netfilter: flowtable: allow unidirectional rules

Modify flow table offload to support unidirectional connections by
extending enum nf_flow_flags with new "NF_FLOW_HW_BIDIRECTIONAL" flag. Only
offload reply direction when the flag is set. This infrastructure change is
necessary to support offloading UDP NEW connections in original direction
in following patches in series.
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netfilter/nf_flow_table.h

@@ -164,6 +164,7 @@ enum nf_flow_flags {
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
 	NF_FLOW_HW_PENDING,
+	NF_FLOW_HW_BIDIRECTIONAL,
 };
 
 enum flow_offload_type {

net/netfilter/nf_flow_table_offload.c

@@ -895,8 +895,9 @@ static int flow_offload_rule_add(struct flow_offload_work *offload,
 
 	ok_count += flow_offload_tuple_add(offload, flow_rule[0],
 					   FLOW_OFFLOAD_DIR_ORIGINAL);
-	ok_count += flow_offload_tuple_add(offload, flow_rule[1],
-					   FLOW_OFFLOAD_DIR_REPLY);
+	if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags))
+		ok_count += flow_offload_tuple_add(offload, flow_rule[1],
+						   FLOW_OFFLOAD_DIR_REPLY);
 	if (ok_count == 0)
 		return -ENOENT;
 
@@ -926,7 +927,8 @@ static void flow_offload_work_del(struct flow_offload_work *offload)
 {
 	clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
 	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL);
-	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY);
+	if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags))
+		flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY);
 	set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags);
 }
 
@@ -946,7 +948,9 @@ static void flow_offload_work_stats(struct flow_offload_work *offload)
 	u64 lastused;
 
 	flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]);
-	flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]);
+	if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags))
+		flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY,
+					 &stats[1]);
 
 	lastused = max_t(u64, stats[0].lastused, stats[1].lastused);
 	offload->flow->timeout = max_t(u64, offload->flow->timeout,