leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'tunnels'

Browse Source 
Pravin B Shelar says:

====================
Following patch series restructure GRE and IPIP tunneling code
to make it modular. It adds ip_tunnel module which acts as
generic tunneling layer which has common code.

These patches do not change any functionality.
v3:v4:
 - Fixed compilation error in ipv6.
 - Few coding style fixes.
v2-v3:
 - Use GPL exports for all export symbols.
 - Set default config NET_IP_TUNNEL to m.
v1-v2:
 - Dropped patch to convert gre_proto_lock to rtnl lock.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2013-03-26 12:27:27 -04:00
commit dbbd136c7d
20 changed files with 1693 additions and 2204 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/net/Kconfig
View File

@ -151,6 +151,7 @@ config MACVTAP
config VXLAN
tristate "Virtual eXtensible Local Area Network (VXLAN)"
depends on INET
select NET_IP_TUNNEL
---help---
This allows one to create vxlan virtual interfaces that provide
Layer 2 Networks over Layer 3 Networks. VXLAN is often used

100
drivers/net/vxlan.c
View File

@ -33,7 +33,7 @@
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ip.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/rtnetlink.h>
@ -101,20 +101,10 @@ struct vxlan_fdb {
u8 eth_addr[ETH_ALEN];
};
/* Per-cpu network traffic stats */
struct vxlan_stats {
u64 rx_packets;
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
/* Pseudo network device */
struct vxlan_dev {
struct hlist_node hlist;
struct net_device *dev;
struct vxlan_stats __percpu *stats;
__u32 vni; /* virtual network id */
__be32 gaddr; /* multicast group */
__be32 saddr; /* source address */
@ -667,7 +657,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
struct iphdr *oip;
struct vxlanhdr *vxh;
struct vxlan_dev *vxlan;
struct vxlan_stats *stats;
struct pcpu_tstats *stats;
__u32 vni;
int err;
@ -743,7 +733,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
}
}
stats = this_cpu_ptr(vxlan->stats);
stats = this_cpu_ptr(vxlan->dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
@ -874,28 +864,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
}
/* Extract dsfield from inner protocol */
static inline u8 vxlan_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 vxlan_ecn_encap(u8 tos,
const struct iphdr *iph,
const struct sk_buff *skb)
{
u8 inner = vxlan_get_dsfield(iph, skb);
return INET_ECN_encapsulate(tos, inner);
}
static void vxlan_sock_free(struct sk_buff *skb)
{
sock_put(skb->sk);
@ -974,8 +942,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
/* short-circuited back to local bridge */
if (netif_rx(skb) == NET_RX_SUCCESS) {
struct vxlan_stats *stats =
this_cpu_ptr(vxlan->stats);
struct pcpu_tstats *stats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
@ -1007,7 +974,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
tos = vxlan->tos;
if (tos == 1)
tos = vxlan_get_dsfield(old_iph, skb);
tos = ip_tunnel_get_dsfield(old_iph, skb);
src_port = vxlan_src_port(vxlan, skb);
@ -1058,7 +1025,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = IPPROTO_UDP;
iph->tos = vxlan_ecn_encap(tos, old_iph, skb);
iph->tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
@ -1183,10 +1150,8 @@ static void vxlan_cleanup(unsigned long arg)
/* Setup stats when device is created */
static int vxlan_init(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
vxlan->stats = alloc_percpu(struct vxlan_stats);
if (!vxlan->stats)
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
@ -1242,49 +1207,6 @@ static int vxlan_stop(struct net_device *dev)
return 0;
}
/* Merge per-cpu statistics */
static struct rtnl_link_stats64 *vxlan_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_stats tmp, sum = { 0 };
unsigned int cpu;
for_each_possible_cpu(cpu) {
unsigned int start;
const struct vxlan_stats *stats
= per_cpu_ptr(vxlan->stats, cpu);
do {
start = u64_stats_fetch_begin_bh(&stats->syncp);
memcpy(&tmp, stats, sizeof(tmp));
} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
sum.tx_bytes += tmp.tx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.rx_bytes += tmp.rx_bytes;
sum.rx_packets += tmp.rx_packets;
}
stats->tx_bytes = sum.tx_bytes;
stats->tx_packets = sum.tx_packets;
stats->rx_bytes = sum.rx_bytes;
stats->rx_packets = sum.rx_packets;
stats->multicast = dev->stats.multicast;
stats->rx_length_errors = dev->stats.rx_length_errors;
stats->rx_frame_errors = dev->stats.rx_frame_errors;
stats->rx_errors = dev->stats.rx_errors;
stats->tx_dropped = dev->stats.tx_dropped;
stats->tx_carrier_errors = dev->stats.tx_carrier_errors;
stats->tx_aborted_errors = dev->stats.tx_aborted_errors;
stats->collisions = dev->stats.collisions;
stats->tx_errors = dev->stats.tx_errors;
return stats;
}
/* Stub, nothing needs to be done. */
static void vxlan_set_multicast_list(struct net_device *dev)
{
@ -1295,7 +1217,7 @@ static const struct net_device_ops vxlan_netdev_ops = {
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
.ndo_get_stats64 = vxlan_stats64,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_set_rx_mode = vxlan_set_multicast_list,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
@ -1312,9 +1234,7 @@ static struct device_type vxlan_type = {
static void vxlan_free(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
free_percpu(vxlan->stats);
free_percpu(dev->tstats);
free_netdev(dev);
}

