Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-23 04:31:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.

Browse Source 
The Bareudp tunnel module provides a generic L3 encapsulation
tunnelling module for tunnelling different protocols like MPLS,
IP,NSH etc inside a UDP tunnel.

Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Martin Varghese 2020-02-24 10:57:50 +05:30 committed by David S. Miller
parent 48851e9e80
commit 571912c69f
11 changed files with 952 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
Documentation/networking/bareudp.rst Normal file
View File

@ -0,0 +1,34 @@
.. SPDX-License-Identifier: GPL-2.0
========================================
Bare UDP Tunnelling Module Documentation
========================================
There are various L3 encapsulation standards using UDP being discussed to
leverage the UDP based load balancing capability of different networks.
MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.
The Bareudp tunnel module provides a generic L3 encapsulation tunnelling
support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside
a UDP tunnel.
Usage
------
1) Device creation & deletion
a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847.
This creates a bareudp tunnel device which tunnels L3 traffic with ethertype
0x8847 (MPLS traffic). The destination port of the UDP header will be set to
6635.The device will listen on UDP port 6635 to receive traffic.
b) ip link delete bareudp0
2) Device Usage
The bareudp device could be used along with OVS or flower filter in TC.
The OVS or TC flower layer must set the tunnel information in SKB dst field before
sending packet buffer to the bareudp device for transmission. On reception the
bareudp device extracts and stores the tunnel information in SKB dst field before
passing the packet buffer to the network stack.

1
Documentation/networking/index.rst
View File

@ -8,6 +8,7 @@ Contents:
netdev-FAQ
af_xdp
bareudp
batman-adv
can
can_ucan_protocol

13
drivers/net/Kconfig
View File

@ -258,6 +258,19 @@ config GENEVE
To compile this driver as a module, choose M here: the module
will be called geneve.
config BAREUDP
tristate "Bare UDP Encapsulation"
depends on INET
depends on IPV6 || !IPV6
select NET_UDP_TUNNEL
select GRO_CELLS
help
This adds a bare UDP tunnel module for tunnelling different
kinds of traffic like MPLS, IP, etc. inside a UDP tunnel.
To compile this driver as a module, choose M here: the module
will be called bareudp.
config GTP
tristate "GPRS Tunneling Protocol datapath (GTP-U)"
depends on INET

1
drivers/net/Makefile
View File

@ -29,6 +29,7 @@ obj-$(CONFIG_VETH) += veth.o
obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
obj-$(CONFIG_VXLAN) += vxlan.o
obj-$(CONFIG_GENEVE) += geneve.o
obj-$(CONFIG_BAREUDP) += bareudp.o
obj-$(CONFIG_GTP) += gtp.o
obj-$(CONFIG_NLMON) += nlmon.o
obj-$(CONFIG_NET_VRF) += vrf.o

743
drivers/net/bareudp.c Normal file
View File

@ -0,0 +1,743 @@
// SPDX-License-Identifier: GPL-2.0
/* Bareudp: UDP tunnel encasulation for different Payload types like
* MPLS, NSH, IP, etc.
* Copyright (c) 2019 Nokia, Inc.
* Authors: Martin Varghese, <martin.varghese@nokia.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/etherdevice.h>
#include <linux/hash.h>
#include <net/dst_metadata.h>
#include <net/gro_cells.h>
#include <net/rtnetlink.h>
#include <net/protocol.h>
#include <net/ip6_tunnel.h>
#include <net/ip_tunnels.h>
#include <net/udp_tunnel.h>
#include <net/bareudp.h>
#define BAREUDP_BASE_HLEN sizeof(struct udphdr)
#define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \
sizeof(struct udphdr))
#define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \
sizeof(struct udphdr))
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");
/* per-network namespace private data for this module */
static unsigned int bareudp_net_id;
struct bareudp_net {
struct list_head bareudp_list;
};
/* Pseudo network device */
struct bareudp_dev {
struct net *net; /* netns for packet i/o */
struct net_device *dev; /* netdev for bareudp tunnel */
__be16 ethertype;
__be16 port;
u16 sport_min;
struct socket __rcu *sock;
struct list_head next; /* bareudp node on namespace list */
struct gro_cells gro_cells;
};
static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct metadata_dst *tun_dst = NULL;
struct pcpu_sw_netstats *stats;
struct bareudp_dev *bareudp;
unsigned short family;
unsigned int len;
__be16 proto;
void *oiph;
int err;
bareudp = rcu_dereference_sk_user_data(sk);
if (!bareudp)
goto drop;
if (skb->protocol == htons(ETH_P_IP))
family = AF_INET;
else
family = AF_INET6;
proto = bareudp->ethertype;
if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN,
proto,
!net_eq(bareudp->net,
dev_net(bareudp->dev)))) {
bareudp->dev->stats.rx_dropped++;
goto drop;
}
tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0);
if (!tun_dst) {
bareudp->dev->stats.rx_dropped++;
goto drop;
}
skb_dst_set(skb, &tun_dst->dst);
skb->dev = bareudp->dev;
oiph = skb_network_header(skb);
skb_reset_network_header(skb);
if (family == AF_INET)
err = IP_ECN_decapsulate(oiph, skb);
#if IS_ENABLED(CONFIG_IPV6)
else
err = IP6_ECN_decapsulate(oiph, skb);
#endif
if (unlikely(err)) {
if (log_ecn_error) {
if (family == AF_INET)
net_info_ratelimited("non-ECT from %pI4 "
"with TOS=%#x\n",
&((struct iphdr *)oiph)->saddr,
((struct iphdr *)oiph)->tos);
#if IS_ENABLED(CONFIG_IPV6)
else
net_info_ratelimited("non-ECT from %pI6\n",
&((struct ipv6hdr *)oiph)->saddr);
#endif
}
if (err > 1) {
++bareudp->dev->stats.rx_frame_errors;
++bareudp->dev->stats.rx_errors;
goto drop;
}
}
len = skb->len;
err = gro_cells_receive(&bareudp->gro_cells, skb);
if (likely(err == NET_RX_SUCCESS)) {
stats = this_cpu_ptr(bareudp->dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += len;
u64_stats_update_end(&stats->syncp);
}
return 0;
drop:
/* Consume bad packet */
kfree_skb(skb);
return 0;
}
static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb)
{
return 0;
}
static int bareudp_init(struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
int err;
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
err = gro_cells_init(&bareudp->gro_cells, dev);
if (err) {
free_percpu(dev->tstats);
return err;
}
return 0;
}
static void bareudp_uninit(struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
gro_cells_destroy(&bareudp->gro_cells);
free_percpu(dev->tstats);
}
static struct socket *bareudp_create_sock(struct net *net, __be16 port)
{
struct udp_port_cfg udp_conf;
struct socket *sock;
int err;
memset(&udp_conf, 0, sizeof(udp_conf));
#if IS_ENABLED(CONFIG_IPV6)
udp_conf.family = AF_INET6;
#else
udp_conf.family = AF_INET;
#endif
udp_conf.local_udp_port = port;
/* Open UDP socket */
err = udp_sock_create(net, &udp_conf, &sock);
if (err < 0)
return ERR_PTR(err);
return sock;
}
/* Create new listen socket if needed */
static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port)
{
struct udp_tunnel_sock_cfg tunnel_cfg;
struct socket *sock;
sock = bareudp_create_sock(bareudp->net, port);
if (IS_ERR(sock))
return PTR_ERR(sock);
/* Mark socket as an encapsulation socket */
memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
tunnel_cfg.sk_user_data = bareudp;
tunnel_cfg.encap_type = 1;
tunnel_cfg.encap_rcv = bareudp_udp_encap_recv;
tunnel_cfg.encap_err_lookup = bareudp_err_lookup;
tunnel_cfg.encap_destroy = NULL;
setup_udp_tunnel_sock(bareudp->net, sock, &tunnel_cfg);
if (sock->sk->sk_family == AF_INET6)
udp_encap_enable();
rcu_assign_pointer(bareudp->sock, sock);
return 0;
}
static int bareudp_open(struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
int ret = 0;
ret = bareudp_socket_create(bareudp, bareudp->port);
return ret;
}
static void bareudp_sock_release(struct bareudp_dev *bareudp)
{
struct socket *sock;
sock = bareudp->sock;
rcu_assign_pointer(bareudp->sock, NULL);
synchronize_net();
udp_tunnel_sock_release(sock);
}
static int bareudp_stop(struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
bareudp_sock_release(bareudp);
return 0;
}
static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct bareudp_dev *bareudp,
const struct ip_tunnel_info *info)
{
bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev));
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct socket *sock = rcu_dereference(bareudp->sock);
bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
const struct ip_tunnel_key *key = &info->key;
struct rtable *rt;
__be16 sport, df;
int min_headroom;
__u8 tos, ttl;
__be32 saddr;
int err;
if (!sock)
return -ESHUTDOWN;
rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr, info,
IPPROTO_UDP, use_cache);
if (IS_ERR(rt))
return PTR_ERR(rt);
skb_tunnel_check_pmtu(skb, &rt->dst,
BAREUDP_IPV4_HLEN + info->options_len);
sport = udp_flow_src_port(bareudp->net, skb,
bareudp->sport_min, USHRT_MAX,
true);
tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
skb_scrub_packet(skb, xnet);
if (!skb_pull(skb, skb_network_offset(skb)))
goto free_dst;
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len +
BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr);
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
goto free_dst;
err = udp_tunnel_handle_offloads(skb, udp_sum);
if (err)
goto free_dst;
skb_set_inner_protocol(skb, bareudp->ethertype);
udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst,
tos, ttl, df, sport, bareudp->port,
!net_eq(bareudp->net, dev_net(bareudp->dev)),
!(info->key.tun_flags & TUNNEL_CSUM));
return 0;
free_dst:
dst_release(&rt->dst);
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct bareudp_dev *bareudp,
const struct ip_tunnel_info *info)
{
bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev));
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct socket *sock = rcu_dereference(bareudp->sock);
bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
const struct ip_tunnel_key *key = &info->key;
struct dst_entry *dst = NULL;
struct in6_addr saddr, daddr;
int min_headroom;
__u8 prio, ttl;
__be16 sport;
int err;
if (!sock)
return -ESHUTDOWN;
dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, &saddr, info,
IPPROTO_UDP, use_cache);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len);
sport = udp_flow_src_port(bareudp->net, skb,
bareudp->sport_min, USHRT_MAX,
true);
prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
skb_scrub_packet(skb, xnet);
if (!skb_pull(skb, skb_network_offset(skb)))
goto free_dst;
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len +
BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr);
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
goto free_dst;
err = udp_tunnel_handle_offloads(skb, udp_sum);
if (err)
goto free_dst;
daddr = info->key.u.ipv6.dst;
udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev,
&saddr, &daddr, prio, ttl,
info->key.label, sport, bareudp->port,
!(info->key.tun_flags & TUNNEL_CSUM));
return 0;
free_dst:
dst_release(dst);
return err;
}
#endif
static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
struct ip_tunnel_info *info = NULL;
int err;
if (skb->protocol != bareudp->ethertype) {
err = -EINVAL;
goto tx_error;
}
info = skb_tunnel_info(skb);
if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
err = -EINVAL;
goto tx_error;
}
rcu_read_lock();
#if IS_ENABLED(CONFIG_IPV6)
if (info->mode & IP_TUNNEL_INFO_IPV6)
err = bareudp6_xmit_skb(skb, dev, bareudp, info);
else
#endif
err = bareudp_xmit_skb(skb, dev, bareudp, info);
rcu_read_unlock();
if (likely(!err))
return NETDEV_TX_OK;
tx_error:
dev_kfree_skb(skb);
if (err == -ELOOP)
dev->stats.collisions++;
else if (err == -ENETUNREACH)
dev->stats.tx_carrier_errors++;
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
static int bareudp_fill_metadata_dst(struct net_device *dev,
struct sk_buff *skb)
{
struct ip_tunnel_info *info = skb_tunnel_info(skb);
struct bareudp_dev *bareudp = netdev_priv(dev);
bool use_cache;
use_cache = ip_tunnel_dst_cache_usable(skb, info);
if (ip_tunnel_info_af(info) == AF_INET) {
struct rtable *rt;
__be32 saddr;
rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr,
info, IPPROTO_UDP, use_cache);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
info->key.u.ipv4.src = saddr;
#if IS_ENABLED(CONFIG_IPV6)
} else if (ip_tunnel_info_af(info) == AF_INET6) {
struct dst_entry *dst;
struct in6_addr saddr;
struct socket *sock = rcu_dereference(bareudp->sock);
dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock,
&saddr, info, IPPROTO_UDP,
use_cache);
if (IS_ERR(dst))
return PTR_ERR(dst);
dst_release(dst);
info->key.u.ipv6.src = saddr;
#endif
} else {
return -EINVAL;
}
info->key.tp_src = udp_flow_src_port(bareudp->net, skb,
bareudp->sport_min,
USHRT_MAX, true);
info->key.tp_dst = bareudp->port;
return 0;
}
static const struct net_device_ops bareudp_netdev_ops = {
.ndo_init = bareudp_init,
.ndo_uninit = bareudp_uninit,
.ndo_open = bareudp_open,
.ndo_stop = bareudp_stop,
.ndo_start_xmit = bareudp_xmit,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_fill_metadata_dst = bareudp_fill_metadata_dst,
};
static const struct nla_policy bareudp_policy[IFLA_BAREUDP_MAX + 1] = {
[IFLA_BAREUDP_PORT] = { .type = NLA_U16 },
[IFLA_BAREUDP_ETHERTYPE] = { .type = NLA_U16 },
[IFLA_BAREUDP_SRCPORT_MIN] = { .type = NLA_U16 },
};
/* Info for udev, that this is a virtual tunnel endpoint */
static struct device_type bareudp_type = {
.name = "bareudp",
};
/* Initialize the device structure. */
static void bareudp_setup(struct net_device *dev)
{
dev->netdev_ops = &bareudp_netdev_ops;
dev->needs_free_netdev = true;
SET_NETDEV_DEVTYPE(dev, &bareudp_type);
dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
dev->features |= NETIF_F_RXCSUM;
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
dev->hard_header_len = 0;
dev->addr_len = 0;
dev->mtu = ETH_DATA_LEN;
dev->min_mtu = IPV4_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - BAREUDP_BASE_HLEN;
dev->type = ARPHRD_NONE;
netif_keep_dst(dev);
dev->priv_flags |= IFF_NO_QUEUE;
dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
}
static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
if (!data) {
NL_SET_ERR_MSG(extack,
"Not enough attributes provided to perform the operation");
return -EINVAL;
}
return 0;
}
static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf)
{
if (!data[IFLA_BAREUDP_PORT] || !data[IFLA_BAREUDP_ETHERTYPE])
return -EINVAL;
if (data[IFLA_BAREUDP_PORT])
conf->port = nla_get_u16(data[IFLA_BAREUDP_PORT]);
if (data[IFLA_BAREUDP_ETHERTYPE])
conf->ethertype = nla_get_u16(data[IFLA_BAREUDP_ETHERTYPE]);
if (data[IFLA_BAREUDP_SRCPORT_MIN])
conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]);
return 0;
}
static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn,
const struct bareudp_conf *conf)
{
struct bareudp_dev *bareudp, *t = NULL;
list_for_each_entry(bareudp, &bn->bareudp_list, next) {
if (conf->port == bareudp->port)
t = bareudp;
}
return t;
}
static int bareudp_configure(struct net *net, struct net_device *dev,
struct bareudp_conf *conf)
{
struct bareudp_net *bn = net_generic(net, bareudp_net_id);
struct bareudp_dev *t, *bareudp = netdev_priv(dev);
int err;
bareudp->net = net;
bareudp->dev = dev;
t = bareudp_find_dev(bn, conf);
if (t)
return -EBUSY;
bareudp->port = conf->port;
bareudp->ethertype = conf->ethertype;
bareudp->sport_min = conf->sport_min;
err = register_netdevice(dev);
