1 files changed, 189 insertions, 107 deletions

diff --git a/include/net/route.h b/include/net/route.h
index b8c1f7703fc..b17cf28f996 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -30,55 +30,57 @@
 #include <net/inet_sock.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
+#include <linux/rcupdate.h>
 #include <linux/route.h>
 #include <linux/ip.h>
 #include <linux/cache.h>
 #include <linux/security.h>
 
-#ifndef __KERNEL__
-#warning This file is not supposed to be used outside of kernel.
-#endif
+/* IPv4 datagram length is stored into 16bit field (tot_len) */
+#define IP_MAX_MTU	0xFFFFU
 
 #define RTO_ONLINK	0x01
 
-#define RTO_CONN	0
-/* RTO_CONN is not used (being alias for 0), but preserved not to break
- * some modules referring to it. */
-
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
+#define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
 struct fib_nh;
-struct inet_peer;
+struct fib_info;
 struct rtable {
 	struct dst_entry	dst;
 
-	/* Cache lookup keys */
-	struct flowi		fl;
-
 	int			rt_genid;
-	unsigned		rt_flags;
+	unsigned int		rt_flags;
 	__u16			rt_type;
+	__u8			rt_is_input;
+	__u8			rt_uses_gateway;
 
-	__be32			rt_dst;	/* Path destination	*/
-	__be32			rt_src;	/* Path source		*/
 	int			rt_iif;
 
 	/* Info on neighbour */
 	__be32			rt_gateway;
 
 	/* Miscellaneous cached information */
-	__be32			rt_spec_dst; /* RFC1122 specific destination */
-	struct inet_peer	*peer; /* long-living peer info */
+	u32			rt_pmtu;
+
+	struct list_head	rt_uncached;
 };
 
-static inline bool rt_is_input_route(struct rtable *rt)
+static inline bool rt_is_input_route(const struct rtable *rt)
+{
+	return rt->rt_is_input != 0;
+}
+
+static inline bool rt_is_output_route(const struct rtable *rt)
 {
-	return rt->fl.iif != 0;
+	return rt->rt_is_input == 0;
 }
 
-static inline bool rt_is_output_route(struct rtable *rt)
+static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
 {
-	return rt->fl.iif == 0;
+	if (rt->rt_gateway)
+		return rt->rt_gateway;
+	return daddr;
 }
 
 struct ip_rt_acct {
@@ -89,68 +91,118 @@ struct ip_rt_acct {
 };
 
 struct rt_cache_stat {
-        unsigned int in_hit;
         unsigned int in_slow_tot;
         unsigned int in_slow_mc;
         unsigned int in_no_route;
         unsigned int in_brd;
         unsigned int in_martian_dst;
         unsigned int in_martian_src;
-        unsigned int out_hit;
         unsigned int out_slow_tot;
         unsigned int out_slow_mc;
-        unsigned int gc_total;
-        unsigned int gc_ignored;
-        unsigned int gc_goal_miss;
-        unsigned int gc_dst_overflow;
-        unsigned int in_hlist_search;
-        unsigned int out_hlist_search;
 };
 
 extern struct ip_rt_acct __percpu *ip_rt_acct;
 
 struct in_device;
-extern int		ip_rt_init(void);
-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(void);
-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 int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
-				 u8 tos, struct net_device *devin, bool noref);
 
-static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
-				 u8 tos, struct net_device *devin)
+int ip_rt_init(void);
+void rt_cache_flush(struct net *net);
+void rt_flush_dev(struct net_device *dev);
+struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
+struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
+				    struct sock *sk);
+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,
+		.flowi4_tos = tos,
+		.daddr = daddr,
+		.saddr = saddr,
+	};
+	return ip_route_output_key(net, &fl4);
+}
+
+static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
+						   struct sock *sk,
+						   __be32 daddr, __be32 saddr,
+						   __be16 dport, __be16 sport,
+						   __u8 proto, __u8 tos, int oif)
 {
-	return ip_route_input_common(skb, dst, src, tos, devin, false);
+	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
+			   RT_SCOPE_UNIVERSE, proto,
+			   sk ? inet_sk_flowi_flags(sk) : 0,
+			   daddr, saddr, dport, sport);
+	if (sk)
+		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+	return ip_route_output_flow(net, fl4, sk);
 }
 
-static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-				       u8 tos, struct net_device *devin)
+static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4,
+						 __be32 daddr, __be32 saddr,
+						 __be32 gre_key, __u8 tos, int oif)
 {
-	return ip_route_input_common(skb, dst, src, tos, devin, true);
+	memset(fl4, 0, sizeof(*fl4));
+	fl4->flowi4_oif = oif;
+	fl4->daddr = daddr;
+	fl4->saddr = saddr;
+	fl4->flowi4_tos = tos;
+	fl4->flowi4_proto = IPPROTO_GRE;
+	fl4->fl4_gre_key = gre_key;
+	return ip_route_output_key(net, fl4);
 }
 
