[PATCH net 10/10] netfilter: nft_ct: move custom expectation support to helper

Originally, the ct expectation support called nf_ct_helper_ext_add() for
confirmed conntracks, which is invalid, triggering a splat. This was
fixed by commit 1710eb913bdc ("netfilter: nft_ct: skip expectations for
confirmed conntrack") which restricted it to confirmed conntracks.

However, early insertion of expectations into the expectations list when
the conntrack is unconfirmed leads to stale entries pointing to the
wrong hlist_head through .pprev due to ct extension reallocation.

Commit 7c9664351980 ("netfilter: move nat hlist_head to nf_conn") moved
the nat hlist_head to nf_conn for this reason:

     1. ...
     2. When reallocation of extension area occurs we need to fixup the
        bysource hash head via hlist_replace_rcu.

But I'd rather not increase the size of the struct nf_conn for this
feature, it only supports for creating expectations in the other
direction and it was broken with DNAT too.

The existing feature has very limited scope because of a pre-existing
issue: two different connections can create the same expectation leading
to expect_clash(), resulting in packet drops.

To address this issue, add an internal ct helper and attach it to the
conntrack entry to streamline the custom ct expectation support with
existing ct helpers.

Expose a new nf_conntrack_helper_free() function to safely release the
internal helper that is allocated and attached to the conntrack entry to
create the custom expectations.

Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support")
Reported-by: Jaeyeong Lee <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Pablo Neira Ayuso <[email protected]>
---
 include/net/netfilter/nf_conntrack_helper.h |   2 +
 net/netfilter/nf_conntrack_helper.c         |  18 ++-
 net/netfilter/nft_ct.c                      | 127 +++++++++++++++-----
 3 files changed, 114 insertions(+), 33 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index c761cd8158b2..4420846e41f2 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -114,6 +114,8 @@ int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int,
 void nf_conntrack_helpers_unregister(struct nf_conntrack_helper **,
 				     unsigned int);
 
+void nf_conntrack_helper_free(struct nf_conntrack_helper *me);
+
 #define nf_conntrack_helper_deprecated(name) \
 	pr_warn("The %s conntrack helper is scheduled for removal.\n"	\
 		"Please contact the netfilter-devel mailing list if you still need this.\n", name)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 500509b17663..1197e8793494 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -456,13 +456,8 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
 	return this == me;
 }
 
-void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
+void nf_conntrack_helper_free(struct nf_conntrack_helper *me)
 {
-	mutex_lock(&nf_ct_helper_mutex);
-	hlist_del_rcu(&me->hnode);
-	nf_ct_helper_count--;
-	mutex_unlock(&nf_ct_helper_mutex);
-
 	/* This helper is going away, disable it. */
 	rcu_assign_pointer(me->help, NULL);
 
@@ -476,6 +471,17 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	if (refcount_dec_and_test(&me->ct_refcnt))
 		kfree_rcu(me, rcu);
 }
+EXPORT_SYMBOL_GPL(nf_conntrack_helper_free);
+
+void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
+{
+	mutex_lock(&nf_ct_helper_mutex);
+	hlist_del_rcu(&me->hnode);
+	nf_ct_helper_count--;
+	mutex_unlock(&nf_ct_helper_mutex);
+
+	nf_conntrack_helper_free(me);
+}
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
 void nf_ct_helper_init(struct nf_conntrack_helper *helper,
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 03a88c77e0f0..30c9358dbf48 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1213,6 +1213,8 @@ struct nft_ct_expect_obj {
 	u8		l4proto;
 	u8		size;
 	u32		timeout;
+
+	struct nf_conntrack_helper *helper;
 };
 
 static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
@@ -1226,6 +1228,73 @@ static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
 	return 0;
 }
 
