openvswitch: Add original direction conntrack tuple to sw_flow_key.
Add the fields of the conntrack original direction 5-tuple to struct
sw_flow_key. The new fields are initially marked as non-existent, and
are populated whenever a conntrack action is executed and either finds
or generates a conntrack entry. This means that these fields exist
for all packets that were not rejected by conntrack as untrackable.
The original tuple fields in the sw_flow_key are filled from the
original direction tuple of the conntrack entry relating to the
current packet, or from the original direction tuple of the master
conntrack entry, if the current conntrack entry has a master.
Generally, expected connections of connections having an assigned
helper (e.g., FTP), have a master conntrack entry.
The main purpose of the new conntrack original tuple fields is to
allow matching on them for policy decision purposes, with the premise
that the admissibility of tracked connections reply packets (as well
as original direction packets), and both direction packets of any
related connections may be based on ACL rules applying to the master
connection's original direction 5-tuple. This also makes it easier to
make policy decisions when the actual packet headers might have been
transformed by NAT, as the original direction 5-tuple represents the
packet headers before any such transformation.
When using the original direction 5-tuple the admissibility of return
and/or related packets need not be based on the mere existence of a
conntrack entry, allowing separation of admission policy from the
established conntrack state. While existence of a conntrack entry is
required for admission of the return or related packets, policy
changes can render connections that were initially admitted to be
rejected or dropped afterwards. If the admission of the return and
related packets was based on mere conntrack state (e.g., connection
being in an established state), a policy change that would make the
connection rejected or dropped would need to find and delete all
conntrack entries affected by such a change. When using the original
direction 5-tuple matching the affected conntrack entries can be
allowed to time out instead, as the established state of the
connection would not need to be the basis for packet admission any
more.
It should be noted that the directionality of related connections may
be the same or different than that of the master connection, and
neither the original direction 5-tuple nor the conntrack state bits
carry this information. If needed, the directionality of the master
connection can be stored in master's conntrack mark or labels, which
are automatically inherited by the expected related connections.
The fact that neither ARP nor ND packets are trackable by conntrack
allows mutual exclusion between ARP/ND and the new conntrack original
tuple fields. Hence, the IP addresses are overlaid in union with ARP
and ND fields. This allows the sw_flow_key to not grow much due to
this patch, but it also means that we must be careful to never use the
new key fields with ARP or ND packets. ARP is easy to distinguish and
keep mutually exclusive based on the ethernet type, but ND being an
ICMPv6 protocol requires a bit more attention.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c87d359..989f38f 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -129,7 +129,9 @@
/* The following mask attributes allowed only if they
* pass the validation tests. */
mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4)
+ | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)
| (1 << OVS_KEY_ATTR_IPV6)
+ | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)
| (1 << OVS_KEY_ATTR_TCP)
| (1 << OVS_KEY_ATTR_TCP_FLAGS)
| (1 << OVS_KEY_ATTR_UDP)
@@ -161,8 +163,10 @@
if (match->key->eth.type == htons(ETH_P_IP)) {
key_expected |= 1 << OVS_KEY_ATTR_IPV4;
- if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+ if (match->mask && match->mask->key.eth.type == htons(0xffff)) {
mask_allowed |= 1 << OVS_KEY_ATTR_IPV4;
+ mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4;
+ }
if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
if (match->key->ip.proto == IPPROTO_UDP) {
@@ -196,8 +200,10 @@
if (match->key->eth.type == htons(ETH_P_IPV6)) {
key_expected |= 1 << OVS_KEY_ATTR_IPV6;
- if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+ if (match->mask && match->mask->key.eth.type == htons(0xffff)) {
mask_allowed |= 1 << OVS_KEY_ATTR_IPV6;
+ mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6;
+ }
if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
if (match->key->ip.proto == IPPROTO_UDP) {
@@ -230,6 +236,12 @@
htons(NDISC_NEIGHBOUR_SOLICITATION) ||
match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
key_expected |= 1 << OVS_KEY_ATTR_ND;
+ /* Original direction conntrack tuple
+ * uses the same space as the ND fields
+ * in the key, so both are not allowed
+ * at the same time.
