ipv4: Add FIB nexthop exceptions.

In a regime where we have subnetted route entries, we need a way to
store persistent storage about destination specific learned values
such as redirects and PMTU values.

This is implemented here via nexthop exceptions.

The initial implementation is a 2048 entry hash table with relaiming
starting at chain length 5.  A more sophisticated scheme can be
devised if that proves necessary.

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

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;
 };
 
 /*

net/ipv4/fib_semantics.c

@@ -140,6 +140,27 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
 	},
 };
 
+static void free_nh_exceptions(struct fib_nh *nh)
+{
+	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	int i;
+
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = rcu_dereference(hash[i].chain);
+		while (fnhe) {
+			struct fib_nh_exception *next;
+
+			next = rcu_dereference(fnhe->fnhe_next);
+			kfree(fnhe);
+
+			fnhe = next;
+		}
+	}
+	kfree(hash);
+}
+
 /* Release a nexthop info record */
 static void free_fib_info_rcu(struct rcu_head *head)
 {
@@ -148,6 +169,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
 			dev_put(nexthop_nh->nh_dev);
+		if (nexthop_nh->nh_exceptions)
+			free_nh_exceptions(nexthop_nh);
 	} endfor_nexthops(fi);
 
 	release_net(fi->fib_net);