diff options
author | Pravin B Shelar <pshelar@nicira.com> | 2013-03-25 14:49:35 +0000 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-03-26 12:27:18 -0400 |
commit | c54419321455631079c7d6e60bc732dd0c5914c5 (patch) | |
tree | a0ad703b72313b98e70f4166bcea9a328d09e937 /include | |
parent | eaac5f3d3ad33547b299935e6db0cfc7be9a576a (diff) | |
download | op-kernel-dev-c54419321455631079c7d6e60bc732dd0c5914c5.zip op-kernel-dev-c54419321455631079c7d6e60bc732dd0c5914c5.tar.gz |
GRE: Refactor GRE tunneling code.
Following patch refactors GRE code into ip tunneling code and GRE
specific code. Common tunneling code is moved to ip_tunnel module.
ip_tunnel module is written as generic library which can be used
by different tunneling implementations.
ip_tunnel module contains following components:
- packet xmit and rcv generic code. xmit flow looks like
(gre_xmit/ipip_xmit)->ip_tunnel_xmit->ip_local_out.
- hash table of all devices.
- lookup for tunnel devices.
- control plane operations like device create, destroy, ioctl, netlink
operations code.
- registration for tunneling modules, like gre, ipip etc.
- define single pcpu_tstats dev->tstats.
- struct tnl_ptk_info added to pass parsed tunnel packet parameters.
ipip.h header is renamed to ip_tunnel.h
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r-- | include/net/gre.h | 51 | ||||
-rw-r--r-- | include/net/ip6_tunnel.h | 1 | ||||
-rw-r--r-- | include/net/ip_tunnels.h | 177 | ||||
-rw-r--r-- | include/net/ipip.h | 84 |
4 files changed, 229 insertions, 84 deletions
diff --git a/include/net/gre.h b/include/net/gre.h index 8266547..9f03a39 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -2,6 +2,7 @@ #define __LINUX_GRE_H #include <linux/skbuff.h> +#include <net/ip_tunnels.h> #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 @@ -12,7 +13,57 @@ struct gre_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); }; +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 + int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); +static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static inline __be16 tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + #endif diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index ebdef7f..4da5de1 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -3,6 +3,7 @@ #include <linux/ipv6.h> #include <linux/netdevice.h> +#include <linux/if_tunnel.h> #include <linux/ip6_tunnel.h> #define IP6TUNNEL_ERR_TIMEO (30*HZ) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h new file mode 100644 index 0000000..4b6f0b2 --- /dev/null +++ b/include/net/ip_tunnels.h @@ -0,0 +1,177 @@ +#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/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) + +/* 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_prl_entry { + struct ip_tunnel_prl_entry __rcu *next; + __be32 addr; + u16 flags; + struct rcu_head rcu_head; +}; + +struct ip_tunnel { + struct ip_tunnel __rcu *next; + struct hlist_node hash_node; + struct net_device *dev; + + 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 hlen; /* Precalculated header length */ + int mlink; + + struct ip_tunnel_parm parms; + + /* 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) + +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 10 +#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) + +struct ip_tunnel_net { + struct hlist_head *tunnels; + struct net_device *fb_tunnel_dev; +}; + +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); +int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, + struct rtnl_link_ops *ops, char *devname); + +void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn); + +void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const struct iphdr *tnl_params); +int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +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); + +/* 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); +} + +static inline void tunnel_ip_select_ident(struct sk_buff *skb, + const struct iphdr *old_iph, + struct dst_entry *dst) +{ + struct iphdr *iph = ip_hdr(skb); + + /* Use inner packet iph-id if possible. */ + if (skb->protocol == htons(ETH_P_IP) && old_iph->id) + iph->id = old_iph->id; + else + __ip_select_ident(iph, dst, + (skb_shinfo(skb)->gso_segs ?: 1) - 1); +} + +static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + int err; + int pkt_len = skb->len - skb_transport_offset(skb); + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); + + nf_reset(skb); + + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } +} +#endif /* __NET_IP_TUNNELS_H */ diff --git a/include/net/ipip.h b/include/net/ipip.h deleted file mode 100644 index 483b91a..0000000 --- a/include/net/ipip.h +++ /dev/null @@ -1,84 +0,0 @@ -#ifndef __NET_IPIP_H -#define __NET_IPIP_H 1 - -#include <linux/if_tunnel.h> -#include <net/gro_cells.h> -#include <net/ip.h> - -/* Keep error state on tunnel for 30 sec */ -#define IPTUNNEL_ERR_TIMEO (30*HZ) - -/* 6rd prefix/relay information */ -struct ip_tunnel_6rd_parm { - struct in6_addr prefix; - __be32 relay_prefix; - u16 prefixlen; - u16 relay_prefixlen; -}; - -struct ip_tunnel { - struct ip_tunnel __rcu *next; - struct net_device *dev; - - 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 hlen; /* Precalculated GRE header length */ - int mlink; - - struct ip_tunnel_parm parms; - - /* 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 */ - - struct gro_cells gro_cells; -}; - -struct ip_tunnel_prl_entry { - struct ip_tunnel_prl_entry __rcu *next; - __be32 addr; - u16 flags; - struct rcu_head rcu_head; -}; - -static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev) -{ - int err; - int pkt_len = skb->len - skb_transport_offset(skb); - struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); - - nf_reset(skb); - - err = ip_local_out(skb); - if (likely(net_xmit_eval(err) == 0)) { - u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - u64_stats_update_end(&tstats->syncp); - } else { - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - } -} - -static inline void tunnel_ip_select_ident(struct sk_buff *skb, - const struct iphdr *old_iph, - struct dst_entry *dst) -{ - struct iphdr *iph = ip_hdr(skb); - - /* Use inner packet iph-id if possible. */ - if (skb->protocol == htons(ETH_P_IP) && old_iph->id) - iph->id = old_iph->id; - else - __ip_select_ident(iph, dst, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); -} -#endif |