Skip to content

L
linux
Commit c5441932 authored by Pravin B Shelar's avatar Pravin B Shelar Committed by David S. Miller
Browse files
Options

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: default avatarPravin B Shelar <pshelar@nicira.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent eaac5f3d
Show whitespace changes
Inline Side-by-side
Showing with 1594 additions and 1199 deletions
drivers/net/vxlan.c
View file @ c5441932
......@@ -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>
......
include/net/gre.h
View file @ c5441932
......@@ -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
include/net/ip6_tunnel.h
View file @ c5441932
......@@ -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)
......
include/net/ipip.h → include/net/ip_tunnels.h
View file @ c5441932
#ifndef __NET_IPIP_H
#define __NET_IPIP_H 1
#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 */
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 hlen; /* Precalculated header length */
int mlink;
struct ip_tunnel_parm parms;
......@@ -37,17 +61,100 @@ struct ip_tunnel {
#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;
};
struct ip_tunnel_prl_entry {
struct ip_tunnel_prl_entry __rcu *next;
__be32 addr;
u16 flags;
struct rcu_head rcu_head;
#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;
......@@ -67,18 +174,4 @@ static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
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
#endif /* __NET_IP_TUNNELS_H */
net/ipv4/Kconfig
View file @ c5441932
......@@ -186,9 +186,14 @@ 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
......
net/ipv4/Makefile
View file @ c5441932
......@@ -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
......
net/ipv4/af_inet.c
View file @ c5441932
......@@ -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>
......
net/ipv4/gre.c
View file @ c5441932
......@@ -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)
{
......
net/ipv4/ip_gre.c
View file @ c5441932
......@@ -37,7 +37,7 @@
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ipip.h>
#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
......@@ -108,15 +108,6 @@
fatal route to network, even if it were you who configured
fatal static route: you are innocent. :-)
3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
practically identical code. It would be good to glue them
together, but it is not very evident, how to make them modular.
sit is integral part of IPv6, ipip and gre are naturally modular.
We could extract common parts (hash table, ioctl etc)
to a separate module (ip_tunnel.c).
Alexey Kuznetsov.
*/
......@@ -126,400 +117,135 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);
static int ipgre_tunnel_bind_dev(struct net_device *dev);
/* Fallback tunnel: no source, no destination, no key, no options */
#define HASH_SIZE 16
static int ipgre_net_id __read_mostly;
struct ipgre_net {
struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
struct net_device *fb_tunnel_dev;
};
static int gre_tap_net_id __read_mostly;
/* Tunnel hash table */
/*
4 hash tables:
3: (remote,local)
2: (remote,*)
1: (*,local)
0: (*,*)
We require exact key match i.e. if a key is present in packet
it will match only tunnel with the same key; if it is not present,
it will match only keyless tunnel.
All keysless packets, if not matched configured keyless tunnels
will match fallback tunnel.
*/
static __sum16 check_checksum(struct sk_buff *skb)
{
__sum16 csum = 0;
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
#define tunnels_r_l tunnels[3]
#define tunnels_r tunnels[2]
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
if (!csum)
break;
/* Fall through. */
static struct rtnl_link_stats64 *ipgre_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;
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
break;
}
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;
return csum;
}
/* Does key in tunnel parameters match packet */
static bool ipgre_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
static int ip_gre_calc_hlen(__be16 o_flags)
{
if (p->i_flags & GRE_KEY) {
if (flags & GRE_KEY)
return key == p->i_key;
else
return false; /* key expected, none present */
} else
return !(flags & GRE_KEY);
}
int addend = 4;
/* Given src, dst and key, find appropriate for input tunnel. */
if (o_flags&TUNNEL_CSUM)
addend += 4;
if (o_flags&TUNNEL_KEY)
addend += 4;
if (o_flags&TUNNEL_SEQ)
addend += 4;
return addend;
}
static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
__be32 remote, __be32 local,
__be16 flags, __be32 key,
__be16 gre_proto)
static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
bool *csum_err, int *hdr_len)
{
struct net *net = dev_net(dev);
int link = dev->ifindex;
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(key);
struct ip_tunnel *t, *cand = NULL;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
ARPHRD_ETHER : ARPHRD_IPGRE;
int score, cand_score = 4;
for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
if (local != t->parms.iph.saddr ||
remote != t->parms.iph.daddr ||
!(t->dev->flags & IFF_UP))
continue;
if (!ipgre_key_match(&t->parms, flags, key))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
struct iphdr *iph = ip_hdr(skb);
struct gre_base_hdr *greh;
__be32 *options;
for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
if (remote != t->parms.iph.daddr ||
!(t->dev->flags & IFF_UP))
continue;
if (!ipgre_key_match(&t->parms, flags, key))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
if ((local != t->parms.iph.saddr &&
(local != t->parms.iph.daddr ||
!ipv4_is_multicast(local))) ||
!(t->dev->flags & IFF_UP))
continue;
if (!ipgre_key_match(&t->parms, flags, key))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
return -EINVAL;
for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
if (t->parms.i_key != key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
greh = (struct gre_base_hdr *)((u8 *)iph + (iph->ihl << 2));
if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
return -EINVAL;
if (cand != NULL)
return cand;
tpi->flags = gre_flags_to_tnl_flags(greh->flags);
*hdr_len = ip_gre_calc_hlen(tpi->flags);
dev = ign->fb_tunnel_dev;
if (dev->flags & IFF_UP)
return netdev_priv(dev);
if (!pskb_may_pull(skb, *hdr_len))
return -EINVAL;
return NULL;
}
tpi->proto = greh->protocol;
static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
unsigned int h = HASH(key);
int prio = 0;
if (local)
prio |= 1;
if (remote && !ipv4_is_multicast(remote)) {
prio |= 2;
h ^= HASH(remote);
options = (__be32 *)(greh + 1);
if (greh->flags & GRE_CSUM) {
if (check_checksum(skb)) {
*csum_err = true;
return -EINVAL;
}
options++;
}
return &ign->tunnels[prio][h];
}
static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel *t)
{
return __ipgre_bucket(ign, &t->parms);
}
static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
if (greh->flags & GRE_KEY) {
tpi->key = *options;
options++;
} else
tpi->key = 0;
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
if (unlikely(greh->flags & GRE_SEQ)) {
tpi->seq = *options;
options++;
} else
tpi->seq = 0;
static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp;
struct ip_tunnel *iter;
for (tp = ipgre_bucket(ign, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
tpi->proto = htons(ETH_P_IP);
if ((*(u8 *)options & 0xF0) != 0x40) {
*hdr_len += 4;
if (!pskb_may_pull(skb, *hdr_len))
return -EINVAL;
}
}
}
static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
struct ip_tunnel_parm *parms,
int type)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
int link = parms->link;
struct ip_tunnel *t;
struct ip_tunnel __rcu **tp;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
for (tp = __ipgre_bucket(ign, parms);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next)
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
key == t->parms.i_key &&
link == t->parms.link &&
type == t->dev->type)
break;
return t;
}
static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
struct ip_tunnel *t, *nt;
struct net_device *dev;
char name[IFNAMSIZ];
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
if (t || !create)
return t;
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else
strcpy(name, "gre%d");
dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
if (!dev)
return NULL;
dev_net_set(dev, net);
nt = netdev_priv(dev);
nt->parms = *parms;
dev->rtnl_link_ops = &ipgre_link_ops;
dev->mtu = ipgre_tunnel_bind_dev(dev);
if (register_netdevice(dev) < 0)
goto failed_free;
/* Can use a lockless transmit, unless we generate output sequences */
if (!(nt->parms.o_flags & GRE_SEQ))
dev->features |= NETIF_F_LLTX;
dev_hold(dev);
ipgre_tunnel_link(ign, nt);
return nt;
failed_free:
free_netdev(dev);
return NULL;
}
static void ipgre_tunnel_uninit(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
ipgre_tunnel_unlink(ign, netdev_priv(dev));
dev_put(dev);
return 0;
}
static void ipgre_err(struct sk_buff *skb, u32 info)
{
/* All the routers (except for Linux) return only
/* All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
Moreover, Cisco "wise men" put GRE key to the third word
in GRE header. It makes impossible maintaining even soft state for keyed
GRE tunnels with enabled checksum. Tell them "thank you".
in GRE header. It makes impossible maintaining even soft
state for keyed GRE tunnels with enabled checksum. Tell
them "thank you".
Well, I wonder, rfc1812 was written by Cisco employee,
what the hell these idiots break standards established
by themselves???
*/
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn;
const struct iphdr *iph = (const struct iphdr *)skb->data;
__be16 *p = (__be16 *)(skb->data+(iph->ihl<<2));
int grehlen = (iph->ihl<<2) + 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
__be16 flags;
__be32 key = 0;
struct tnl_ptk_info tpi;
int hdr_len;
bool csum_err = false;
flags = p[0];
if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
if (flags&(GRE_VERSION|GRE_ROUTING))
if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len)) {
if (!csum_err) /* ignore csum errors. */
return;
if (flags&GRE_KEY) {
grehlen += 4;
if (flags&GRE_CSUM)
grehlen += 4;
}
}
/* If only 8 bytes returned, keyed message will be dropped here */
if (skb_headlen(skb) < grehlen)
return;
if (flags & GRE_KEY)
key = *(((__be32 *)p) + (grehlen / 4) - 1);
switch (type) {
default:
case ICMP_PARAMETERPROB:
......@@ -548,8 +274,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
}
t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
flags, key, p[1]);
if (tpi.proto == htons(ETH_P_TEB))
itn = net_generic(net, gre_tap_net_id);
else
itn = net_generic(net, ipgre_net_id);
t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
iph->daddr, iph->saddr, tpi.key);
if (t == NULL)
return;
......@@ -578,158 +309,33 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
t->err_time = jiffies;
}
static inline u8
ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
{
u8 inner = 0;
if (skb->protocol == htons(ETH_P_IP))
inner = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
return INET_ECN_encapsulate(tos, inner);
}
static int ipgre_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn;
const struct iphdr *iph;
u8 *h;
__be16 flags;
__sum16 csum = 0;
__be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
int err;
if (!pskb_may_pull(skb, 16))
goto drop;
iph = ip_hdr(skb);
h = skb->data;
flags = *(__be16 *)h;
struct tnl_ptk_info tpi;
int hdr_len;
bool csum_err = false;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
- We do not support routing headers.