51
include/net/gre.h
View File

@ -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

1
include/net/ip6_tunnel.h
View File

@ -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)

177
include/net/ip_tunnels.h Normal file
View File

@ -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 */

84
include/net/ipip.h
View File

@ -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

7
net/ipv4/Kconfig
View File

@ -166,6 +166,7 @@ config IP_PNP_RARP
config NET_IPIP
tristate "IP: tunneling"
select INET_TUNNEL
select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
@ -186,9 +187,14 @@ config NET_IPGRE_DEMUX
This is helper module to demultiplex GRE packets on GRE version field criteria.
Required by ip_gre and pptp modules.
config NET_IP_TUNNEL
tristate
default n
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
select NET_IP_TUNNEL
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
@ -313,6 +319,7 @@ config SYN_COOKIES
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
select INET_TUNNEL
select NET_IP_TUNNEL
depends on INET_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within

1
net/ipv4/Makefile
View File

@ -13,6 +13,7 @@ obj-y := route.o inetpeer.o protocol.o \
fib_frontend.o fib_semantics.o fib_trie.o \
inet_fragment.o ping.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o

1
net/ipv4/af_inet.c
View File

@ -111,7 +111,6 @@
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>

5
net/ipv4/gre.c
View File

@ -27,11 +27,6 @@
static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
static DEFINE_SPINLOCK(gre_proto_lock);
struct gre_base_hdr {
__be16 flags;
__be16 protocol;
};
#define GRE_HEADER_SECTION 4
int gre_add_protocol(const struct gre_protocol *proto, u8 version)
{

1554
net/ipv4/ip_gre.c
View File

File diff suppressed because it is too large Load Diff

1035
net/ipv4/ip_tunnel.c Normal file
View File

File diff suppressed because it is too large Load Diff

42
net/ipv4/ip_vti.c
View File

@ -38,7 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
@ -82,44 +82,6 @@ static int vti_tunnel_bind_dev(struct net_device *dev);
} while (0)
static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->multicast = dev->stats.multicast;
tot->rx_crc_errors = dev->stats.rx_crc_errors;
tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
tot->rx_length_errors = dev->stats.rx_length_errors;
tot->rx_errors = dev->stats.rx_errors;
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
return tot;
}
static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
{
@ -597,7 +559,7 @@ static const struct net_device_ops vti_netdev_ops = {
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = vti_tunnel_ioctl,
.ndo_change_mtu = vti_tunnel_change_mtu,
.ndo_get_stats64 = vti_get_stats64,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void vti_dev_free(struct net_device *dev)

