From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alexander Duyck Subject: [RFC PATCH 09/11] i40e/i40evf: Add support for GSO partial with UDP_TUNNEL_CSUM and GRE_CSUM Date: Thu, 07 Apr 2016 18:32:49 -0400 Message-ID: <20160407223249.11142.77910.stgit@ahduyck-xeon-server> References: <20160407222211.11142.41024.stgit@ahduyck-xeon-server> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: herbert@gondor.apana.org.au, tom@herbertland.com, jesse@kernel.org, alexander.duyck@gmail.com, edumazet@google.com, netdev@vger.kernel.org, davem@davemloft.net Return-path: Received: from mail-pf0-f181.google.com ([209.85.192.181]:36217 "EHLO mail-pf0-f181.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932149AbcDGWcx (ORCPT ); Thu, 7 Apr 2016 18:32:53 -0400 Received: by mail-pf0-f181.google.com with SMTP id e128so63612898pfe.3 for ; Thu, 07 Apr 2016 15:32:52 -0700 (PDT) In-Reply-To: <20160407222211.11142.41024.stgit@ahduyck-xeon-server> Sender: netdev-owner@vger.kernel.org List-ID: 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 --- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +++++- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 7 ++++++- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 7 ++++++- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 6 +++++- 4 files changed, 22 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 07a70c4ac49f..6c095b07ce82 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9119,17 +9119,21 @@ 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; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 6e44cf118843..ede4183468b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2300,11 +2300,15 @@ 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; @@ -2481,6 +2485,7 @@ 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 f101895ecf4a..6ce00547c13e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1565,11 +1565,15 @@ 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; @@ -1704,6 +1708,7 @@ 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 806da2686623..9c78c6d6afcb 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2346,17 +2346,21 @@ 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;