mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Tom Herbert](/assets/img/avatar_default.png)
Add support for remote checksum offload in VXLAN. This uses a reserved bit to indicate that RCO is being done, and uses the low order reserved eight bits of the VNI to hold the start and offset values in a compressed manner. Start is encoded in the low order seven bits of VNI. This is start >> 1 so that the checksum start offset is 0-254 using even values only. Checksum offset (transport checksum field) is indicated in the high order bit in the low order byte of the VNI. If the bit is set, the checksum field is for UDP (so offset = start + 6), else checksum field is for TCP (so offset = start + 16). Only TCP and UDP are supported in this implementation. Remote checksum offload for VXLAN is described in: https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
116 lines
3.1 KiB
C
116 lines
3.1 KiB
C
#ifndef __NET_VXLAN_H
|
|
#define __NET_VXLAN_H 1
|
|
|
|
#include <linux/ip.h>
|
|
#include <linux/ipv6.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/udp.h>
|
|
|
|
#define VNI_HASH_BITS 10
|
|
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
|
|
|
|
/* VXLAN protocol header */
|
|
struct vxlanhdr {
|
|
__be32 vx_flags;
|
|
__be32 vx_vni;
|
|
};
|
|
|
|
/* VXLAN header flags. */
|
|
#define VXLAN_HF_VNI 0x08000000
|
|
#define VXLAN_HF_RCO 0x00200000
|
|
|
|
/* Remote checksum offload header option */
|
|
#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
|
|
#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
|
|
#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
|
|
#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
|
|
#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
|
|
|
|
#define VXLAN_N_VID (1u << 24)
|
|
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
|
|
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
|
|
|
|
struct vxlan_sock;
|
|
typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
|
|
|
|
/* per UDP socket information */
|
|
struct vxlan_sock {
|
|
struct hlist_node hlist;
|
|
vxlan_rcv_t *rcv;
|
|
void *data;
|
|
struct work_struct del_work;
|
|
struct socket *sock;
|
|
struct rcu_head rcu;
|
|
struct hlist_head vni_list[VNI_HASH_SIZE];
|
|
atomic_t refcnt;
|
|
struct udp_offload udp_offloads;
|
|
u32 flags;
|
|
};
|
|
|
|
#define VXLAN_F_LEARN 0x01
|
|
#define VXLAN_F_PROXY 0x02
|
|
#define VXLAN_F_RSC 0x04
|
|
#define VXLAN_F_L2MISS 0x08
|
|
#define VXLAN_F_L3MISS 0x10
|
|
#define VXLAN_F_IPV6 0x20
|
|
#define VXLAN_F_UDP_CSUM 0x40
|
|
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
|
|
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
|
|
#define VXLAN_F_REMCSUM_TX 0x200
|
|
#define VXLAN_F_REMCSUM_RX 0x400
|
|
|
|
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
|
|
vxlan_rcv_t *rcv, void *data,
|
|
bool no_share, u32 flags);
|
|
|
|
void vxlan_sock_release(struct vxlan_sock *vs);
|
|
|
|
int vxlan_xmit_skb(struct vxlan_sock *vs,
|
|
struct rtable *rt, struct sk_buff *skb,
|
|
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
|
|
__be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
|
|
|
|
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
|
|
netdev_features_t features)
|
|
{
|
|
u8 l4_hdr = 0;
|
|
|
|
if (!skb->encapsulation)
|
|
return features;
|
|
|
|
switch (vlan_get_protocol(skb)) {
|
|
case htons(ETH_P_IP):
|
|
l4_hdr = ip_hdr(skb)->protocol;
|
|
break;
|
|
case htons(ETH_P_IPV6):
|
|
l4_hdr = ipv6_hdr(skb)->nexthdr;
|
|
break;
|
|
default:
|
|
return features;;
|
|
}
|
|
|
|
if ((l4_hdr == IPPROTO_UDP) &&
|
|
(skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
|
|
skb->inner_protocol != htons(ETH_P_TEB) ||
|
|
(skb_inner_mac_header(skb) - skb_transport_header(skb) !=
|
|
sizeof(struct udphdr) + sizeof(struct vxlanhdr))))
|
|
return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK);
|
|
|
|
return features;
|
|
}
|
|
|
|
/* IP header + UDP + VXLAN + Ethernet header */
|
|
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
|
|
/* IPv6 header + UDP + VXLAN + Ethernet header */
|
|
#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
|
|
|
|
#if IS_ENABLED(CONFIG_VXLAN)
|
|
void vxlan_get_rx_port(struct net_device *netdev);
|
|
#else
|
|
static inline void vxlan_get_rx_port(struct net_device *netdev)
|
|
{
|
|
}
|
|
#endif
|
|
#endif
|