aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorFlorian Westphal2020-05-10 14:28:07 +0200
committerPablo Neira Ayuso2020-05-11 17:46:24 +0200
commit54ab49fde95605a1077f759ce454d94e84b5ca45 (patch)
treefe0fa28f4b54125fdc767bd13ee8ae15efbbdb0e /net
parent1d10da0eb09484ae087836da28258316ef4a02be (diff)
netfilter: conntrack: fix infinite loop on rmmod
'rmmod nf_conntrack' can hang forever, because the netns exit gets stuck in nf_conntrack_cleanup_net_list(): i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&net->ct.count) != 0) busy = 1; } if (busy) { schedule(); goto i_see_dead_people; } When nf_ct_iterate_cleanup iterates the conntrack table, all nf_conn structures can be found twice: once for the original tuple and once for the conntracks reply tuple. get_next_corpse() only calls the iterator when the entry is in original direction -- the idea was to avoid unneeded invocations of the iterator callback. When support for clashing entries was added, the assumption that all nf_conn objects are added twice, once in original, once for reply tuple no longer holds -- NF_CLASH_BIT entries are only added in the non-clashing reply direction. Thus, if at least one NF_CLASH entry is in the list then nf_conntrack_cleanup_net_list() always skips it completely. During normal netns destruction, this causes a hang of several seconds, until the gc worker removes the entry (NF_CLASH entries always have a 1 second timeout). But in the rmmod case, the gc worker has already been stopped, so ct.count never becomes 0. We can fix this in two ways: 1. Add a second test for CLASH_BIT and call iterator for those entries as well, or: 2. Skip the original tuple direction and use the reply tuple. 2) is simpler, so do that. Fixes: 6a757c07e51f80ac ("netfilter: conntrack: allow insertion of clashing entries") Reported-by: Chen Yi <yiche@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net')
-rw-r--r--net/netfilter/nf_conntrack_core.c13
1 files changed, 12 insertions, 1 deletions
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0173398f4ced..1d57b95d3481 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2139,8 +2139,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
nf_conntrack_lock(lockp);
if (*bucket < nf_conntrack_htable_size) {
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+ if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
continue;
+ /* All nf_conn objects are added to hash table twice, one
+ * for original direction tuple, once for the reply tuple.
+ *
+ * Exception: In the IPS_NAT_CLASH case, only the reply
+ * tuple is added (the original tuple already existed for
+ * a different object).
+ *
+ * We only need to call the iterator once for each
+ * conntrack, so we just use the 'reply' direction
+ * tuple while iterating.
+ */
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
goto found;