net: sched: add helper support in act_ct

This patch is to add helper support in act_ct for OVS actions=ct(alg=xxx)
offloading, which is corresponding to Commit cae3a2627520 ("openvswitch:
Allow attaching helpers to ct action") in OVS kernel part.

The difference is when adding TC actions family and proto cannot be got
from the filter/match, other than helper name in tb[TCA_CT_HELPER_NAME],
we also need to send the family in tb[TCA_CT_HELPER_FAMILY] and the
proto in tb[TCA_CT_HELPER_PROTO] to kernel.

Acked-by: Marcelo Ricardo Leitner <[e-mail]>
Signed-off-by: Xin Long <[e-mail]>
Signed-off-by: Paolo Abeni <[e-mail]>

include/net/tc_act/tc_ct.h

···
 #include <net/netfilter/nf_conntrack_labels.h>
 
 struct tcf_ct_params {
+	struct nf_conntrack_helper *helper;
 	struct nf_conn *tmpl;
 	u16 zone;
 

include/uapi/linux/tc_act/tc_ct.h

···
 	TCA_CT_NAT_PORT_MIN,	/* be16 */
 	TCA_CT_NAT_PORT_MAX,	/* be16 */
 	TCA_CT_PAD,
+	TCA_CT_HELPER_NAME,	/* string */
+	TCA_CT_HELPER_FAMILY,	/* u8 */
+	TCA_CT_HELPER_PROTO,	/* u8 */
 	__TCA_CT_MAX
 };
 

net/sched/act_ct.c

···
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/netfilter/nf_conntrack_act_ct.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <uapi/linux/netfilter/nf_nat.h>
 
 static struct workqueue_struct *act_ct_wq;
···
 
 /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
 static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
-				   u16 zone_id, bool force)
+				   struct tcf_ct_params *p)
 {
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
···
 		return false;
 	if (!net_eq(net, read_pnet(&ct->ct_net)))
 		goto drop_ct;
-	if (nf_ct_zone(ct)->id != zone_id)
+	if (nf_ct_zone(ct)->id != p->zone)
 		goto drop_ct;
+	if (p->helper) {
+		struct nf_conn_help *help;
+
+		help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
+		if (help && rcu_access_pointer(help->helper) != p->helper)
+			goto drop_ct;
+	}
 
 	/* Force conntrack entry direction. */
-	if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
+	if ((p->ct_action & TCA_CT_ACT_FORCE) &&
+	    CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 		if (nf_ct_is_confirmed(ct))
 			nf_ct_kill(ct);
 
···
 
 static void tcf_ct_params_free(struct tcf_ct_params *params)
 {
+	if (params->helper) {
+#if IS_ENABLED(CONFIG_NF_NAT)
+		if (params->ct_action & TCA_CT_ACT_NAT)
+			nf_nat_helper_put(params->helper);
+#endif
+		nf_conntrack_helper_put(params->helper);
+	}
 	if (params->ct_ft)
 		tcf_ct_flow_table_put(params->ct_ft);
 	if (params->tmpl)
···
 		      struct tcf_result *res)
 {
 	struct net *net = dev_net(skb->dev);
-	bool cached, commit, clear, force;
 	enum ip_conntrack_info ctinfo;
 	struct tcf_ct *c = to_ct(a);
 	struct nf_conn *tmpl = NULL;
 	struct nf_hook_state state;
+	bool cached, commit, clear;
 	int nh_ofs, err, retval;
 	struct tcf_ct_params *p;
+	bool add_helper = false;
 	bool skip_add = false;
 	bool defrag = false;
 	struct nf_conn *ct;
···
 	retval = READ_ONCE(c->tcf_action);
 	commit = p->ct_action & TCA_CT_ACT_COMMIT;
 	clear = p->ct_action & TCA_CT_ACT_CLEAR;
-	force = p->ct_action & TCA_CT_ACT_FORCE;
 	tmpl = p->tmpl;
 
 	tcf_lastuse_update(&c->tcf_tm);
···
 	 * actually run the packet through conntrack twice unless it's for a
 	 * different zone.
 	 */
-	cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
+	cached = tcf_ct_skb_nfct_cached(net, skb, p);
 	if (!cached) {
 		if (tcf_ct_flow_table_lookup(p, skb, family)) {
 			skip_add = true;
···
 	err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
 	if (err != NF_ACCEPT)
 		goto drop;
+
+	if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) {
+		err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC);
+		if (err)
+			goto drop;
+		add_helper = true;
+		if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) {
+			if (!nfct_seqadj_ext_add(ct))
+				goto drop;
+		}
+	}
+
+	if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) {
+		if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT)
+			goto drop;
+	}
 
 	if (commit) {
 		tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
···
 	[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
 	[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
+	[TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN },
+	[TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 },
+	[TCA_CT_HELPER_PROTO] = { .type = NLA_U8 },
 };
 
 static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
···
 {
 	struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
 	struct nf_conntrack_zone zone;
+	int err, family, proto, len;
 	struct nf_conn *tmpl;
-	int err;
+	char *name;
 
 	p->zone = NF_CT_DEFAULT_ZONE_ID;
 
···
 		NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
 		return -ENOMEM;
 	}
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	p->tmpl = tmpl;
+	if (tb[TCA_CT_HELPER_NAME]) {
+		name = nla_data(tb[TCA_CT_HELPER_NAME]);
+		len = nla_len(tb[TCA_CT_HELPER_NAME]);
+		if (len > 16 || name[len - 1] != '\0') {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name.");
+			err = -EINVAL;
+			goto err;
+		}
+		family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET;
+		proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP;
+		err = nf_ct_add_helper(tmpl, name, family, proto,
+				       p->ct_action & TCA_CT_ACT_NAT, &p->helper);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to add helper");
+			goto err;
+		}
+	}
 
+	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	return 0;
+err:
+	nf_ct_put(p->tmpl);
+	p->tmpl = NULL;
+	return err;
 }
 
 static int tcf_ct_init(struct net *net, struct nlattr *nla,
···
 	return 0;
 }
 
+static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper)
+{
+	if (!helper)
+		return 0;
+
+	if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) ||
+	    nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) ||
+	    nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum))
+		return -1;
+
+	return 0;
+}
+
 static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
 			      int bind, int ref)
 {
···
 		goto nla_put_failure;
 
 	if (tcf_ct_dump_nat(skb, p))
+		goto nla_put_failure;
+
+	if (tcf_ct_dump_helper(skb, p->helper))
 		goto nla_put_failure;
 
 skip_dump: