ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing

While forwarding we should not use the protocol path mtu to calculate
the mtu for a forwarded packet but instead use the interface mtu.

We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was
introduced for multicast forwarding. But as it does not conflict with
our usage in unicast code path it is perfect for reuse.

I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu
along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular
dependencies because of IPSKB_FORWARDED.

Because someone might have written a software which does probe
destinations manually and expects the kernel to honour those path mtus
I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone
can disable this new behaviour. We also still use mtus which are locked on a
route for forwarding.

The reason for this change is, that path mtus information can be injected
into the kernel via e.g. icmp_err protocol handler without verification
of local sockets. As such, this could cause the IPv4 forwarding path to
wrongfully emit fragmentation needed notifications or start to fragment
packets along a path.

Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED
won't be set and further fragmentation logic will use the path mtu to
determine the fragmentation size. They also recheck packet size with
help of path mtu discovery and report appropriate errors.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: John Heffner <johnwheffner@gmail.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 37 insertions, 16 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index 535664477c4..0dab95c2e4d 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -263,6 +263,39 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
 		 !(dst_metric_locked(dst, RTAX_MTU)));
 }
 
+static inline bool ip_sk_accept_pmtu(const struct sock *sk)
+{
+	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;
+}
+
+static inline bool ip_sk_use_pmtu(const struct sock *sk)
+{
+	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
+}
+
+static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
+						    bool forwarding)
+{
+	struct net *net = dev_net(dst->dev);
+
+	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
+	    dst_metric_locked(dst, RTAX_MTU) ||
+	    !forwarding)
+		return dst_mtu(dst);
+
+	return min(dst->dev->mtu, IP_MAX_MTU);
+}
+
+static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
+{
+	if (!skb->sk || ip_sk_use_pmtu(skb->sk)) {
+		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
+		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
+	} else {
+		return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	}
+}
+
 void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
 
 static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 929a668e91a..80f500a2949 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -70,6 +70,7 @@ struct netns_ipv4 {
 
 	int sysctl_tcp_ecn;
 	int sysctl_ip_no_pmtu_disc;
+	int sysctl_ip_fwd_use_pmtu;
 
 	kgid_t sysctl_ping_group_range[2];
 
diff --git a/include/net/route.h b/include/net/route.h
index 638e3ebf76f..9d1f423d594 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -36,6 +36,9 @@
 #include <linux/cache.h>
 #include <linux/security.h>
 
+/* IPv4 datagram length is stored into 16bit field (tot_len) */
+#define IP_MAX_MTU	0xFFFFU
+
 #define RTO_ONLINK	0x01
 
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
@@ -311,20 +314,4 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 	return hoplimit;
 }
 
-static inline bool ip_sk_accept_pmtu(const struct sock *sk)
-{
-	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;
-}
-
-static inline bool ip_sk_use_pmtu(const struct sock *sk)
-{
-	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
-}
-
-static inline int ip_skb_dst_mtu(const struct sk_buff *skb)
-{
-	return (!skb->sk || ip_sk_use_pmtu(skb->sk)) ?
-	       dst_mtu(skb_dst(skb)) : skb_dst(skb)->dev->mtu;
-}
-
 #endif	/* _ROUTE_H */