Merge branch 'nexthop_exceptions'

These patches implement the final mechanism necessary to really allow
us to go without the route cache in ipv4.

We need a place to have long-term storage of PMTU/redirect information
which is independent of the routes themselves, yet does not get us
back into a situation where we have to write to metrics or anything
like that.

For this we use an "next-hop exception" table in the FIB nexthops.

The one thing I desperately want to avoid is having to create clone
routes in the FIB trie for this purpose, because that is very
expensive.   However, I'm willing to entertain such an idea later
if this current scheme proves to have downsides that the FIB trie
variant would not have.

In order to accomodate this any such scheme, we need to be able to
produce a full flow key at PMTU/redirect time.  That required an
adjustment of the interface call-sites used to propagate these events.

For a PMTU/redirect with a fully specified socket, we pass that socket
and use it to produce the flow key.

Otherwise we use a passed in SKB to formulate the key.  There are two
cases that need to be distinguished, ICMP message processing (in which
case the IP header is at skb->data) and output packet processing
(mostly tunnels, and in all such cases the IP header is at ip_hdr(skb)).

We also have to make the code able to handle the case where the dst
itself passed into the dst_ops->{update_pmtu,redirect} method is
invalidated.  This matters for calls from sockets that have cached
that route.  We provide a inet{,6} helper function for this purpose,
and edit SCTP specially since it caches routes at the transport rather
than socket level.

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 30 insertions, 6 deletions

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 085931fa7ce0..d079fc61c123 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -24,8 +24,10 @@ struct dst_ops {
 					  struct net_device *dev, int how);
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
-	void			(*update_pmtu)(struct dst_entry *dst, u32 mtu);
-	void			(*redirect)(struct dst_entry *dst, struct sk_buff *skb);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
 	int			(*local_out)(struct sk_buff *skb);
 	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
 						struct sk_buff *skb,
diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index df2a857e853d..04642c920431 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -43,4 +43,6 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
 extern int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl);
+
+extern struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET6_CONNECTION_SOCK_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 291e7cee14e7..2cf44b4ed2e6 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -337,4 +337,6 @@ extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 				      char __user *optval, int __user *optlen);
 extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 				      char __user *optval, unsigned int optlen);
+
+extern struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5697acefeba3..e9ee1ca07087 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -18,6 +18,7 @@
 
 #include <net/flow.h>
 #include <linux/seq_file.h>
+#include <linux/rcupdate.h>
 #include <net/fib_rules.h>
 #include <net/inetpeer.h>
 
@@ -46,6 +47,22 @@ struct fib_config {
 
 struct fib_info;
 
+struct fib_nh_exception {
+	struct fib_nh_exception __rcu	*fnhe_next;
+	__be32				fnhe_daddr;
+	u32				fnhe_pmtu;
+	u32				fnhe_gw;
+	unsigned long			fnhe_expires;
+	unsigned long			fnhe_stamp;
+};
+
+struct fnhe_hash_bucket {
+	struct fib_nh_exception __rcu	*chain;
+};
+
+#define FNHE_HASH_SIZE		2048
+#define FNHE_RECLAIM_DEPTH	5
+
 struct fib_nh {
 	struct net_device	*nh_dev;
 	struct hlist_node	nh_hash;
@@ -63,6 +80,7 @@ struct fib_nh {
 	__be32			nh_gw;
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
+	struct fnhe_hash_bucket	*nh_exceptions;
 };
 
 /*
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 1f2735dba753..ff499640528b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -519,10 +519,10 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
 	return frag;
 }
 
-static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
 {
 
-	sctp_assoc_sync_pmtu(asoc);
+	sctp_assoc_sync_pmtu(sk, asoc);
 	asoc->pmtu_pending = 0;
 }
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index fecdf31816f2..536e439ddf1d 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1091,7 +1091,7 @@ void sctp_transport_burst_limited(struct sctp_transport *);
 void sctp_transport_burst_reset(struct sctp_transport *);
 unsigned long sctp_transport_timeout(struct sctp_transport *);
 void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sctp_transport *, u32);
+void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
 void sctp_transport_immediate_rtx(struct sctp_transport *);
 
 
@@ -2003,7 +2003,7 @@ void sctp_assoc_update(struct sctp_association *old,
 
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
-void sctp_assoc_sync_pmtu(struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
 void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
 void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
 void sctp_assoc_set_primary(struct sctp_association *,