linux内核TCP/IP源码浅析

目录

  • 数据接收流程图
  • 硬件层
  • 网络层
    • ip_rcv
    • ip_rcv_core
    • ip_rcv_finish 和 ip_rcv_finish_core
    • ip_local_deliver
    • ip_local_deliver_finish 和 ip_protocol_deliver_rcu
  • 传输层
    • tcp_v4_rcv
    • tcp_v4_do_rcv
    • tcp_rcv_state_process
    • tcp_rcv_established
    • tcp_recvmsg
  • 数据结构
    • ethhdr
    • iphdr
    • tcphdr
    • udphdr
    • socket
    • sock
    • sock_common
    • sk_buff

linux内核源码下载:https://cdn.kernel.org/pub/linux/kernel/
我下载的是:linux-5.11.1.tar.gz
linux源码在线看:https://elixir.bootlin.com/linux/v5.11/source

数据接收流程图

1,一般网卡接收数据是以触发中断来接收的,在网卡driver中,接收到数据时,往kernel的api:netif_rx()丢。
2,接着数据被送到IP层ip_local_deliver_finish(),经过剥离ip头部,把数据往TCP层发。
3,tcp层tcp_v4_rcv()收到数据后,再调用tcp_rcv_established()(ack也是其中的tcp_ack()发送的)处理,如果当前用户进程没有正在读取数据,则将其插入到接收队列中,tcp_queue_rcv()则判断接收队列是否为空,如果不为空,则将skb合并到接收队列的尾部,最后由tcp_recvmsg()从接收列队中一个一个的将skb读取到用户设置的buffer中去。
4,上层通过recvmsg等函数去接收数据时,就是从buffer中去读取的。

调用栈:

1、从下往上:网络设备接口-> Netif_rx -> ip_rcv -> ip_rcv_finished -> ip_local_deliver -> ip_local_deliver_finished -> tcp_v4_rcv -> tcp_v4_do_rcv -> tcp_rcv_established -> tcp_data_queue ->sk_data_ready

2、从上往下:应用层recvfrom -> SYSCALL_DEFINE2 -> __sys_recvfrom -> sock_recvmsg -> sock_recvmsg_nosec -> inet_recvmsg -> tcp_recvmsg -> 读取队列

linux内核TCP/IP源码浅析_第1张图片

硬件层

netif_rx()
所在目录:/linux-5.11.1/net/core/dev.c。

/**
 *	netif_rx	-	post buffer to the network code	把接收数据投递到网络层代码
 *	@skb: buffer to post	要投递的数据buf
 *
 *	This function receives a packet from a device driver and queues it for
 *	the upper (protocol) levels to process.  It always succeeds. The buffer
 *	may be dropped during processing for congestion control or by the
 *	protocol layers.
 * 此函数从设备驱动程序接收数据包,并将其排队到上层(协议)级别处理。
 * 它总是成功的。缓冲区可以在拥塞控制处理期间或通过协议层被丢弃。
 *	return values:
 *	NET_RX_SUCCESS	(no congestion)
 *	NET_RX_DROP     (packet was dropped)
 *
 */

int netif_rx(struct sk_buff *skb)
{
	int ret;

	trace_netif_rx_entry(skb);
	
	ret = netif_rx_internal(skb);//把网卡接收的skb存储起来
	trace_netif_rx_exit(ret);

	return ret;
}

该函数在网卡驱动程序与linux内核之间建立了一道桥梁,将网卡接收上来的数据包(sk_buff形式)插入内核维护的接收缓冲区队列当中。
他的主要任务是把数据帧添加到CPU的输入队列input_pkt_queue中。随后标记软中断来处理后续上传数据帧给TCP/IP协议栈。

网络层

所在目录:/linux-5.11.1/net/ipv4/ip_input.c。
ip_local_deliver(解析IP头部,组包)
ip_local_deliver_finish(根据IP报头的protocol字段,找到对应的L4协议,TCP/UDP)。

ip_rcv

/* from 	ip_input.c
 * IP receive entry point
 * IP接收入口函数
 */
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
	   struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);
	
	skb = ip_rcv_core(skb, net);//IP层主要处理函数
	if (skb == NULL)
		return NET_RX_DROP;
	//钩子函数,通过iptables的PRE_ROUTING链,如果继续则进入ip_rcv_finish
	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip_rcv_finish);
}

ip_rcv_core

/*	from 	ip_input.c
 *	IP层接收主处理函数
 * 	Main IP Receive routine.
 */
static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
{
	const struct iphdr *iph;
	u32 len;

	/* When the interface is in promisc. mode, drop all the crap
	 * that it receives, do not try to analyse it.
	 */
	 //丢弃PACKET_OTHERHOST类型的包
	if (skb->pkt_type == PACKET_OTHERHOST)
		goto drop;

