Add a new function ovs_ct_find_existing() to find an existing
conntrack entry for which this packet was already applied to. This is
only to be called when there is evidence that the packet was already
tracked and committed, but we lost the ct reference due to an
userspace upcall.
ovs_ct_find_existing() is called from skb_nfct_cached(), which can now
hide the fact that the ct reference may have been lost due to an
upcall. This allows ovs_ct_commit() to be simplified.
This patch is needed by later "openvswitch: Interface with NAT" patch,
as we need to be able to pass the packet through NAT using the
original ct reference also after the reference is lost after an
upcall.
Signed-off-by: Jarno Rajahalme <jrajahalme@xxxxxxxxxx>
---
net/openvswitch/conntrack.c | 95 ++++++++++++++++++++++++++++++++++++++-------
1 file changed, 82 insertions(+), 13 deletions(-)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 10f4a6e..0c371d0 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -359,16 +359,87 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
return __nf_ct_expect_find(net, zone, &tuple);
}
+/* Find an existing conntrack entry for which this packet was already applied
+ * to. This is only called when there is evidence that the packet was already
+ * tracked and commited, but we lost the ct reference due to an userspace
+ * upcall. This means that on entry skb->nfct is NULL.
+ * On success, returns conntrack ptr, sets skb->nfct and ctinfo.
+ * Must be called rcu_read_lock()ed. */
+static struct nf_conn *
+ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
+ u_int8_t l3num, struct sk_buff *skb,
+ enum ip_conntrack_info *ctinfo)
+{
+ struct nf_conntrack_l3proto *l3proto;
+ struct nf_conntrack_l4proto *l4proto;
+ struct nf_conntrack_tuple tuple;
+ struct nf_conntrack_tuple_hash *h;
+ struct nf_conn *ct;
+ unsigned int dataoff;
+ u_int8_t protonum;
+
+ BUG_ON(skb->nfct != NULL);
+
+ l3proto = __nf_ct_l3proto_find(l3num);
+ if (!l3proto) {
+ pr_debug("ovs_ct_find_existing: Can't get l3proto\n");
+ return NULL;
+ }
+ if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
+ &protonum) <= 0) {
+ pr_debug("ovs_ct_find_existing: Can't get protonum\n");
+ return NULL;
+ }
+ l4proto = __nf_ct_l4proto_find(l3num, protonum);
+ if (!l4proto) {
+ pr_debug("ovs_ct_find_existing: Can't get l4proto\n");
+ return NULL;
+ }
+ if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
+ protonum, net, &tuple, l3proto, l4proto)) {
+ pr_debug("ovs_ct_find_existing: Can't get tuple\n");
+ return NULL;
+ }
+
+ /* look for tuple match */
+ h = nf_conntrack_find_get(net, zone, &tuple);
+ if (!h)
+ return NULL; /* Not found. */
+
+ ct = nf_ct_tuplehash_to_ctrack(h);
+
+ *ctinfo = nf_ct_get_info(h);
+ if (*ctinfo == IP_CT_NEW) {
+ /* This should not happen. */
+ WARN_ONCE(1, "ovs_ct_find_existing: new packet for %p\n", ct);
+ }
+ skb->nfct = &ct->ct_general;
+ skb->nfctinfo = *ctinfo;
+ return ct;
+}
+
/* Determine whether skb->nfct is equal to the result of conntrack lookup. */
-static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb,
- const struct ovs_conntrack_info *info)
+static bool skb_nfct_cached(struct net *net,
+ const struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info,
+ struct sk_buff *skb)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
+ /* If no ct, check if we have evidence that an existing conntrack entry
+ * might be found for this skb. This happens when we lose a skb->nfct
+ * due to an upcall. If the connection was not confirmed, it is not
+ * cached and needs to be run through conntrack again. */
+ if (!ct && key->ct.state & OVS_CS_F_TRACKED
+ && !(key->ct.state & OVS_CS_F_INVALID)
+ && key->ct.zone == info->zone.id)
+ ct = ovs_ct_find_existing(net, &info->zone, info->family, skb,
+ &ctinfo);
if (!ct)
return false;
+
if (!net_eq(net, read_pnet(&ct->ct_net)))
return false;
if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct)))
@@ -397,7 +468,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
* actually run the packet through conntrack twice unless it's for a
* different zone.
*/
- if (!skb_nfct_cached(net, skb, info)) {
+ if (!skb_nfct_cached(net, key, info, skb)) {
struct nf_conn *tmpl = info->ct;
/* Associate skb with specified zone. */
@@ -431,6 +502,13 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
{
struct nf_conntrack_expect *exp;
+ /* If we pass an expected packet through nf_conntrack_in() the
+ * expectiation will be removed, but the packet could still be lost in
+ * upcall processing. To prevent this from happening we perform an
+ * explicit expectation lookup. Expected connections are always new,
+ * and will be passed through conntrack only when they are committed,
+ * as it is OK to remove the expectation at that time.
+ */
exp = ovs_ct_expect_find(net, &info->zone, info->family, skb);
if (exp) {
u8 state;
@@ -453,21 +531,12 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
- u8 state;
int err;
- state = key->ct.state;
- if (key->ct.zone == info->zone.id &&
- ((state & OVS_CS_F_TRACKED) && !(state & OVS_CS_F_NEW))) {
- /* Previous lookup has shown that this connection is already
- * tracked and committed. Skip committing.
- */
- return 0;
- }
-
err = __ovs_ct_lookup(net, key, info, skb);
if (err)
return err;
+ /* This is a no-op if the connection has already been confirmed. */
if (nf_conntrack_confirm(skb) != NF_ACCEPT)
return -EINVAL;
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
