1 files changed, 214 insertions, 159 deletions

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0ca2bb8ed026..2b6ac7069dc1 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -41,21 +41,26 @@ static struct workqueue_struct *act_ct_wq;
 static struct rhashtable zones_ht;
 static DEFINE_MUTEX(zones_mutex);
 
+struct zones_ht_key {
+	struct net *net;
+	u16 zone;
+};
+
 struct tcf_ct_flow_table {
 	struct rhash_head node; /* In zones tables */
 
 	struct rcu_work rwork;
 	struct nf_flowtable nf_ft;
 	refcount_t ref;
-	u16 zone;
+	struct zones_ht_key key;
 
 	bool dying;
 };
 
 static const struct rhashtable_params zones_params = {
 	.head_offset = offsetof(struct tcf_ct_flow_table, node),
-	.key_offset = offsetof(struct tcf_ct_flow_table, zone),
-	.key_len = sizeof_field(struct tcf_ct_flow_table, zone),
+	.key_offset = offsetof(struct tcf_ct_flow_table, key),
+	.key_len = offsetofend(struct zones_ht_key, zone),
 	.automatic_shrinking = true,
 };
 
@@ -170,11 +175,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
 
 static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
 					      enum ip_conntrack_dir dir,
+					      enum ip_conntrack_info ctinfo,
 					      struct flow_action *action)
 {
 	struct nf_conn_labels *ct_labels;
 	struct flow_action_entry *entry;
-	enum ip_conntrack_info ctinfo;
 	u32 *act_ct_labels;
 
 	entry = tcf_ct_flow_table_flow_action_get_next(action);
@@ -182,8 +187,6 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
 #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
 	entry->ct_metadata.mark = READ_ONCE(ct->mark);
 #endif
-	ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
-					     IP_CT_ESTABLISHED_REPLY;
 	/* aligns with the CT reference on the SKB nf_ct_set */
 	entry->ct_metadata.cookie = (unsigned long)ct | ctinfo;
 	entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL;
@@ -237,22 +240,28 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net,
 }
 
 static int tcf_ct_flow_table_fill_actions(struct net *net,
-					  const struct flow_offload *flow,
+					  struct flow_offload *flow,
 					  enum flow_offload_tuple_dir tdir,
 					  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action *action = &flow_rule->rule->action;
 	int num_entries = action->num_entries;
 	struct nf_conn *ct = flow->ct;
+	enum ip_conntrack_info ctinfo;
 	enum ip_conntrack_dir dir;
 	int i, err;
 
 	switch (tdir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
 		dir = IP_CT_DIR_ORIGINAL;
+		ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ?
+			IP_CT_ESTABLISHED : IP_CT_NEW;
+		if (ctinfo == IP_CT_ESTABLISHED)
+			set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
 		break;
 	case FLOW_OFFLOAD_DIR_REPLY:
 		dir = IP_CT_DIR_REPLY;
+		ctinfo = IP_CT_ESTABLISHED_REPLY;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -262,7 +271,7 @@ static int tcf_ct_flow_table_fill_actions(struct net *net,
 	if (err)
 		goto err_nat;
 
-	tcf_ct_flow_table_add_action_meta(ct, dir, action);
+	tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action);
 	return 0;
 
 err_nat:
@@ -274,18 +283,50 @@ err_nat:
 	return err;
 }
 
+static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
+{
+	return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) &&
+	       test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) &&
+	       !test_bit(NF_FLOW_HW_PENDING, &flow->flags) &&
+	       !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
+}
+
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_put(ct_ft);
+}
+
 static struct nf_flowtable_type flowtable_ct = {
+	.gc		= tcf_ct_flow_is_outdated,
 	.action		= tcf_ct_flow_table_fill_actions,
+	.get		= tcf_ct_nf_get,
+	.put		= tcf_ct_nf_put,
 	.owner		= THIS_MODULE,
 };
 
 static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
 {
+	struct zones_ht_key key = { .net = net, .zone = params->zone };
 	struct tcf_ct_flow_table *ct_ft;
 	int err = -ENOMEM;
 
 	mutex_lock(&zones_mutex);
-	ct_ft = rhashtable_lookup_fast(&zones_ht, &params->zone, zones_params);
+	ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params);
 	if (ct_ft && refcount_inc_not_zero(&ct_ft->ref))
 		goto out_unlock;
 