*/
if (flags&(GRE_VERSION|GRE_ROUTING))
goto drop;
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
}
offset += 4;
}
if (flags&GRE_KEY) {
key = *(__be32 *)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
seqno = ntohl(*(__be32 *)(h + offset));
offset += 4;
}
}
gre_proto = *(__be16 *)(h + 2);
tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, flags, key,
gre_proto);
if (tunnel) {
struct pcpu_tstats *tstats;
secpath_reset(skb);
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (rt_is_output_route(skb_rtable(skb)))
goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
tunnel->dev->stats.rx_crc_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
tunnel->dev->stats.rx_fifo_errors++;
tunnel->dev->stats.rx_errors++;
if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len) < 0)
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
tunnel->dev->stats.rx_length_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tpi.proto == htons(ETH_P_TEB))
itn = net_generic(net, gre_tap_net_id);
else
itn = net_generic(net, ipgre_net_id);
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
iph->saddr, iph->daddr, tpi.key);
__skb_tunnel_rx(skb, tunnel->dev);
skb_reset_network_header(skb);
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);
gro_cells_receive(&tunnel->gro_cells, skb);
if (tunnel) {
ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
kfree_skb(skb);
return 0;
......@@ -746,7 +352,7 @@ static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff
skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
return skb;
} else if (skb->ip_summed == CHECKSUM_PARTIAL &&
tunnel->parms.o_flags&GRE_CSUM) {
tunnel->parms.o_flags&TUNNEL_CSUM) {
err = skb_checksum_help(skb);
if (unlikely(err))
goto error;
......@@ -760,480 +366,157 @@ static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff
return ERR_PTR(err);
}
static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *gre_build_header(struct sk_buff *skb,
const struct tnl_ptk_info *tpi,
int hdr_len)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *old_iph;
const struct iphdr *tiph;
struct flowi4 fl4;
u8 tos;
__be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int gre_hlen;
__be32 dst;
int mtu;
u8 ttl;
int err;
skb = handle_offloads(tunnel, skb);
if (IS_ERR(skb)) {
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
if (!skb->encapsulation) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
old_iph = ip_hdr(skb);
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
struct gre_base_hdr *greh;
if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
tiph = (const struct iphdr *)skb->data;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
}
skb_push(skb, hdr_len);
if ((dst = tiph->daddr) == 0) {
/* NBMA tunnel */
greh = (struct gre_base_hdr *)skb->data;
greh->flags = tnl_flags_to_gre_flags(tpi->flags);
greh->protocol = tpi->proto;
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, old_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
if (tpi->flags&TUNNEL_SEQ) {
*ptr = tpi->seq;
ptr--;
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
if (tpi->flags&TUNNEL_KEY) {
*ptr = tpi->key;
ptr--;
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
if (tpi->flags&TUNNEL_CSUM &&
!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
*(__sum16 *)ptr = 0;
*(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
skb->len, 0));
}
#endif
else
goto tx_error;
}
ttl = tiph->ttl;
tos = tiph->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
}
return skb;
}
rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
tunnel->parms.o_key, RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
tdev = rt->dst.dev;
static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params,
__be16 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct tnl_ptk_info tpi;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
df = tiph->frag_off;
if (df)
mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen;
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
tpi.flags = tunnel->parms.o_flags;
tpi.proto = proto;
tpi.key = tunnel->parms.o_key;
if (tunnel->parms.o_flags & TUNNEL_SEQ)
tunnel->o_seqno++;
tpi.seq = htonl(tunnel->o_seqno);
if (skb->protocol == htons(ETH_P_IP)) {
df |= (old_iph->frag_off&htons(IP_DF));
if (!skb_is_gso(skb) &&
(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 IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
if ((tunnel->parms.iph.daddr &&
!ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
}
/* Push GRE header. */
skb = gre_build_header(skb, &tpi, tunnel->hlen);
if (unlikely(!skb)) {
dev->stats.tx_dropped++;
return;
}
if (!skb_is_gso(skb) &&
mtu >= IPV6_MIN_MTU &&
mtu < skb->len - tunnel->hlen + gre_hlen) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
}
#endif
ip_tunnel_xmit(skb, dev, tnl_params);
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tnl_params;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb = handle_offloads(tunnel, skb);
if (IS_ERR(skb))
goto out;
max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;
if (dev->header_ops) {
/* Need space for new headers */
if (skb_cow_head(skb, dev->needed_headroom -
(tunnel->hlen + sizeof(struct iphdr))));
goto free_skb;
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 (max_headroom > dev->needed_headroom)
dev->needed_headroom = 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);
/* Warning : tiph value might point to freed memory */
}
tnl_params = (const struct iphdr *)skb->data;
skb_push(skb, gre_hlen);
skb_reset_network_header(skb);
skb_set_transport_header(skb, sizeof(*iph));
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.
/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
* to gre header.
*/
skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
} else {
if (skb_cow_head(skb, dev->needed_headroom))
goto free_skb;
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = IPPROTO_GRE;
iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
iph->ttl = ttl;
tunnel_ip_select_ident(skb, old_iph, &rt->dst);
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
iph->ttl = old_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
#endif
else
iph->ttl = ip4_dst_hoplimit(&rt->dst);
}
((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
htons(ETH_P_TEB) : skb->protocol;
if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
__be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4);
if (tunnel->parms.o_flags&GRE_SEQ) {
++tunnel->o_seqno;
*ptr = htonl(tunnel->o_seqno);
ptr--;
}
if (tunnel->parms.o_flags&GRE_KEY) {
*ptr = tunnel->parms.o_key;
ptr--;
}
/* Skip GRE checksum if skb is getting offloaded. */
if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) &&
(tunnel->parms.o_flags&GRE_CSUM)) {
int offset = skb_transport_offset(skb);
if (skb_has_shared_frag(skb)) {
err = __skb_linearize(skb);
if (err)
goto tx_error;
tnl_params = &tunnel->parms.iph;
}
*ptr = 0;
*(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
skb->len - offset,
0));
}
}
__gre_xmit(skb, dev, tnl_params, skb->protocol);
iptunnel_xmit(skb, dev);
return NETDEV_TX_OK;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
free_skb:
dev_kfree_skb(skb);
out:
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
static int ipgre_tunnel_bind_dev(struct net_device *dev)
static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
int hlen = LL_MAX_HEADER;
int mtu = ETH_DATA_LEN;
int addend = sizeof(struct iphdr) + 4;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
struct flowi4 fl4;
struct rtable *rt;
rt = ip_route_output_gre(dev_net(dev), &fl4,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
struct ip_tunnel *tunnel = netdev_priv(dev);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
mtu = tdev->mtu;
}
dev->iflink = tunnel->parms.link;
skb = handle_offloads(tunnel, skb);
if (IS_ERR(skb))
goto out;
/* Precalculate GRE options length */
if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
if (tunnel->parms.o_flags&GRE_CSUM)
addend += 4;
if (tunnel->parms.o_flags&GRE_KEY)
addend += 4;
if (tunnel->parms.o_flags&GRE_SEQ)
addend += 4;
}
dev->needed_headroom = addend + hlen;
mtu -= dev->hard_header_len + addend;
if (skb_cow_head(skb, dev->needed_headroom))
goto free_skb;
if (mtu < 68)
mtu = 68;
__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB));
tunnel->hlen = addend;
/* TCP offload with GRE SEQ is not supported. */
if (!(tunnel->parms.o_flags & GRE_SEQ)) {
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
}
return NETDEV_TX_OK;
return mtu;
free_skb:
dev_kfree_skb(skb);
out:
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
static int
ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
static int ipgre_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 ipgre_net *ign = net_generic(net, ipgre_net_id);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
if (dev == ign->fb_tunnel_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
t = ipgre_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;
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;
return -EFAULT;
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
goto done;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
if (!(p.i_flags&GRE_KEY))
p.i_key = 0;
if (!(p.o_flags&GRE_KEY))
p.o_key = 0;
t = ipgre_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
unsigned int nflags = 0;
t = netdev_priv(dev);
if (ipv4_is_multicast(p.iph.daddr))
nflags = IFF_BROADCAST;
else if (p.iph.daddr)
nflags = IFF_POINTOPOINT;
if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
err = -EINVAL;
break;
}
ipgre_tunnel_unlink(ign, t);
synchronize_net();
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
t->parms.i_key = p.i_key;
t->parms.o_key = p.o_key;
memcpy(dev->dev_addr, &p.iph.saddr, 4);
memcpy(dev->broadcast, &p.iph.daddr, 4);
ipgre_tunnel_link(ign, t);
netdev_state_change(dev);
}
}
if (t) {
err = 0;
if (cmd == SIOCCHGTUNNEL) {
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;
dev->mtu = ipgre_tunnel_bind_dev(dev);
netdev_state_change(dev);
}
}
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 == ign->fb_tunnel_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -ENOENT;
if ((t = ipgre_tunnel_locate(net, &p, 0)) == NULL)
goto done;
err = -EPERM;
if (t == netdev_priv(ign->fb_tunnel_dev))
goto done;
dev = t->dev;
}
unregister_netdevice(dev);
err = 0;
break;
default:
err = -EINVAL;
((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) {
return -EINVAL;
}
p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
done:
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
}
static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
if (new_mtu < 68 ||
new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
return -EINVAL;
dev->mtu = new_mtu;
p.i_flags = tnl_flags_to_gre_flags(p.i_flags);
p.o_flags = tnl_flags_to_gre_flags(p.o_flags);
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
return 0;
}
......@@ -1263,25 +546,23 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
...
ftp fec0:6666:6666::193.233.7.65
...
*/
static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr, unsigned int len)
{
struct ip_tunnel *t = netdev_priv(dev);
struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
__be16 *p = (__be16 *)(iph+1);
struct iphdr *iph;
struct gre_base_hdr *greh;
memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
p[0] = t->parms.o_flags;
p[1] = htons(type);
iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph));
greh = (struct gre_base_hdr *)(iph+1);
greh->flags = tnl_flags_to_gre_flags(t->parms.o_flags);
greh->protocol = htons(type);
/*
* Set the source hardware address.
*/
memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
/* Set the source hardware address. */
if (saddr)
memcpy(&iph->saddr, saddr, 4);
if (daddr)
......@@ -1289,7 +570,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
if (iph->daddr)
return t->hlen;
return -t->hlen;
return -(t->hlen + sizeof(*iph));
}
static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
......@@ -1343,31 +624,21 @@ static int ipgre_close(struct net_device *dev)
}
return 0;
}
#endif
static const struct net_device_ops ipgre_netdev_ops = {
.ndo_init = ipgre_tunnel_init,
.ndo_uninit = ipgre_tunnel_uninit,
.ndo_uninit = ip_tunnel_uninit,
#ifdef CONFIG_NET_IPGRE_BROADCAST
.ndo_open = ipgre_open,
.ndo_stop = ipgre_close,
#endif
.ndo_start_xmit = ipgre_tunnel_xmit,
.ndo_start_xmit = ipgre_xmit,
.ndo_do_ioctl = ipgre_tunnel_ioctl,
.ndo_change_mtu = ipgre_tunnel_change_mtu,
.ndo_get_stats64 = ipgre_get_stats64,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipgre_dev_free(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
gro_cells_destroy(&tunnel->gro_cells);
free_percpu(dev->tstats);
free_netdev(dev);
}
#define GRE_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
......@@ -1376,35 +647,49 @@ static void ipgre_dev_free(struct net_device *dev)
static void ipgre_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipgre_netdev_ops;
dev->destructor = ipgre_dev_free;
ip_tunnel_setup(dev, ipgre_net_id);
}
static void __gre_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel;
tunnel = netdev_priv(dev);
tunnel->hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
tunnel->parms.iph.protocol = IPPROTO_GRE;
dev->type = ARPHRD_IPGRE;
dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4;
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->features |= GRE_FEATURES;
dev->features |= NETIF_F_NETNS_LOCAL | GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
/* TCP offload with GRE SEQ is not supported. */
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
/* Can use a lockless transmit, unless we generate
* output sequences
*/
dev->features |= NETIF_F_LLTX;
}
}
static int ipgre_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel;
struct iphdr *iph;
int err;
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
__gre_tunnel_init(dev);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &iph->saddr, 4);
memcpy(dev->broadcast, &iph->daddr, 4);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
dev->type = ARPHRD_IPGRE;
dev->flags = IFF_NOARP;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->addr_len = 4;