if (err)
return err;
list_add(&bareudp->next, &bn->bareudp_list);
return 0;
}
static int bareudp_link_config(struct net_device *dev,
struct nlattr *tb[])
{
int err;
if (tb[IFLA_MTU]) {
err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
if (err)
return err;
}
return 0;
}
static int bareudp_newlink(struct net *net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct bareudp_conf conf;
int err;
err = bareudp2info(data, &conf);
if (err)
return err;
err = bareudp_configure(net, dev, &conf);
if (err)
return err;
err = bareudp_link_config(dev, tb);
if (err)
return err;
return 0;
}
static void bareudp_dellink(struct net_device *dev, struct list_head *head)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
list_del(&bareudp->next);
unregister_netdevice_queue(dev, head);
}
static size_t bareudp_get_size(const struct net_device *dev)
{
return nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_PORT */
nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_ETHERTYPE */
nla_total_size(sizeof(__u16)) + /* IFLA_BAREUDP_SRCPORT_MIN */
0;
}
static int bareudp_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct bareudp_dev *bareudp = netdev_priv(dev);
if (nla_put_be16(skb, IFLA_BAREUDP_PORT, bareudp->port))
goto nla_put_failure;
if (nla_put_be16(skb, IFLA_BAREUDP_ETHERTYPE, bareudp->ethertype))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_BAREUDP_SRCPORT_MIN, bareudp->sport_min))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static struct rtnl_link_ops bareudp_link_ops __read_mostly = {
.kind = "bareudp",
.maxtype = IFLA_BAREUDP_MAX,
.policy = bareudp_policy,
.priv_size = sizeof(struct bareudp_dev),
.setup = bareudp_setup,
.validate = bareudp_validate,
.newlink = bareudp_newlink,
.dellink = bareudp_dellink,
.get_size = bareudp_get_size,
.fill_info = bareudp_fill_info,
};
struct net_device *bareudp_dev_create(struct net *net, const char *name,
u8 name_assign_type,
struct bareudp_conf *conf)
{
struct nlattr *tb[IFLA_MAX + 1];
struct net_device *dev;
LIST_HEAD(list_kill);
int err;
memset(tb, 0, sizeof(tb));
dev = rtnl_create_link(net, name, name_assign_type,
&bareudp_link_ops, tb, NULL);
if (IS_ERR(dev))
return dev;
err = bareudp_configure(net, dev, conf);
if (err) {
free_netdev(dev);
return ERR_PTR(err);
}
err = dev_set_mtu(dev, IP_MAX_MTU - BAREUDP_BASE_HLEN);
if (err)
goto err;
err = rtnl_configure_link(dev, NULL);
if (err < 0)
goto err;
return dev;
err:
bareudp_dellink(dev, &list_kill);
unregister_netdevice_many(&list_kill);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(bareudp_dev_create);
static __net_init int bareudp_init_net(struct net *net)
{
struct bareudp_net *bn = net_generic(net, bareudp_net_id);
INIT_LIST_HEAD(&bn->bareudp_list);
return 0;
}
static void bareudp_destroy_tunnels(struct net *net, struct list_head *head)
{
struct bareudp_net *bn = net_generic(net, bareudp_net_id);
struct bareudp_dev *bareudp, *next;
list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next)
unregister_netdevice_queue(bareudp->dev, head);
}
static void __net_exit bareudp_exit_batch_net(struct list_head *net_list)
{
struct net *net;
LIST_HEAD(list);
rtnl_lock();
list_for_each_entry(net, net_list, exit_list)
bareudp_destroy_tunnels(net, &list);
/* unregister the devices gathered above */
unregister_netdevice_many(&list);
rtnl_unlock();
}
static struct pernet_operations bareudp_net_ops = {
.init = bareudp_init_net,
.exit_batch = bareudp_exit_batch_net,
.id = &bareudp_net_id,
.size = sizeof(struct bareudp_net),
};
static int __init bareudp_init_module(void)
{
int rc;
rc = register_pernet_subsys(&bareudp_net_ops);
if (rc)
goto out1;
rc = rtnl_link_register(&bareudp_link_ops);
if (rc)
goto out2;
return 0;
out2:
unregister_pernet_subsys(&bareudp_net_ops);
out1:
return rc;
}
late_initcall(bareudp_init_module);
static void __exit bareudp_cleanup_module(void)
{
rtnl_link_unregister(&bareudp_link_ops);
unregister_pernet_subsys(&bareudp_net_ops);
}
module_exit(bareudp_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Martin Varghese <martin.varghese@nokia.com>");
MODULE_DESCRIPTION("Interface driver for UDP encapsulated traffic");

