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();/** 如果待输出的数据包已准备好路由缓存，* 则无需再查找路由，直接跳转到packet_routed* 处作处理。*/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. *//** 如果输出该数据包的传输控制块中* 缓存了输出路由缓存项，则需检测* 该路由缓存项是否过期。* 如果过期，重新通过输出网络设备、* 目的地址、源地址等信息查找输出* 路由缓存项。如果查找到对应的路* 由缓存项，则将其缓存到传输控制* 块中，否则丢弃该数据包。* 如果未过期，则直接使用缓存在* 传输控制块中的路由缓存项。*/rt = (struct rtable *)__sk_dst_check(sk, 0);if (!rt) { /* 缓存过期 */__be32 daddr;/* Use correct destination address if we have options. */daddr = inet->inet_daddr; /* 目的地址 */if (inet_opt && inet_opt->opt.srr)daddr = inet_opt->opt.faddr; /* 严格路由选项 *//* If this fails, retransmit mechanism of transport layer will* keep trying until route appears or the connection times* itself out.*/ /* 查找路由缓存 */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);  /* 设置控制块的路由缓存 */}skb_dst_set_noref(skb, &rt->dst);/* 将路由设置到skb中 */packet_routed:/** 查找到输出路由后，先进行严格源路由* 选项的处理。如果存在严格源路由选项，* 并且数据包的下一跳地址和网关地址不* 一致，则丢弃该数据包。*/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. *//** 设置IP首部中各字段的值。如果存在IP选项，* 则在IP数据包首部中构建IP选项。*/skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));skb_reset_network_header(skb);iph = ip_hdr(skb);/* 构造ip头 */*((__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);elseiph->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. *//* 构造ip选项 */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 ? *//** 设置输出数据包的QoS类型。*/skb->priority = sk->sk_priority;skb->mark = sk->sk_mark;res = ip_local_out(net, sk, skb);  /* 输出 */rcu_read_unlock();return res;no_route:rcu_read_unlock();/** 如果查找不到对应的路由缓存项，* 在此处理，将该数据包丢弃。*/IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);kfree_skb(skb);return -EHOSTUNREACH;
}

int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,__be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
{struct inet_sock *inet = inet_sk(sk);struct rtable *rt = skb_rtable(skb);struct net *net = sock_net(sk);struct iphdr *iph;/* Build the IP header. 构造ip首部*/skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));skb_reset_network_header(skb);iph = ip_hdr(skb);iph->version  = 4;iph->ihl      = 5;iph->tos      = inet->tos;iph->ttl      = ip_select_ttl(inet, &rt->dst);iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);iph->saddr    = saddr;iph->protocol = sk->sk_protocol;/* 分片与否 */if (ip_dont_fragment(sk, &rt->dst)) {iph->frag_off = htons(IP_DF);iph->id = 0;} else {iph->frag_off = 0;__ip_select_ident(net, iph, 1);}/*处理ip选项字段*/if (opt && opt->opt.optlen) {iph->ihl += opt->opt.optlen>>2;ip_options_build(skb, &opt->opt, daddr, rt, 0);}/* QOS优先级 */skb->priority = sk->sk_priority;skb->mark = sk->sk_mark;/* Send it out. */return ip_local_out(net, skb->sk, skb);
}

View Code

void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,const struct ip_options *sopt,__be32 daddr, __be32 saddr,const struct ip_reply_arg *arg,unsigned int len)
{struct ip_options_data replyopts;struct ipcm_cookie ipc;struct flowi4 fl4;struct rtable *rt = skb_rtable(skb);struct net *net = sock_net(sk);struct sk_buff *nskb;int err;int oif;/* 获取ip选项用于处理原路由选项 */if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))return;ipc.addr = daddr;ipc.opt = NULL;ipc.tx_flags = 0;ipc.ttl = 0;ipc.tos = -1;
/* 如果输入的ip 数据包文启用了路由选项
将得到的下一跳地址作为目的ip地址*/if (replyopts.opt.opt.optlen) {ipc.opt = &replyopts.opt;if (replyopts.opt.opt.srr)daddr = replyopts.opt.opt.faddr;}oif = arg->bound_dev_if; /*设置 输出接口 */if (!oif && netif_index_is_l3_master(net, skb->skb_iif))oif = skb->skb_iif;/* 查路由 根据目的地址 原地址 查找 */flowi4_init_output(&fl4, oif,IP4_REPLY_MARK(net, skb->mark),RT_TOS(arg->tos),RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,ip_reply_arg_flowi_flags(arg),daddr, saddr,tcp_hdr(skb)->source, tcp_hdr(skb)->dest);security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));rt = ip_route_output_key(net, &fl4);if (IS_ERR(rt))/*如果没有命中路由,终止*/return;inet_sk(sk)->tos = arg->tos;sk->sk_priority = skb->priority;sk->sk_protocol = ip_hdr(skb)->protocol;sk->sk_bound_dev_if = arg->bound_dev_if;sk->sk_sndbuf = sysctl_wmem_default;/*将数据报文添加到队列末尾中或者复制到新生成的skb中去 并添加到输出队列*/err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,len, 0, &ipc, &rt, MSG_DONTWAIT);if (unlikely(err)) {ip_flush_pending_frames(sk);goto out;}nskb = skb_peek(&sk->sk_write_queue);if (nskb) {/* 如果发送队列有skb，则计算校验和，发送 */if (arg->csumoffset >= 0)*((__sum16 *)skb_transport_header(nskb) +arg->csumoffset) = csum_fold(csum_add(nskb->csum,arg->csum));nskb->ip_summed = CHECKSUM_NONE;ip_push_pending_frames(sk, &fl4);// 发送数据
    }
out:ip_rt_put(rt);
}
int ip_send_skb(struct net *net, struct sk_buff *skb)
{int err;err = ip_local_out(net, skb->sk, skb);if (err) {if (err > 0)err = net_xmit_errno(err);if (err)IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);}return err;
}int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
{struct sk_buff *skb;skb = ip_finish_skb(sk, fl4);if (!skb)return 0;/* Netfilter gets whole the not fragmented skb. */return ip_send_skb(sock_net(sk), skb);
}