@@ -294,7 +335,7 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
 		goto err_alloc;
 	refcount_set(&ct_ft->ref, 1);
 
-	ct_ft->zone = params->zone;
+	ct_ft->key = key;
 	err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params);
 	if (err)
 		goto err_insert;
@@ -324,9 +365,13 @@ err_alloc:
 	return err;
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+	refcount_inc(&ct_ft->ref);
+}
+
 static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 {
-	struct flow_block_cb *block_cb, *tmp_cb;
 	struct tcf_ct_flow_table *ct_ft;
 	struct flow_block *block;
 
@@ -334,13 +379,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 			     rwork);
 	nf_flow_table_free(&ct_ft->nf_ft);
 
-	/* Remove any remaining callbacks before cleanup */
 	block = &ct_ft->nf_ft.flow_block;
 	down_write(&ct_ft->nf_ft.flow_block_lock);
-	list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
-		list_del(&block_cb->list);
-		flow_block_cb_free(block_cb);
-	}
+	WARN_ON(!list_empty(&block->cb_list));
 	up_write(&ct_ft->nf_ft.flow_block_lock);
 	kfree(ct_ft);
 
@@ -363,9 +404,20 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
 	entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
 }
 
+static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry)
+{
+	struct nf_conn_act_ct_ext *act_ct_ext;
+
+	act_ct_ext = nf_conn_act_ct_ext_find(entry->ct);
+	if (act_ct_ext) {
+		tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
+		tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
+	}
+}
+
 static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
 				  struct nf_conn *ct,
-				  bool tcp)
+				  bool tcp, bool bidirectional)
 {
 	struct nf_conn_act_ct_ext *act_ct_ext;
 	struct flow_offload *entry;
@@ -384,6 +436,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
 		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 	}
+	if (bidirectional)
+		__set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags);
 
 	act_ct_ext = nf_conn_act_ct_ext_find(ct);
 	if (act_ct_ext) {
@@ -407,26 +461,34 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
 					   struct nf_conn *ct,
 					   enum ip_conntrack_info ctinfo)
 {
-	bool tcp = false;
-
-	if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) ||
-	    !test_bit(IPS_ASSURED_BIT, &ct->status))
-		return;
+	bool tcp = false, bidirectional = true;
 
 	switch (nf_ct_protonum(ct)) {
 	case IPPROTO_TCP:
-		tcp = true;
-		if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
+		if ((ctinfo != IP_CT_ESTABLISHED &&
+		     ctinfo != IP_CT_ESTABLISHED_REPLY) ||
+		    !test_bit(IPS_ASSURED_BIT, &ct->status) ||
+		    ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
 			return;
+
+		tcp = true;
 		break;
 	case IPPROTO_UDP:
+		if (!nf_ct_is_confirmed(ct))
+			return;
+		if (!test_bit(IPS_ASSURED_BIT, &ct->status))
+			bidirectional = false;
 		break;
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	case IPPROTO_GRE: {
 		struct nf_conntrack_tuple *tuple;
 
-		if (ct->status & IPS_NAT_MASK)
+		if ((ctinfo != IP_CT_ESTABLISHED &&
+		     ctinfo != IP_CT_ESTABLISHED_REPLY) ||
+		    !test_bit(IPS_ASSURED_BIT, &ct->status) ||
+		    ct->status & IPS_NAT_MASK)
 			return;
+
 		tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
 		/* No support for GRE v1 */
 		if (tuple->src.u.gre.key || tuple->dst.u.gre.key)
@@ -442,7 +504,7 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
 	    ct->status & IPS_SEQ_ADJUST)
 		return;
 
