4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal fw@strlen.de
[ Upstream commit b0feacaad13a0aa9657c37ed80991575981e2e3b ]
nf_ct_iterate_cleanup_net currently calls iter() callback also for conntracks on the unconfirmed list, but this is unsafe.
Acesses to nf_conn are fine, but some users access the extension area in the iter() callback, but that does only work reliably for confirmed conntracks (ct->ext can be reallocated at any time for unconfirmed conntrack).
The seond issue is that there is a short window where a conntrack entry is neither on the list nor in the table: To confirm an entry, it is first removed from the unconfirmed list, then insert into the table.
Fix this by iterating the unconfirmed list first and marking all entries as dying, then wait for rcu grace period.
This makes sure all entries that were about to be confirmed either are in the main table, or will be dropped soon.
Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nf_conntrack_core.c | 39 ++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-)
--- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1542,7 +1542,6 @@ get_next_corpse(struct net *net, int (*i struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; - int cpu; spinlock_t *lockp;
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { @@ -1564,24 +1563,40 @@ get_next_corpse(struct net *net, int (*i cond_resched(); }
+ return NULL; +found: + atomic_inc(&ct->ct_general.use); + spin_unlock(lockp); + local_bh_enable(); + return ct; +} + +static void +__nf_ct_unconfirmed_destroy(struct net *net) +{ + int cpu; + for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct ct_pcpu *pcpu; + + pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
spin_lock_bh(&pcpu->lock); hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) { + struct nf_conn *ct; + ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - set_bit(IPS_DYING_BIT, &ct->status); + + /* we cannot call iter() on unconfirmed list, the + * owning cpu can reallocate ct->ext at any time. + */ + set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&pcpu->lock); cond_resched(); } - return NULL; -found: - atomic_inc(&ct->ct_general.use); - spin_unlock(lockp); - local_bh_enable(); - return ct; }
void nf_ct_iterate_cleanup(struct net *net, @@ -1596,6 +1611,10 @@ void nf_ct_iterate_cleanup(struct net *n if (atomic_read(&net->ct.count) == 0) return;
+ __nf_ct_unconfirmed_destroy(net); + + synchronize_net(); + while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */