net/mlx5: E-Switch, Add ovs internal port mapping to metadata support

Adding infrastructure to map ovs internal port device to vport
match metadata to support offload of rules with internal port as
the filter device or as the destination device.

The infrastructure allows adding and removing internal port device
to an eswitch database and getting a unique vport metadata value to
be placed and match on in reg_c0 when offloading rules that are coming
from or going to an internal port.

The new int port metadata can be written to the source port register
in HW to indicate that current source port of the packet is the
internal port and not one of the actual HW vports (uplink or VF).
Using this method, it is possible to offload TC rules with an OVS
internal port as their destination port (overwriting the src vport
register) or as the filter port (matching on the value of the src
vport register and making sure it matches to the internal port's
value).

There is also a need to handle a miss case where the packet's
src port value was changed in HW to an internal port but a following
rule which matches on this new src port value wasn't found in HW.

In such case, the packet will be forwarded to the driver with
metadata which allows driver to restore the info of the internal
port's netdevice. Once this info is restored, the uplink driver
can forward the packet to the relevant netdevice in SW.

Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

1 files changed, 40 insertions, 3 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index de683724e184..c69129940268 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -20,6 +20,7 @@
 #include "lib/port_tun.h"
 #include "en/tc/sample.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en/tc/int_port.h"
 
 struct mlx5e_rep_indr_block_priv {
 	struct net_device *netdev;
@@ -672,12 +673,43 @@ static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *sk
 	mlx5_rep_tc_post_napi_receive(tc_priv);
 }
 
+static bool mlx5e_restore_skb_int_port(struct mlx5e_priv *priv, struct sk_buff *skb,
+				       struct mlx5_mapped_obj *mapped_obj,
+				       struct mlx5e_tc_update_priv *tc_priv,
+				       bool *forward_tx,
+				       u32 reg_c1)
+{
+	u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+
+	/* Tunnel restore takes precedence over int port restore */
+	if (tunnel_id)
+		return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
+
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &uplink_rpriv->uplink_priv;
+
+	if (mlx5e_tc_int_port_dev_fwd(uplink_priv->int_port_priv, skb,
+				      mapped_obj->int_port_metadata, forward_tx)) {
+		/* Set fwd_dev for future dev_put */
+		tc_priv->fwd_dev = skb->dev;
+
+		return true;
+	}
+
+	return false;
+}
+
 void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 			  struct sk_buff *skb)
 {
+	u32 reg_c1 = be32_to_cpu(cqe->ft_metadata);
 	struct mlx5e_tc_update_priv tc_priv = {};
 	struct mlx5_mapped_obj mapped_obj;
 	struct mlx5_eswitch *esw;
+	bool forward_tx = false;
 	struct mlx5e_priv *priv;
 	u32 reg_c0;
 	int err;
@@ -702,21 +734,26 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 	}
 
 	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
-		u32 reg_c1 = be32_to_cpu(cqe->ft_metadata);
-
 		if (!mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, &tc_priv) &&
 		    !mlx5_ipsec_is_rx_flow(cqe))
 			goto free_skb;
 	} else if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) {
 		mlx5e_restore_skb_sample(priv, skb, &mapped_obj, &tc_priv);
 		goto free_skb;
+	} else if (mapped_obj.type == MLX5_MAPPED_OBJ_INT_PORT_METADATA) {
+		if (!mlx5e_restore_skb_int_port(priv, skb, &mapped_obj, &tc_priv,
+						&forward_tx, reg_c1))
+			goto free_skb;
 	} else {
 		netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type);
 		goto free_skb;
 	}
 
 forward:
-	napi_gro_receive(rq->cq.napi, skb);
+	if (forward_tx)
+		dev_queue_xmit(skb);
+	else
+		napi_gro_receive(rq->cq.napi, skb);
 
 	mlx5_rep_tc_post_napi_receive(&tc_priv);