netfilter: ctnetlink: fix soft lockup when netlink adds new entries (v2)
Marcell Zambo and Janos Farago noticed and reported that when
new conntrack entries are added via netlink and the conntrack table
gets full, soft lockup happens. This is because the nf_conntrack_lock
is held while nf_conntrack_alloc is called, which is in turn wants
to lock nf_conntrack_lock while evicting entries from the full table.
The patch fixes the soft lockup with limiting the holding of the
nf_conntrack_lock to the minimum, where it's absolutely required.
It required to extend (and thus change) nf_conntrack_hash_insert
so that it makes sure conntrack and ctnetlink do not add the same entry
twice to the conntrack table.
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 76613f5..ed86a3b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -404,19 +404,49 @@
&net->ct.hash[repl_hash]);
}
-void nf_conntrack_hash_insert(struct nf_conn *ct)
+int
+nf_conntrack_hash_check_insert(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
unsigned int hash, repl_hash;
+ struct nf_conntrack_tuple_hash *h;
+ struct hlist_nulls_node *n;
u16 zone;
zone = nf_ct_zone(ct);
- hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ repl_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ spin_lock_bh(&nf_conntrack_lock);
+
+ /* See if there's one in the list already, including reverse */
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
+ if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ &h->tuple) &&
+ zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+ goto out;
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+ if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ &h->tuple) &&
+ zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+ goto out;
+
+ add_timer(&ct->timeout);
+ nf_conntrack_get(&ct->ct_general);
__nf_conntrack_hash_insert(ct, hash, repl_hash);
+ NF_CT_STAT_INC(net, insert);
+ spin_unlock_bh(&nf_conntrack_lock);
+
+ return 0;
+
+out:
+ NF_CT_STAT_INC(net, insert_failed);
+ spin_unlock_bh(&nf_conntrack_lock);
+ return -EEXIST;
}
-EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert);
+EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
/* Confirm a connection given skb; places it in hash table */
int