net/mlx4_en: Add netdev support for TCP/IP offloads of vxlan tunneling

When the device tunneling offloads mode is vxlan do the following

 - call SET_PORT with the relevant setting

 - add DMFS steering vxlan rule for the device self and multicast mac addresses
   of the form: {<ETH, outer-mac> <VXLAN, ANY vnid> <ETH, ANY mac>} --> RSS QP

 - set relevant QPC fields in RSS context and RX ring QPs

 - in TX flow, set WQE fields to generate HW checksum, and handle gso skbs
   which are marked for encapsulation such that the HW will segment them properly.

 - in RX flow, read HW offloaded checksum for encapsulated packets from the CQE

 - advertize hw_enc_features and NETIF_F_GSO_UDP_TUNNEL to the networking stack

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 94 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6f920900e841..b68dde09bf4b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -468,6 +468,53 @@ static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
 	memset(&dst_mac[ETH_ALEN], 0, 2);
 }
 
+
+static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *addr,
+				    int qpn, u64 *reg_id)
+{
+	int err;
+	struct mlx4_spec_list spec_eth_outer = { {NULL} };
+	struct mlx4_spec_list spec_vxlan     = { {NULL} };
+	struct mlx4_spec_list spec_eth_inner = { {NULL} };
+
+	struct mlx4_net_trans_rule rule = {
+		.queue_mode = MLX4_NET_TRANS_Q_FIFO,
+		.exclusive = 0,
+		.allow_loopback = 1,
+		.promisc_mode = MLX4_FS_REGULAR,
+		.priority = MLX4_DOMAIN_NIC,
+	};
+
+	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+		return 0; /* do nothing */
+
+	rule.port = priv->port;
+	rule.qpn = qpn;
+	INIT_LIST_HEAD(&rule.list);
+
+	spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH;
+	memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN);
+	memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+
+	spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN;    /* any vxlan header */
+	spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH;	 /* any inner eth header */
+
+	list_add_tail(&spec_eth_outer.list, &rule.list);
+	list_add_tail(&spec_vxlan.list,     &rule.list);
+	list_add_tail(&spec_eth_inner.list, &rule.list);
+
+	err = mlx4_flow_attach(priv->mdev->dev, &rule, reg_id);
+	if (err) {
+		en_err(priv, "failed to add vxlan steering rule, err %d\n", err);
+		return err;
+	}
+	en_dbg(DRV, priv, "added vxlan steering rule, mac %pM reg_id %llx\n", addr, *reg_id);
+	return 0;
+}
+
+
 static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
 				unsigned char *mac, int *qpn, u64 *reg_id)
 {
@@ -585,6 +632,10 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 	if (err)
 		goto steer_err;
 
+	if (mlx4_en_tunnel_steer_add(priv, priv->dev->dev_addr, *qpn,
+				     &priv->tunnel_reg_id))
+		goto tunnel_err;
+
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
 		err = -ENOMEM;
@@ -599,6 +650,9 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 	return 0;
 
 alloc_err:
+	if (priv->tunnel_reg_id)
+		mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+tunnel_err:
 	mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);
 
 steer_err:
@@ -642,6 +696,11 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
 			}
 		}
 
+		if (priv->tunnel_reg_id) {
+			mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+			priv->tunnel_reg_id = 0;
+		}
+
 		en_dbg(DRV, priv, "Releasing qp: port %d, qpn %d\n",
 		       priv->port, qpn);
 		mlx4_qp_release_range(dev, qpn, 1);
@@ -1044,6 +1103,12 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
 				if (err)
 					en_err(priv, "Fail to detach multicast address\n");
 
+				if (mclist->tunnel_reg_id) {
+					err = mlx4_flow_detach(priv->mdev->dev, mclist->tunnel_reg_id);
+					if (err)
+						en_err(priv, "Failed to detach multicast address\n");
+				}
+
 				/* remove from list */
 				list_del(&mclist->list);
 				kfree(mclist);
@@ -1061,6 +1126,10 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
 				if (err)
 					en_err(priv, "Fail to attach multicast address\n");
 
+				err = mlx4_en_tunnel_steer_add(priv, &mc_list[10], priv->base_qpn,
+							       &mclist->tunnel_reg_id);
+				if (err)
+					en_err(priv, "Failed to attach multicast address\n");
 			}
 		}
 	}
@@ -1598,6 +1667,15 @@ int mlx4_en_start_port(struct net_device *dev)
 		goto tx_err;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+		if (err) {
+			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
+			       err);
+			goto tx_err;
+		}
+	}
+
 	/* Init port */
 	en_dbg(HW, priv, "Initializing port\n");
 	err = mlx4_INIT_PORT(mdev->dev, priv->port);
@@ -2400,6 +2478,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
 		dev->priv_flags |= IFF_UNICAST_FLT;
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+					NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 
 	netif_carrier_off(dev);
@@ -2429,6 +2514,15 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		goto out;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+		if (err) {
+			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
+			       err);
+			goto out;
+		}
+	}
+
 	/* Init port */
 	en_warn(priv, "Initializing port\n");
 	err = mlx4_INIT_PORT(mdev->dev, priv->port);