+struct nft_ct_expect_data {
+	struct nft_ct_expect_obj	obj;
+	enum ip_conntrack_dir		dir;
+	atomic_t			num_expects;
+};
+
+static int ct_expect_help(struct sk_buff *skb, unsigned int protoff,
+			  struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	struct nft_ct_expect_data *expect_data;
+	struct nf_conntrack_expect *exp;
+	int ret = NF_ACCEPT;
+
+	expect_data = nfct_help_data(ct);
+	if (!expect_data)
+		return NF_ACCEPT;
+
+	if (expect_data->dir != dir)
+		return NF_ACCEPT;
+
+	if (!atomic_add_unless(&expect_data->num_expects, 1, expect_data->obj.size))
+		return NF_ACCEPT;
+
+	exp = nf_ct_expect_alloc(ct);
+	if (!exp) {
+		atomic_dec(&expect_data->num_expects);
+		return NF_DROP;
+	}
+
+	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
+			  &ct->tuplehash[!dir].tuple.src.u3,
+			  &ct->tuplehash[!dir].tuple.dst.u3,
+			  expect_data->obj.l4proto, NULL, &expect_data->obj.dport);
+	exp->timeout += expect_data->obj.timeout;
+
+	if (nf_ct_expect_related(exp, 0) != 0) {
+		atomic_dec(&expect_data->num_expects);
+		ret = NF_DROP;
+	}
+
+	nf_ct_expect_put(exp);
+
+	return ret;
+}
+
+static int nft_ct_expect_helper_alloc(struct nft_ct_expect_obj *priv)
+{
+	struct nf_conntrack_helper *ct_expect_helper;
+
+	ct_expect_helper = kzalloc_obj(struct nf_conntrack_helper);
+	if (!ct_expect_helper)
+		return -ENOMEM;
+
+	snprintf(ct_expect_helper->name, sizeof(ct_expect_helper->name), "%s",
+		 "nft_ct_expect");
+	ct_expect_helper->me = THIS_MODULE;
+	ct_expect_helper->expect_policy[NF_CT_EXPECT_CLASS_DEFAULT].max_expected = priv->size;
+	rcu_assign_pointer(ct_expect_helper->help, ct_expect_help);
+	refcount_set(&ct_expect_helper->ct_refcnt, 1);
+
+	/* No need to register this helper, this is internal. */
+	priv->helper = ct_expect_helper;
+
+	return 0;
+}
+
 static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[],
 				  struct nft_object *obj)
@@ -1233,6 +1302,8 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	struct nft_ct_expect_obj *priv = nft_obj_data(obj);
 	int err;
 
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nft_ct_expect_data));
+
 	if (!tb[NFTA_CT_EXPECT_L4PROTO] ||
 	    !tb[NFTA_CT_EXPECT_DPORT] ||
 	    !tb[NFTA_CT_EXPECT_TIMEOUT] ||
@@ -1273,13 +1344,26 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
 
-	return nf_ct_netns_get(ctx->net, ctx->family);
+	err = nf_ct_netns_get(ctx->net, ctx->family);
+	if (err < 0)
+		return err;
+
+	err = nft_ct_expect_helper_alloc(priv);
+	if (err < 0) {
+		nf_ct_netns_put(ctx->net, ctx->family);
+		return err;
+	}
+
+	return err;
 }
 
 static void nft_ct_expect_obj_destroy(const struct nft_ctx *ctx,
-				       struct nft_object *obj)
+				      struct nft_object *obj)
 {
+	const struct nft_ct_expect_obj *priv = nft_obj_data(obj);
+
 	nf_ct_netns_put(ctx->net, ctx->family);
+	nf_conntrack_helper_free(priv->helper);
 }
 
 static int nft_ct_expect_obj_dump(struct sk_buff *skb,
@@ -1302,50 +1386,39 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 				   const struct nft_pktinfo *pkt)
 {
 	const struct nft_ct_expect_obj *priv = nft_obj_data(obj);
-	struct nf_conntrack_expect *exp;
+	struct nft_ct_expect_data *expect_data;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn_help *help;
-	enum ip_conntrack_dir dir;
-	u16 l3num = priv->l3num;
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(pkt->skb, &ctinfo);
-	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) {
+	if (!ct || nf_ct_is_template(ct) || nf_ct_is_confirmed(ct)) {
 		regs->verdict.code = NFT_BREAK;
 		return;
 	}
-	dir = CTINFO2DIR(ctinfo);
 
 	help = nfct_help(ct);
-	if (!help)
-		help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
-	if (!help) {
-		regs->verdict.code = NF_DROP;
-		return;
-	}
-
-	if (help->expecting[NF_CT_EXPECT_CLASS_DEFAULT] >= priv->size) {
+	if (help) {
 		regs->verdict.code = NFT_BREAK;
 		return;
 	}
-	if (l3num == NFPROTO_INET)
-		l3num = nf_ct_l3num(ct);
 
-	exp = nf_ct_expect_alloc(ct);
-	if (exp == NULL) {
+	help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+	if (!help) {
 		regs->verdict.code = NF_DROP;
 		return;
 	}
-	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, l3num,
-		          &ct->tuplehash[!dir].tuple.src.u3,
-		          &ct->tuplehash[!dir].tuple.dst.u3,
-		          priv->l4proto, NULL, &priv->dport);
-	exp->timeout += priv->timeout;
 
-	if (nf_ct_expect_related(exp, 0) != 0)
-		regs->verdict.code = NF_DROP;
+	expect_data = nfct_help_data(ct);
+	if (!expect_data) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+	expect_data->obj = *priv;
+	expect_data->dir = CTINFO2DIR(ctinfo);
 
-	nf_ct_expect_put(exp);
+	if (help && refcount_inc_not_zero(&priv->helper->ct_refcnt))
+		rcu_assign_pointer(help->helper, priv->helper);
 }
 
 static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = {
-- 
2.47.3