From: Chris Mi <cmi@nvidia.com>
Date: Tue, 26 Oct 2021 17:08:24 +0800
Subject: net/mlx5e: Specify out ifindex when looking up decap route
Patch-mainline: v5.17-rc1
Git-commit: 819c319c8c919307fa764ff02a228c06e727501c
References: jsc#PED-1549

There is a use case that the local and remote VTEPs are in the same
host. Currently, the out ifindex is not specified when looking up the
decap route for offloads. So in this case, a local route is returned
and the route dev is lo.

Actual tunnel interface can be created with a parameter "dev" [1],
which specifies the physical device to use for tunnel endpoint
communication. Pass this parameter to driver when looking up decap
route for offloads. So that a unicast route will be returned.

[1] ip link add name vxlan1 type vxlan id 100 dev enp4s0f0 remote 1.1.1.1 dstport 4789

Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c       |   23 +++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h       |    3 +
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c |    4 +-
 3 files changed, 16 insertions(+), 14 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -103,7 +103,7 @@ static int get_route_and_out_devs(struct
 }
 
 static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv,
-				       struct net_device *mirred_dev,
+				       struct net_device *dev,
 				       struct mlx5e_tc_tun_route_attr *attr)
 {
 	struct net_device *route_dev;
@@ -122,13 +122,13 @@ static int mlx5e_route_lookup_ipv4_get(s
 		uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 		attr->fl.fl4.flowi4_oif = uplink_dev->ifindex;
 	} else {
-		struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev);
+		struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(dev);
 
 		if (tunnel && tunnel->get_remote_ifindex)
-			attr->fl.fl4.flowi4_oif = tunnel->get_remote_ifindex(mirred_dev);
+			attr->fl.fl4.flowi4_oif = tunnel->get_remote_ifindex(dev);
 	}
 
-	rt = ip_route_output_key(dev_net(mirred_dev), &attr->fl.fl4);
+	rt = ip_route_output_key(dev_net(dev), &attr->fl.fl4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -440,10 +440,10 @@ release_neigh:
 
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv,
-				       struct net_device *mirred_dev,
+				       struct net_device *dev,
 				       struct mlx5e_tc_tun_route_attr *attr)
 {
-	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev);
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(dev);
 	struct net_device *route_dev;
 	struct net_device *out_dev;
 	struct dst_entry *dst;
@@ -451,8 +451,8 @@ static int mlx5e_route_lookup_ipv6_get(s
 	int ret;
 
 	if (tunnel && tunnel->get_remote_ifindex)
-		attr->fl.fl6.flowi6_oif = tunnel->get_remote_ifindex(mirred_dev);
-	dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, &attr->fl.fl6,
+		attr->fl.fl6.flowi6_oif = tunnel->get_remote_ifindex(dev);
+	dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(dev), NULL, &attr->fl.fl6,
 					      NULL);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
@@ -708,7 +708,8 @@ release_neigh:
 
 int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
-			      struct mlx5_flow_attr *flow_attr)
+			      struct mlx5_flow_attr *flow_attr,
+			      struct net_device *filter_dev)
 {
 	struct mlx5_esw_flow_attr *esw_attr = flow_attr->esw_attr;
 	struct mlx5e_tc_int_port *int_port;
@@ -720,14 +721,14 @@ int mlx5e_tc_tun_route_lookup(struct mlx
 		/* Addresses are swapped for decap */
 		attr.fl.fl4.saddr = esw_attr->rx_tun_attr->dst_ip.v4;
 		attr.fl.fl4.daddr = esw_attr->rx_tun_attr->src_ip.v4;
-		err = mlx5e_route_lookup_ipv4_get(priv, priv->netdev, &attr);
+		err = mlx5e_route_lookup_ipv4_get(priv, filter_dev, &attr);
 	}
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 	else if (flow_attr->tun_ip_version == 6) {
 		/* Addresses are swapped for decap */
 		attr.fl.fl6.saddr = esw_attr->rx_tun_attr->dst_ip.v6;
 		attr.fl.fl6.daddr = esw_attr->rx_tun_attr->src_ip.v6;
-		err = mlx5e_route_lookup_ipv6_get(priv, priv->netdev, &attr);
+		err = mlx5e_route_lookup_ipv6_get(priv, filter_dev, &attr);
 	}
 #endif
 	else
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -94,7 +94,8 @@ mlx5e_tc_tun_update_header_ipv6(struct m
 #endif
 int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
-			      struct mlx5_flow_attr *attr);
+			      struct mlx5_flow_attr *attr,
+			      struct net_device *filter_dev);
 
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev);
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -1159,7 +1159,7 @@ int mlx5e_attach_decap_route(struct mlx5
 
 	tbl_time_before = mlx5e_route_tbl_get_last_update(priv);
 	tbl_time_after = tbl_time_before;
-	err = mlx5e_tc_tun_route_lookup(priv, &parse_attr->spec, attr);
+	err = mlx5e_tc_tun_route_lookup(priv, &parse_attr->spec, attr, parse_attr->filter_dev);
 	if (err || !esw_attr->rx_tun_attr->decap_vport)
 		goto out;
 
@@ -1480,7 +1480,7 @@ static void mlx5e_reoffload_decap(struct
 
 		parse_attr = attr->parse_attr;
 		spec = &parse_attr->spec;
-		err = mlx5e_tc_tun_route_lookup(priv, spec, attr);
+		err = mlx5e_tc_tun_route_lookup(priv, spec, attr, parse_attr->filter_dev);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "Failed to lookup route for flow, %d\n",
 				       err);