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 1710eb913b ("netfilter: nft_ct: skip expectations for
confirmed conntrack") which restricted it to unconfirmed 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 7c96643519 ("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.

I'd rather not increase the size of the struct nf_conn for this feature
has very limited scope: only one expectation can be created at a time
given expect_clash() will make nf_ct_expect_related() reports EBUSY.
For this reason, relax nf_ct_expect_related() not to drop packets in
case expectation creation fails, therefore, expectation creation becomes
best effort.

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_release() function to release the
internal helper that is allocated and attached to the conntrack entry to
create the custom expectations. The nft_ct module removal always waits
for rcu grace period, then the NULL helper callback is observed after
this.

This patch also restricts the creation of expectations to different
helpers other than this custom helper that is created for this type of
expectations.

Fixes: 857b46027d ("netfilter: nft_ct: add ct expectations support")
Reported-by: Jaeyeong Lee <iostreampy@proton.me>
Link: https://patch.msgid.link/20260715144755.00ea7dfcd9f@proton.me
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/netfilter/nf_conntrack_helper.h

@@ -106,6 +106,7 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 int nf_conntrack_helper_register(struct nf_conntrack_helper *, struct nf_conntrack_helper **);
 int __nf_conntrack_helper_register(struct nf_conntrack_helper *);
 void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
+void nf_conntrack_helper_release(struct nf_conntrack_helper *);
 
 int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int,
 				  struct nf_conntrack_helper **);

net/netfilter/nf_conntrack_helper.c

@@ -448,6 +448,15 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
 	return this == me;
 }
 
+void nf_conntrack_helper_release(struct nf_conntrack_helper *me)
+{
+	nf_ct_expect_iterate_destroy(expect_iter_me, me);
+
+	if (refcount_dec_and_test(&me->ct_refcnt))
+		kfree_rcu(me, rcu);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_helper_release);
+
 void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 {
 	mutex_lock(&nf_ct_helper_mutex);
@@ -463,10 +472,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	 */
 	synchronize_rcu();
 
-	nf_ct_expect_iterate_destroy(expect_iter_me, me);
-
-	if (refcount_dec_and_test(&me->ct_refcnt))
-		kfree_rcu(me, rcu);
+	nf_conntrack_helper_release(me);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 

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 +1228,93 @@ static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_NF_NAT)
+static void nft_ct_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this)
+{
+	const struct nf_ct_helper_expectfn *expfn;
+
+	expfn = nf_ct_helper_expectfn_find_by_name("nat-follow-master");
+	if (expfn)
+		expfn->expectfn(ct, this);
+}
+#endif
+
+struct nft_ct_expect_data {
+	struct nft_ct_expect_obj	obj;
+	enum ip_conntrack_dir		dir;
+};
+
+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;
+	u16 l3num;
+
+	if (nf_ct_is_confirmed(ct))
+		return NF_ACCEPT;
+
+	expect_data = nfct_help_data(ct);
+	if (!expect_data)
+		return NF_ACCEPT;
+
+	if (expect_data->dir != dir)
+		return NF_ACCEPT;
+
+	exp = nf_ct_expect_alloc(ct);
+	if (!exp)
+		return NF_DROP;
+
+	if (expect_data->obj.l3num == NFPROTO_INET)
+		l3num = nf_ct_l3num(ct);
+	else
+		l3num = expect_data->obj.l3num;
+
+	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, l3num,
+			  &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 IS_ENABLED(CONFIG_NF_NAT)
+	if (ct->status & IPS_NAT_MASK) {
+		exp->saved_proto.tcp.port = expect_data->obj.dport;
+		exp->dir = !dir;
+		exp->expectfn = nft_ct_nat_follow_master;
+	}
+#endif
+	if (nf_ct_expect_related(exp, 0) != 0)
+		ret = NF_ACCEPT;
+
+	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,
+				       GFP_KERNEL_ACCOUNT);
+	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 +1322,8 @@ 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] ||
@@ -1272,13 +1363,31 @@ 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]);
+	if (!priv->size)
+		priv->size = NF_CT_EXPECT_MAX_CNT;
 
-	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);
+	struct nf_conntrack_helper *me = priv->helper;
+
+	/* This helper is going away, disable it. */
+	rcu_assign_pointer(me->help, NULL);
+	nf_conntrack_helper_release(me);
 	nf_ct_netns_put(ctx->net, ctx->family);
 }
 
@@ -1297,27 +1406,14 @@ static int nft_ct_expect_obj_dump(struct sk_buff *skb,
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_NF_NAT)
-static void nft_ct_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this)
-{
-	const struct nf_ct_helper_expectfn *expfn;
-
-	expfn = nf_ct_helper_expectfn_find_by_name("nat-follow-master");
-	if (expfn)
-		expfn->expectfn(ct, this);
-}
-#endif
-
 static void nft_ct_expect_obj_eval(struct nft_object *obj,
 				   struct nft_regs *regs,
 				   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);
@@ -1325,45 +1421,30 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 		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 = NFT_BREAK;
+		return;
+	}
+
+	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) {
+	expect_data = nfct_help_data(ct);
+	if (!expect_data) {
 		regs->verdict.code = NFT_BREAK;
 		return;
 	}
-	if (l3num == NFPROTO_INET)
-		l3num = nf_ct_l3num(ct);
+	expect_data->obj = *priv;
+	expect_data->obj.helper = NULL;
+	expect_data->dir = CTINFO2DIR(ctinfo);
 
-	exp = nf_ct_expect_alloc(ct);
-	if (exp == NULL) {
-		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 IS_ENABLED(CONFIG_NF_NAT)
-	if (ct->status & IPS_NAT_MASK) {
-		exp->saved_proto.tcp.port = priv->dport;
-		exp->dir = !dir;
-		exp->expectfn = nft_ct_nat_follow_master;
-	}
-#endif
-	if (nf_ct_expect_related(exp, 0) != 0)
-		regs->verdict.code = NF_DROP;
-
-	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] = {