	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (!skb) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto out;
	}
	//尝试以最小长度获取ip头,获取不到则返回error
	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto inhdr_error;
	//获取ip头
	iph = ip_hdr(skb);

	/*
	 *	RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
	 *
	 *	Is the datagram acceptable?
	 *
	 *	1.	Length at least the size of an ip header
	 *	2.	Version of 4
	 *	3.	Checksums correctly. [Speed optimisation for later, skip loopback checksums]
	 *	4.	Doesn't have a bogus length
	 */
	//校验ip头的长度和版本
	if (iph->ihl < 5 || iph->version != 4)
		goto inhdr_error;

	BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
	BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
	BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
	__IP_ADD_STATS(net,
		       IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
		       max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
	//尝试以ip头携带的ip头部长度获取ip头,获取失败返回error
	if (!pskb_may_pull(skb, iph->ihl*4))
		goto inhdr_error;

	iph = ip_hdr(skb);

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto csum_error;
	//skb的长度,比ip头携带的ip包总长度小,丢弃报文
    //ip包总长度,比ip头长度小,返回error
	len = ntohs(iph->tot_len);
	if (skb->len < len) {
		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
		goto drop;
	} else if (len < (iph->ihl*4))
		goto inhdr_error;

	/* Our transport medium may have padded the buffer out. Now we know it
	 * is IP we can trim to the true length of the frame.
	 * Note this now means skb->len holds ntohs(iph->tot_len).
	 */
	if (pskb_trim_rcsum(skb, len)) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	iph = ip_hdr(skb);
	//获取传输层数据指针
	skb->transport_header = skb->network_header + iph->ihl*4;

	/* Remove any debris in the socket control block */
	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
	IPCB(skb)->iif = skb->skb_iif;

	/* Must drop socket now because of tproxy. */
	if (!skb_sk_is_prefetched(skb))
		skb_orphan(skb);

	return skb;

csum_error:
	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
inhdr_error:
	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
	kfree_skb(skb);
out:
	return NULL;
}

ip_rcv_finish 和 ip_rcv_finish_core

ip_input.c

static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	int ret;

	/* if ingress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	 //如果数据报属于L3层,则传递给其处理程序进行处理
	skb = l3mdev_ip_rcv(skb);
	if (!skb)
		return NET_RX_SUCCESS;

	ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
	//dst_input实际上会调用skb->dst->input(skb).input函数会根据路由信息设置为合适的
    //函数指针,如果是递交到本地的则为ip_local_deliver,若是转发则为ip_forward.
	if (ret != NET_RX_DROP)
		ret = dst_input(skb);
	return ret;
}

ip_input.c

static int ip_rcv_finish_core(struct net *net, struct sock *sk,
			      struct sk_buff *skb, struct net_device *dev,
			      const struct sk_buff *hint)
{
	const struct iphdr *iph = ip_hdr(skb);
	int (*edemux)(struct sk_buff *skb);
	struct rtable *rt;
	int err;

	if (ip_can_use_hint(skb, iph, hint)) {
		err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
					dev, hint);
		if (unlikely(err))
			goto drop_error;
	}

	if (net->ipv4.sysctl_ip_early_demux &&
	    !skb_dst(skb) &&
	    !skb->sk &&
	    !ip_is_fragment(iph)) {
		const struct net_protocol *ipprot;
		int protocol = iph->protocol;

		ipprot = rcu_dereference(inet_protos[protocol]);
		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
			err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux,
					      udp_v4_early_demux, skb);
			if (unlikely(err))
				goto drop_error;
			/* must reload iph, skb->head might have changed */
			iph = ip_hdr(skb);
		}
	}

	/*
	 *	Initialise the virtual path cache for the packet. It describes
	 *	how the packet travels inside Linux networking.
	 *	为数据包初始化虚拟路径缓存,它描述了数据包是如何在linux网络中传播的
	 */
	 //通常从外界接收的数据包,skb->dst不会包含路由信息,暂时还不知道在何处会设置这个字段
     //ip_route_input函数会根据路由表设置路由信息
	if (!skb_valid_dst(skb)) {
		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
					   iph->tos, dev);
		if (unlikely(err))
			goto drop_error;
	}
//更新统计数据
#ifdef CONFIG_IP_ROUTE_CLASSID
	if (unlikely(skb_dst(skb)->tclassid)) {
		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
		u32 idx = skb_dst(skb)->tclassid;
		st[idx&0xFF].o_packets++;
		st[idx&0xFF].o_bytes += skb->len;
		st[(idx>>16)&0xFF].i_packets++;
		st[(idx>>16)&0xFF].i_bytes += skb->len;
	}
#endif
	//如果IP头部大于20字节,则表示IP头部包含IP选项,需要进行选项处理
	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
		goto drop;
	//skb_rtable函数等同于skb_dst函数,获取skb->dst
	rt = skb_rtable(skb);
	if (rt->rt_type == RTN_MULTICAST) {
		__IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len);
	} else if (rt->rt_type == RTN_BROADCAST) {
		__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
	} else if (skb->pkt_type == PACKET_BROADCAST ||
		   skb->pkt_type == PACKET_MULTICAST) {
		struct in_device *in_dev = __in_dev_get_rcu(dev);