if (iph->daddr) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
......@@ -1418,106 +703,30 @@ static int ipgre_tunnel_init(struct net_device *dev)
} else
dev->header_ops = &ipgre_header_ops;
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
err = gro_cells_init(&tunnel->gro_cells, dev);
if (err) {
free_percpu(dev->tstats);
return err;
}
return 0;
}
static void ipgre_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->protocol = IPPROTO_GRE;
iph->ihl = 5;
tunnel->hlen = sizeof(struct iphdr) + 4;
dev_hold(dev);
return ip_tunnel_init(dev);
}
static const struct gre_protocol ipgre_protocol = {
.handler = ipgre_rcv,
.err_handler = ipgre_err,
};
static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
{
int prio;
for (prio = 0; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
struct ip_tunnel *t;
t = rtnl_dereference(ign->tunnels[prio][h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, head);
t = rtnl_dereference(t->next);
}
}
}
}
static int __net_init ipgre_init_net(struct net *net)
{
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int err;
ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
ipgre_tunnel_setup);
if (!ign->fb_tunnel_dev) {
err = -ENOMEM;
goto err_alloc_dev;
}
dev_net_set(ign->fb_tunnel_dev, net);
ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;
if ((err = register_netdev(ign->fb_tunnel_dev)))
goto err_reg_dev;
rcu_assign_pointer(ign->tunnels_wc[0],
netdev_priv(ign->fb_tunnel_dev));
return 0;
err_reg_dev:
ipgre_dev_free(ign->fb_tunnel_dev);
err_alloc_dev:
return err;
return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
}
static void __net_exit ipgre_exit_net(struct net *net)
{
struct ipgre_net *ign;
LIST_HEAD(list);
ign = net_generic(net, ipgre_net_id);
rtnl_lock();
ipgre_destroy_tunnels(ign, &list);
unregister_netdevice_many(&list);
rtnl_unlock();
struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
.exit = ipgre_exit_net,
.id = &ipgre_net_id,
.size = sizeof(struct ipgre_net),
.size = sizeof(struct ip_tunnel_net),
};
static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
......@@ -1562,7 +771,7 @@ static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
return ipgre_tunnel_validate(tb, data);
}
static void ipgre_netlink_parms(struct nlattr *data[],
static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[],
struct ip_tunnel_parm *parms)
{
memset(parms, 0, sizeof(*parms));
......@@ -1576,10 +785,10 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
if (data[IFLA_GRE_IFLAGS])
parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);
parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS]));
if (data[IFLA_GRE_OFLAGS])
parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);
parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS]));
if (data[IFLA_GRE_IKEY])
parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);
......@@ -1603,148 +812,46 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->iph.frag_off = htons(IP_DF);
}
static int ipgre_tap_init(struct net_device *dev)
static int gre_tap_init(struct net_device *dev)
{
struct ip_tunnel *tunnel;
tunnel = netdev_priv(dev);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
ipgre_tunnel_bind_dev(dev);
__gre_tunnel_init(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
return ip_tunnel_init(dev);
}
static const struct net_device_ops ipgre_tap_netdev_ops = {
.ndo_init = ipgre_tap_init,
.ndo_uninit = ipgre_tunnel_uninit,
.ndo_start_xmit = ipgre_tunnel_xmit,
static const struct net_device_ops gre_tap_netdev_ops = {
.ndo_init = gre_tap_init,
.ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = gre_tap_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ipgre_tunnel_change_mtu,
.ndo_get_stats64 = ipgre_get_stats64,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipgre_tap_setup(struct net_device *dev)
{
ether_setup(dev);
dev->netdev_ops = &ipgre_tap_netdev_ops;
dev->destructor = ipgre_dev_free;
dev->iflink = 0;
dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
dev->netdev_ops = &gre_tap_netdev_ops;
ip_tunnel_setup(dev, gre_tap_net_id);
}
static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
static int ipgre_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct ip_tunnel *nt;
struct net *net = dev_net(dev);
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int mtu;
int err;
nt = netdev_priv(dev);
ipgre_netlink_parms(data, &nt->parms);
if (ipgre_tunnel_find(net, &nt->parms, dev->type))
return -EEXIST;
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
mtu = ipgre_tunnel_bind_dev(dev);
if (!tb[IFLA_MTU])
dev->mtu = mtu;
/* Can use a lockless transmit, unless we generate output sequences */
if (!(nt->parms.o_flags & GRE_SEQ))
dev->features |= NETIF_F_LLTX;
err = register_netdevice(dev);
if (err)
goto out;
dev_hold(dev);
ipgre_tunnel_link(ign, nt);
struct ip_tunnel_parm p;
out:
return err;
ipgre_netlink_parms(data, tb, &p);
return ip_tunnel_newlink(dev, tb, &p);
}
static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
struct ip_tunnel *t, *nt;
struct net *net = dev_net(dev);
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
struct ip_tunnel_parm p;
int mtu;
if (dev == ign->fb_tunnel_dev)
return -EINVAL;
nt = netdev_priv(dev);
ipgre_netlink_parms(data, &p);
t = ipgre_tunnel_locate(net, &p, 0);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else {
t = nt;
if (dev->type != ARPHRD_ETHER) {
unsigned int nflags = 0;
if (ipv4_is_multicast(p.iph.daddr))
nflags = IFF_BROADCAST;
else if (p.iph.daddr)
nflags = IFF_POINTOPOINT;
if ((dev->flags ^ nflags) &
(IFF_POINTOPOINT | IFF_BROADCAST))
return -EINVAL;
}
ipgre_tunnel_unlink(ign, t);
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
t->parms.i_key = p.i_key;
if (dev->type != ARPHRD_ETHER) {
memcpy(dev->dev_addr, &p.iph.saddr, 4);
memcpy(dev->broadcast, &p.iph.daddr, 4);
}
ipgre_tunnel_link(ign, t);
netdev_state_change(dev);
}
t->parms.o_key = p.o_key;
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;
mtu = ipgre_tunnel_bind_dev(dev);
if (!tb[IFLA_MTU])
dev->mtu = mtu;
netdev_state_change(dev);
}
return 0;
ipgre_netlink_parms(data, tb, &p);
return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipgre_get_size(const struct net_device *dev)
......@@ -1779,8 +886,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
struct ip_tunnel_parm *p = &t->parms;
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS, tnl_flags_to_gre_flags(p->i_flags)) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(p->o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
......@@ -1818,6 +925,7 @@ static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
.validate = ipgre_tunnel_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
.dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
......@@ -1831,13 +939,28 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
.validate = ipgre_tap_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
.dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
/*
* And now the modules code and kernel interface.
