netdev - [PATCH 16/36] netfilter: conntrack: fix lookup race during hash resize

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1462819614-5402-17-git-send-email-pablo@netfilter.org>
Date:	Mon,  9 May 2016 20:46:34 +0200
From:	Pablo Neira Ayuso <pablo@...filter.org>
To:	netfilter-devel@...r.kernel.org
Cc:	davem@...emloft.net, netdev@...r.kernel.org
Subject: [PATCH 16/36] netfilter: conntrack: fix lookup race during hash resize

From: Florian Westphal <fw@...len.de>

When resizing the conntrack hash table at runtime via
echo 42 > /sys/module/nf_conntrack/parameters/hashsize, we are racing with
the conntrack lookup path -- reads can happen in parallel and nothing
prevents readers from observing a the newly allocated hash but the old
size (or vice versa).

So access to hash[bucket] can trigger OOB read access in case the table got
expanded and we saw the new size but the old hash pointer (or it got shrunk
and we got new hash ptr but the size of the old and larger table):

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN
CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 4.6.0-rc2+ #107
[..]
Call Trace:
[<ffffffff822c3d6a>] ? nf_conntrack_tuple_taken+0x12a/0xe90
[<ffffffff822c3ac1>] ? nf_ct_invert_tuplepr+0x221/0x3a0
[<ffffffff8230e703>] get_unique_tuple+0xfb3/0x2760

Use generation counter to obtain the address/length of the same table.

Also add a synchronize_net before freeing the old hash.
AFAICS, without it we might access ct_hash[bucket] after ct_hash has been
freed, provided that lockless reader got delayed by another event:

CPU1			CPU2
seq_begin
seq_retry
<delay>			resize occurs
			free oldhash
for_each(oldhash[size])

Note that resize is only supported in init_netns, it took over 2 minutes
of constant resizing+flooding to produce the warning, so this isn't a
big problem in practice.

Signed-off-by: Florian Westphal <fw@...len.de>
Signed-off-by: Pablo Neira Ayuso <pablo@...filter.org>
---
 net/netfilter/nf_conntrack_core.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 1b63359..29fa08b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -469,11 +469,18 @@ ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple, u32 hash)
 {
 	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_head *ct_hash;
 	struct hlist_nulls_node *n;
-	unsigned int bucket = hash_bucket(hash, net);
+	unsigned int bucket, sequence;
 
 begin:
-	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
+	do {
+		sequence = read_seqcount_begin(&nf_conntrack_generation);
+		bucket = hash_bucket(hash, net);
+		ct_hash = net->ct.hash;
+	} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
+
+	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
 		if (nf_ct_key_equal(h, tuple, zone)) {
 			NF_CT_STAT_INC_ATOMIC(net, found);
 			return h;
@@ -722,15 +729,21 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 	struct net *net = nf_ct_net(ignored_conntrack);
 	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_head *ct_hash;
+	unsigned int hash, sequence;
 	struct hlist_nulls_node *n;
 	struct nf_conn *ct;
-	unsigned int hash;
 
 	zone = nf_ct_zone(ignored_conntrack);
-	hash = hash_conntrack(net, tuple);
 
 	rcu_read_lock();
-	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
+	do {
+		sequence = read_seqcount_begin(&nf_conntrack_generation);
+		hash = hash_conntrack(net, tuple);
+		ct_hash = net->ct.hash;
+	} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
+
+	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (ct != ignored_conntrack &&
 		    nf_ct_tuple_equal(tuple, &h->tuple) &&
@@ -1607,6 +1620,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	nf_conntrack_all_unlock();
 	local_bh_enable();
 
+	synchronize_net();
 	nf_ct_free_hashtable(old_hash, old_size);
 	return 0;
 }
-- 
2.1.4