[PATCH] net/mlx5: fix tunnel header with IPIP offload

[Jiawei Wang]

For the flows with multiple tunnel layers and containing
tunnel decap and modify actions, for example:

... / vxlan / eth / ipv4 proto is 4 / end
actions raw_decap / modify_field / ...
(note: proto 4 means we have the IP-over-IP tunnel in VXLAN payload)

We have added the multiple tunnel layers validation rejecting
the flows like above mentioned one.

The hardware supports the above match combination till the inner
IP-over-IP header (not including the last one), both for IP-over-IPv4
and IP-over-IPv6, so we should not blindly reject. Also, for the modify
actions following the decap we should set the layer attributes correctly.

This patch reverts the below code changes to support the match, and
adjusts the layers update in case of decap with outer tunnel header.

Fixes: fa06906a48ee ("net/mlx5: fix IPIP multi-tunnel validation")
Cc: stable at dpdk.org

Signed-off-by: Jiawei Wang <jiaweiw at nvidia.com>
Acked-by: Slava Ovsiienko <viacheslavo at nvidia.com>
---
 drivers/net/mlx5/mlx5_flow.c    |  4 ++--
 drivers/net/mlx5/mlx5_flow_dv.c | 11 ++++++++---
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 06b465de7a..7ebe67028d 100644
--- a/drivers/net/mlx5/mlx5_flow.c
+++ b/drivers/net/mlx5/mlx5_flow.c
@@ -2512,7 +2512,7 @@ mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item,
 					  RTE_FLOW_ERROR_TYPE_ITEM, item,
 					  "IPv4 cannot follow L2/VLAN layer "
 					  "which ether type is not IPv4");
-	if (item_flags & MLX5_FLOW_LAYER_TUNNEL) {
+	if (item_flags & MLX5_FLOW_LAYER_IPIP) {
 		if (mask && spec)
 			next_proto = mask->hdr.next_proto_id &
 				     spec->hdr.next_proto_id;
@@ -2620,7 +2620,7 @@ mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item,
 					  "which ether type is not IPv6");
 	if (mask && mask->hdr.proto == UINT8_MAX && spec)
 		next_proto = spec->hdr.proto;
-	if (item_flags & MLX5_FLOW_LAYER_TUNNEL) {
+	if (item_flags & MLX5_FLOW_LAYER_IPIP) {
 		if (next_proto == IPPROTO_IPIP || next_proto == IPPROTO_IPV6)
 			return rte_flow_error_set(error, EINVAL,
 						  RTE_FLOW_ERROR_TYPE_ITEM,
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
index 4bdcb1815b..bf093ab981 100644
--- a/drivers/net/mlx5/mlx5_flow_dv.c
+++ b/drivers/net/mlx5/mlx5_flow_dv.c
@@ -109,6 +109,7 @@ flow_dv_attr_init(const struct rte_flow_item *item, union flow_dv_attr *attr,
 		  struct mlx5_flow *dev_flow, bool tunnel_decap)
 {
 	uint64_t layers = dev_flow->handle->layers;
+	bool tunnel_match = false;
 
 	/*
 	 * If layers is already initialized, it means this dev_flow is the
@@ -145,8 +146,10 @@ flow_dv_attr_init(const struct rte_flow_item *item, union flow_dv_attr *attr,
 		case RTE_FLOW_ITEM_TYPE_GENEVE:
 		case RTE_FLOW_ITEM_TYPE_MPLS:
 		case RTE_FLOW_ITEM_TYPE_GTP:
-			if (tunnel_decap)
+			if (tunnel_decap) {
 				attr->attr = 0;
+				tunnel_match = true;
+			}
 			break;
 		case RTE_FLOW_ITEM_TYPE_IPV4:
 			if (!attr->ipv6)
@@ -160,7 +163,8 @@ flow_dv_attr_init(const struct rte_flow_item *item, union flow_dv_attr *attr,
 				    ((const struct rte_flow_item_ipv4 *)
 				      (item->mask))->hdr.next_proto_id;
 			if ((next_protocol == IPPROTO_IPIP ||
-			    next_protocol == IPPROTO_IPV6) && tunnel_decap)
+			    next_protocol == IPPROTO_IPV6) && tunnel_decap &&
+			    !tunnel_match)
 				attr->attr = 0;
 			break;
 		case RTE_FLOW_ITEM_TYPE_IPV6:
@@ -175,7 +179,8 @@ flow_dv_attr_init(const struct rte_flow_item *item, union flow_dv_attr *attr,
 				    ((const struct rte_flow_item_ipv6 *)
 				      (item->mask))->hdr.proto;
 			if ((next_protocol == IPPROTO_IPIP ||
-			    next_protocol == IPPROTO_IPV6) && tunnel_decap)
+			    next_protocol == IPPROTO_IPV6) && tunnel_decap &&
+			    !tunnel_match)
 				attr->attr = 0;
 			break;
 		case RTE_FLOW_ITEM_TYPE_UDP:
-- 
2.18.1