr,
+                .saddr = saddr,
+                .flowi4_tos = tos,
+                .flowi4_proto = IPPROTO_GRE,
+                .fl4_gre_key = gre_key,
+        };
+        return ip_route_output_key(net, &fl4);
+}
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
                                  u8 tos, struct net_device *devin, bool noref);
@@ -146,6 +208,7 @@ extern int		ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
 
 struct in_ifaddr;
 extern void fib_add_ifaddr(struct in_ifaddr *);
+extern void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
 static inline void ip_rt_put(struct rtable * rt)
 {
@@ -162,57 +225,68 @@ static inline char rt_tos2priority(u8 tos)
         return ip_tos2prio[IPTOS_TOS(tos)>>1];
 }
 
-static inline int ip_route_connect(struct rtable **rp, __be32 dst,
-                                   __be32 src, u32 tos, int oif, u8 protocol,
-                                   __be16 sport, __be16 dport, struct sock *sk,
-                                   int flags)
+static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
+                                              int oif, u8 protocol,
+                                              __be16 sport, __be16 dport,
+                                              struct sock *sk, bool can_sleep)
 {
-        struct flowi fl = { .oif = oif,
-                            .mark = sk->sk_mark,
-                            .fl4_dst = dst,
-                            .fl4_src = src,
-                            .fl4_tos = tos,
-                            .proto = protocol,
-                            .fl_ip_sport = sport,
-                            .fl_ip_dport = dport };
-        int err;
+        struct flowi4 fl4 = {
+                .flowi4_oif = oif,
+                .flowi4_mark = sk->sk_mark,
+                .daddr = dst,
+                .saddr = src,
+                .flowi4_tos = tos,
+                .flowi4_proto = protocol,
+                .fl4_sport = sport,
+                .fl4_dport = dport,
+        };
         struct net *net = sock_net(sk);
+        struct rtable *rt;
 
         if (inet_sk(sk)->transparent)
-                fl.flags |= FLOWI_FLAG_ANYSRC;
+                fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+        if (protocol == IPPROTO_TCP)
+                fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS;
+        if (can_sleep)
+                fl4.flowi4_flags |= FLOWI_FLAG_CAN_SLEEP;
 
         if (!dst || !src) {
-                err = __ip_route_output_key(net, rp, &fl);
-                if (err)
-                        return err;
-                fl.fl4_dst = (*rp)->rt_dst;
-                fl.fl4_src = (*rp)->rt_src;
-                ip_rt_put(*rp);
-                *rp = NULL;
+                rt = __ip_route_output_key(net, &fl4);
+                if (IS_ERR(rt))
+                        return rt;
+                fl4.daddr = rt->rt_dst;
+                fl4.saddr = rt->rt_src;
+                ip_rt_put(rt);
         }
-        security_sk_classify_flow(sk, &fl);
-        return ip_route_output_flow(net, rp, &fl, sk, flags);
+        security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+        return ip_route_output_flow(net, &fl4, sk);
 }
 
-static inline int ip_route_newports(struct rtable **rp, u8 protocol,
-                                    __be16 sport, __be16 dport, struct sock *sk)
+static inline struct rtable *ip_route_newports(struct rtable *rt,
+                                               u8 protocol, __be16 orig_sport,
+                                               __be16 orig_dport, __be16 sport,
+                                               __be16 dport, struct sock *sk)
 {
-        if (sport != (*rp)->fl.fl_ip_sport ||
-            dport != (*rp)->fl.fl_ip_dport) {
-                struct flowi fl;
-
-                memcpy(&fl, &(*rp)->fl, sizeof(fl));
-                fl.fl_ip_sport = sport;
-                fl.fl_ip_dport = dport;
-                fl.proto = protocol;
+        if (sport != orig_sport || dport != orig_dport) {
+                struct flowi4 fl4 = {
+                        .flowi4_oif = rt->rt_oif,
+                        .flowi4_mark = rt->rt_mark,
+                        .daddr = rt->rt_dst,
+                        .saddr = rt->rt_src,
+                        .flowi4_tos = rt->rt_tos,
+                        .flowi4_proto = protocol,
+                        .fl4_sport = sport,
+                        .fl4_dport = dport
+                };
                 if (inet_sk(sk)->transparent)
-                        fl.flags |= FLOWI_FLAG_ANYSRC;
-                ip_rt_put(*rp);
-                *rp = NULL;
-                security_sk_classify_flow(sk, &fl);
-                return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0);
+                        fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+                if (protocol == IPPROTO_TCP)
+                        fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS;
+                ip_rt_put(rt);
+                security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+                return ip_route_output_flow(sock_net(sk), &fl4, sk);
         }
-        return 0;
+        return rt;
 }
 
 extern void rt_bind_peer(struct rtable *rt, int create);