AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-13 10:37:45 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
ee122c79d4
linux_dsm_epyc7002/include/net/ip_tunnels.h
Thomas Graf ee122c79d4 vxlan: Flow based tunneling 
Allows putting a VXLAN device into a new flow-based mode in which
skbs with a ip_tunnel_info dst metadata attached will be encapsulated
according to the instructions stored in there with the VXLAN device
defaults taken into consideration.

Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is
set, the packet processing will populate a ip_tunnel_info struct for
each packet received and attach it to the skb using the new metadata
dst.  The metadata structure will contain the outer header and tunnel
header fields which have been stripped off. Layers further up in the
stack such as routing, tc or netfitler can later match on these fields
and perform forwarding. It is the responsibility of upper layers to
ensure that the flag is set if the metadata is needed. The flag limits
the additional cost of metadata collecting based on demand.

This prepares the VXLAN device to be steered by the routing and other
subsystems which allows to support encapsulation for a large number
of tunnel endpoints and tunnel ids through a single net_device which
improves the scalability.

It also allows for OVS to leverage this mode which in turn allows for
the removal of the OVS specific VXLAN code.

Because the skb is currently scrubed in vxlan_rcv(), the attachment of
the new dst metadata is postponed until after scrubing which requires
the temporary addition of a new member to vxlan_metadata. This member
is removed again in a later commit after the indirect VXLAN receive API
has been removed.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 10:39:06 -07:00