		/* RFC 1122 3.3.6:
		 *
		 *   When a host sends a datagram to a link-layer broadcast
		 *   address, the IP destination address MUST be a legal IP
		 *   broadcast or IP multicast address.
		 *
		 *   A host SHOULD silently discard a datagram that is received
		 *   via a link-layer broadcast (see Section 2.4) but does not
		 *   specify an IP multicast or broadcast destination address.
		 *
		 * This doesn't explicitly say L2 *broadcast*, but broadcast is
		 * in a way a form of multicast and the most common use case for
		 * this is 802.11 protecting against cross-station spoofing (the
		 * so-called "hole-196" attack) so do it for both.
		 */
		if (in_dev &&
		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
			goto drop;
	}

	return NET_RX_SUCCESS;

drop:
	kfree_skb(skb);
	return NET_RX_DROP;

drop_error:
	if (err == -EXDEV)
		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
	goto drop;
}

ip_local_deliver

ip_input.c

/*	将IP数据包传递到更高的协议层。
 *  Deliver IP Packets to the higher protocol layers.
 */
int ip_local_deliver(struct sk_buff *skb)
{
    /*		
     * Reassemble IP fragments.
     * 分片重组
     */
    struct net *net = dev_net(skb->dev);
  
    if (ip_is_fragment(ip_hdr(skb))) {
        if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
            return 0;
    }

    /* 经过LOCAL_IN钩子点 */
    return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
               net, NULL, skb, skb->dev, NULL,
               ip_local_deliver_finish);
}

ip_local_deliver_finish 和 ip_protocol_deliver_rcu

ip_input.c

static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	 /* 去掉ip头 */
	__skb_pull(skb, skb_network_header_len(skb));

	rcu_read_lock();//获取锁
	ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
	rcu_read_unlock();

	return 0;
}
void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
	const struct net_protocol *ipprot;
	int raw, ret;

resubmit:
	/* 原始套接口,复制一个副本,输出到该套接口 */
	raw = raw_local_deliver(skb, protocol);

	/* 获取协议处理结构 */
	ipprot = rcu_dereference(inet_protos[protocol]);
	if (ipprot) {
		if (!ipprot->no_policy) {
			if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				kfree_skb(skb);
				return;
			}
			nf_reset_ct(skb);
		}
		//注册tcp和udp接收函数
		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv,
				      skb);
		if (ret < 0) {
			protocol = -ret;
			goto resubmit;
		}
		__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
	} else {
		if (!raw) {/* 原始套接口未接收或接收异常 */
			if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
				/* 发送icmp */
				icmp_send(skb, ICMP_DEST_UNREACH,
					  ICMP_PROT_UNREACH, 0);
			}
			kfree_skb(skb);
		} else {
			/* 原始套接口接收 */
			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
			 /* 释放包 */
			consume_skb(skb);
		}
	}
}

传输层

根据IP报头协议,以TCP为例,TCP接收函数为:int tcp_v4_rcv(struct sk_buff *skb)。
所在目录:/linux-5.11.1/net/ipv4/tcp_ipv4.c。
linux内核TCP/IP源码浅析_第2张图片

tcp_v4_rcv

tcp_input.c

/*	TCP 接收数据的入口
 *	From tcp_input.c	
 *	skb:从 IP 层传递过来的数据报
 */

int tcp_v4_rcv(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct sk_buff *skb_to_free;
	int sdif = inet_sdif(skb);
	int dif = inet_iif(skb);
	const struct iphdr *iph;
	const struct tcphdr *th;
	bool refcounted;
	struct sock *sk;
	int ret;
	/* 如果不是发往本机的就直接丢弃 */
	if (skb->pkt_type != PACKET_HOST)
		goto discard_it;

	/* Count it even if it's bad */
	__TCP_INC_STATS(net, TCP_MIB_INSEGS);
	
