netfilter: ctnetlink: fix refcnt leak in dying/unconfirmed list dumper

'last' keeps track of the ct that had its refcnt bumped during previous
dump cycle.  Thus it must not be overwritten until end-of-function.

Another (unrelated, theoretical) issue: Don't attempt to bump refcnt of a conntrack
whose reference count is already 0.  Such conntrack is being destroyed
right now, its memory is freed once we release the percpu dying spinlock.

Fixes: b7779d06 ('netfilter: conntrack: spinlock per cpu to protect special lists.')
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index ef0eedd..70123f4 100644 (file)
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1150,7 +1150,7 @@ static int ctnetlink_done_list(struct netlink_callback *cb)
 static int
 ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
 {
-       struct nf_conn *ct, *last = NULL;
+       struct nf_conn *ct, *last;
        struct nf_conntrack_tuple_hash *h;
        struct hlist_nulls_node *n;
        struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
@@ -1163,6 +1163,8 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
        if (cb->args[2])
                return 0;
 
+       last = (struct nf_conn *)cb->args[1];
+
        for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
                struct ct_pcpu *pcpu;
 
@@ -1171,7 +1173,6 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 
                pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
                spin_lock_bh(&pcpu->lock);
-               last = (struct nf_conn *)cb->args[1];
                list = dying ? &pcpu->dying : &pcpu->unconfirmed;
 restart:
                hlist_nulls_for_each_entry(h, n, list, hnnode) {
@@ -1190,7 +1191,8 @@ restart:
                                                  ct);
                        rcu_read_unlock();
                        if (res < 0) {
-                               nf_conntrack_get(&ct->ct_general);
+                               if (!atomic_inc_not_zero(&ct->ct_general.use))
+                                       continue;
                                cb->args[0] = cpu;
                                cb->args[1] = (unsigned long)ct;
                                spin_unlock_bh(&pcpu->lock);