bridge_netfilter: No ICMP packet on IPv4 fragmentation error
When bridge netfilter re-fragments an IP packet for output, all
packets that can not be re-fragmented to their original input size
should be silently discarded.
However, current bridge netfilter output path generates an ICMP packet
with 'size exceeded MTU' message for such packets, this is a bug.
This patch refactors the ip_fragment() API to allow two separate
use cases. The bridge netfilter user case will not
send ICMP, the routing output will, as before.
Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 2b0e8bb..1d2eb32 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -853,6 +853,25 @@
return br_dev_queue_push_xmit(sk, skb);
}
+static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct sock *, struct sk_buff *))
+{
+ unsigned int mtu = ip_skb_dst_mtu(skb);
+ struct iphdr *iph = ip_hdr(skb);
+ struct rtable *rt = skb_rtable(skb);
+ struct net_device *dev = rt->dst.dev;
+
+ if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
+ (IPCB(skb)->frag_max_size &&
+ IPCB(skb)->frag_max_size > mtu))) {
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
+
+ return ip_do_fragment(sk, skb, output);
+}
+
static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
{
int ret;
@@ -886,7 +905,7 @@
skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
data->size);
- ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
+ ret = br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit);
} else {
nf_bridge_info_free(skb);
ret = br_dev_queue_push_xmit(sk, skb);