	/*
	如果 TCP 段在传输过程中被分片了,则到达本地后会在 IP 层重新组装。
	组装完成后,报文分片都存储在链表中。在此,需把存储在分片中的报文
	复制到 SKB 的线性存储区域中。如果发生异常,则丢弃该报文。
	*/
	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		goto discard_it;

	th = (const struct tcphdr *)skb->data;//获得tcp头

	/*
	如果 TCP 的首部长度小于不带数据的 TCP 的首部长度,则说明 TCP 数据异常。
	统计相关信息后,丢弃。
	*/
	if (unlikely(th->doff < sizeof(struct tcphdr) / 4))
		goto bad_packet;
	//保证skb的线性区域至少包括实际的TCP首部
	if (!pskb_may_pull(skb, th->doff * 4))
		goto discard_it;

	/* An explanation is required here, I think.
	 * Packet length and doff are validated by header prediction,
	 * provided case of th->doff==0 is eliminated.
	 * So, we defer the checks. */
	//验证 TCP 首部中的校验和,如校验和有误,则说明报文已损坏,统计相关信息后丢弃。
	if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo))
		goto csum_error;

	//初始化skb中的控制块
	th = (const struct tcphdr *)skb->data;//tcp头
	iph = ip_hdr(skb);//IP头

	/* 在 ehash 或 bhash 散列表中根据地址和端口来查找传
	输控制块。如果在 ehash 中找到,则表示已经经历了三次握手并且已建立了连接,可以
	进行正常的通信。如果在 bhash 中找到,则表示已经绑定已经绑定了端口,处于侦听
	状态。如果在两个散列表中都查找不到,说明此时对应的传输控制块还没有创建,跳转
	到no_tcp_socket 处处理。
	*/
lookup:
	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
			       th->dest, sdif, &refcounted);
	if (!sk)
		goto no_tcp_socket;

process:
//TCP_TIME_WAIT需要做特殊处理,这里先不关注
	if (sk->sk_state == TCP_TIME_WAIT)
		goto do_time_wait;

	if (sk->sk_state == TCP_NEW_SYN_RECV) {
		struct request_sock *req = inet_reqsk(sk);
		bool req_stolen = false;
		struct sock *nsk;

		sk = req->rsk_listener;
		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
			sk_drops_add(sk, skb);
			reqsk_put(req);
			goto discard_it;
		}
		if (tcp_checksum_complete(skb)) {
			reqsk_put(req);
			goto csum_error;
		}
		if (unlikely(sk->sk_state != TCP_LISTEN)) {
			inet_csk_reqsk_queue_drop_and_put(sk, req);
			goto lookup;
		}
		/* We own a reference on the listener, increase it again
		 * as we might lose it too soon.
		 */
		sock_hold(sk);
		refcounted = true;
		nsk = NULL;
		if (!tcp_filter(sk, skb)) {
			th = (const struct tcphdr *)skb->data;
			iph = ip_hdr(skb);
			tcp_v4_fill_cb(skb, iph, th);
			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
		}
		if (!nsk) {
			reqsk_put(req);
			if (req_stolen) {
				/* Another cpu got exclusive access to req
				 * and created a full blown socket.
				 * Try to feed this packet to this socket
				 * instead of discarding it.
				 */
				tcp_v4_restore_cb(skb);
				sock_put(sk);
				goto lookup;
			}
			goto discard_and_relse;
		}
		if (nsk == sk) {
			reqsk_put(req);
			tcp_v4_restore_cb(skb);
		} else if (tcp_child_process(sk, nsk, skb)) {
			tcp_v4_send_reset(nsk, skb);
			goto discard_and_relse;
		} else {
			sock_put(sk);
			return 0;
		}
	}
	/*ttl 小于给定的最小的 ttl*/
	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
		goto discard_and_relse;
	}
	//查找 IPsec 数据库,如果查找失败,进行相应处理.
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;
	//md5 相关
	if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))
		goto discard_and_relse;

	nf_reset_ct(skb);
	//TCP套接字过滤器,如果数据包被过滤掉了,结束处理过程 -> sk_filter_trim_cap
	if (tcp_filter(sk, skb))
		goto discard_and_relse;
	th = (const struct tcphdr *)skb->data;
	iph = ip_hdr(skb);
	tcp_v4_fill_cb(skb, iph, th);
	//到了传输层,该字段已经没有意义,将其置为空
	skb->dev = NULL;

	/*LISTEN 状态 */
	if (sk->sk_state == TCP_LISTEN) {
		ret = tcp_v4_do_rcv(sk, skb);//交由tcp_v4_do_rcv()处理
		goto put_and_return;
	}

	sk_incoming_cpu_update(sk);
	//先持锁,这样进程上下文和其它软中断则无法操作该TCB
	bh_lock_sock_nested(sk);
	tcp_segs_in(tcp_sk(sk), skb);
	ret = 0;
	 //如果当前TCB没有被进程上下文锁定,首先尝试将数据包放入prequeue队列,
	//如果prequeue队列没有处理,再将其处理后放入receive队列。如果TCB已
	//经被进程上下文锁定,那么直接将数据包放入backlog队列
	if (!sock_owned_by_user(sk)) {
		skb_to_free = sk->sk_rx_skb_cache;
		sk->sk_rx_skb_cache = NULL;
		ret = tcp_v4_do_rcv(sk, skb);
	} else {
		if (tcp_add_backlog(sk, skb))//TCB被用户进程锁定,直接将数据包放入backlog队列
			goto discard_and_relse;
		skb_to_free = NULL;
	}
	bh_unlock_sock(sk);//释放锁
	if (skb_to_free)
		__kfree_skb(skb_to_free);

put_and_return:
	if (refcounted)
		sock_put(sk);//释放TCB引用计数,当计数为 0 的时候,使用 sk\_free 释放传输控制块

	return ret;//返回处理结果
	
//处理没有创建传输控制块收到报文,校验错误,坏包的情况,给对端发送 RST 报文。
no_tcp_socket:
/* 查找 IPsec 数据库,如果查找失败,进行相应处理.*/
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	tcp_v4_fill_cb(skb, iph, th);

	if (tcp_checksum_complete(skb)) {
csum_error:
		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
bad_packet:
		__TCP_INC_STATS(net, TCP_MIB_INERRS);
	} else {
		tcp_v4_send_reset(NULL, skb);
	}

discard_it:
	/* Discard frame. */
	//丢弃帧
	kfree_skb(skb);
	return 0;

discard_and_relse:
	sk_drops_add(sk, skb);
	if (refcounted)
		sock_put(sk);
	goto discard_it;
//处理TIME_WAIT状态
do_time_wait:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		/*inet_timewait_sock 减少引用计数 */
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}

	tcp_v4_fill_cb(skb, iph, th);

	if (tcp_checksum_complete(skb)) {
		inet_twsk_put(inet_twsk(sk));
		goto csum_error;
	}
	//根据返回值进行相应处理
	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
	case TCP_TW_SYN: {
		struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
							&tcp_hashinfo, skb,
							__tcp_hdrlen(th),
							iph->saddr, th->source,
							iph->daddr, th->dest,
							inet_iif(skb),
							sdif);
		if (sk2) {
			inet_twsk_deschedule_put(inet_twsk(sk));
			sk = sk2;
			tcp_v4_restore_cb(skb);
			refcounted = false;
			goto process;
		}
	}
		/* to ACK */
		fallthrough;
	case TCP_TW_ACK:
		tcp_v4_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		tcp_v4_send_reset(sk, skb);
		inet_twsk_deschedule_put(inet_twsk(sk));
		goto discard_it;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

tcp_v4_do_rcv

所在目录:/linux-5.11.1/net/ipv4/tcp_ipv4.c。


/* The socket must have it's spinlock held when we get
 * here, unless it is a TCP_LISTEN socket.
 * socket必须有自旋锁,除非是TCP_LISTEN socket.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 * 我们这里有一个潜在的双锁情况,所以即使在做积压处理时,我们也使用BH锁定方案。这是因为我们不能用原来的自旋锁来睡觉。
 */
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sock *rsk;

	 /* 当状态为ESTABLISHED时,用tcp_rcv_established()接收处理 */
	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		struct dst_entry *dst = sk->sk_rx_dst;

		sock_rps_save_rxhash(sk, skb);
		sk_mark_napi_id(sk, skb);
		if (dst) {
			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
			    !dst->ops->check(dst, 0)) {
				dst_release(dst);
				sk->sk_rx_dst = NULL;
			}
		}
		/* 连接已建立时的处理路径 */
		tcp_rcv_established(sk, skb);
		return 0;
	}

	if (tcp_checksum_complete(skb))
		goto csum_err;

	/* 如果这个sock处于监听状态,被动打开时的处理,包括收到SYN或ACK */
	if (sk->sk_state == TCP_LISTEN) {
		/*
		NULL,错误
		nsk == sk,接收到 SYN
		nsk != sk,接收到 ACK
		*/
		struct sock *nsk = tcp_v4_cookie_check(sk, skb);

		if (!nsk)
			goto discard;
		if (nsk != sk) {
			if (tcp_child_process(sk, nsk, skb)) { /* 处理新的sock ,初始化子传输控制块*/
				rsk = nsk;
				goto reset;//失败时,给客户端发送 RST 段进行复位
			}
			return 0;
		}
	} else
		sock_rps_save_rxhash(sk, skb);

	/* 处理除了ESTABLISHED和TIME_WAIT之外的所有状态 */
	if (tcp_rcv_state_process(sk, skb)) {
		rsk = sk;
		goto reset;
	}
	return 0;

reset:
	tcp_v4_send_reset(rsk, skb); /* 发送被动的RST包 */
discard:
	kfree_skb(skb);
	/* Be careful here. If this function gets more complicated and
	 * gcc suffers from register pressure on the x86, sk (in %ebx)
	 * might be destroyed here. This current version compiles correctly,
	 * but you have been warned.
	 */
	return 0;

csum_err:
	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
	goto discard;
}

tcp_rcv_state_process

tcp_input.c
tcp_rcv_state_process实现了 TCP 状态机相对核心的一个部分。该函数可以处理除 ESTABLISHED 和 TIME_WAIT 状态以外的情况下的接收过程。

/*
 *	This function implements the receiving procedure of RFC 793 for
 *	all states except ESTABLISHED and TIME_WAIT.
 *	It's called from both tcp_v4_rcv and tcp_v6_rcv and should be
 *	address independent.
 *	该函数实现了除已建立状态和TIME_WAIT外的所有状态的RFC 793的接收过程。
 *	它从tcp_v4_rcv和tcp_v6_rcv都调用,应该是独立的地址。
 *sk: 传输控制块
 *skb:缓存块
 */

int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	const struct tcphdr *th = tcp_hdr(skb);
	struct request_sock *req;
	int queued = 0;
	bool acceptable;

	switch (sk->sk_state) {
	case TCP_CLOSE:/* CLOSE 状态的处理代码 */
		goto discard;

	case TCP_LISTEN:/* LISTEN 状态的处理代码 */
		if (th->ack)
			return 1;

		if (th->rst)
			goto discard;

		if (th->syn) {
			if (th->fin)
				goto discard;
			/* It is possible that we process SYN packets from backlog,
			 * so we need to make sure to disable BH and RCU right there.
			 */
			rcu_read_lock();
			local_bh_disable();
			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
			local_bh_enable();
			rcu_read_unlock();

			if (!acceptable)
				return 1;
			consume_skb(skb);
			return 0;
		}
		goto discard;

	case TCP_SYN_SENT://客户端发送SYN第一次握手,等待服务端回复SYN+ACK第二次握手
		tp->rx_opt.saw_tstamp = 0;
		tcp_mstamp_refresh(tp);
		queued = tcp_rcv_synsent_state_process(sk, skb, th);
		if (queued >= 0)
			return queued;

		/* Do step6 onward by hand. */
		tcp_urg(sk, skb, th);
		__kfree_skb(skb);
		tcp_data_snd_check(sk);
		return 0;
	}

	tcp_mstamp_refresh(tp);
	tp->rx_opt.saw_tstamp = 0;
	req = rcu_dereference_protected(tp->fastopen_rsk,
					lockdep_sock_is_held(sk));
	if (req) {
		bool req_stolen;

		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
		    sk->sk_state != TCP_FIN_WAIT1);

		if (!tcp_check_req(sk, skb, req, true, &req_stolen))
			goto discard;
	}

	if (!th->ack && !th->rst && !th->syn)
		goto discard;

	if (!tcp_validate_incoming(sk, skb, th, 0))
		return 0;

	/* step 5: check the ACK field */
	//对收到的 ACK 段进行处理判断是否正确接收,如果正确接收就会发送返回非零值。
	acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
				      FLAG_UPDATE_TS_RECENT |
				      FLAG_NO_CHALLENGE_ACK) > 0;

	if (!acceptable) {
		if (sk->sk_state == TCP_SYN_RECV)
			return 1;	/* send one RST */
		tcp_send_challenge_ack(sk, skb);
		goto discard;
	}
	switch (sk->sk_state) {
	case TCP_SYN_RECV://服务端发送SYN+ACK第二次握手,等待客户端回复ACK第三次握手
		tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
		if (!tp->srtt_us)
			tcp_synack_rtt_meas(sk, req);

		if (req) {
			tcp_rcv_synrecv_state_fastopen(sk);
		} else {
			tcp_try_undo_spurious_syn(sk);
			tp->retrans_stamp = 0;
			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,
					  skb);
			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
		}
		smp_mb();
		//进行一系列的初始化,开启相应拥塞控制等,并且将 TCP 的状态置为 TCP_ESTABLISHED。
		tcp_set_state(sk, TCP_ESTABLISHED);
		sk->sk_state_change(sk);

		/* Note, that this wakeup is only for marginal crossed SYN case.
		 * Passively open sockets are not waked up, because
		 * sk->sk_sleep == NULL and sk->sk_socket == NULL.
		 */
		 //发信号给那些将通过该套接口发送数据的进程,通知它们套接口目前已经可以发送数据了
		if (sk->sk_socket)
			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);

		//初始化传输控制块的各个字段,对时间戳进行处理。
		tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
		tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);

		if (tp->rx_opt.tstamp_ok)
			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;

		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
			tcp_update_pacing_rate(sk);

