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>
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e3adceb..160e86d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -39,6 +39,7 @@
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
 #include <linux/tcp.h>
+#include <linux/ip.h>
 #include <linux/moduleparam.h>
 
 #include "mlx4_en.h"
@@ -560,7 +561,10 @@
 	int real_size;
 
 	if (skb_is_gso(skb)) {
-		*lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb->encapsulation)
+			*lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
+		else
+			*lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		real_size = CTRL_SIZE + skb_shinfo(skb)->nr_frags * DS_SIZE +
 			ALIGN(*lso_header_size + 4, DS_SIZE);
 		if (unlikely(*lso_header_size != skb_headlen(skb))) {
@@ -859,6 +863,14 @@
 		tx_info->inl = 1;
 	}
 
+	if (skb->encapsulation) {
+		struct iphdr *ipv4 = (struct iphdr *)skb_inner_network_header(skb);
+		if (ipv4->protocol == IPPROTO_TCP || ipv4->protocol == IPPROTO_UDP)
+			op_own |= cpu_to_be32(MLX4_WQE_CTRL_IIP | MLX4_WQE_CTRL_ILP);
+		else
+			op_own |= cpu_to_be32(MLX4_WQE_CTRL_IIP);
+	}
+
 	ring->prod += nr_txbb;
 
 	/* If we used a bounce buffer then copy descriptor back into place */