linux-sg2042/drivers/net/geneve.c

727 lines
18 KiB
C
Raw Normal View History

/*
* GENEVE: Generic Network Virtualization Encapsulation
*
* Copyright (c) 2015 Red Hat, Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/hash.h>
#include <net/dst_metadata.h>
#include <net/rtnetlink.h>
#include <net/geneve.h>
#define GENEVE_NETDEV_VER "0.6"
#define GENEVE_UDP_PORT 6081
#define GENEVE_N_VID (1u << 24)
#define GENEVE_VID_MASK (GENEVE_N_VID - 1)
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
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 */
struct geneve_net {
struct list_head geneve_list;
struct hlist_head vni_list[VNI_HASH_SIZE];
struct geneve_dev __rcu *collect_md_tun;
};
/* Pseudo network device */
struct geneve_dev {
struct hlist_node hlist; /* vni hash table */
struct net *net; /* netns for packet i/o */
struct net_device *dev; /* netdev for geneve tunnel */
struct geneve_sock *sock; /* socket used for geneve tunnel */
u8 vni[3]; /* virtual network ID for tunnel */
u8 ttl; /* TTL override */
u8 tos; /* TOS override */
struct sockaddr_in remote; /* IPv4 address for link partner */
struct list_head next; /* geneve's per namespace list */
__be16 dst_port;
bool collect_md;
};
static int geneve_net_id;
static inline __u32 geneve_net_vni_hash(u8 vni[3])
{
__u32 vnid;
vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
return hash_32(vnid, VNI_HASH_BITS);
}
static __be64 vni_to_tunnel_id(const __u8 *vni)
{
#ifdef __BIG_ENDIAN
return (vni[0] << 16) | (vni[1] << 8) | vni[2];
#else
return (__force __be64)(((__force u64)vni[0] << 40) |
((__force u64)vni[1] << 48) |
((__force u64)vni[2] << 56));
#endif
}
static struct geneve_dev *geneve_lookup(struct geneve_net *gn,
struct geneve_sock *gs,
struct iphdr *iph,
struct genevehdr *gnvh)
{
struct inet_sock *sk = inet_sk(gs->sock->sk);
struct hlist_head *vni_list_head;
struct geneve_dev *geneve;
__u32 hash;
geneve = rcu_dereference(gn->collect_md_tun);
if (geneve)
return geneve;
/* Find the device for this VNI */
hash = geneve_net_vni_hash(gnvh->vni);
vni_list_head = &gn->vni_list[hash];
hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
if (!memcmp(gnvh->vni, geneve->vni, sizeof(geneve->vni)) &&
iph->saddr == geneve->remote.sin_addr.s_addr &&
sk->inet_sport == geneve->dst_port) {
return geneve;
}
}
return NULL;
}
/* geneve receive/decap routine */
static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
{
struct genevehdr *gnvh = geneve_hdr(skb);
struct metadata_dst *tun_dst = NULL;
struct geneve_dev *geneve = NULL;
struct pcpu_sw_netstats *stats;
struct geneve_net *gn;
struct iphdr *iph;
int err;
iph = ip_hdr(skb); /* Still outer IP header... */
gn = gs->rcv_data;
geneve = geneve_lookup(gn, gs, iph, gnvh);
if (!geneve)
goto drop;
if (ip_tunnel_collect_metadata() || geneve->collect_md) {
__be16 flags;
void *opts;
flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
(gnvh->oam ? TUNNEL_OAM : 0) |
(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
tun_dst = udp_tun_rx_dst(skb, AF_INET, flags,
vni_to_tunnel_id(gnvh->vni),
gnvh->opt_len * 4);
if (!tun_dst)
goto drop;
/* Update tunnel dst according to Geneve options. */
opts = ip_tunnel_info_opts(&tun_dst->u.tun_info,
gnvh->opt_len * 4);
memcpy(opts, gnvh->options, gnvh->opt_len * 4);
} else {
/* Drop packets w/ critical options,
* since we don't support any...
*/
if (gnvh->critical)
goto drop;
}
skb_reset_mac_header(skb);
skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
skb->protocol = eth_type_trans(skb, geneve->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
if (tun_dst)
skb_dst_set(skb, &tun_dst->dst);
/* Ignore packet loops (and multicast echo) */
if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
goto drop;
skb_reset_network_header(skb);
iph = ip_hdr(skb); /* Now inner IP header... */
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) {
++geneve->dev->stats.rx_frame_errors;
++geneve->dev->stats.rx_errors;
goto drop;
}
}
stats = this_cpu_ptr(geneve->dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
netif_rx(skb);
return;
drop:
/* Consume bad packet */
kfree_skb(skb);
}
/* Setup stats when device is created */
static int geneve_init(struct net_device *dev)
{
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
}
static void geneve_uninit(struct net_device *dev)
{
free_percpu(dev->tstats);
}
static int geneve_open(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
struct net *net = geneve->net;
struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
struct geneve_sock *gs;
gs = geneve_sock_add(net, geneve->dst_port, geneve_rx, gn,
false, false);
if (IS_ERR(gs))
return PTR_ERR(gs);
geneve->sock = gs;
return 0;
}
static int geneve_stop(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
struct geneve_sock *gs = geneve->sock;
geneve_sock_release(gs);
return 0;
}
static struct rtable *geneve_get_rt(struct sk_buff *skb,
struct net_device *dev,
struct flowi4 *fl4,
struct ip_tunnel_info *info)
{
struct geneve_dev *geneve = netdev_priv(dev);
struct rtable *rt = NULL;
__u8 tos;
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_mark = skb->mark;
fl4->flowi4_proto = IPPROTO_UDP;
if (info) {
fl4->daddr = info->key.u.ipv4.dst;
fl4->saddr = info->key.u.ipv4.src;
fl4->flowi4_tos = RT_TOS(info->key.tos);
} else {
tos = geneve->tos;
if (tos == 1) {
const struct iphdr *iip = ip_hdr(skb);
tos = ip_tunnel_get_dsfield(iip, skb);
}
fl4->flowi4_tos = RT_TOS(tos);
fl4->daddr = geneve->remote.sin_addr.s_addr;
}
rt = ip_route_output_key(geneve->net, fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr);
dev->stats.tx_carrier_errors++;
return rt;
}
if (rt->dst.dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr);
dev->stats.collisions++;
ip_rt_put(rt);
return ERR_PTR(-EINVAL);
}
return rt;
}
/* Convert 64 bit tunnel ID to 24 bit VNI. */
static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
{
#ifdef __BIG_ENDIAN
vni[0] = (__force __u8)(tun_id >> 16);
vni[1] = (__force __u8)(tun_id >> 8);
vni[2] = (__force __u8)tun_id;
#else
vni[0] = (__force __u8)((__force u64)tun_id >> 40);
vni[1] = (__force __u8)((__force u64)tun_id >> 48);
vni[2] = (__force __u8)((__force u64)tun_id >> 56);
#endif
}
static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
struct geneve_sock *gs = geneve->sock;
struct ip_tunnel_info *info = NULL;
struct rtable *rt = NULL;
const struct iphdr *iip; /* interior IP header */
struct flowi4 fl4;
__u8 tos, ttl;
__be16 sport;
bool xnet;
int err;
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
if (geneve->collect_md) {
info = skb_tunnel_info(skb);
if (unlikely(info && info->mode != IP_TUNNEL_INFO_TX)) {
netdev_dbg(dev, "no tunnel metadata\n");
goto tx_error;
}
}
rt = geneve_get_rt(skb, dev, &fl4, info);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
dev->stats.tx_carrier_errors++;
goto tx_error;
}
skb_reset_mac_header(skb);
xnet = !net_eq(geneve->net, dev_net(geneve->dev));
if (info) {
const struct ip_tunnel_key *key = &info->key;
bool udp_csum;
u8 *opts = NULL;
u8 vni[3];
__be16 df;
tunnel_id_to_vni(key->tun_id, vni);
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
udp_csum = !!(key->tun_flags & TUNNEL_CSUM);
if (key->tun_flags & TUNNEL_GENEVE_OPT)
opts = ip_tunnel_info_opts(info, info->options_len);
err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr,
key->tos, key->ttl, df,
sport, geneve->dst_port,
key->tun_flags, vni,
info->options_len, opts, udp_csum, xnet);
} else {
iip = ip_hdr(skb);
tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
ttl = geneve->ttl;
if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
ttl = 1;
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
/* no need to handle local destination and encap bypass...yet... */
err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr, tos,
ttl, 0, sport, geneve->dst_port, 0,
geneve->vni, 0, NULL, false, xnet);
}
if (err < 0)
ip_rt_put(rt);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return NETDEV_TX_OK;
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static const struct net_device_ops geneve_netdev_ops = {
.ndo_init = geneve_init,
.ndo_uninit = geneve_uninit,
.ndo_open = geneve_open,
.ndo_stop = geneve_stop,
.ndo_start_xmit = geneve_xmit,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
};
static void geneve_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
{
strlcpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version));
strlcpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver));
}
static const struct ethtool_ops geneve_ethtool_ops = {
.get_drvinfo = geneve_get_drvinfo,
.get_link = ethtool_op_get_link,
};
/* Info for udev, that this is a virtual tunnel endpoint */
static struct device_type geneve_type = {
.name = "geneve",
};
/* Initialize the device structure. */
static void geneve_setup(struct net_device *dev)
{
ether_setup(dev);
dev->netdev_ops = &geneve_netdev_ops;
dev->ethtool_ops = &geneve_ethtool_ops;
dev->destructor = free_netdev;
SET_NETDEV_DEVTYPE(dev, &geneve_type);
dev->features |= NETIF_F_LLTX;
dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
dev->features |= NETIF_F_RXCSUM;
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->vlan_features = dev->features;
dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
netif_keep_dst(dev);
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
eth_hw_addr_random(dev);
}
static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
[IFLA_GENEVE_ID] = { .type = NLA_U32 },
[IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
[IFLA_GENEVE_TTL] = { .type = NLA_U8 },
[IFLA_GENEVE_TOS] = { .type = NLA_U8 },
[IFLA_GENEVE_PORT] = { .type = NLA_U16 },
[IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG },
};
static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
if (!data)
return -EINVAL;
if (data[IFLA_GENEVE_ID]) {
__u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]);
if (vni >= GENEVE_VID_MASK)
return -ERANGE;
}
return 0;
}
static int geneve_configure(struct net *net, struct net_device *dev,
__be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos,
__u16 dst_port, bool metadata)
{
struct geneve_net *gn = net_generic(net, geneve_net_id);
struct geneve_dev *dummy, *geneve = netdev_priv(dev);
struct hlist_head *vni_list_head;
struct sockaddr_in remote; /* IPv4 address for link partner */
__u32 hash;
int err;
if (metadata) {
if (rtnl_dereference(gn->collect_md_tun))
return -EEXIST;
if (!list_empty(&gn->geneve_list))
return -EPERM;
} else {
if (rtnl_dereference(gn->collect_md_tun))
return -EPERM;
}
geneve->net = net;
geneve->dev = dev;
geneve->vni[0] = (vni & 0x00ff0000) >> 16;
geneve->vni[1] = (vni & 0x0000ff00) >> 8;
geneve->vni[2] = vni & 0x000000ff;
geneve->remote.sin_addr.s_addr = rem_addr;
if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr)))
return -EINVAL;
remote = geneve->remote;
if (metadata) {
if (rem_addr || vni || tos || ttl)
return -EINVAL;
}
hash = geneve_net_vni_hash(geneve->vni);
vni_list_head = &gn->vni_list[hash];
hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
if (!memcmp(geneve->vni, dummy->vni, sizeof(dummy->vni)) &&
!memcmp(&remote, &dummy->remote, sizeof(dummy->remote)) &&
htons(dst_port) == dummy->dst_port) {
return -EBUSY;
}
}
geneve->ttl = ttl;
geneve->tos = tos;
geneve->dst_port = htons(dst_port);
geneve->collect_md = metadata;
err = register_netdevice(dev);
if (err)
return err;
list_add(&geneve->next, &gn->geneve_list);
hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]);
if (geneve->collect_md)
rcu_assign_pointer(gn->collect_md_tun, geneve);
return 0;
}
static int geneve_newlink(struct net *net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
__u16 dst_port = GENEVE_UDP_PORT;
__u8 ttl = 0, tos = 0;
bool metadata = false;
__be32 rem_addr;
__u32 vni;
if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
return -EINVAL;
vni = nla_get_u32(data[IFLA_GENEVE_ID]);
rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);
if (data[IFLA_GENEVE_TTL])
ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
if (data[IFLA_GENEVE_TOS])
tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
if (data[IFLA_GENEVE_PORT])
dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]);
if (data[IFLA_GENEVE_COLLECT_METADATA])
metadata = true;
return geneve_configure(net, dev, rem_addr, vni,
ttl, tos, dst_port, metadata);
}
static void geneve_dellink(struct net_device *dev, struct list_head *head)
{
struct geneve_dev *geneve = netdev_priv(dev);
if (geneve->collect_md) {
struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
rcu_assign_pointer(gn->collect_md_tun, NULL);
}
if (!hlist_unhashed(&geneve->hlist))
hlist_del_rcu(&geneve->hlist);
list_del(&geneve->next);
unregister_netdevice_queue(dev, head);
}
static size_t geneve_get_size(const struct net_device *dev)
{
return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */
nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */
nla_total_size(sizeof(__u16)) + /* IFLA_GENEVE_PORT */
nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */
0;
}
static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
__u32 vni;
vni = (geneve->vni[0] << 16) | (geneve->vni[1] << 8) | geneve->vni[2];
if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
goto nla_put_failure;
if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
geneve->remote.sin_addr.s_addr))
goto nla_put_failure;
if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) ||
nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port)))
goto nla_put_failure;
if (geneve->collect_md) {
if (nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA))
goto nla_put_failure;
}
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static struct rtnl_link_ops geneve_link_ops __read_mostly = {
.kind = "geneve",
.maxtype = IFLA_GENEVE_MAX,
.policy = geneve_policy,
.priv_size = sizeof(struct geneve_dev),
.setup = geneve_setup,
.validate = geneve_validate,
.newlink = geneve_newlink,
.dellink = geneve_dellink,
.get_size = geneve_get_size,
.fill_info = geneve_fill_info,
};
struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
u8 name_assign_type, u16 dst_port)
{
struct nlattr *tb[IFLA_MAX + 1];
struct net_device *dev;
int err;
memset(tb, 0, sizeof(tb));
dev = rtnl_create_link(net, name, name_assign_type,
&geneve_link_ops, tb);
if (IS_ERR(dev))
return dev;
err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true);
if (err) {
free_netdev(dev);
return ERR_PTR(err);
}
return dev;
}
EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
static __net_init int geneve_init_net(struct net *net)
{
struct geneve_net *gn = net_generic(net, geneve_net_id);
unsigned int h;
INIT_LIST_HEAD(&gn->geneve_list);
for (h = 0; h < VNI_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&gn->vni_list[h]);
return 0;
}
static void __net_exit geneve_exit_net(struct net *net)
{
struct geneve_net *gn = net_generic(net, geneve_net_id);
struct geneve_dev *geneve, *next;
struct net_device *dev, *aux;
LIST_HEAD(list);
rtnl_lock();
/* gather any geneve devices that were moved into this ns */
for_each_netdev_safe(net, dev, aux)
if (dev->rtnl_link_ops == &geneve_link_ops)
unregister_netdevice_queue(dev, &list);
/* now gather any other geneve devices that were created in this ns */
list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
/* If geneve->dev is in the same netns, it was already added
* to the list by the previous loop.
*/
if (!net_eq(dev_net(geneve->dev), net))
unregister_netdevice_queue(geneve->dev, &list);
}
/* unregister the devices gathered above */
unregister_netdevice_many(&list);
rtnl_unlock();
}
static struct pernet_operations geneve_net_ops = {
.init = geneve_init_net,
.exit = geneve_exit_net,
.id = &geneve_net_id,
.size = sizeof(struct geneve_net),
};
static int __init geneve_init_module(void)
{
int rc;
rc = register_pernet_subsys(&geneve_net_ops);
if (rc)
goto out1;
rc = rtnl_link_register(&geneve_link_ops);
if (rc)
goto out2;
return 0;
out2:
unregister_pernet_subsys(&geneve_net_ops);
out1:
return rc;
}
late_initcall(geneve_init_module);
static void __exit geneve_cleanup_module(void)
{
rtnl_link_unregister(&geneve_link_ops);
unregister_pernet_subsys(&geneve_net_ops);
}
module_exit(geneve_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_VERSION(GENEVE_NETDEV_VER);
MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>");
MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("geneve");