diff options
| author | Andy Zhou <azhou@nicira.com> | 2015-05-15 23:15:37 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-05-19 06:15:39 +0200 |
| commit | 49d16b23cd1e61c028ee088c5a64e9ac6a9c6147 (patch) | |
| tree | 446c416b396c4561bd5616f6fba2ef52c43c8d06 /net/ipv4 | |
| parent | IPv4: skip ICMP for bridge contrack users when defrag expires (diff) | |
| download | linux-49d16b23cd1e61c028ee088c5a64e9ac6a9c6147.tar.xz linux-49d16b23cd1e61c028ee088c5a64e9ac6a9c6147.zip | |
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>
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/ip_output.c | 40 |
1 files changed, 28 insertions, 12 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 2acc5dc32807..8d91b922fcfe 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,6 +83,9 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); +static int ip_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)); + /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { @@ -478,6 +481,28 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static int ip_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) +{ + struct iphdr *iph = ip_hdr(skb); + unsigned int mtu = ip_skb_dst_mtu(skb); + + if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || + (IPCB(skb)->frag_max_size && + IPCB(skb)->frag_max_size > mtu))) { + struct rtable *rt = skb_rtable(skb); + struct net_device *dev = rt->dst.dev; + + IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + kfree_skb(skb); + return -EMSGSIZE; + } + + return ip_do_fragment(sk, skb, output); +} + /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus @@ -485,8 +510,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -int ip_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip_do_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) { struct iphdr *iph; int ptr; @@ -507,15 +532,6 @@ int ip_fragment(struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(skb); - 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); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); - kfree_skb(skb); - return -EMSGSIZE; - } /* * Setup starting values. @@ -751,7 +767,7 @@ fail: IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; } -EXPORT_SYMBOL(ip_fragment); +EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) |