304 lines
8.4 KiB
C
Raw Blame History

#ifndef __NET_IP_TUNNELS_H
#define __NET_IP_TUNNELS_H 1
#include <linux/if_tunnel.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/u64_stats_sync.h>
#include <net/dsfield.h>
#include <net/gro_cells.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif
/* Keep error state on tunnel for 30 sec */
#define IPTUNNEL_ERR_TIMEO (30*HZ)
/* Used to memset ip_tunnel padding. */
#define IP_TUNNEL_KEY_SIZE \
(offsetof(struct ip_tunnel_key, tp_dst) + \
FIELD_SIZEOF(struct ip_tunnel_key, tp_dst))
struct ip_tunnel_key {
__be64 tun_id;
__be32 ipv4_src;
__be32 ipv4_dst;
__be16 tun_flags;
__u8 ipv4_tos;
__u8 ipv4_ttl;
__be16 tp_src;
__be16 tp_dst;
} __packed __aligned(4); /* Minimize padding. */
/* Indicates whether the tunnel info structure represents receive
* or transmit tunnel parameters.
*/
enum {
IP_TUNNEL_INFO_RX,
IP_TUNNEL_INFO_TX,
};
struct ip_tunnel_info {
struct ip_tunnel_key key;
const void *options;
u8 options_len;
u8 mode;
};
/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
struct in6_addr prefix;
__be32 relay_prefix;
u16 prefixlen;
u16 relay_prefixlen;
};
#endif
struct ip_tunnel_encap {
__u16 type;
__u16 flags;
__be16 sport;
__be16 dport;
};
struct ip_tunnel_prl_entry {
struct ip_tunnel_prl_entry __rcu *next;
__be32 addr;
u16 flags;
struct rcu_head rcu_head;
};
struct ip_tunnel_dst {
struct dst_entry __rcu *dst;
__be32 saddr;
};
struct ip_tunnel {
struct ip_tunnel __rcu *next;
struct hlist_node hash_node;
struct net_device *dev;
struct net *net; /* netns for packet i/o */
int err_count; /* Number of arrived ICMP errors */
unsigned long err_time; /* Time when the last ICMP error
* arrived */
/* These four fields used only by GRE */
__u32 i_seqno; /* The last seen seqno */
__u32 o_seqno; /* The last output seqno */
int tun_hlen; /* Precalculated header length */
int mlink;
struct ip_tunnel_dst __percpu *dst_cache;
struct ip_tunnel_parm parms;
int encap_hlen; /* Encap header length (FOU,GUE) */
struct ip_tunnel_encap encap;
int hlen; /* tun_hlen + encap_hlen */
/* for SIT */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm ip6rd;
#endif
struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
unsigned int prl_count; /* # of entries in PRL */
int ip_tnl_net_id;
struct gro_cells gro_cells;
};
#define TUNNEL_CSUM __cpu_to_be16(0x01)
#define TUNNEL_ROUTING __cpu_to_be16(0x02)
#define TUNNEL_KEY __cpu_to_be16(0x04)
#define TUNNEL_SEQ __cpu_to_be16(0x08)
#define TUNNEL_STRICT __cpu_to_be16(0x10)
#define TUNNEL_REC __cpu_to_be16(0x20)
#define TUNNEL_VERSION __cpu_to_be16(0x40)
#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100)
#define TUNNEL_OAM __cpu_to_be16(0x0200)
#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800)
#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000)
#define TUNNEL_OPTIONS_PRESENT (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT)
struct tnl_ptk_info {
__be16 flags;
__be16 proto;
__be32 key;
__be32 seq;
};
#define PACKET_RCVD 0
#define PACKET_REJECT 1
#define IP_TNL_HASH_BITS 7
#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS)
struct ip_tunnel_net {
struct net_device *fb_tunnel_dev;
struct hlist_head tunnels[IP_TNL_HASH_SIZE];
};
struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi4 *fl4);
};
#define MAX_IPTUN_ENCAP_OPS 8
extern const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS];
int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
unsigned int num);
int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
unsigned int num);
static inline void __ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
__be32 saddr, __be32 daddr,
u8 tos, u8 ttl,
__be16 tp_src, __be16 tp_dst,
__be64 tun_id, __be16 tun_flags,
const void *opts, u8 opts_len)
{
tun_info->key.tun_id = tun_id;
tun_info->key.ipv4_src = saddr;
tun_info->key.ipv4_dst = daddr;
tun_info->key.ipv4_tos = tos;
tun_info->key.ipv4_ttl = ttl;
tun_info->key.tun_flags = tun_flags;
/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
* the upper tunnel are used.
* E.g: GRE over IPSEC, the tp_src and tp_port are zero.
*/
tun_info->key.tp_src = tp_src;
tun_info->key.tp_dst = tp_dst;
/* Clear struct padding. */
if (sizeof(tun_info->key) != IP_TUNNEL_KEY_SIZE)
memset((unsigned char *)&tun_info->key + IP_TUNNEL_KEY_SIZE,
0, sizeof(tun_info->key) - IP_TUNNEL_KEY_SIZE);
tun_info->options = opts;
tun_info->options_len = opts_len;
}
static inline void ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
const struct iphdr *iph,
__be16 tp_src, __be16 tp_dst,
__be64 tun_id, __be16 tun_flags,
const void *opts, u8 opts_len)
{
__ip_tunnel_info_init(tun_info, iph->saddr, iph->daddr,
iph->tos, iph->ttl, tp_src, tp_dst,
tun_id, tun_flags, opts, opts_len);
}
#ifdef CONFIG_INET
int ip_tunnel_init(struct net_device *dev);
void ip_tunnel_uninit(struct net_device *dev);
void ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
struct net *ip_tunnel_get_link_net(const struct net_device *dev);
int ip_tunnel_get_iflink(const struct net_device *dev);
int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname);
void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol);
int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
u8 *protocol, struct flowi4 *fl4);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot);
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
int link, __be16 flags,
__be32 remote, __be32 local,
__be32 key);
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi, bool log_ecn_error);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
void ip_tunnel_setup(struct net_device *dev, int net_id);
void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
int ip_tunnel_encap_setup(struct ip_tunnel *t,
struct ip_tunnel_encap *ipencap);
/* Extract dsfield from inner protocol */
static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
const struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
return ipv6_get_dsfield((const struct ipv6hdr *)iph);
else
return 0;
}
/* Propogate ECN bits out */
static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
const struct sk_buff *skb)
{
u8 inner = ip_tunnel_get_dsfield(iph, skb);
return INET_ECN_encapsulate(tos, inner);
}
int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet);
struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
int gso_type_mask);
static inline void iptunnel_xmit_stats(int err,
struct net_device_stats *err_stats,
struct pcpu_sw_netstats __percpu *stats)
{
if (err > 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
u64_stats_update_begin(&tstats->syncp);
tstats->tx_bytes += err;
tstats->tx_packets++;
u64_stats_update_end(&tstats->syncp);
} else if (err < 0) {
err_stats->tx_errors++;
err_stats->tx_aborted_errors++;
} else {
err_stats->tx_dropped++;
}
}
static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info, size_t n)
{
return info + 1;
}
#endif /* CONFIG_INET */
#endif /* __NET_IP_TUNNELS_H */
Reference in New Issue View Git Blame Copy Permalink