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 7026b1ddb6 'netfilter: Pass socket pointer down through okfn().'

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/ip.h b/include/net/ip.h
index 37165fba3741ac68e5a93a8a22473eae70361e45..08f36cd2b874b5493bc9b51c4071722591dcc321 100644 (file)
--- 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
index 2d25979273a6f57378da645460d9d6c2a0d91e5c..77e7f69bf80d4ca8e31e09b5b07230bca1abf170 100644 (file)
--- 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
index 124bf0a663283502deb03397343160d493a378b1..4bd4921639c3e6415f8899896f72fe1564a68c55 100644 (file)
--- 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;