748
net/ipv4/ipip.c
View File

@ -111,227 +111,21 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#define HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int ipip_net_id __read_mostly;
struct ipip_net {
struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_wc[1];
struct ip_tunnel __rcu **tunnels[4];
struct net_device *fb_tunnel_dev;
};
static int ipip_tunnel_init(struct net_device *dev);
static void ipip_tunnel_setup(struct net_device *dev);
static void ipip_dev_free(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;
static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
tot->collisions = dev->stats.collisions;
return tot;
}
static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
{
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(local);
struct ip_tunnel *t;
struct ipip_net *ipn = net_generic(net, ipip_net_id);
for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
return t;
t = rcu_dereference(ipn->tunnels_wc[0]);
if (t && (t->dev->flags&IFF_UP))
return t;
return NULL;
}
static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
unsigned int h = 0;
int prio = 0;
if (remote) {
prio |= 2;
h ^= HASH(remote);
}
if (local) {
prio |= 1;
h ^= HASH(local);
}
return &ipn->tunnels[prio][h];
}
static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
struct ip_tunnel *t)
{
return __ipip_bucket(ipn, &t->parms);
}
static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp;
struct ip_tunnel *iter;
for (tp = ipip_bucket(ipn, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
static int ipip_tunnel_create(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ipip_net *ipn = net_generic(net, ipip_net_id);
int err;
err = ipip_tunnel_init(dev);
if (err < 0)
goto out;
err = register_netdevice(dev);
if (err < 0)
goto out;
strcpy(t->parms.name, dev->name);
dev->rtnl_link_ops = &ipip_link_ops;
dev_hold(dev);
ipip_tunnel_link(ipn, t);
return 0;
out:
return err;
}
static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
struct ip_tunnel *t, *nt;
struct ip_tunnel __rcu **tp;
struct net_device *dev;
char name[IFNAMSIZ];
struct ipip_net *ipn = net_generic(net, ipip_net_id);
for (tp = __ipip_bucket(ipn, parms);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
return t;
}
if (!create)
return NULL;
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else
strcpy(name, "tunl%d");
dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
if (dev == NULL)
return NULL;
dev_net_set(dev, net);
nt = netdev_priv(dev);
nt->parms = *parms;
if (ipip_tunnel_create(dev) < 0)
goto failed_free;
return nt;
failed_free:
ipip_dev_free(dev);
return NULL;
}
/* called with RTNL */
static void ipip_tunnel_uninit(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct ipip_net *ipn = net_generic(net, ipip_net_id);
if (dev == ipn->fb_tunnel_dev)
RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);
else
ipip_tunnel_unlink(ipn, netdev_priv(dev));
dev_put(dev);
}
static int ipip_err(struct sk_buff *skb, u32 info)
{
@ -339,41 +133,17 @@ static int ipip_err(struct sk_buff *skb, u32 info)
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
int err;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return 0;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return 0;
break;
case ICMP_REDIRECT:
break;
}
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
err = -ENOENT;
t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->daddr, iph->saddr, 0);
if (t == NULL)
goto out;
@ -403,53 +173,29 @@ static int ipip_err(struct sk_buff *skb, u32 info)
else
t->err_count = 1;
t->err_time = jiffies;
out:
out:
return err;
}
static const struct tnl_ptk_info tpi = {
/* no tunnel info required for ipip. */
.proto = htons(ETH_P_IP),
};
static int ipip_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
int err;
tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
skb->protocol = htons(ETH_P_IP);
skb->pkt_type = PACKET_HOST;
__skb_tunnel_rx(skb, tunnel->dev);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
&iph->saddr, iph->tos);
if (err > 1) {
++tunnel->dev->stats.rx_frame_errors;
++tunnel->dev->stats.rx_errors;
goto drop;
}
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
netif_rx(skb);
return 0;
return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
return -1;
@ -463,333 +209,64 @@ drop:
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
const struct iphdr *old_iph;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
struct flowi4 fl4;
int mtu;
if (skb->protocol != htons(ETH_P_IP))
if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
old_iph = ip_hdr(skb);
if (tos & 1)
tos = old_iph->tos;
if (!dst) {
/* NBMA tunnel */
if ((rt = skb_rtable(skb)) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
dst = rt_nexthop(rt, old_iph->daddr);
}
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
dst, tiph->saddr,
0, 0,
IPPROTO_IPIP, RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
df |= old_iph->frag_off & htons(IP_DF);
if (df) {
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
dev->stats.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if ((old_iph->frag_off & htons(IP_DF)) &&
mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = (LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr));
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
if (!skb->encapsulation) {
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
if (skb->ip_summed != CHECKSUM_PARTIAL)
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = INET_ECN_encapsulate(tos, old_iph->tos);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
tunnel_ip_select_ident(skb, old_iph, &rt->dst);
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = old_iph->ttl;
iptunnel_xmit(skb, dev);
ip_tunnel_xmit(skb, dev, tiph);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static void ipip_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
if (iph->daddr) {
struct rtable *rt;
struct flowi4 fl4;
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
iph->daddr, iph->saddr,
0, 0,
IPPROTO_IPIP,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
if (tdev) {
dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - sizeof(struct iphdr);
}
dev->iflink = tunnel->parms.link;
}
static void ipip_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
{
struct net *net = dev_net(t->dev);
struct ipip_net *ipn = net_generic(net, ipip_net_id);
ipip_tunnel_unlink(ipn, t);
synchronize_net();
t->parms.iph.saddr = p->iph.saddr;
t->parms.iph.daddr = p->iph.daddr;
memcpy(t->dev->dev_addr, &p->iph.saddr, 4);
memcpy(t->dev->broadcast, &p->iph.daddr, 4);
ipip_tunnel_link(ipn, t);
