ipv4: Fix ip_skb_dst_mtu to use the sk passed by ip_finish_output

ip_skb_dst_mtu uses skb->sk, assuming it is an AF_INET socket (e.g. it calls ip_sk_use_pmtu which casts sk as an inet_sk). However, in the case of UDP tunneling, the skb->sk is not necessarily an inet socket (could be AF_PACKET socket, or AF_UNSPEC if arriving from tun/tap). OTOH, the sk passed as an argument throughout IP stack's output path is the one which is of PMTU interest: - In case of local sockets, sk is same as skb->sk; - In case of a udp tunnel, sk is the tunneling socket. Fix, by passing ip_finish_output's sk to ip_skb_dst_mtu. This augments 7026b1d 'netfilter: Pass socket pointer down through okfn().' Signed-off-by: Shmulik Ladkani <[email protected]> Reviewed-by: Hannes Frederic Sowa <[email protected]> Signed-off-by: David S. Miller <[email protected]>
josf · Jun 30, 2016 · fedbb6b · fedbb6b
1 parent 5ab0d6a
commit fedbb6b
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 6 deletions.
diff --git a/include/net/ip.h b/include/net/ip.h
@@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	return min(dst->dev->mtu, IP_MAX_MTU);
 }
 
-static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
+static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
+					  const struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
-
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
@@ -700,7 +700,7 @@ static int
 br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		  int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
-	unsigned int mtu = ip_skb_dst_mtu(skb);
+	unsigned int mtu = ip_skb_dst_mtu(sk, skb);
 	struct iphdr *iph = ip_hdr(skb);
 
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
@@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 		return dst_output(net, sk, skb);
 	}
 #endif
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
@@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 	iph = ip_hdr(skb);
 
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
 		mtu = IPCB(skb)->frag_max_size;