Linux IP处理之ip_queue_xmit

ip_queue_xmit()完成面向连接套接字的包输出，当套接字处于连接状态时,
所有从套接字发出的包都具有确定的路由, 无需为每一个输出包查询它的目的入口,
可将套接字直接绑定到路由入口上, 这由套接字的目的缓冲指针(dst_cache)来完成.
ip_queue_xmit()首先为输入包建立IP包头, 经过本地包过滤器后,再将IP包分片输出(ip_fragment)。

/* Note: skb->sk can be different from sk, in case of tunnels */
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct ip_options_rcu *inet_opt;
struct flowi4 *fl4;
struct rtable *rt;
struct iphdr *iph;
int res;


/* Skip all of this if the packet is already routed,
* f.e. by something like SCTP.
*/
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
fl4 = &fl->u.ip4;
rt = skb_rtable(skb);
if (rt)
goto packet_routed;


/* Make sure we can route this packet. */
rt = (struct rtable *)__sk_dst_check(sk, 0);
if (!rt) {
__be32 daddr;


/* Use correct destination address if we have options. */
daddr = inet->inet_daddr;
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;


/* If this fails, retransmit mechanism of transport layer will
* keep trying until route appears or the connection times
* itself out.
*/
rt = ip_route_output_ports(net, fl4, sk,
  daddr, inet->inet_saddr,
  inet->inet_dport,
  inet->inet_sport,
  sk->sk_protocol,
  RT_CONN_FLAGS(sk),
  sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto no_route;
sk_setup_caps(sk, &rt->dst);
}
skb_dst_set_noref(skb, &rt->dst);


packet_routed:
if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
goto no_route;


/* OK, we know where to send it, allocate and build IP header. */
skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->ttl      = ip_select_ttl(inet, &rt->dst);
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);


/* Transport layer set skb->h.foo itself. */


if (inet_opt && inet_opt->opt.optlen) {
iph->ihl += inet_opt->opt.optlen >> 2;
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}


ip_select_ident_segs(net, skb, sk,
    skb_shinfo(skb)->gso_segs ?: 1);


/* TODO : should we use skb->sk here instead of sk ? */
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;


res = ip_local_out(net, sk, skb);
rcu_read_unlock();
return res;


no_route:
rcu_read_unlock();
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EHOSTUNREACH;
}