netfilter: ctnetlink: dump entries from the dying and unconfirmed lists

This patch adds a new operation to dump the content of the dying and
unconfirmed lists.

Under some situations, the global conntrack counter can be inconsistent
with the number of entries that we can dump from the conntrack table.
The way to resolve this is to allow dumping the content of the unconfirmed
and dying lists, so far it was not possible to look at its content.

This provides some extra instrumentation to resolve problematic situations
in which anyone suspects memory leaks.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/uapi/linux/netfilter/nfnetlink_conntrack.h

@@ -9,6 +9,8 @@ enum cntl_msg_types {
 	IPCTNL_MSG_CT_GET_CTRZERO,
 	IPCTNL_MSG_CT_GET_STATS_CPU,
 	IPCTNL_MSG_CT_GET_STATS,
+	IPCTNL_MSG_CT_GET_DYING,
+	IPCTNL_MSG_CT_GET_UNCONFIRMED,
 
 	IPCTNL_MSG_MAX
 };

net/netfilter/nf_conntrack_netlink.c

@@ -1089,6 +1089,112 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	return err == -EAGAIN ? -ENOBUFS : err;
 }
 
+static int ctnetlink_done_list(struct netlink_callback *cb)
+{
+	if (cb->args[1])
+		nf_ct_put((struct nf_conn *)cb->args[1]);
+	return 0;
+}
+
+static int
+ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb,
+		    struct hlist_nulls_head *list)
+{
+	struct nf_conn *ct, *last;
+	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_node *n;
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	u_int8_t l3proto = nfmsg->nfgen_family;
+	int res;
+
+	if (cb->args[2])
+		return 0;
+
+	spin_lock_bh(&nf_conntrack_lock);
+	last = (struct nf_conn *)cb->args[1];
+restart:
+	hlist_nulls_for_each_entry(h, n, list, hnnode) {
+		ct = nf_ct_tuplehash_to_ctrack(h);
+		if (l3proto && nf_ct_l3num(ct) != l3proto)
+			continue;
+		if (cb->args[1]) {
+			if (ct != last)
+				continue;
+			cb->args[1] = 0;
+		}
+		rcu_read_lock();
+		res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
+					  cb->nlh->nlmsg_seq,
+					  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+					  ct);
+		rcu_read_unlock();
+		if (res < 0) {
+			nf_conntrack_get(&ct->ct_general);
+			cb->args[1] = (unsigned long)ct;
+			goto out;
+		}
+	}
+	if (cb->args[1]) {
+		cb->args[1] = 0;
+		goto restart;
+	} else
+		cb->args[2] = 1;
+out:
+	spin_unlock_bh(&nf_conntrack_lock);
+	if (last)
+		nf_ct_put(last);
+
+	return skb->len;
+}
+
+static int
+ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+
+	return ctnetlink_dump_list(skb, cb, &net->ct.dying);
+}
+
+static int
+ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb,
+		       const struct nlmsghdr *nlh,
+		       const struct nlattr * const cda[])
+{
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = ctnetlink_dump_dying,
+			.done = ctnetlink_done_list,
+		};
+		return netlink_dump_start(ctnl, skb, nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int
+ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+
+	return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed);
+}
+
+static int
+ctnetlink_get_ct_unconfirmed(struct sock *ctnl, struct sk_buff *skb,
+			     const struct nlmsghdr *nlh,
+			     const struct nlattr * const cda[])
+{
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = ctnetlink_dump_unconfirmed,
+			.done = ctnetlink_done_list,
+		};
+		return netlink_dump_start(ctnl, skb, nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
 #ifdef CONFIG_NF_NAT_NEEDED
 static int
 ctnetlink_parse_nat_setup(struct nf_conn *ct,
@@ -2712,6 +2818,8 @@ static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = {
 					    .policy = ct_nla_policy },
 	[IPCTNL_MSG_CT_GET_STATS_CPU]	= { .call = ctnetlink_stat_ct_cpu },
 	[IPCTNL_MSG_CT_GET_STATS]	= { .call = ctnetlink_stat_ct },
+	[IPCTNL_MSG_CT_GET_DYING]	= { .call = ctnetlink_get_ct_dying },
+	[IPCTNL_MSG_CT_GET_UNCONFIRMED]	= { .call = ctnetlink_get_ct_unconfirmed },
 };
 
 static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = {