/* Must be called with rcu_read_lock. */
static void netdev_port_receive(struct sk_buff *skb)
{
struct vport *vport;
vport = ovs_netdev_get_vport(skb->dev);
if (unlikely(!vport))
goto error;
if (unlikely(skb_warn_if_lro(skb)))
goto error;
/* Make our own copy of the packet. Otherwise we will mangle the
* packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return;
skb_push(skb, ETH_HLEN);
skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
return;
error:
kfree_skb(skb);
}
static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
int tunnel_hlen;
__be16 df, flags;
int err;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
key = &tun_info->key;
rt = gre_get_rt(skb, dev, &fl, key);
if (IS_ERR(rt))
goto err_free_skb;
tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
/* Called with rcu_read_lock and bottom-halves disabled. */
static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
#ifndef HAVE_METADATA_DST
netdev_port_receive(skb, NULL);
#else
netdev_port_receive(skb, skb_tunnel_info(skb));
#endif
return RX_HANDLER_CONSUMED;
}
int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
struct net *net,
struct sk_buff *skb,
u8 ipproto,
__be16 tp_src,
__be16 tp_dst)
{
struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info;
struct ip_tunnel_info *tun_info = skb_tunnel_info(skb);
const struct ip_tunnel_key *tun_key;
u32 skb_mark = skb->mark;
struct rtable *rt;
struct flowi4 fl;
if (unlikely(!tun_info))
return -EINVAL;
if (ip_tunnel_info_af(tun_info) != AF_INET)
return -EINVAL;
tun_key = &tun_info->key;
/* Route lookup to get srouce IP address.
* The process may need to be changed if the corresponding process
* in vports ops changed.
*/
rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
/* Generate egress_tun_info based on tun_info,
* saddr, tp_src and tp_dst
*/
ip_tunnel_key_init(&egress_tun_info->key,
fl.saddr, tun_key->u.ipv4.dst,
tun_key->tos,
tun_key->ttl,
tp_src, tp_dst,
tun_key->tun_id,
tun_key->tun_flags);
egress_tun_info->options_len = tun_info->options_len;
egress_tun_info->mode = tun_info->mode;
upcall->egress_tun_opts = ip_tunnel_info_opts(tun_info);
return 0;
}
static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel_info *tun_info;
struct net *net = dev_net(dev);
const struct ip_tunnel_key *key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
int tunnel_hlen;
__be16 df, flags;
int err;
tun_info = skb_tunnel_info(skb, AF_INET);
if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX))
goto err_free_skb;
key = &tun_info->key;
memset(&fl, 0, sizeof(fl));
fl.daddr = key->ipv4_dst;
fl.saddr = key->ipv4_src;
fl.flowi4_tos = RT_TOS(key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_GRE;
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt))
goto err_free_skb;
tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
static struct rtable *prepare_fb_xmit(struct sk_buff *skb,
struct net_device *dev,
struct flowi4 *fl,
int tunnel_hlen)
{
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
struct rtable *rt = NULL;
int min_headroom;
bool use_cache;
int err;
tun_info = skb_tunnel_info(skb);
key = &tun_info->key;
use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);
if (use_cache)
rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl->saddr);
if (!rt) {
rt = gre_get_rt(skb, dev, fl, key);
if (IS_ERR(rt))
goto err_free_skb;
if (use_cache)
dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst,
fl->saddr);
}
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
u32 headroom = sizeof(struct iphdr);
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
const struct iphdr *inner_iph;
struct rtable *rt;
struct flowi4 fl4;
__be16 df = 0;
u8 tos, ttl;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto tx_error;
key = &tun_info->key;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
tos = key->tos;
if (tos == 1) {
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);
}
init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
RT_TOS(tos), tunnel->parms.link);
if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
goto tx_error;
rt = ip_route_output_key(tunnel->net, &fl4);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = key->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
if (key->tun_flags & TUNNEL_DONT_FRAGMENT)
df = htons(IP_DF);
else if (skb->protocol == htons(ETH_P_IP))
df = inner_iph->frag_off & htons(IP_DF);
headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
if (headroom > dev->needed_headroom)
dev->needed_headroom = headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
ip_rt_put(rt);
goto tx_dropped;
}
iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
return;
tx_error:
dev->stats.tx_errors++;
goto kfree;
tx_dropped:
dev->stats.tx_dropped++;
kfree:
kfree_skb(skb);
}