+ */
+ mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
if (match->mask && (match->mask->key.tp.src == htons(0xff)))
mask_allowed |= 1 << OVS_KEY_ATTR_ND;
}
@@ -282,7 +294,7 @@
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
* updating this function.
*/
- BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26);
+ BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
@@ -295,6 +307,7 @@
+ nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */
+ nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */
+ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
@@ -355,6 +368,10 @@
[OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) },
[OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) },
+ [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = {
+ .len = sizeof(struct ovs_key_ct_tuple_ipv4) },
+ [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = {
+ .len = sizeof(struct ovs_key_ct_tuple_ipv6) },
};
static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -430,9 +447,8 @@
return __parse_flow_nlattrs(attr, a, attrsp, log, true);
}
-static int parse_flow_nlattrs(const struct nlattr *attr,
- const struct nlattr *a[], u64 *attrsp,
- bool log)
+int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[],
+ u64 *attrsp, bool log)
{
return __parse_flow_nlattrs(attr, a, attrsp, log, false);
}
@@ -1082,6 +1098,34 @@
sizeof(*cl), is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
}
+ if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) {
+ const struct ovs_key_ct_tuple_ipv4 *ct;
+
+ ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]);
+
+ SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask);
+ SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv4_proto, is_mask);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4);
+ }
+ if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) {
+ const struct ovs_key_ct_tuple_ipv6 *ct;
+
+ ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]);
+
+ SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src,
+ sizeof(match->key->ipv6.ct_orig.src),
+ is_mask);
+ SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst,
+ sizeof(match->key->ipv6.ct_orig.dst),
+ is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
+ SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv6_proto, is_mask);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
+ }
/* For layer 3 packets the Ethernet type is provided
* and treated as metadata but no MAC addresses are provided.
@@ -1493,9 +1537,12 @@
/**
* ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
- * @key: Receives extracted in_port, priority, tun_key and skb_mark.
- * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
- * sequence.
+ * @net: Network namespace.
+ * @key: Receives extracted in_port, priority, tun_key, skb_mark and conntrack
+ * metadata.
+ * @a: Array of netlink attributes holding parsed %OVS_KEY_ATTR_* Netlink
+ * attributes.
+ * @attrs: Bit mask for the netlink attributes included in @a.
* @log: Boolean to allow kernel error logging. Normally true, but when
* probing for feature compatibility this should be passed in as false to
* suppress unnecessary error logging.
@@ -1504,25 +1551,23 @@
* take the same form accepted by flow_from_nlattrs(), but only enough of it to
* get the metadata, that is, the parts of the flow key that cannot be
* extracted from the packet itself.
+ *
+ * This must be called before the packet key fields are filled in 'key'.
*/
-int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr,
- struct sw_flow_key *key,
- bool log)
+int ovs_nla_get_flow_metadata(struct net *net,
+ const struct nlattr *a[OVS_KEY_ATTR_MAX + 1],
+ u64 attrs, struct sw_flow_key *key, bool log)
{
- const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
struct sw_flow_match match;
- u64 attrs = 0;
- int err;
-
- err = parse_flow_nlattrs(attr, a, &attrs, log);
- if (err)
- return -EINVAL;
memset(&match, 0, sizeof(match));
match.key = key;
memset(&key->ct, 0, sizeof(key->ct));
+ memset(&key->ipv4.ct_orig, 0, sizeof(key->ipv4.ct_orig));
+ memset(&key->ipv6.ct_orig, 0, sizeof(key->ipv6.ct_orig));
+
key->phy.in_port = DP_MAX_PORTS;
return metadata_from_nlattrs(net, &match, &attrs, a, false, log);
@@ -1584,7 +1629,7 @@
if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark))
goto nla_put_failure;
- if (ovs_ct_put_key(output, skb))
+ if (ovs_ct_put_key(swkey, output, skb))
goto nla_put_failure;
if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) {