*/
static int __net_init ipgre_tap_init_net(struct net *net)
{
return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL);
}
static void __net_exit ipgre_tap_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipgre_tap_net_ops = {
.init = ipgre_tap_init_net,
.exit = ipgre_tap_exit_net,
.id = &gre_tap_net_id,
.size = sizeof(struct ip_tunnel_net),
};
static int __init ipgre_init(void)
{
......@@ -1849,6 +972,10 @@ static int __init ipgre_init(void)
if (err < 0)
return err;
err = register_pernet_device(&ipgre_tap_net_ops);
if (err < 0)
goto pnet_tap_faied;
err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
if (err < 0) {
pr_info("%s: can't add protocol\n", __func__);
......@@ -1863,16 +990,17 @@ static int __init ipgre_init(void)
if (err < 0)
goto tap_ops_failed;
out:
return err;
return 0;
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
unregister_pernet_device(&ipgre_tap_net_ops);
pnet_tap_faied:
unregister_pernet_device(&ipgre_net_ops);
goto out;
return err;
}
static void __exit ipgre_fini(void)
......@@ -1881,6 +1009,7 @@ static void __exit ipgre_fini(void)
rtnl_link_unregister(&ipgre_link_ops);
if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
pr_info("%s: can't remove protocol\n", __func__);
unregister_pernet_device(&ipgre_tap_net_ops);
unregister_pernet_device(&ipgre_net_ops);
}
......@@ -1890,3 +1019,4 @@ MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
MODULE_ALIAS_NETDEV("gre0");
MODULE_ALIAS_NETDEV("gretap0");
net/ipv4/ip_tunnel.c 0 → 100644
View file @ c5441932
/*
* Copyright (c) 2013 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/rculist.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.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
static unsigned int ip_tunnel_hash(struct ip_tunnel_net *itn,
__be32 key, __be32 remote)
{
return hash_32((__force u32)key ^ (__force u32)remote,
IP_TNL_HASH_BITS);
}
/* Often modified stats are per cpu, other are shared (netdev->stats) */
struct rtnl_link_stats64 *ip_tunnel_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;
tot->collisions = dev->stats.collisions;
return tot;
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
{
if (p->i_flags & TUNNEL_KEY) {
if (flags & TUNNEL_KEY)
return key == p->i_key;
else
/* key expected, none present */
return false;
} else
return !(flags & TUNNEL_KEY);
}
/* Fallback tunnel: no source, no destination, no key, no options
Tunnel hash table:
We require exact key match i.e. if a key is present in packet
it will match only tunnel with the same key; if it is not present,
it will match only keyless tunnel.
All keysless packets, if not matched configured keyless tunnels
will match fallback tunnel.
Given src, dst and key, find appropriate for input tunnel.
*/
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
int link, __be16 flags,
__be32 remote, __be32 local,
__be32 key)
{
unsigned int hash;
struct ip_tunnel *t, *cand = NULL;
struct hlist_head *head;
hash = ip_tunnel_hash(itn, key, remote);
head = &itn->tunnels[hash];
hlist_for_each_entry_rcu(t, head, hash_node) {
if (local != t->parms.iph.saddr ||
remote != t->parms.iph.daddr ||
!(t->dev->flags & IFF_UP))
continue;
if (!ip_tunnel_key_match(&t->parms, flags, key))
continue;
if (t->parms.link == link)
return t;
else
cand = t;
}
hlist_for_each_entry_rcu(t, head, hash_node) {
if (remote != t->parms.iph.daddr ||
!(t->dev->flags & IFF_UP))
continue;
if (!ip_tunnel_key_match(&t->parms, flags, key))
continue;
if (t->parms.link == link)
return t;
else if (!cand)
cand = t;
}
hash = ip_tunnel_hash(itn, key, 0);
head = &itn->tunnels[hash];
hlist_for_each_entry_rcu(t, head, hash_node) {
if ((local != t->parms.iph.saddr &&
(local != t->parms.iph.daddr ||
!ipv4_is_multicast(local))) ||
!(t->dev->flags & IFF_UP))
continue;
if (!ip_tunnel_key_match(&t->parms, flags, key))
continue;
if (t->parms.link == link)
return t;
else if (!cand)
cand = t;
}
if (flags & TUNNEL_NO_KEY)
goto skip_key_lookup;
hlist_for_each_entry_rcu(t, head, hash_node) {
if (t->parms.i_key != key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->parms.link == link)
return t;
else if (!cand)
cand = t;
}
skip_key_lookup:
if (cand)
return cand;
if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
return netdev_priv(itn->fb_tunnel_dev);
return NULL;
}
EXPORT_SYMBOL_GPL(ip_tunnel_lookup);
static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
struct ip_tunnel_parm *parms)
{
unsigned int h;
__be32 remote;
if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
remote = parms->iph.daddr;
else
remote = 0;
h = ip_tunnel_hash(itn, parms->i_key, remote);
return &itn->tunnels[h];
}
static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t)
{
struct hlist_head *head = ip_bucket(itn, &t->parms);
hlist_add_head_rcu(&t->hash_node, head);
}
static void ip_tunnel_del(struct ip_tunnel *t)
{
hlist_del_init_rcu(&t->hash_node);
}
static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
struct ip_tunnel_parm *parms,
int type)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
int link = parms->link;
struct ip_tunnel *t = NULL;
struct hlist_head *head = ip_bucket(itn, parms);
hlist_for_each_entry_rcu(t, head, hash_node) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
key == t->parms.i_key &&
link == t->parms.link &&
type == t->dev->type)
break;
}
return t;
}
static struct net_device *__ip_tunnel_create(struct net *net,
const struct rtnl_link_ops *ops,
struct ip_tunnel_parm *parms)
{
int err;
struct ip_tunnel *tunnel;
struct net_device *dev;
char name[IFNAMSIZ];
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else {