-	tcf_ct_flow_table_add(ct_ft, ct, tcp);
+	tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional);
 }
 
 static bool
@@ -596,6 +658,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	struct flow_offload_tuple tuple = {};
 	enum ip_conntrack_info ctinfo;
 	struct tcphdr *tcph = NULL;
+	bool force_refresh = false;
 	struct flow_offload *flow;
 	struct nf_conn *ct;
 	u8 dir;
@@ -621,15 +684,40 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 	ct = flow->ct;
 
+	if (dir == FLOW_OFFLOAD_DIR_REPLY &&
+	    !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) {
+		/* Only offload reply direction after connection became
+		 * assured.
+		 */
+		if (test_bit(IPS_ASSURED_BIT, &ct->status))
+			set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
+		else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags))
+			/* If flow_table flow has already been updated to the
+			 * established state, then don't refresh.
+			 */
+			return false;
+		force_refresh = true;
+	}
+
 	if (tcph && (unlikely(tcph->fin || tcph->rst))) {
 		flow_offload_teardown(flow);
 		return false;
 	}
 
-	ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
-						    IP_CT_ESTABLISHED_REPLY;
+	if (dir == FLOW_OFFLOAD_DIR_ORIGINAL)
+		ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ?
+			IP_CT_ESTABLISHED : IP_CT_NEW;
+	else
+		ctinfo = IP_CT_ESTABLISHED_REPLY;
+
+	nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
+	tcf_ct_flow_ct_ext_ifidx_update(flow);
+	flow_offload_refresh(nf_ft, flow, force_refresh);
+	if (!test_bit(IPS_ASSURED_BIT, &ct->status)) {
+		/* Process this flow in SW to allow promoting to ASSURED */
+		return false;
+	}
 
-	flow_offload_refresh(nf_ft, flow);
 	nf_conntrack_get(&ct->ct_general);
 	nf_ct_set(skb, ct, ctinfo);
 	if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
@@ -652,7 +740,6 @@ static struct tc_action_ops act_ct_ops;
 
 struct tc_ct_action_net {
 	struct tc_action_net tn; /* Must be first */
-	bool labels;
 };
 
 /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
@@ -695,31 +782,6 @@ drop_ct:
 	return false;
 }
 
-/* Trim the skb to the length specified by the IP/IPv6 header,
- * removing any trailing lower-layer padding. This prepares the skb
- * for higher-layer processing that assumes skb->len excludes padding
- * (such as nf_ip_checksum). The caller needs to pull the skb to the
- * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
- */
-static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
-{
-	unsigned int len;
-
-	switch (family) {
-	case NFPROTO_IPV4:
-		len = ntohs(ip_hdr(skb)->tot_len);
-		break;
-	case NFPROTO_IPV6:
-		len = sizeof(struct ipv6hdr)
-			+ ntohs(ipv6_hdr(skb)->payload_len);
-		break;
-	default:
-		len = skb->len;
-	}
-
-	return pskb_trim_rcsum(skb, len);
-}
-
 static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
 {
 	u8 family = NFPROTO_UNSPEC;
@@ -779,6 +841,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
+	u8 proto;
 	u16 mru;
 
 	/* Previously seen (loopback)? Ignore. */
@@ -793,51 +856,14 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	if (err || !frag)
 		return err;
 
-	skb_get(skb);
-	mru = tc_skb_cb(skb)->mru;
-
-	if (family == NFPROTO_IPV4) {
-		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-		local_bh_disable();
-		err = ip_defrag(net, skb, user);
-		local_bh_enable();
-		if (err && err != -EINPROGRESS)
-			return err;
-
-		if (!err) {
-			*defrag = true;
-			mru = IPCB(skb)->frag_max_size;
-		}
-	} else { /* NFPROTO_IPV6 */
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
-		err = nf_ct_frag6_gather(net, skb, user);
-		if (err && err != -EINPROGRESS)
-			goto out_free;
-
-		if (!err) {
-			*defrag = true;
-			mru = IP6CB(skb)->frag_max_size;
-		}
-#else
-		err = -EOPNOTSUPP;
-		goto out_free;
-#endif
-	}
+	err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru);
+	if (err)
+		return err;
 
-	if (err != -EINPROGRESS)
-		tc_skb_cb(skb)->mru = mru;
-	skb_clear_hash(skb);
-	skb->ignore_df = 1;
-	return err;
+	*defrag = true;
+	tc_skb_cb(skb)->mru = mru;
 
-out_free:
-	kfree_skb(skb);
-	return err;
+	return 0;
 }
 
 static void tcf_ct_params_free(struct tcf_ct_params *params)
@@ -851,8 +877,13 @@ static void tcf_ct_params_free(struct tcf_ct_params *params)
 	}
 	if (params->ct_ft)
 		tcf_ct_flow_table_put(params->ct_ft);
-	if (params->tmpl)
+	if (params->tmpl) {
+		if (params->put_labels)
+			nf_connlabels_put(nf_ct_net(params->tmpl));
+
 		nf_ct_put(params->tmpl);
+	}
+
 	kfree(params);
 }
 
@@ -913,11 +944,13 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
 		action |= BIT(NF_NAT_MANIP_DST);
 
 	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
+	if (err != NF_ACCEPT)
+		return err & NF_VERDICT_MASK;
 
 	if (action & BIT(NF_NAT_MANIP_SRC))
-		tc_skb_cb(skb)->post_ct_snat = 1;
+		qdisc_skb_cb(skb)->post_ct_snat = 1;
 	if (action & BIT(NF_NAT_MANIP_DST))
-		tc_skb_cb(skb)->post_ct_dnat = 1;
+		qdisc_skb_cb(skb)->post_ct_dnat = 1;
 
 	return err;
 #else
@@ -944,7 +977,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 
 	p = rcu_dereference_bh(c->params);
 
-	retval = READ_ONCE(c->tcf_action);
+	retval = p->action;
 	commit = p->ct_action & TCA_CT_ACT_COMMIT;
 	clear = p->ct_action & TCA_CT_ACT_CLEAR;
 	tmpl = p->tmpl;
@@ -953,7 +986,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_action_update_bstats(&c->common, skb);
 
 	if (clear) {
-		tc_skb_cb(skb)->post_ct = false;
+		qdisc_skb_cb(skb)->post_ct = false;
 		ct = nf_ct_get(skb, &ctinfo);
 		if (ct) {
 			nf_ct_put(ct);
@@ -973,14 +1006,10 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	nh_ofs = skb_network_offset(skb);
 	skb_pull_rcsum(skb, nh_ofs);
 	err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
-	if (err == -EINPROGRESS) {
-		retval = TC_ACT_STOLEN;
-		goto out_clear;
-	}
 	if (err)
-		goto drop;
+		goto out_frag;
 
-	err = tcf_ct_skb_network_trim(skb, family);
+	err = nf_ct_skb_network_trim(skb, family);
 	if (err)
 		goto drop;
 
@@ -1008,7 +1037,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 		state.pf = family;
 		err = nf_conntrack_in(skb, &state);
 		if (err != NF_ACCEPT)
-			goto out_push;
+			goto nf_error;
 	}
 
 do_nat:
@@ -1020,7 +1049,7 @@ do_nat:
 
 	err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
 	if (err != NF_ACCEPT)
-		goto drop;
+		goto nf_error;
 
 	if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) {
 		err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC);
@@ -1034,8 +1063,9 @@ do_nat:
 	}
 
 	if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) {
-		if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT)
-			goto drop;
+		err = nf_ct_helper(skb, ct, ctinfo, family);
+		if (err != NF_ACCEPT)
+			goto nf_error;
 	}
 
 	if (commit) {
@@ -1043,13 +1073,22 @@ do_nat:
 		tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
 
 		if (!nf_ct_is_confirmed(ct))
-			nf_conn_act_ct_ext_add(ct);
+			nf_conn_act_ct_ext_add(skb, ct, ctinfo);
 
