net/ipv6: Add helper to return path MTU based on fib result

Determine path MTU from a FIB lookup result. Logic is based on
ip6_dst_mtu_forward plus lookup of nexthop exception.

Add ip6_dst_mtu_forward to ipv6_stubs to handle access by core
bpf code.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

6 files changed, 68 insertions, 0 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index ff766ab207e0..c07d4dd09361 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -236,6 +236,8 @@ struct ipv6_stub {
 						   struct flowi6 *fl6, int oif,
 						   const struct sk_buff *skb,
 						   int strict);
+	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
+				 struct in6_addr *saddr);
 
 	void (*udpv6_encap_enable)(void);
 	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index cc70f6da8462..7897efe80727 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -412,6 +412,12 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
 	return f6i->fib6_nh.nh_dev;
 }
 
+static inline
+struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
+{
+	return f6i->fib6_nh.nh_lwtstate;
+}
+
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int flags);
 
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 4cf1ef935ed9..7b9c82de11cc 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -300,6 +300,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 	return mtu;
 }
 
+u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
+		      struct in6_addr *saddr);
+
 struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 				   struct net_device *dev, struct sk_buff *skb,
 				   const void *daddr);
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 2fe754fd4f5e..5cd0029d930e 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -161,12 +161,20 @@ eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
 	return f6i;
 }
 
+static u32
+eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
+			       struct in6_addr *saddr)
+{
+	return 0;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
 	.fib6_get_table    = eafnosupport_fib6_get_table,
 	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
 	.fib6_lookup       = eafnosupport_fib6_lookup,
 	.fib6_multipath_select = eafnosupport_fib6_multipath_select,
+	.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 50de8b0d4f70..9ed0eae91758 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -894,6 +894,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.fib6_table_lookup = fib6_table_lookup,
 	.fib6_lookup       = fib6_lookup,
 	.fib6_multipath_select = fib6_multipath_select,
+	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
 	.udpv6_encap_enable = udpv6_encap_enable,
 	.ndisc_send_na = ndisc_send_na,
 	.nd_tbl	= &nd_tbl,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cc24ed3bc334..dc5d5c84dbef 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2603,6 +2603,54 @@ out:
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+/* MTU selection:
+ * 1. mtu on route is locked - use it
+ * 2. mtu from nexthop exception
+ * 3. mtu from egress device
+ *
+ * based on ip6_dst_mtu_forward and exception logic of
+ * rt6_find_cached_rt; called with rcu_read_lock
+ */
+u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
+		      struct in6_addr *saddr)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct in6_addr *src_key;
+	struct inet6_dev *idev;
+	u32 mtu = 0;
+
+	if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
+		mtu = f6i->fib6_pmtu;
+		if (mtu)
+			goto out;
+	}
+
+	src_key = NULL;
+#ifdef CONFIG_IPV6_SUBTREES
+	if (f6i->fib6_src.plen)
+		src_key = saddr;
+#endif
+
+	bucket = rcu_dereference(f6i->rt6i_exception_bucket);
+	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
+	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
+
+	if (likely(!mtu)) {
+		struct net_device *dev = fib6_info_nh_dev(f6i);
+
+		mtu = IPV6_MIN_MTU;
+		idev = __in6_dev_get(dev);
+		if (idev && idev->cnf.mtu6 > mtu)
+			mtu = idev->cnf.mtu6;
+	}
+
+	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+out:
+	return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
+}
+
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 				  struct flowi6 *fl6)
 {