19
include/net/bareudp.h Normal file
View File

@ -0,0 +1,19 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_BAREUDP_H
#define __NET_BAREUDP_H
#include <linux/types.h>
#include <linux/skbuff.h>
struct bareudp_conf {
__be16 ethertype;
__be16 port;
u16 sport_min;
};
struct net_device *bareudp_dev_create(struct net *net, const char *name,
u8 name_assign_type,
struct bareudp_conf *info);
#endif

6
include/net/ipv6.h
View File

@ -1027,6 +1027,12 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst,
bool connected);
struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
struct net_device *dev,
struct net *net, struct socket *sock,
struct in6_addr *saddr,
const struct ip_tunnel_info *info,
u8 protocol, bool use_cache);
struct dst_entry *ip6_blackhole_route(struct net *net,
struct dst_entry *orig_dst);

6
include/net/route.h
View File

@ -128,6 +128,12 @@ static inline struct rtable *__ip_route_output_key(struct net *net,
struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
const struct sock *sk);
struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
struct net_device *dev,
struct net *net, __be32 *saddr,
const struct ip_tunnel_info *info,
u8 protocol, bool use_cache);
struct dst_entry *ipv4_blackhole_route(struct net *net,
struct dst_entry *dst_orig);

11
include/uapi/linux/if_link.h
View File

@ -590,6 +590,17 @@ enum ifla_geneve_df {
GENEVE_DF_MAX = __GENEVE_DF_END - 1,
};
/* Bareudp section */
enum {
IFLA_BAREUDP_UNSPEC,
IFLA_BAREUDP_PORT,
IFLA_BAREUDP_ETHERTYPE,
IFLA_BAREUDP_SRCPORT_MIN,
__IFLA_BAREUDP_MAX
};
#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
/* PPP section */
enum {
IFLA_PPP_UNSPEC,

48
net/ipv4/route.c
View File

@ -2774,6 +2774,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
struct net_device *dev,
struct net *net, __be32 *saddr,
const struct ip_tunnel_info *info,
u8 protocol, bool use_cache)
{
#ifdef CONFIG_DST_CACHE
struct dst_cache *dst_cache;
#endif
struct rtable *rt = NULL;
struct flowi4 fl4;
__u8 tos;
#ifdef CONFIG_DST_CACHE
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
rt = dst_cache_get_ip4(dst_cache, saddr);
if (rt)
return rt;
}
#endif
memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_mark = skb->mark;
fl4.flowi4_proto = protocol;
fl4.daddr = info->key.u.ipv4.dst;
fl4.saddr = info->key.u.ipv4.src;
tos = info->key.tos;
fl4.flowi4_tos = RT_TOS(tos);
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
return ERR_PTR(-ENETUNREACH);
}
if (rt->dst.dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
ip_rt_put(rt);
return ERR_PTR(-ELOOP);
}
#ifdef CONFIG_DST_CACHE
if (use_cache)
dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
#endif
*saddr = fl4.saddr;
return rt;
}
EXPORT_SYMBOL_GPL(ip_route_output_tunnel);
/* called with rcu_read_lock held */
static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
struct rtable *rt, u32 table_id, struct flowi4 *fl4,

70
net/ipv6/ip6_output.c
View File

@ -54,6 +54,7 @@
#include <linux/mroute6.h>
#include <net/l3mdev.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@ -1196,6 +1197,75 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
}
EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
/**
* ip6_dst_lookup_tunnel - perform route lookup on tunnel
* @skb: Packet for which lookup is done
* @dev: Tunnel device
* @net: Network namespace of tunnel device
* @sk: Socket which provides route info
* @saddr: Memory to store the src ip address
* @info: Tunnel information
* @protocol: IP protocol
* @use_cahce: Flag to enable cache usage
* This function performs a route lookup on a tunnel
*
* It returns a valid dst pointer and stores src address to be used in
* tunnel in param saddr on success, else a pointer encoded error code.
*/
struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
struct net_device *dev,
struct net *net,
struct socket *sock,
struct in6_addr *saddr,
const struct ip_tunnel_info *info,
u8 protocol,
bool use_cache)
{
struct dst_entry *dst = NULL;
#ifdef CONFIG_DST_CACHE
struct dst_cache *dst_cache;
#endif
struct flowi6 fl6;
__u8 prio;
#ifdef CONFIG_DST_CACHE
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
dst = dst_cache_get_ip6(dst_cache, saddr);
if (dst)
return dst;
}
#endif
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = protocol;
fl6.daddr = info->key.u.ipv6.dst;
fl6.saddr = info->key.u.ipv6.src;
prio = info->key.tos;
fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio),
info->key.label);
dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
NULL);
if (IS_ERR(dst)) {
netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr);
return ERR_PTR(-ENETUNREACH);
}
if (dst->dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr);
dst_release(dst);
return ERR_PTR(-ELOOP);
}
#ifdef CONFIG_DST_CACHE
if (use_cache)
dst_cache_set_ip6(dst_cache, dst, &fl6.saddr);
#endif
*saddr = fl6.saddr;
return dst;
}
EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel);
static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
gfp_t gfp)
{