diff options
author | David S. Miller | 2012-08-23 03:48:21 +0200 |
---|---|---|
committer | David S. Miller | 2012-08-23 03:48:52 +0200 |
commit | bf277b0ccea7d2422b85e232017ce3fddbe9c49c (patch) | |
tree | 252232255b8a6024eccf2fea668bb89de5ae3073 /net/netfilter/ipvs/ip_vs_core.c | |
parent | Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsh... (diff) | |
parent | netfilter: remove unnecessary goto statement for error recovery (diff) | |
download | kernel-qcow2-linux-bf277b0ccea7d2422b85e232017ce3fddbe9c49c.tar.gz kernel-qcow2-linux-bf277b0ccea7d2422b85e232017ce3fddbe9c49c.tar.xz kernel-qcow2-linux-bf277b0ccea7d2422b85e232017ce3fddbe9c49c.zip |
Merge git://1984.lsi.us.es/nf-next
Pablo Neira Ayuso says:
====================
This is the first batch of Netfilter and IPVS updates for your
net-next tree. Mostly cleanups for the Netfilter side. They are:
* Remove unnecessary RTNL locking now that we have support
for namespace in nf_conntrack, from Patrick McHardy.
* Cleanup to eliminate unnecessary goto in the initialization
path of several Netfilter tables, from Jean Sacren.
* Another cleanup from Wu Fengguang, this time to PTR_RET instead
of if IS_ERR then return PTR_ERR.
* Use list_for_each_entry_continue_rcu in nf_iterate, from
Michael Wang.
* Add pmtu_disc sysctl option to disable PMTU in their tunneling
transmitter, from Julian Anastasov.
* Generalize application protocol registration in IPVS and modify
IPVS FTP helper to use it, from Julian Anastasov.
* update Kconfig. The IPVS FTP helper depends on the Netfilter FTP
helper for NAT support, from Julian Anastasov.
* Add logic to update PMTU for IPIP packets in IPVS, again
from Julian Anastasov.
* A couple of sparse warning fixes for IPVS and Netfilter from
Claudiu Ghioc and Patrick McHardy respectively.
Patrick's IPv6 NAT changes will follow after this batch, I need
to flush this batch first before refreshing my tree.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/netfilter/ipvs/ip_vs_core.c')
-rw-r--r-- | net/netfilter/ipvs/ip_vs_core.c | 76 |
1 files changed, 73 insertions, 3 deletions
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b54eccef40b5..58918e20f9d5 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; - unsigned int offset, ihl, verdict; + unsigned int offset, offset2, ihl, verdict; + bool ipip; *related = 1; @@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) net = skb_net(skb); + /* Special case for errors for IPIP packets */ + ipip = false; + if (cih->protocol == IPPROTO_IPIP) { + if (unlikely(cih->frag_off & htons(IP_OFFSET))) + return NF_ACCEPT; + /* Error for our IPIP must arrive at LOCAL_IN */ + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) + return NF_ACCEPT; + offset += cih->ihl * 4; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (cih == NULL) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + ipip = true; + } + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); + offset2 = offset; offset += cih->ihl * 4; ip_vs_fill_iphdr(AF_INET, cih, &ciph); - /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1); + /* The embedded headers contain source and dest in reverse order. + * For IPIP this is error for request, not for reply. + */ + cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1); if (!cp) return NF_ACCEPT; @@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) goto out; } + if (ipip) { + __be32 info = ic->un.gateway; + + /* Update the MTU */ + if (ic->type == ICMP_DEST_UNREACH && + ic->code == ICMP_FRAG_NEEDED) { + struct ip_vs_dest *dest = cp->dest; + u32 mtu = ntohs(ic->un.frag.mtu); + + /* Strip outer IP and ICMP, go to IPIP header */ + __skb_pull(skb, ihl + sizeof(_icmph)); + offset2 -= ihl + sizeof(_icmph); + skb_reset_network_header(skb); + IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", + &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); + rcu_read_lock(); + ipv4_update_pmtu(skb, dev_net(skb->dev), + mtu, 0, 0, 0, 0); + rcu_read_unlock(); + /* Client uses PMTUD? */ + if (!(cih->frag_off & htons(IP_DF))) + goto ignore_ipip; + /* Prefer the resulting PMTU */ + if (dest) { + spin_lock(&dest->dst_lock); + if (dest->dst_cache) + mtu = dst_mtu(dest->dst_cache); + spin_unlock(&dest->dst_lock); + } + if (mtu > 68 + sizeof(struct iphdr)) + mtu -= sizeof(struct iphdr); + info = htonl(mtu); + } + /* Strip outer IP, ICMP and IPIP, go to IP header of + * original request. + */ + __skb_pull(skb, offset2); + skb_reset_network_header(skb); + IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", + &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, + ic->type, ic->code, ntohl(info)); + icmp_send(skb, ic->type, ic->code, info); + /* ICMP can be shorter but anyways, account it */ + ip_vs_out_stats(cp, skb); + +ignore_ipip: + consume_skb(skb); + verdict = NF_STOLEN; + goto out; + } + /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) |