[PATCH net 11/14] netfilter: nf_conntrack_expect: store netns and zone in expectation

[Florian Westphal <fw@strlen.de>]

From: Pablo Neira Ayuso <pablo@netfilter.org>

__nf_ct_expect_find() and nf_ct_expect_find_get() are called under
rcu_read_lock() but they dereference the master conntrack via
exp->master.

Since the expectation does not hold a reference on the master conntrack,
this could be dying conntrack or different recycled conntrack than the
real master due to SLAB_TYPESAFE_RCU.

Store the netns, the master_tuple and the zone in struct
nf_conntrack_expect as a safety measure.

This patch is required by the follow up fix not to dump expectations
that do not belong to this netns.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_conntrack_expect.h | 18 +++++++++++++++++-
 net/netfilter/nf_conntrack_expect.c         |  8 ++++++--
 net/netfilter/nf_conntrack_netlink.c        |  3 +++
 3 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 1b01400b10bd..e9a8350e7ccf 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -22,10 +22,16 @@ struct nf_conntrack_expect {
 	/* Hash member */
 	struct hlist_node hnode;
 
+	/* Network namespace */
+	possible_net_t net;
+
 	/* We expect this tuple, with the following mask */
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_mask mask;
 
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	struct nf_conntrack_zone zone;
+#endif
 	/* Usage count. */
 	refcount_t use;
 
@@ -62,7 +68,17 @@ struct nf_conntrack_expect {
 
 static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp)
 {
-	return nf_ct_net(exp->master);
+	return read_pnet(&exp->net);
+}
+
+static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a,
+					    const struct nf_conntrack_zone *b)
+{
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	return a->zone.id == b->id;
+#else
+	return true;
+#endif
 }
 
 #define NF_CT_EXP_POLICY_NAME_LEN	16
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 2505d1f4b68c..8896fb20b58e 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -113,8 +113,8 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
 		const struct net *net)
 {
 	return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-	       net_eq(net, nf_ct_net(i->master)) &&
-	       nf_ct_zone_equal_any(i->master, zone);
+	       net_eq(net, read_pnet(&i->net)) &&
+	       nf_ct_exp_zone_equal_any(i, zone);
 }
 
 bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
@@ -324,6 +324,8 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 		       const union nf_inet_addr *daddr,
 		       u_int8_t proto, const __be16 *src, const __be16 *dst)
 {
+	struct net *net = read_pnet(&exp->master->ct_net);
+
 	int len;
 
 	if (family == AF_INET)
@@ -335,6 +337,8 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 	exp->class = class;
 	exp->expectfn = NULL;
 	rcu_assign_pointer(exp->helper, nfct_help(exp->master)->helper);
+	write_pnet(&exp->net, net);
+	exp->zone = exp->master->zone;
 	exp->tuple.src.l3num = family;
 	exp->tuple.dst.protonum = proto;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 89540112d165..2ec33c0518e9 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3538,6 +3538,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
+	struct net *net = read_pnet(&ct->ct_net);
 	struct nf_conntrack_expect *exp;
 	struct nf_conn_help *help;
 	u32 class = 0;
@@ -3577,6 +3578,8 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 
 	exp->class = class;
 	exp->master = ct;
+	write_pnet(&exp->net, net);
+	exp->zone = ct->zone;
 	if (!helper)
 		helper = rcu_dereference(help->helper);
 	rcu_assign_pointer(exp->helper, helper);
-- 
2.52.0