1 files changed, 56 insertions, 85 deletions

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0ca2bb8ed026..9cc0bc7c71ed 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -170,11 +170,11 @@ 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 +182,6 @@ 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 +235,28 @@ 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 +266,7 @@ 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:
@@ -365,7 +369,7 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
 
 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 +388,8 @@ 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 +413,34 @@ 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 +456,7 @@ 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
@@ -621,13 +635,30 @@ 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;
+	}
+
 	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;
 
 	flow_offload_refresh(nf_ft, flow);
 	nf_conntrack_get(&ct->ct_general);
@@ -695,31 +726,6 @@ 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 +785,7 @@ 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. */
@@ -794,50 +801,14 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		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)
@@ -980,7 +951,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	if (err)
 		goto drop;
 
-	err = tcf_ct_skb_network_trim(skb, family);
+	err = nf_ct_skb_network_trim(skb, family);
 	if (err)
 		goto drop;