 		/* This will take care of sending queued events
 		 * even if the connection is already confirmed.
 		 */
-		if (nf_conntrack_confirm(skb) != NF_ACCEPT)
-			goto drop;
+		err = nf_conntrack_confirm(skb);
+		if (err != NF_ACCEPT)
+			goto nf_error;
+
+		/* The ct may be dropped if a clash has been resolved,
+		 * so it's necessary to retrieve it from skb again to
+		 * prevent UAF.
+		 */
+		ct = nf_ct_get(skb, &ctinfo);
+		if (!ct)
+			skip_add = true;
 	}
 
 	if (!skip_add)
@@ -1058,16 +1097,36 @@ do_nat:
 out_push:
 	skb_push_rcsum(skb, nh_ofs);
 
-	tc_skb_cb(skb)->post_ct = true;
+	qdisc_skb_cb(skb)->post_ct = true;
 	tc_skb_cb(skb)->zone = p->zone;
 out_clear:
 	if (defrag)
 		qdisc_skb_cb(skb)->pkt_len = skb->len;
 	return retval;
 
+out_frag:
+	if (err != -EINPROGRESS)
+		tcf_action_inc_drop_qstats(&c->common);
+	return TC_ACT_CONSUMED;
+
 drop:
 	tcf_action_inc_drop_qstats(&c->common);
 	return TC_ACT_SHOT;
+
+nf_error:
+	/* some verdicts store extra data in upper bits, such
+	 * as errno or queue number.
+	 */
+	switch (err & NF_VERDICT_MASK) {
+	case NF_DROP:
+		goto drop;
+	case NF_STOLEN:
+		tcf_action_inc_drop_qstats(&c->common);
+		return TC_ACT_CONSUMED;
+	default:
+		DEBUG_NET_WARN_ON_ONCE(1);
+		goto drop;
+	}
 }
 
 static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
@@ -1124,9 +1183,8 @@ static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
 		range->min_addr.ip =
 			nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]);
 
-		range->max_addr.ip = max_attr ?
-				     nla_get_in_addr(max_attr) :
-				     range->min_addr.ip;
+		range->max_addr.ip =
+			nla_get_in_addr_default(max_attr, range->min_addr.ip);
 	} else if (tb[TCA_CT_NAT_IPV6_MIN]) {
 		struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX];
 
@@ -1176,9 +1234,9 @@ static int tcf_ct_fill_params(struct net *net,
 			      struct nlattr **tb,
 			      struct netlink_ext_ack *extack)
 {
-	struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
 	struct nf_conntrack_zone zone;
 	int err, family, proto, len;
+	bool put_labels = false;
 	struct nf_conn *tmpl;
 	char *name;
 
@@ -1208,15 +1266,20 @@ static int tcf_ct_fill_params(struct net *net,
 	}
 
 	if (tb[TCA_CT_LABELS]) {
+		unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8;
+
 		if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
 			NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled.");
 			return -EOPNOTSUPP;
 		}
 
-		if (!tn->labels) {
+		if (nf_connlabels_get(net, n_bits - 1)) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length");
 			return -EOPNOTSUPP;
+		} else {
+			put_labels = true;
 		}
+
 		tcf_ct_set_key_val(tb,
 				   p->labels, TCA_CT_LABELS,
 				   p->labels_mask, TCA_CT_LABELS_MASK,
@@ -1250,8 +1313,9 @@ static int tcf_ct_fill_params(struct net *net,
 			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;
+		family = nla_get_u8_default(tb[TCA_CT_HELPER_FAMILY], AF_INET);
+		proto = nla_get_u8_default(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) {
@@ -1260,9 +1324,15 @@ static int tcf_ct_fill_params(struct net *net,
 		}
 	}
 
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+	p->put_labels = put_labels;
+
+	if (p->ct_action & TCA_CT_ACT_COMMIT)
+		__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	return 0;
 err:
+	if (put_labels)
+		nf_connlabels_put(net);
+
 	nf_ct_put(p->tmpl);
 	p->tmpl = NULL;
 	return err;
@@ -1312,7 +1382,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		res = ACT_P_CREATED;
 	} else {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
@@ -1339,6 +1409,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 	if (err)
 		goto cleanup;
 
