summaryrefslogtreecommitdiff
path: root/net/openvswitch/conntrack.c
diff options
context:
space:
mode:
authorEd Swierk <eswierk@skyportsystems.com>2018-02-01 05:48:02 +0300
committerDavid S. Miller <davem@davemloft.net>2018-02-01 17:46:22 +0300
commit9382fe71c0058465e942a633869629929102843d (patch)
treea67c6d0859748ef1a443189f08113e2b855a691b /net/openvswitch/conntrack.c
parent3aff3b4b986e51bcf4ab249e5d48d39596e0df6a (diff)
downloadlinux-9382fe71c0058465e942a633869629929102843d.tar.xz
openvswitch: Remove padding from packet before L3+ conntrack processing
IPv4 and IPv6 packets may arrive with lower-layer padding that is not included in the L3 length. For example, a short IPv4 packet may have up to 6 bytes of padding following the IP payload when received on an Ethernet device with a minimum packet length of 64 bytes. Higher-layer processing functions in netfilter (e.g. nf_ip_checksum(), and help() in nf_conntrack_ftp) assume skb->len reflects the length of the L3 header and payload, rather than referring back to ip_hdr->tot_len or ipv6_hdr->payload_len, and get confused by lower-layer padding. In the normal IPv4 receive path, ip_rcv() trims the packet to ip_hdr->tot_len before invoking netfilter hooks. In the IPv6 receive path, ip6_rcv() does the same using ipv6_hdr->payload_len. Similarly in the br_netfilter receive path, br_validate_ipv4() and br_validate_ipv6() trim the packet to the L3 length before invoking netfilter hooks. Currently in the OVS conntrack receive path, ovs_ct_execute() pulls the skb to the L3 header but does not trim it to the L3 length before calling nf_conntrack_in(NF_INET_PRE_ROUTING). When nf_conntrack_proto_tcp encounters a packet with lower-layer padding, nf_ip_checksum() fails causing a "nf_ct_tcp: bad TCP checksum" log message. While extra zero bytes don't affect the checksum, the length in the IP pseudoheader does. That length is based on skb->len, and without trimming, it doesn't match the length the sender used when computing the checksum. In ovs_ct_execute(), trim the skb to the L3 length before higher-layer processing. Signed-off-by: Ed Swierk <eswierk@skyportsystems.com> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/openvswitch/conntrack.c')
-rw-r--r--net/openvswitch/conntrack.c34
1 files changed, 34 insertions, 0 deletions
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 62f36cc938ca..c5904f629091 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1098,6 +1098,36 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
return 0;
}
+/* Trim the skb to the length specified by the IP/IPv6 header,
+ * removing any trailing lower-layer padding. This prepares the skb
+ * for higher-layer processing that assumes skb->len excludes padding
+ * (such as nf_ip_checksum). The caller needs to pull the skb to the
+ * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
+ */
+static int ovs_skb_network_trim(struct sk_buff *skb)
+{
+ unsigned int len;
+ int err;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ len = ntohs(ip_hdr(skb)->tot_len);
+ break;
+ case htons(ETH_P_IPV6):
+ len = sizeof(struct ipv6hdr)
+ + ntohs(ipv6_hdr(skb)->payload_len);
+ break;
+ default:
+ len = skb->len;
+ }
+
+ err = pskb_trim_rcsum(skb, len);
+ if (err)
+ kfree_skb(skb);
+
+ return err;
+}
+
/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
* value if 'skb' is freed.
*/
@@ -1112,6 +1142,10 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
nh_ofs = skb_network_offset(skb);
skb_pull_rcsum(skb, nh_ofs);
+ err = ovs_skb_network_trim(skb);
+ if (err)
+ return err;
+
if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
err = handle_fragments(net, key, info->zone.id, skb);
if (err)