diff options
| author | Huy Nguyen <huyn@nvidia.com> | 2021-06-14 17:33:48 +0300 |
|---|---|---|
| committer | Saeed Mahameed <saeedm@nvidia.com> | 2021-06-22 15:24:32 -0700 |
| commit | fa4535238fb5f306f95de89371a993057b32b2a4 (patch) | |
| tree | 0f73787c8b0b8519900cbe39684fd14d054fcf61 /net/xfrm | |
| parent | dd7cf00f87dc6cba8dd87dd6c9a5f18f187976ff (diff) | |
| download | linux-fa4535238fb5f306f95de89371a993057b32b2a4.tar.bz2 | |
net/xfrm: Add inner_ipproto into sec_path
The inner_ipproto saves the inner IP protocol of the plain
text packet. This allows vendor's IPsec feature making offload
decision at skb's features_check and configuring hardware at
ndo_start_xmit.
For example, ConnectX6-DX IPsec device needs the plaintext's
IP protocol to support partial checksum offload on
VXLAN/GENEVE packet over IPsec transport mode tunnel.
Signed-off-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Huy Nguyen <huyn@nvidia.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Diffstat (limited to 'net/xfrm')
| -rw-r--r-- | net/xfrm/xfrm_output.c | 41 |
1 files changed, 40 insertions, 1 deletions
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index e4cb0ff4dcf4..e321fc63a2e9 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -565,6 +565,42 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb return 0; } +/* For partial checksum offload, the outer header checksum is calculated + * by software and the inner header checksum is calculated by hardware. + * This requires hardware to know the inner packet type to calculate + * the inner header checksum. Save inner ip protocol here to avoid + * traversing the packet in the vendor's xmit code. + * If the encap type is IPIP, just save skb->inner_ipproto. Otherwise, + * get the ip protocol from the IP header. + */ +static void xfrm_get_inner_ipproto(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + const struct ethhdr *eth; + + if (!xo) + return; + + if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) { + xo->inner_ipproto = skb->inner_ipproto; + return; + } + + if (skb->inner_protocol_type != ENCAP_TYPE_ETHER) + return; + + eth = (struct ethhdr *)skb_inner_mac_header(skb); + + switch (ntohs(eth->h_proto)) { + case ETH_P_IPV6: + xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr; + break; + case ETH_P_IP: + xo->inner_ipproto = inner_ip_hdr(skb)->protocol; + break; + } +} + int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -594,12 +630,15 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return -ENOMEM; } - skb->encapsulation = 1; sp->olen++; sp->xvec[sp->len++] = x; xfrm_state_hold(x); + if (skb->encapsulation) + xfrm_get_inner_ipproto(skb); + skb->encapsulation = 1; + if (skb_is_gso(skb)) { if (skb->inner_protocol) return xfrm_output_gso(net, sk, skb); |