		/* Prevent spurious tcp_cwnd_restart() on first data packet */
		tp->lsndtime = tcp_jiffies32;

		//更新最近一次的发送数据报的时间,初始化与路径 MTU 有关的成员,并计算有关TCP 首部预测的标志
		tcp_initialize_rcv_mss(sk);
		tcp_fast_path_on(tp);
		break;

	case TCP_FIN_WAIT1: {//发送SIN+ACK第一次挥手后,等待对方回复ACK第二次挥手
		int tmo;

		if (req)
			tcp_rcv_synrecv_state_fastopen(sk);

		if (tp->snd_una != tp->write_seq)
			break;

		tcp_set_state(sk, TCP_FIN_WAIT2);
		sk->sk_shutdown |= SEND_SHUTDOWN;

		sk_dst_confirm(sk);

		if (!sock_flag(sk, SOCK_DEAD)) {
			/* Wake up lingering close() */
			sk->sk_state_change(sk);
			break;
		}

		if (tp->linger2 < 0) {
			tcp_done(sk);
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
			return 1;
		}
		if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
		    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
			/* Receive out of order FIN after close() */
			if (tp->syn_fastopen && th->fin)
				tcp_fastopen_active_disable(sk);
			tcp_done(sk);
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
			return 1;
		}

		tmo = tcp_fin_time(sk);
		if (tmo > TCP_TIMEWAIT_LEN) {
			inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
		} else if (th->fin || sock_owned_by_user(sk)) {
			/* Bad case. We could lose such FIN otherwise.
			 * It is not a big problem, but it looks confusing
			 * and not so rare event. We still can lose it now,
			 * if it spins in bh_lock_sock(), but it is really
			 * marginal case.
			 */
			inet_csk_reset_keepalive_timer(sk, tmo);
		} else {
			tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
			goto discard;
		}
		break;
	}

	case TCP_CLOSING:
		if (tp->snd_una == tp->write_seq) {
			tcp_time_wait(sk, TCP_TIME_WAIT, 0);
			goto discard;
		}
		break;

	case TCP_LAST_ACK:
		if (tp->snd_una == tp->write_seq) {
			tcp_update_metrics(sk);
			tcp_done(sk);
			goto discard;
		}
		break;
	}

	/* step 6: check the URG bit */
	tcp_urg(sk, skb, th);

	/* step 7: process the segment text */
	switch (sk->sk_state) {
	case TCP_CLOSE_WAIT:
	case TCP_CLOSING:
	case TCP_LAST_ACK:
		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
			if (sk_is_mptcp(sk))
				mptcp_incoming_options(sk, skb);
			break;
		}
		fallthrough;
	case TCP_FIN_WAIT1:
	case TCP_FIN_WAIT2:
		/* RFC 793 says to queue data in these states,
		 * RFC 1122 says we MUST send a reset.
		 * BSD 4.4 also does reset.
		 */
		if (sk->sk_shutdown & RCV_SHUTDOWN) {
			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
				tcp_reset(sk, skb);
				return 1;
			}
		}
		fallthrough;
	case TCP_ESTABLISHED://对已接收到的 TCP 段排队,在建立连接阶段一般不会收到 TCP 段
		tcp_data_queue(sk, skb);
		queued = 1;
		break;
	}

	/* tcp_data could move socket to TIME-WAIT */
	//此时状态不为 CLOSE,故而就回去检测是否数据和 ACK 要发送。
	//其次,根据 queue 标志来确定是否释放接收到的 TCP 段,如果接收到的 TCP 段已添加到接收队列中,则不释放
	if (sk->sk_state != TCP_CLOSE) {
		tcp_data_snd_check(sk);
		tcp_ack_snd_check(sk);
	}

	if (!queued) {
discard:
		tcp_drop(sk, skb);
	}
	return 0;
}

tcp_rcv_established

1、状态为ESTABLISHED时,用tcp_rcv_established()接收处理。
2. 状态为LISTEN时,说明这个sock处于监听状态,用于被动打开的接收处理,包括SYN和ACK。
3. 当状态不为ESTABLISHED或TIME_WAIT时,用tcp_rcv_state_process()处理。

所在目录:/linux-5.11.1/net/ipv4/tcp_input.c。

int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
			struct tcphdr *th, unsigned len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int res;
 
	/*
	 *	Header prediction.
	 *	The code loosely follows the one in the famous
	 *	"30 instruction TCP receive" Van Jacobson mail.
	 *
	 *	Van's trick is to deposit buffers into socket queue
	 *	on a device interrupt, to call tcp_recv function
	 *	on the receive process context and checksum and copy
	 *	the buffer to user space. smart...
	 *
	 *	Our current scheme is not silly either but we take the
	 *	extra cost of the net_bh soft interrupt processing...
	 *	We do checksum and copy also but from device to kernel.
	 */
 
	tp->rx_opt.saw_tstamp = 0;
 