if (strlen(ops->kind) + 3 >= IFNAMSIZ) {
err = -E2BIG;
goto failed;
}
strlcpy(name, ops->kind, IFNAMSIZ);
strncat(name, "%d", 2);
}
ASSERT_RTNL();
dev = alloc_netdev(ops->priv_size, name, ops->setup);
if (!dev) {
err = -ENOMEM;
goto failed;
}
dev_net_set(dev, net);
dev->rtnl_link_ops = ops;
tunnel = netdev_priv(dev);
tunnel->parms = *parms;
err = register_netdevice(dev);
if (err)
goto failed_free;
return dev;
failed_free:
free_netdev(dev);
failed:
return ERR_PTR(err);
}
static inline struct rtable *ip_route_output_tunnel(struct net *net,
struct flowi4 *fl4,
int proto,
__be32 daddr, __be32 saddr,
__be32 key, __u8 tos, int oif)
{
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_oif = oif;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->flowi4_tos = tos;
fl4->flowi4_proto = proto;
fl4->fl4_gre_key = key;
return ip_route_output_key(net, fl4);
}
static int ip_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *iph;
int hlen = LL_MAX_HEADER;
int mtu = ETH_DATA_LEN;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
iph = &tunnel->parms.iph;
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
struct flowi4 fl4;
struct rtable *rt;
rt = ip_route_output_tunnel(dev_net(dev), &fl4,
tunnel->parms.iph.protocol,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
mtu = tdev->mtu;
}
dev->iflink = tunnel->parms.link;
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
if (mtu < 68)
mtu = 68;
return mtu;
}
static struct ip_tunnel *ip_tunnel_create(struct net *net,
struct ip_tunnel_net *itn,
struct ip_tunnel_parm *parms)
{
struct ip_tunnel *nt, *fbt;
struct net_device *dev;
BUG_ON(!itn->fb_tunnel_dev);
fbt = netdev_priv(itn->fb_tunnel_dev);
dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
if (IS_ERR(dev))
return NULL;
dev->mtu = ip_tunnel_bind_dev(dev);
nt = netdev_priv(dev);
ip_tunnel_add(itn, nt);
return nt;
}
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi, bool log_ecn_error)
{
struct pcpu_tstats *tstats;
const struct iphdr *iph = ip_hdr(skb);
int err;
secpath_reset(skb);
skb->protocol = tpi->proto;
skb->mac_header = skb->network_header;
__pskb_pull(skb, tunnel->hlen);
skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (rt_is_output_route(skb_rtable(skb)))
goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
tunnel->dev->stats.rx_crc_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&TUNNEL_SEQ) {
if (!(tpi->flags&TUNNEL_SEQ) ||
(tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
tunnel->dev->stats.rx_fifo_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
tunnel->dev->stats.rx_length_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
skb->pkt_type = PACKET_HOST;
__skb_tunnel_rx(skb, tunnel->dev);
skb_reset_network_header(skb);
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);
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
drop:
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct iphdr *iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int mtu;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
rt = ip_route_output_tunnel(dev_net(dev), &fl4,
tunnel->parms.iph.protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
df = tnl_params->frag_off;
if (df)
mtu = dst_mtu(&rt->dst) - dev->hard_header_len
- sizeof(struct iphdr);
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
df |= (inner_iph->frag_off&htons(IP_DF));
if (!skb_is_gso(skb) &&
(inner_iph->frag_off&htons(IP_DF)) &&
mtu < ntohs(inner_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
mtu >= IPV6_MIN_MTU) {
if ((tunnel->parms.iph.daddr &&
!ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
}
}
if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
mtu < skb->len) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
}
#endif
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;
}
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
+ rt->dst.header_len;
if (max_headroom > dev->needed_headroom) {
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return;
}
}
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = tnl_params->protocol;
iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
iph->ttl = ttl;
tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
iptunnel_xmit(skb, dev);
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(ip_tunnel_xmit);
static void ip_tunnel_update(struct ip_tunnel_net *itn,
struct ip_tunnel *t,
struct net_device *dev,
struct ip_tunnel_parm *p,
bool set_mtu)
{
ip_tunnel_del(t);
t->parms.iph.saddr = p->iph.saddr;
t->parms.iph.daddr = p->iph.daddr;
t->parms.i_key = p->i_key;
t->parms.o_key = p->o_key;
if (dev->type != ARPHRD_ETHER) {
memcpy(dev->dev_addr, &p->iph.saddr, 4);
memcpy(dev->broadcast, &p->iph.daddr, 4);
}
ip_tunnel_add(itn, 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) {
int mtu;
t->parms.link = p->link;
mtu = ip_tunnel_bind_dev(dev);
if (set_mtu)
dev->mtu = mtu;
}
netdev_state_change(dev);
}
int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
{
int err = 0;
struct ip_tunnel *t;
struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
BUG_ON(!itn->fb_tunnel_dev);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
if (dev == itn->fb_tunnel_dev)
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (t == NULL)
t = netdev_priv(dev);
memcpy(p, &t->parms, sizeof(*p));
break;
case SIOCADDTUNNEL:
case SIOCCHGTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
if (p->iph.ttl)
p->iph.frag_off |= htons(IP_DF);
if (!(p->i_flags&TUNNEL_KEY))
p->i_key = 0;
if (!(p->o_flags&TUNNEL_KEY))
p->o_key = 0;
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (!t && (cmd == SIOCADDTUNNEL))