+	params->action = parm->action;
 	spin_lock_bh(&c->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	params = rcu_replace_pointer(c->params, params,
@@ -1372,8 +1443,8 @@ static void tcf_ct_cleanup(struct tc_action *a)
 }
 
 static int tcf_ct_dump_key_val(struct sk_buff *skb,
-			       void *val, int val_type,
-			       void *mask, int mask_type,
+			       const void *val, int val_type,
+			       const void *mask, int mask_type,
 			       int len)
 {
 	int err;
@@ -1394,9 +1465,9 @@ static int tcf_ct_dump_key_val(struct sk_buff *skb,
 	return 0;
 }
 
-static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
+static int tcf_ct_dump_nat(struct sk_buff *skb, const struct tcf_ct_params *p)
 {
-	struct nf_nat_range2 *range = &p->range;
+	const struct nf_nat_range2 *range = &p->range;
 
 	if (!(p->ct_action & TCA_CT_ACT_NAT))
 		return 0;
@@ -1434,7 +1505,8 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
 	return 0;
 }
 
-static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper)
+static int tcf_ct_dump_helper(struct sk_buff *skb,
+			      const struct nf_conntrack_helper *helper)
 {
 	if (!helper)
 		return 0;
@@ -1451,9 +1523,8 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
 			      int bind, int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
-	struct tcf_ct *c = to_ct(a);
-	struct tcf_ct_params *p;
-
+	const struct tcf_ct *c = to_ct(a);
+	const struct tcf_ct_params *p;
 	struct tc_ct opt = {
 		.index   = c->tcf_index,
 		.refcnt  = refcount_read(&c->tcf_refcnt) - ref,
@@ -1461,10 +1532,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
 	};
 	struct tcf_t t;
 
-	spin_lock_bh(&c->tcf_lock);
-	p = rcu_dereference_protected(c->params,
-				      lockdep_is_held(&c->tcf_lock));
-	opt.action = c->tcf_action;
+	rcu_read_lock();
+	p = rcu_dereference(c->params);
+	opt.action = p->action;
 
 	if (tcf_ct_dump_key_val(skb,
 				&p->ct_action, TCA_CT_ACTION,
@@ -1509,11 +1579,11 @@ skip_dump:
 	tcf_tm_dump(&t, &c->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD))
 		goto nla_put_failure;
-	spin_unlock_bh(&c->tcf_lock);
+	rcu_read_unlock();
 
 	return skb->len;
 nla_put_failure:
-	spin_unlock_bh(&c->tcf_lock);
+	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
@@ -1534,6 +1604,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
 	if (bind) {
 		struct flow_action_entry *entry = entry_data;
 
+		if (tcf_ct_helper(act))
+			return -EOPNOTSUPP;
+
 		entry->id = FLOW_ACTION_CT;
 		entry->ct.action = tcf_ct_action(act);
 		entry->ct.zone = tcf_ct_zone(act);
@@ -1560,35 +1633,17 @@ static struct tc_action_ops act_ct_ops = {
 	.offload_act_setup =	tcf_ct_offload_act_setup,
 	.size		=	sizeof(struct tcf_ct),
 };
+MODULE_ALIAS_NET_ACT("ct");
 
 static __net_init int ct_init_net(struct net *net)
 {
-	unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8;
 	struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
 
-	if (nf_connlabels_get(net, n_bits - 1)) {
-		tn->labels = false;
-		pr_err("act_ct: Failed to set connlabels length");
-	} else {
-		tn->labels = true;
-	}
-
 	return tc_action_net_init(net, &tn->tn, &act_ct_ops);
 }
 
 static void __net_exit ct_exit_net(struct list_head *net_list)
 {
-	struct net *net;
-
-	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list) {
-		struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
-
-		if (tn->labels)
-			nf_connlabels_put(net);
-	}
-	rtnl_unlock();
-
 	tc_action_net_exit(net_list, act_ct_ops.net_id);
 }