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 <adu...@mirantis.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 8 +++++++-
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 14 +++++++++++---
drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 14 +++++++++++---
drivers/net/ethernet/intel/i40evf/i40evf_main.c | 8 +++++++-
4 files changed, 36 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c
b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 39b0009253c2..ac3964a9f5c0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9050,6 +9050,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
NETIF_F_TSO6 |
NETIF_F_TSO_ECN |
NETIF_F_GSO_GRE |
+ NETIF_F_GSO_GRE_CSUM |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM |
0;
@@ -9074,7 +9075,12 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
netdev->features |= NETIF_F_NTUPLE;
if (pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)
- netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ else
+ netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+ netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ netdev->features |= NETIF_F_GSO_PARTIAL | netdev->gso_partial_features;
/* copy netdev features into list of user selectable features */
netdev->hw_features |= netdev->features;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5d5fa5359a1d..50aa76d7f92e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2297,9 +2297,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct
sk_buff *skb,
ip.v6->payload_len = 0;
}
- if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+ if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+ SKB_GSO_GRE_CSUM |
+ 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_UDP_TUNNEL |
+ SKB_GSO_UDP_TUNNEL_CSUM))
+ l4.udp->len = 0;
+
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
/* determine offset of outer transport header */
l4_offset = l4.hdr - skb->data;
@@ -2470,7 +2477,8 @@ 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_UDP_TUNNEL_CSUM))
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) &&
+ !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
/* record tunnel offload values */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 04aabc52ba0d..1bb7c3efa36c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1564,9 +1564,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct
sk_buff *skb,
ip.v6->payload_len = 0;
}
- if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+ if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+ SKB_GSO_GRE_CSUM |
+ 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_UDP_TUNNEL |
+ SKB_GSO_UDP_TUNNEL_CSUM))
+ l4.udp->len = 0;
+
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
/* determine offset of outer transport header */
l4_offset = l4.hdr - skb->data;
@@ -1695,7 +1702,8 @@ 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_UDP_TUNNEL_CSUM))
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) &&
+ !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
/* record tunnel offload values */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index e3973684746b..ed3c9310c3e0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2331,7 +2331,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
NETIF_F_TSO |
NETIF_F_TSO6 |
NETIF_F_TSO_ECN |
- NETIF_F_GSO_GRE |
+ NETIF_F_GSO_GRE |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_RXCSUM |
NETIF_F_GRO;
@@ -2342,11 +2342,17 @@ int i40evf_process_config(struct i40evf_adapter
*adapter)
NETIF_F_TSO6 |
NETIF_F_TSO_ECN |
NETIF_F_GSO_GRE |
+ NETIF_F_GSO_GRE_CSUM |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM;
if (adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE)
netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ else
+ netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+ netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ netdev->features |= NETIF_F_GSO_PARTIAL | netdev->gso_partial_features;
/* copy netdev features into list of user selectable features */
netdev->hw_features |= netdev->features;