t = ip_tunnel_create(net, itn, p);
if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
unsigned int nflags = 0;
if (ipv4_is_multicast(p->iph.daddr))
nflags = IFF_BROADCAST;
else if (p->iph.daddr)
nflags = IFF_POINTOPOINT;
if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
err = -EINVAL;
break;
}
t = netdev_priv(dev);
}
}
if (t) {
err = 0;
ip_tunnel_update(itn, t, dev, p, true);
} else
err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
break;
case SIOCDELTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
if (dev == itn->fb_tunnel_dev) {
err = -ENOENT;
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (t == NULL)
goto done;
err = -EPERM;
if (t == netdev_priv(itn->fb_tunnel_dev))
goto done;
dev = t->dev;
}
unregister_netdevice(dev);
err = 0;
break;
default:
err = -EINVAL;
}
done:
return err;
}
EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
if (new_mtu < 68 ||
new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
static void ip_tunnel_dev_free(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
gro_cells_destroy(&tunnel->gro_cells);
free_percpu(dev->tstats);
free_netdev(dev);
}
void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
{
struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn;
itn = net_generic(net, tunnel->ip_tnl_net_id);
if (itn->fb_tunnel_dev != dev) {
ip_tunnel_del(netdev_priv(dev));
unregister_netdevice_queue(dev, head);
}
}
EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname)
{
struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
struct ip_tunnel_parm parms;
itn->tunnels = kzalloc(IP_TNL_HASH_SIZE * sizeof(struct hlist_head), GFP_KERNEL);
if (!itn->tunnels)
return -ENOMEM;
if (!ops) {
itn->fb_tunnel_dev = NULL;
return 0;
}
memset(&parms, 0, sizeof(parms));
if (devname)
strlcpy(parms.name, devname, IFNAMSIZ);
rtnl_lock();
itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
rtnl_unlock();
if (IS_ERR(itn->fb_tunnel_dev)) {
kfree(itn->tunnels);
return PTR_ERR(itn->fb_tunnel_dev);
}
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
{
int h;
for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
struct ip_tunnel *t;
struct hlist_node *n;
struct hlist_head *thead = &itn->tunnels[h];
hlist_for_each_entry_safe(t, n, thead, hash_node)
unregister_netdevice_queue(t->dev, head);
}
if (itn->fb_tunnel_dev)
unregister_netdevice_queue(itn->fb_tunnel_dev, head);
}
void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn)
{
LIST_HEAD(list);
rtnl_lock();
ip_tunnel_destroy(itn, &list);
unregister_netdevice_many(&list);
rtnl_unlock();
kfree(itn->tunnels);
}
EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p)
{
struct ip_tunnel *nt;
struct net *net = dev_net(dev);
struct ip_tunnel_net *itn;
int mtu;
int err;
nt = netdev_priv(dev);
itn = net_generic(net, nt->ip_tnl_net_id);
if (ip_tunnel_find(itn, p, dev->type))
return -EEXIST;
nt->parms = *p;
err = register_netdevice(dev);
if (err)
goto out;
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
mtu = ip_tunnel_bind_dev(dev);
if (!tb[IFLA_MTU])
dev->mtu = mtu;
ip_tunnel_add(itn, nt);
out:
return err;
}
EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p)
{
struct ip_tunnel *t, *nt;
struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
if (dev == itn->fb_tunnel_dev)
return -EINVAL;
nt = netdev_priv(dev);
t = ip_tunnel_find(itn, p, dev->type);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else {
t = nt;
if (dev->type != ARPHRD_ETHER) {
unsigned int nflags = 0;
if (ipv4_is_multicast(p->iph.daddr))
nflags = IFF_BROADCAST;
else if (p->iph.daddr)
nflags = IFF_POINTOPOINT;
if ((dev->flags ^ nflags) &
(IFF_POINTOPOINT | IFF_BROADCAST))
return -EINVAL;
}
}
ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
int ip_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
int err;
dev->destructor = ip_tunnel_dev_free;
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
err = gro_cells_init(&tunnel->gro_cells, dev);
if (err) {
free_percpu(dev->tstats);
return err;
}
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->ihl = 5;
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_init);
void ip_tunnel_uninit(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn;
itn = net_generic(net, tunnel->ip_tnl_net_id);
/* fb_tunnel_dev will be unregisted in net-exit call. */
if (itn->fb_tunnel_dev != dev)
ip_tunnel_del(netdev_priv(dev));
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
/* Do least required initialization, rest of init is done in tunnel_init call */
void ip_tunnel_setup(struct net_device *dev, int net_id)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->ip_tnl_net_id = net_id;
}
EXPORT_SYMBOL_GPL(ip_tunnel_setup);
MODULE_LICENSE("GPL");
net/ipv4/ip_vti.c
View file @ c5441932
......@@ -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>
......
net/ipv4/ipip.c
View file @ c5441932
......@@ -111,7 +111,7 @@
#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>
......
net/ipv4/ipmr.c
View file @ c5441932
......@@ -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>
......
net/ipv6/af_inet6.c
View file @ c5441932
......@@ -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>
......
net/ipv6/ip6_gre.c
View file @ c5441932
......@@ -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>
......
net/ipv6/ip6_tunnel.c
View file @ c5441932
......@@ -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>
......
net/ipv6/sit.c
View file @ c5441932
......@@ -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>
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7