-extern unsigned short	ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev);
-extern void		ip_rt_send_redirect(struct sk_buff *skb);
+int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
+			 u8 tos, struct net_device *devin);
 
-extern unsigned		inet_addr_type(struct net *net, __be32 addr);
-extern unsigned		inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr);
-extern void		ip_rt_multicast_event(struct in_device *);
-extern int		ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
-extern void		ip_rt_get_source(u8 *src, struct rtable *rt);
-extern int		ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
+static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
+				 u8 tos, struct net_device *devin)
+{
+	int err;
+
+	rcu_read_lock();
+	err = ip_route_input_noref(skb, dst, src, tos, devin);
+	if (!err)
+		skb_dst_force(skb);
+	rcu_read_unlock();
+
+	return err;
+}
+
+void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
+		      u32 mark, u8 protocol, int flow_flags);
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
+void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+		   u8 protocol, int flow_flags);
+void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
+void ip_rt_send_redirect(struct sk_buff *skb);
+
+unsigned int inet_addr_type(struct net *net, __be32 addr);
+unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
+				__be32 addr);
+void ip_rt_multicast_event(struct in_device *);
+int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
+void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
 
 struct in_ifaddr;
-extern void fib_add_ifaddr(struct in_ifaddr *);
+void fib_add_ifaddr(struct in_ifaddr *);
+void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
-static inline void ip_rt_put(struct rtable * rt)
+static inline void ip_rt_put(struct rtable *rt)
 {
-	if (rt)
-		dst_release(&rt->dst);
+	/* dst_release() accepts a NULL parameter.
+	 * We rely on dst being first structure in struct rtable
+	 */
+	BUILD_BUG_ON(offsetof(struct rtable, dst) != 0);
+	dst_release(&rt->dst);
 }
 
 #define IPTOS_RT_MASK	(IPTOS_TOS_MASK & ~3)
@@ -162,73 +214,103 @@ 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)
+/* ip_route_connect() and ip_route_newports() work in tandem whilst
+ * binding a socket for a new outgoing connection.
+ *
+ * In order to use IPSEC properly, we must, in the end, have a
+ * route that was looked up using all available keys including source
+ * and destination ports.
+ *
+ * However, if a source port needs to be allocated (the user specified
+ * a wildcard source port) we need to obtain addressing information
+ * in order to perform that allocation.
+ *
+ * So ip_route_connect() looks up a route using wildcarded source and
+ * destination ports in the key, simply so that we can get a pair of
+ * addresses to use for port allocation.
+ *
+ * Later, once the ports are allocated, ip_route_newports() will make
+ * another route lookup if needed to make sure we catch any IPSEC
+ * rules keyed on the port information.
+ *
+ * The callers allocate the flow key on their stack, and must pass in
+ * the same flowi4 object to both the ip_route_connect() and the
+ * ip_route_newports() calls.
+ */
+
+static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src,
+					 u32 tos, int oif, u8 protocol,
+					 __be16 sport, __be16 dport,
+					 struct sock *sk)
 {
-	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 net *net = sock_net(sk);
+	__u8 flow_flags = 0;
 
 	if (inet_sk(sk)->transparent)
-		fl.flags |= FLOWI_FLAG_ANYSRC;
+		flow_flags |= FLOWI_FLAG_ANYSRC;
+
+	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
+			   protocol, flow_flags, dst, src, dport, sport);
+}
+
+static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
+					      __be32 dst, __be32 src, u32 tos,
+					      int oif, u8 protocol,
+					      __be16 sport, __be16 dport,
+					      struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+	struct rtable *rt;
+
+	ip_route_connect_init(fl4, dst, src, tos, oif, protocol,
+			      sport, dport, sk);
 
 	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;
+		ip_rt_put(rt);
+		flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr);
 	}
-	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 flowi4 *fl4, struct rtable *rt,
+					       __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 (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);
+	if (sport != orig_sport || dport != orig_dport) {
+		fl4->fl4_dport = dport;
+		fl4->fl4_sport = sport;
+		ip_rt_put(rt);
+		flowi4_update_output(fl4, sk->sk_bound_dev_if,
+				     RT_CONN_FLAGS(sk), fl4->daddr,
+				     fl4->saddr);
+		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);
-
-static inline struct inet_peer *rt_get_peer(struct rtable *rt)
+static inline int inet_iif(const struct sk_buff *skb)
 {
-	if (rt->peer)
-		return rt->peer;
+	int iif = skb_rtable(skb)->rt_iif;
 
-	rt_bind_peer(rt, 0);
-	return rt->peer;
+	if (iif)
+		return iif;
+	return skb->skb_iif;
 }
 
-static inline int inet_iif(const struct sk_buff *skb)
+extern int sysctl_ip_default_ttl;
+
+static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 {
-	return skb_rtable(skb)->rt_iif;
+	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
+
+	if (hoplimit == 0)
+		hoplimit = sysctl_ip_default_ttl;
+	return hoplimit;
 }
 
 #endif	/* _ROUTE_H */