i40e/i40evf: Add support for GSO partial with UDP_TUNNEL_CSUM and GRE_CSUM

This patch makes it so that i40e and i40evf can use GSO_PARTIAL to support
segmentation for frames with checksums enabled in outer headers.  As a
result we can now send data over these types of tunnels at over 20Gb/s
versus the 12Gb/s that was previously possible on my system.

The advantage with the i40e parts is that this offload is mostly
transparent as the hardware still deals with the inner and/or outer IPv4
headers so the IP ID is still incrementing for both when this offload is
performed.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 19a2d30..8e6c0f2 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9130,20 +9130,25 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
                                   NETIF_F_TSO_ECN              |
                                   NETIF_F_TSO6                 |
                                   NETIF_F_GSO_GRE              |
+                                  NETIF_F_GSO_GRE_CSUM         |
                                   NETIF_F_GSO_IPIP             |
                                   NETIF_F_GSO_SIT              |
                                   NETIF_F_GSO_UDP_TUNNEL       |
                                   NETIF_F_GSO_UDP_TUNNEL_CSUM  |
+                                  NETIF_F_GSO_PARTIAL          |
                                   NETIF_F_SCTP_CRC             |
                                   NETIF_F_RXHASH               |
                                   NETIF_F_RXCSUM               |
                                   0;
 
        if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE))
-               netdev->hw_enc_features ^= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+               netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+       netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
        /* record features VLANs can make use of */
-       netdev->vlan_features |= netdev->hw_enc_features;
+       netdev->vlan_features |= netdev->hw_enc_features |
+                                NETIF_F_TSO_MANGLEID;
 
        if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
                netdev->hw_features |= NETIF_F_NTUPLE;
@@ -9153,6 +9158,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
                               NETIF_F_HW_VLAN_CTAG_RX;
 
        netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
+       netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
 
        if (vsi->type == I40E_VSI_MAIN) {
                SET_NETDEV_DEV(netdev, &pf->pdev->dev);

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 285efe9..2765d7e 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2301,11 +2301,15 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
        }
 
        if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+                                        SKB_GSO_GRE_CSUM |
                                         SKB_GSO_IPIP |
                                         SKB_GSO_SIT |
                                         SKB_GSO_UDP_TUNNEL |
                                         SKB_GSO_UDP_TUNNEL_CSUM)) {
-               if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+               if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+                   (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
+                       l4.udp->len = 0;
+
                        /* determine offset of outer transport header */
                        l4_offset = l4.hdr - skb->data;
 
@@ -2482,6 +2486,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
                /* indicate if we need to offload outer UDP header */
                if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+                   !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
                    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
                        tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
 

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 4633235..ede8dfc 100644 (file)
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1566,11 +1566,15 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
        }
 
        if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+                                        SKB_GSO_GRE_CSUM |
                                         SKB_GSO_IPIP |
                                         SKB_GSO_SIT |
                                         SKB_GSO_UDP_TUNNEL |
                                         SKB_GSO_UDP_TUNNEL_CSUM)) {
-               if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+               if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+                   (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
+                       l4.udp->len = 0;
+
                        /* determine offset of outer transport header */
                        l4_offset = l4.hdr - skb->data;
 
@@ -1705,6 +1709,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
                /* indicate if we need to offload outer UDP header */
                if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+                   !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
                    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
                        tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
 

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index b9b1dd8..9f0bd7a 100644 (file)
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2240,20 +2240,25 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
                                   NETIF_F_TSO_ECN              |
                                   NETIF_F_TSO6                 |
                                   NETIF_F_GSO_GRE              |
+                                  NETIF_F_GSO_GRE_CSUM         |
                                   NETIF_F_GSO_IPIP             |
                                   NETIF_F_GSO_SIT              |
                                   NETIF_F_GSO_UDP_TUNNEL       |
                                   NETIF_F_GSO_UDP_TUNNEL_CSUM  |
+                                  NETIF_F_GSO_PARTIAL          |
                                   NETIF_F_SCTP_CRC             |
                                   NETIF_F_RXHASH               |
                                   NETIF_F_RXCSUM               |
                                   0;
 
        if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE))
-               netdev->hw_enc_features ^= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+               netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+       netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
        /* record features VLANs can make use of */
-       netdev->vlan_features |= netdev->hw_enc_features;
+       netdev->vlan_features |= netdev->hw_enc_features |
+                                NETIF_F_TSO_MANGLEID;
 
        /* Write features and hw_features separately to avoid polluting
         * with, or dropping, features that are set when we registgered.
@@ -2261,6 +2266,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
        netdev->hw_features |= netdev->hw_enc_features;
 
        netdev->features |= netdev->hw_enc_features | I40EVF_VLAN_FEATURES;
+       netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
 
        /* disable VLAN features if not supported */
        if (!(vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN))