net: core: Make the FIB notification chain generic

The FIB notification chain is currently soley used by IPv4 code.
However, we're going to introduce IPv6 FIB offload support, which
requires these notification as well.

As explained in commit c3852ef7f2f8 ("ipv4: fib: Replay events when
registering FIB notifier"), upon registration to the chain, the callee
receives a full dump of the FIB tables and rules by traversing all the
net namespaces. The integrity of the dump is ensured by a per-namespace
sequence counter that is incremented whenever a change to the tables or
rules occurs.

In order to allow more address families to use the chain, each family is
expected to register its fib_notifier_ops in its pernet init. These
operations allow the common code to read the family's sequence counter
as well as dump its tables and rules in the given net namespace.

Additionally, a 'family' parameter is added to sent notifications, so
that listeners could distinguish between the different families.

Implement the common code that allows listeners to register to the chain
and for address families to register their fib_notifier_ops. Subsequent
patches will implement these operations in IPv6.

In the future, ipmr and ip6mr will be extended to provide these
notifications as well.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 37 insertions, 57 deletions

diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
index e0714d975947..7cf1954bbadc 100644
--- a/net/ipv4/fib_notifier.c
+++ b/net/ipv4/fib_notifier.c
@@ -1,86 +1,66 @@
 #include <linux/rtnetlink.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
+#include <linux/socket.h>
 #include <linux/kernel.h>
 #include <net/net_namespace.h>
+#include <net/fib_notifier.h>
 #include <net/netns/ipv4.h>
 #include <net/ip_fib.h>
 
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
-		      enum fib_event_type event_type,
-		      struct fib_notifier_info *info)
+int call_fib4_notifier(struct notifier_block *nb, struct net *net,
+		       enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
 {
-	info->net = net;
-	return nb->notifier_call(nb, event_type, info);
+	info->family = AF_INET;
+	return call_fib_notifier(nb, net, event_type, info);
 }
 
-int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
-		       struct fib_notifier_info *info)
+int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
+			struct fib_notifier_info *info)
 {
+	ASSERT_RTNL();
+
+	info->family = AF_INET;
 	net->ipv4.fib_seq++;
-	info->net = net;
-	return atomic_notifier_call_chain(&fib_chain, event_type, info);
+	return call_fib_notifiers(net, event_type, info);
 }
 
-static unsigned int fib_seq_sum(void)
+static unsigned int fib4_seq_read(struct net *net)
 {
-	unsigned int fib_seq = 0;
-	struct net *net;
+	ASSERT_RTNL();
 
-	rtnl_lock();
-	for_each_net(net)
-		fib_seq += net->ipv4.fib_seq;
-	rtnl_unlock();
-
-	return fib_seq;
+	return net->ipv4.fib_seq;
 }
 
-static bool fib_dump_is_consistent(struct notifier_block *nb,
-				   void (*cb)(struct notifier_block *nb),
-				   unsigned int fib_seq)
+static int fib4_dump(struct net *net, struct notifier_block *nb)
 {
-	atomic_notifier_chain_register(&fib_chain, nb);
-	if (fib_seq == fib_seq_sum())
-		return true;
-	atomic_notifier_chain_unregister(&fib_chain, nb);
-	if (cb)
-		cb(nb);
-	return false;
+	fib_rules_notify(net, nb);
+	fib_notify(net, nb);
+
+	return 0;
 }
 
-#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
-			  void (*cb)(struct notifier_block *nb))
-{
-	int retries = 0;
+static const struct fib_notifier_ops fib4_notifier_ops_template = {
+	.family		= AF_INET,
+	.fib_seq_read	= fib4_seq_read,
+	.fib_dump	= fib4_dump,
+};
 
-	do {
-		unsigned int fib_seq = fib_seq_sum();
-		struct net *net;
+int __net_init fib4_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
 
-		/* Mutex semantics guarantee that every change done to
-		 * FIB tries before we read the change sequence counter
-		 * is now visible to us.
-		 */
-		rcu_read_lock();
-		for_each_net_rcu(net) {
-			fib_rules_notify(net, nb);
-			fib_notify(net, nb);
-		}
-		rcu_read_unlock();
+	net->ipv4.fib_seq = 0;
 
-		if (fib_dump_is_consistent(nb, cb, fib_seq))
-			return 0;
-	} while (++retries < FIB_DUMP_MAX_RETRIES);
+	ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv4.notifier_ops = ops;
 
-	return -EBUSY;
+	return 0;
 }
-EXPORT_SYMBOL(register_fib_notifier);
 
-int unregister_fib_notifier(struct notifier_block *nb)
+void __net_exit fib4_notifier_exit(struct net *net)
 {
-	return atomic_notifier_chain_unregister(&fib_chain, nb);
+	fib_notifier_ops_unregister(net->ipv4.notifier_ops);
 }
-EXPORT_SYMBOL(unregister_fib_notifier);