t->parms.iph.ttl = p->iph.ttl;
t->parms.iph.tos = p->iph.tos;
t->parms.iph.frag_off = p->iph.frag_off;
if (t->parms.link != p->link) {
t->parms.link = p->link;
ipip_tunnel_bind_dev(t->dev);
}
netdev_state_change(t->dev);
}
static int
ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
struct ip_tunnel *t;
struct net *net = dev_net(dev);
struct ipip_net *ipn = net_generic(net, ipip_net_id);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
if (dev == ipn->fb_tunnel_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
t = ipip_tunnel_locate(net, &p, 0);
}
if (t == NULL)
t = netdev_priv(dev);
memcpy(&p, &t->parms, sizeof(p));
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
err = -EFAULT;
break;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
case SIOCADDTUNNEL:
case SIOCCHGTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -EINVAL;
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
goto done;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
t = ipip_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
(!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
err = -EINVAL;
break;
}
t = netdev_priv(dev);
}
ipip_tunnel_update(t, &p);
}
if (t) {
err = 0;
if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
err = -EFAULT;
} else
err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
break;
case SIOCDELTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
if (dev == ipn->fb_tunnel_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -ENOENT;
if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
goto done;
err = -EPERM;
if (t->dev == ipn->fb_tunnel_dev)
goto done;
dev = t->dev;
}
unregister_netdevice(dev);
err = 0;
break;
default:
err = -EINVAL;
}
done:
return err;
}
static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
return -EINVAL;
dev->mtu = new_mtu;
if (p.i_key || p.o_key || p.i_flags || p.o_flags)
return -EINVAL;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
return 0;
}
static const struct net_device_ops ipip_netdev_ops = {
.ndo_uninit = ipip_tunnel_uninit,
.ndo_init = ipip_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ipip_tunnel_ioctl,
.ndo_change_mtu = ipip_tunnel_change_mtu,
.ndo_get_stats64 = ipip_get_stats64,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipip_dev_free(struct net_device *dev)
{
free_percpu(dev->tstats);
free_netdev(dev);
}
#define IPIP_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
@ -798,11 +275,8 @@ static void ipip_dev_free(struct net_device *dev)
static void ipip_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip_netdev_ops;
dev->destructor = ipip_dev_free;
dev->type = ARPHRD_TUNNEL;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
@ -812,46 +286,19 @@ static void ipip_tunnel_setup(struct net_device *dev)
dev->features |= IPIP_FEATURES;
dev->hw_features |= IPIP_FEATURES;
ip_tunnel_setup(dev, ipip_net_id);
}
static int ipip_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
ipip_tunnel_bind_dev(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
}
static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
dev_hold(dev);
rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
return 0;
tunnel->hlen = 0;
tunnel->parms.iph.protocol = IPPROTO_IPIP;
return ip_tunnel_init(dev);
}
static void ipip_netlink_parms(struct nlattr *data[],
@ -891,28 +338,16 @@ static void ipip_netlink_parms(struct nlattr *data[],
static int ipip_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct net *net = dev_net(dev);
struct ip_tunnel *nt;
struct ip_tunnel_parm p;
nt = netdev_priv(dev);
ipip_netlink_parms(data, &nt->parms);
if (ipip_tunnel_locate(net, &nt->parms, 0))
return -EEXIST;
return ipip_tunnel_create(dev);
ipip_netlink_parms(data, &p);
return ip_tunnel_newlink(dev, tb, &p);
}
static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
struct ip_tunnel *t;
struct ip_tunnel_parm p;
struct net *net = dev_net(dev);
struct ipip_net *ipn = net_generic(net, ipip_net_id);
if (dev == ipn->fb_tunnel_dev)
return -EINVAL;
ipip_netlink_parms(data, &p);
@ -920,16 +355,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
(!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
return -EINVAL;
t = ipip_tunnel_locate(net, &p, 0);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else
t = netdev_priv(dev);
ipip_tunnel_update(t, &p);
return 0;
return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipip_get_size(const struct net_device *dev)
@ -986,6 +412,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
.setup = ipip_tunnel_setup,
.newlink = ipip_newlink,
.changelink = ipip_changelink,
.dellink = ip_tunnel_dellink,
.get_size = ipip_get_size,
.fill_info = ipip_fill_info,
};
@ -996,90 +423,29 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
.priority = 1,
};
static const char banner[] __initconst =
KERN_INFO "IPv4 over IPv4 tunneling driver\n";
static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
{
int prio;
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
struct ip_tunnel *t;
t = rtnl_dereference(ipn->tunnels[prio][h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, head);
t = rtnl_dereference(t->next);
}
}
}
}
static int __net_init ipip_init_net(struct net *net)
{
struct ipip_net *ipn = net_generic(net, ipip_net_id);
struct ip_tunnel *t;
int err;
ipn->tunnels[0] = ipn->tunnels_wc;
ipn->tunnels[1] = ipn->tunnels_l;
ipn->tunnels[2] = ipn->tunnels_r;
ipn->tunnels[3] = ipn->tunnels_r_l;
ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
"tunl0",
ipip_tunnel_setup);
if (!ipn->fb_tunnel_dev) {
err = -ENOMEM;
goto err_alloc_dev;
}
dev_net_set(ipn->fb_tunnel_dev, net);
err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
if (err)
goto err_reg_dev;
if ((err = register_netdev(ipn->fb_tunnel_dev)))
goto err_reg_dev;
t = netdev_priv(ipn->fb_tunnel_dev);
strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
ipip_dev_free(ipn->fb_tunnel_dev);
err_alloc_dev:
/* nothing */
return err;
return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
static void __net_exit ipip_exit_net(struct net *net)
{
struct ipip_net *ipn = net_generic(net, ipip_net_id);
LIST_HEAD(list);
rtnl_lock();
ipip_destroy_tunnels(ipn, &list);
unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
unregister_netdevice_many(&list);
rtnl_unlock();
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
.exit = ipip_exit_net,
.id = &ipip_net_id,
.size = sizeof(struct ipip_net),
.size = sizeof(struct ip_tunnel_net),
};
static int __init ipip_init(void)
{
int err;
printk(banner);
pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
err = register_pernet_device(&ipip_net_ops);
if (err < 0)

