static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct ipv6_txoptions *opt = NULL;
struct in6_addr *final_p = NULL, final;
struct flowi fl;
int err = -1;
struct dst_entry *dst;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
fl.fl6_flowlabel = 0;
fl.oif = ireq6->iif;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, &fl);
opt = np->opt;
if (opt != NULL && opt->srcrt != NULL) {
const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto done;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0);
if (err < 0)
goto done;
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v6_csum_finish(skb,
&ireq6->loc_addr,
&ireq6->rmt_addr);
ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
err = ip6_xmit(sk, skb, &fl, opt, 0);
err = net_xmit_eval(err);
}
done:
if (opt != NULL && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return err;
}
int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
int err;
skb->destructor = rxe_skb_tx_dtor;
skb->sk = pkt->qp->sk->sk;
rxe_add_ref(pkt->qp);
atomic_inc(&pkt->qp->skb_out);
if (skb->protocol == htons(ETH_P_IP)) {
err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
} else {
pr_err("Unknown layer 3 protocol: %d\n", skb->protocol);
atomic_dec(&pkt->qp->skb_out);
rxe_drop_ref(pkt->qp);
kfree_skb(skb);
return -EINVAL;
}
if (unlikely(net_xmit_eval(err))) {
pr_debug("error sending packet: %d\n", err);
return -EAGAIN;
}
return 0;
}
int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash(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);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out_sk(sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path
*/
if (dst->dev == dev)
return vrf_local_xmit(skb, dev, dst);
skb_dst_set(skb, dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
ret = vrf_ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct rtable *rt;
const struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.flowi4_oif = inet_iif(skb),
.daddr = iph->saddr,
.saddr = iph->daddr,
.flowi4_tos = RT_CONN_FLAGS(sk),
.flowi4_proto = sk->sk_protocol,
.fl4_sport = dccp_hdr(skb)->dccph_dport,
.fl4_dport = dccp_hdr(skb)->dccph_sport,
};
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
return &rt->dst;
}
static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
struct dst_entry *dst;
struct flowi4 fl4;
dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
ireq->ir_rmt_addr);
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt));
rcu_read_unlock();
err = net_xmit_eval(err);
}
out:
dst_release(dst);
return err;
}
static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct in6_addr *final_p, final;
struct flowi6 fl6;
int err = -1;
struct dst_entry *dst;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = ireq->ir_v6_rmt_addr;
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = ireq->ir_iif;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
rcu_read_lock();
final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto done;
}
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
struct dccp_hdr *dh = dccp_hdr(skb);
struct ipv6_txoptions *opt;
dh->dccph_checksum = dccp_v6_csum_finish(skb,
&ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6.daddr = ireq->ir_v6_rmt_addr;
rcu_read_lock();
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
done:
dst_release(dst);
return err;
}
static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
struct net_device *vrf_dev)
{
struct iphdr *ip4h = ip_hdr(skb);
int ret = NET_XMIT_DROP;
struct flowi4 fl4 = {
/* needed to match OIF rule */
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
FLOWI_FLAG_SKIP_NH_OIF,
.daddr = ip4h->daddr,
};
if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
goto err;
if (!ip4h->saddr) {
ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
RT_SCOPE_LINK);
}
ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
vrf_dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
out:
return ret;
err:
vrf_tx_error(vrf_dev, skb);
goto out;
}
static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
switch (skb->protocol) {
case htons(ETH_P_IP):
return vrf_process_v4_outbound(skb, dev);
case htons(ETH_P_IPV6):
return vrf_process_v6_outbound(skb, dev);
default:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
}
/**
* batadv_send_skb_packet() - send an already prepared packet
* @skb: the packet to send
* @hard_iface: the interface to use to send the broadcast packet
* @dst_addr: the payload destination
*
* Send out an already prepared packet to the given neighbor or broadcast it
* using the specified interface. Either hard_iface or neigh_node must be not
* NULL.
* If neigh_node is NULL, then the packet is broadcasted using hard_iface,
* otherwise it is sent as unicast to the given neighbor.
*
* Regardless of the return value, the skb is consumed.
*
* Return: A negative errno code is returned on a failure. A success does not
* guarantee the frame will be transmitted as it may be dropped due
* to congestion or traffic shaping.
*/
int batadv_send_skb_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
const u8 *dst_addr)
{
struct batadv_priv *bat_priv;
struct ethhdr *ethhdr;
int ret;
bat_priv = netdev_priv(hard_iface->soft_iface);
if (hard_iface->if_status != BATADV_IF_ACTIVE)
goto send_skb_err;
if (unlikely(!hard_iface->net_dev))
goto send_skb_err;
if (!(hard_iface->net_dev->flags & IFF_UP)) {
pr_warn("Interface %s is not up - can't send packet via that interface!\n",
hard_iface->net_dev->name);
goto send_skb_err;
}
/* push to the ethernet header. */
if (batadv_skb_head_push(skb, ETH_HLEN) < 0)
goto send_skb_err;
skb_reset_mac_header(skb);
ethhdr = eth_hdr(skb);
ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr);
ether_addr_copy(ethhdr->h_dest, dst_addr);
ethhdr->h_proto = htons(ETH_P_BATMAN);
skb_set_network_header(skb, ETH_HLEN);
skb->protocol = htons(ETH_P_BATMAN);
skb->dev = hard_iface->net_dev;
/* Save a clone of the skb to use when decoding coded packets */
batadv_nc_skb_store_for_decoding(bat_priv, skb);
/* dev_queue_xmit() returns a negative result on error. However on
* congestion and traffic shaping, it drops and returns NET_XMIT_DROP
* (which is > 0). This will not be treated as an error.
*/
ret = dev_queue_xmit(skb);
return net_xmit_eval(ret);
send_skb_err:
kfree_skb(skb);
return NET_XMIT_DROP;
}
int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len;
struct iphdr *iph;
int err;
/* inlined skb_scrub_packet() */
if (xnet)
skb_orphan(skb);
skb->pkt_type = PACKET_HOST;
#if LINUX_VERSION_CODE > KERNEL_VERSION(3,0,0)
skb->skb_iif = 0;
#endif
skb_dst_drop(skb);
skb->mark = 0;
secpath_reset(skb);
nf_reset(skb);
skb->rxhash = 0;
skb_dst_set(skb, &rt_dst(rt));
#if 0
/* Do not clear ovs_skb_cb. It will be done in gso code. */
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif
/* Push down and install the IP header. */
__skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
tunnel_ip_select_ident(skb,
(const struct iphdr *)skb_inner_network_header(skb),
&rt_dst(rt));
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
}
static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
struct request_values *rvp)
{
struct inet6_request_sock *treq = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff * skb;
struct ipv6_txoptions *opt = NULL;
struct in6_addr * final_p, final;
struct flowi6 fl6;
struct dst_entry *dst;
int err;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = treq->rmt_addr;
fl6.saddr = treq->loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = treq->iif;
fl6.flowi6_mark = inet_rsk(req)->ir_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_rsk(req)->loc_port;
fl6.flowi6_uid = sock_i_uid(sk);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
opt = np->opt;
final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto done;
}
skb = tcp_make_synack(sk, dst, req, rvp);
err = -ENOMEM;
if (skb) {
__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
fl6.daddr = treq->rmt_addr;
err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
err = net_xmit_eval(err);
}
done:
if (opt && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return err;
}
void rpl_iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl,
__be16 df, bool xnet)
{
struct net_device *dev = skb->dev;
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash(skb);
skb_dst_set(skb, &rt->dst);
#if 0
/* Do not clear ovs_skb_cb. It will be done in gso code. */
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif
/* Push down and install the IP header. */
__skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
#ifdef HAVE_IP_SELECT_IDENT_USING_DST_ENTRY
__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
#elif defined(HAVE_IP_SELECT_IDENT_USING_NET)
__ip_select_ident(dev_net(rt->dst.dev), iph,
skb_shinfo(skb)->gso_segs ?: 1);
#else
__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
#endif
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
void rpl_ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
struct net_device *dev)
{
int pkt_len, err;
pkt_len = skb->len - skb_inner_network_offset(skb);
#ifdef HAVE_IP6_LOCAL_OUT_SK
err = ip6_local_out_sk(sk, skb);
#else
err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
#endif
if (net_xmit_eval(err))
pkt_len = -1;
iptunnel_xmit_stats(dev, pkt_len);
}
int iptunnel_xmit(struct sock *sk, struct rtable *rt,
struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len;
struct iphdr *iph;
int err;
nf_reset(skb);
secpath_reset(skb);
skb_clear_hash(skb);
skb_dst_drop(skb);
skb_dst_set(skb, &rt_dst(rt));
#if 0
/* Do not clear ovs_skb_cb. It will be done in gso code. */
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif
/* Push down and install the IP header. */
__skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
#ifdef HAVE_IP_SELECT_IDENT_USING_DST_ENTRY
__ip_select_ident(iph, &rt_dst(rt), (skb_shinfo(skb)->gso_segs ?: 1) - 1);
#else
__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
#endif
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
skb_dst_set(skb, dst);
ret = ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
int rpl_ip_local_out(struct sk_buff *skb)
{
int ret = NETDEV_TX_OK;
int id = -1;
if (skb_is_gso(skb)) {
struct iphdr *iph;
iph = ip_hdr(skb);
id = ntohs(iph->id);
skb = tnl_skb_gso_segment(skb, 0, false);
if (!skb || IS_ERR(skb))
return 0;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
int err;
err = skb_checksum_help(skb);
if (unlikely(err))
return 0;
}
while (skb) {
struct sk_buff *next_skb = skb->next;
struct iphdr *iph;
int err;
skb->next = NULL;
iph = ip_hdr(skb);
if (id >= 0)
iph->id = htons(id++);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#undef ip_local_out
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
ret = err;
skb = next_skb;
}
return ret;
}
static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
{
int err;
const struct iphdr *rxiph;
struct sk_buff *skb;
struct dst_entry *dst;
struct net *net = dev_net(skb_dst(rxskb)->dev);
struct sock *ctl_sk = net->dccp.v4_ctl_sk;
/* Never send a reset in response to a reset. */
if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET)
return;
if (skb_rtable(rxskb)->rt_type != RTN_LOCAL)
return;
dst = dccp_v4_route_skb(net, ctl_sk, rxskb);
if (dst == NULL)
return;
skb = dccp_ctl_make_reset(ctl_sk, rxskb);
if (skb == NULL)
goto out;
rxiph = ip_hdr(rxskb);
dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr,
rxiph->daddr);
skb_dst_set(skb, dst_clone(dst));
local_bh_disable();
bh_lock_sock(ctl_sk);
err = ip_build_and_send_pkt(skb, ctl_sk,
rxiph->daddr, rxiph->saddr, NULL);
bh_unlock_sock(ctl_sk);
if (net_xmit_eval(err) == 0) {
__DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
__DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
}
local_bh_enable();
out:
dst_release(dst);
}
int iptunnel_xmit(struct net *net, struct rtable *rt,
struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df)
{
int pkt_len = skb->len;
struct iphdr *iph;
int err;
nf_reset(skb);
secpath_reset(skb);
skb_clear_rxhash(skb);
skb_dst_drop(skb);
skb_dst_set(skb, &rt_dst(rt));
#if 0
/* Do not clear ovs_skb_cb. It will be done in gso code. */
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif
/* Push down and install the IP header. */
__skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
tunnel_ip_select_ident(skb,
(const struct iphdr *)skb_inner_network_header(skb),
&rt_dst(rt));
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
}
int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code)
{
/*
* FIXME: what if rebuild_header fails?
* Should we be doing a rebuild_header here?
*/
int err = inet_sk_rebuild_header(sk);
if (err == 0) {
struct sk_buff *skb = dccp_make_reset(sk, sk->sk_dst_cache,
code);
if (skb != NULL) {
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
err = inet_csk(sk)->icsk_af_ops->queue_xmit(skb, 0);
return net_xmit_eval(err);
}
}
return err;
}
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash_if_not_l4(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);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
struct flowi *fl)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_parm *parms = &tunnel->parms;
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev; /* Device to other host */
int err;
int mtu;
if (!dst) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
dst_hold(dst);
dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
if (IS_ERR(dst)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
dev->stats.tx_carrier_errors++;
dst_release(dst);
goto tx_error_icmp;
}
tdev = dst->dev;
if (tdev == dev) {
dst_release(dst);
dev->stats.collisions++;
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
} else {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
}
dst_release(dst);
goto tx_error;
}
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(tunnel->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = skb->len;
iptunnel_xmit_stats(dev, err);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path using our local dst
*/
if (dst->dev == net->loopback_dev || dst->dev == dev) {
struct net_vrf *vrf = netdev_priv(dev);
struct rt6_info *rt6_local;
/* release looked up dst and use cached local dst */
dst_release(dst);
rcu_read_lock();
rt6_local = rcu_dereference(vrf->rt6_local);
if (unlikely(!rt6_local)) {
rcu_read_unlock();
goto err;
}
/* Ordering issue: cached local dst is created on newlink
* before the IPv6 initialization. Using the local dst
* requires rt6i_idev to be set so make sure it is.
*/
if (unlikely(!rt6_local->rt6i_idev)) {
rt6_local->rt6i_idev = in6_dev_get(dev);
if (!rt6_local->rt6i_idev) {
rcu_read_unlock();
goto err;
}
}
dst = &rt6_local->dst;
dst_hold(dst);
rcu_read_unlock();
return vrf_local_xmit(skb, dev, &rt6_local->dst);
}
skb_dst_set(skb, dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
ret = vrf_ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
dccp_inc_seqno(&dp->dccps_gss);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
case DCCP_PKT_RESET:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_ack_seq;
/* fall through */
default:
/*
* Set owner/destructor: some skbs are allocated via
* alloc_skb (e.g. when retransmission may happen).
* Only Data, DataAck, and Reset packets should come
* through here with skb->sk set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
dcb->dccpd_seq = dp->dccps_gss;
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
/* Build DCCP header and checksum it. */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->sport;
dh->dccph_dport = inet->dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dp->dccps_awh = dp->dccps_gss;
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, 0, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
/*
* Increment GSS here already in case the option code needs it.
* Update GSS for real only if option processing below succeeds.
*/
dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
case DCCP_PKT_RESET:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* Use ISS on the first (non-retransmitted) Request. */
if (icsk->icsk_retransmits == 0)
dcb->dccpd_seq = dp->dccps_iss;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_ack_seq;
/* fall through */
default:
/*
* Set owner/destructor: some skbs are allocated via
* alloc_skb (e.g. when retransmission may happen).
* Only Data, DataAck, and Reset packets should come
* through here with skb->sk set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
/* Build DCCP header and checksum it. */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->inet_sport;
dh->dccph_dport = inet->inet_dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dccp_update_gss(sk, dcb->dccpd_seq);
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
/*
* Limit Ack window to ISS <= P.ackno <= GSS, so that
* only Responses to Requests we sent are considered.
*/
dp->dccps_awl = dp->dccps_iss;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
struct net_device *vrf_dev)
{
struct iphdr *ip4h = ip_hdr(skb);
int ret = NET_XMIT_DROP;
struct flowi4 fl4 = {
/* needed to match OIF rule */
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
.flowi4_proto = ip4h->protocol,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
struct net *net = dev_net(vrf_dev);
struct rtable *rt;
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path using our local dst
*/
if (rt->dst.dev == net->loopback_dev || rt->dst.dev == vrf_dev) {
struct net_vrf *vrf = netdev_priv(vrf_dev);
struct rtable *rth_local;
struct dst_entry *dst = NULL;
ip_rt_put(rt);
rcu_read_lock();
rth_local = rcu_dereference(vrf->rth_local);
if (likely(rth_local)) {
dst = &rth_local->dst;
dst_hold(dst);
}
rcu_read_unlock();
if (unlikely(!dst))
goto err;
return vrf_local_xmit(skb, vrf_dev, dst);
}
skb_dst_set(skb, &rt->dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
if (!ip4h->saddr) {
ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
RT_SCOPE_LINK);
}
ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
vrf_dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
out:
return ret;
err:
vrf_tx_error(vrf_dev, skb);
goto out;
}
static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
switch (skb->protocol) {
case htons(ETH_P_IP):
return vrf_process_v4_outbound(skb, dev);
case htons(ETH_P_IPV6):
return vrf_process_v6_outbound(skb, dev);
default:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
}
static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
{
netdev_tx_t ret = is_ip_tx_frame(skb, dev);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
dstats->tx_pkts++;
dstats->tx_bytes += skb->len;
u64_stats_update_end(&dstats->syncp);
} else {
this_cpu_inc(dev->dstats->tx_drps);
}
return ret;
}
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
case DCCP_PKT_DATAACK:
case DCCP_PKT_RESET:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
if (icsk->icsk_retransmits == 0)
dcb->dccpd_seq = dp->dccps_iss;
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_ack_seq;
default:
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->sport;
dh->dccph_dport = inet->dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
dh->dccph_x = 1;
dccp_update_gss(sk, dcb->dccpd_seq);
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
dp->dccps_awl = dp->dccps_iss;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, 0, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
static int ip6_tnl_xmit2(struct sk_buff *skb,
struct net_device *dev,
__u8 dsfield,
struct flowi *fl,
int encap_limit,
__u32 *pmtu)
{
struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
int pkt_len;
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(net, NULL, fl);
if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(dst));
skb->transport_header = skb->network_header;
proto = fl->proto;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = ip6_local_out(skb);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
static int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->stat;
struct ipv6hdr *ipv6h = skb->nh.ipv6h;
int encap_limit = -1;
struct ipv6_tel_txoption opt;
__u16 offset;
struct flowi fl;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err;
int pkt_len;
int dsfield;
if (t->recursion++) {
stats->collisions++;
goto tx_err;
}
if (skb->protocol != htons(ETH_P_IPV6) ||
!ip6_tnl_xmit_ctl(t) || ip6ip6_tnl_addr_conflict(t, ipv6h))
goto tx_err;
if ((offset = parse_tlv_tnl_enc_lim(skb, skb->nh.raw)) > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->nh.raw[offset];
if (tel->encap_limit == 0) {
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_HDR_FIELD, offset + 2, skb->dev);
goto tx_err;
}
encap_limit = tel->encap_limit - 1;
} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
memcpy(&fl, &t->fl, sizeof (fl));
proto = fl.proto;
dsfield = ipv6_get_dsfield(ipv6h);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(NULL, &fl);
if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb->dst)
skb->dst->ops->update_pmtu(skb->dst, mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom ||
skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
dst_release(skb->dst);
skb->dst = dst_clone(dst);
skb->h.raw = skb->nh.raw;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb->nh.raw = skb_push(skb, sizeof(struct ipv6hdr));
ipv6h = skb->nh.ipv6h;
*(__be32*)ipv6h = fl.fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl.fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl.fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL,
skb->dst->dev, dst_output);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
t->recursion--;
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
tx_err:
stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
t->recursion--;
return 0;
}
static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
struct flowi *fl)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_parm *parms = &tunnel->parms;
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev; /* Device to other host */
int err;
if (!dst) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
dst_hold(dst);
dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
if (IS_ERR(dst)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
dev->stats.tx_carrier_errors++;
dst_release(dst);
goto tx_error_icmp;
}
tdev = dst->dev;
if (tdev == dev) {
dst_release(dst);
dev->stats.collisions++;
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(tunnel->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = skb->len;
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}