2
net/ipv4/ipmr.c
View File

@ -61,7 +61,7 @@
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/export.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/checksum.h>
#include <net/netlink.h>
#include <net/fib_rules.h>

2
net/ipv6/Kconfig
View File

@ -156,6 +156,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
config IPV6_SIT
tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)"
select INET_TUNNEL
select NET_IP_TUNNEL
select IPV6_NDISC_NODETYPE
default y
---help---
@ -201,6 +202,7 @@ config IPV6_TUNNEL
config IPV6_GRE
tristate "IPv6: GRE tunnel"
select IPV6_TUNNEL
select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the

1
net/ipv6/af_inet6.c
View File

@ -49,7 +49,6 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
#include <net/ipip.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>

45
net/ipv6/ip6_gre.c
View File

@ -38,6 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/addrconf.h>
@ -110,46 +111,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr)
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->multicast = dev->stats.multicast;
tot->rx_crc_errors = dev->stats.rx_crc_errors;
tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
tot->rx_length_errors = dev->stats.rx_length_errors;
tot->rx_frame_errors = dev->stats.rx_frame_errors;
tot->rx_errors = dev->stats.rx_errors;
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
return tot;
}
/* Given src, dst and key, find appropriate for input tunnel. */
static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
@ -1256,7 +1217,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
.ndo_start_xmit = ip6gre_tunnel_xmit,
.ndo_do_ioctl = ip6gre_tunnel_ioctl,
.ndo_change_mtu = ip6gre_tunnel_change_mtu,
.ndo_get_stats64 = ip6gre_get_stats64,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ip6gre_dev_free(struct net_device *dev)
@ -1505,7 +1466,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6gre_tunnel_change_mtu,
.ndo_get_stats64 = ip6gre_get_stats64,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ip6gre_tap_setup(struct net_device *dev)

1
net/ipv6/ip6_tunnel.c
View File

@ -47,6 +47,7 @@
#include <net/icmp.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>

39
net/ipv6/sit.c
View File

@ -49,7 +49,7 @@
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
@ -87,41 +87,6 @@ struct sit_net {
struct net_device *fb_tunnel_dev;
};
static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->rx_errors = dev->stats.rx_errors;
tot->rx_frame_errors = dev->stats.rx_frame_errors;
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
return tot;
}
/*
* Must be invoked with rcu_read_lock
*/
@ -1202,7 +1167,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
.ndo_start_xmit = ipip6_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
.ndo_get_stats64= ipip6_get_stats64,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipip6_dev_free(struct net_device *dev)