	/*	pred_flags is 0xS?10 << 16 + snd_wnd
	 *	if header_prediction is to be made
	 *	'S' will always be tp->tcp_header_len >> 2
	 *	'?' will be 0 for the fast path, otherwise pred_flags is 0 to
	 *  turn it off	(when there are holes in the receive
	 *	 space for instance)
	 *	PSH flag is ignored.
	 */
	//预定向标志和输入数据段的标志比较
	//数据段序列号是否正确
	if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
	    TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
	    !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
		int tcp_header_len = tp->tcp_header_len;
 
		/* Timestamp header prediction: tcp_header_len
		 * is automatically equal to th->doff*4 due to pred_flags
		 * match.
		 */
 
		/* Check timestamp */
		//时间戳选项之外如果还有别的选项就送给Slow Path处理
		if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
			/* No? Slow path! */
			if (!tcp_parse_aligned_timestamp(tp, th))
				goto slow_path;
 
			//对数据包做PAWS快速检查,如果检查走Slow Path处理
			/* If PAWS failed, check it more carefully in slow path */
			if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
				goto slow_path;
 
			/* DO NOT update ts_recent here, if checksum fails
			 * and timestamp was corrupted part, it will result
			 * in a hung connection since we will drop all
			 * future packets due to the PAWS test.
			 */
		}
 
		//数据包长度太小
		if (len <= tcp_header_len) {
			/* Bulk data transfer: sender */
			if (len == tcp_header_len) {
				/* Predicted packet is in window by definition.
				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
				 * Hence, check seq<=rcv_wup reduces to:
				 */
				if (tcp_header_len ==
				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
				    tp->rcv_nxt == tp->rcv_wup)
					tcp_store_ts_recent(tp);
 
				/* We know that such packets are checksummed
				 * on entry.
				 */
				tcp_ack(sk, skb, 0);
				__kfree_skb(skb);
				tcp_data_snd_check(sk);
				return 0;
			} else { /* Header too small */
				TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
				goto discard;
			}
		} else {
			int eaten = 0;
			int copied_early = 0;
 
			//tp->copied_seq表示未读的数据包序列号
			//tp->rcv_nxt表示下一个期望读取的数据包序列号
			//len-tcp_header_len小于tp->ucpoy.len表示数据包还没有复制完
			if (tp->copied_seq == tp->rcv_nxt &&
			    len - tcp_header_len <= tp->ucopy.len) {
#ifdef CONFIG_NET_DMA
				if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
					copied_early = 1;
					eaten = 1;
				}
#endif
				//当前进程是否有锁定
				//当前进程的全局指针current
				//tp->ucopy.task指针是否等于当前进程
				if (tp->ucopy.task == current &&
				    sock_owned_by_user(sk) && !copied_early) {
					__set_current_state(TASK_RUNNING);
				//将数据包复制到应用层空间
					if (!tcp_copy_to_iovec(sk, skb, tcp_header_len))
						eaten = 1;
				}
				//复制成功
				if (eaten) {
					/* Predicted packet is in window by definition.
					 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
					 * Hence, check seq<=rcv_wup reduces to:
					 */
					if (tcp_header_len ==
					    (sizeof(struct tcphdr) +
					     TCPOLEN_TSTAMP_ALIGNED) &&
					    tp->rcv_nxt == tp->rcv_wup)
						tcp_store_ts_recent(tp);
 
					tcp_rcv_rtt_measure_ts(sk, skb);
 
					__skb_pull(skb, tcp_header_len);
					tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
					NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
				}
				//清除prequeue队列中已经复制的数据包,并回复ack
				if (copied_early)
					tcp_cleanup_rbuf(sk, skb->len);
			}
			//复制不成功
			if (!eaten) {
				//从新计算校验和
				if (tcp_checksum_complete_user(sk, skb))
					goto csum_error;
 
				/* Predicted packet is in window by definition.
				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
				 * Hence, check seq<=rcv_wup reduces to:
				 */
				if (tcp_header_len ==
				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
				    tp->rcv_nxt == tp->rcv_wup)
					tcp_store_ts_recent(tp);
 
				tcp_rcv_rtt_measure_ts(sk, skb);
 
				if ((int)skb->truesize > sk->sk_forward_alloc)
					goto step5;
 
				//大块数据传送
				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
				/* Bulk data transfer: receiver */
				//去掉tcp头部
				__skb_pull(skb, tcp_header_len);
				//将数据包加入到sk_receive_queue队列中
				__skb_queue_tail(&sk->sk_receive_queue, skb);
				skb_set_owner_r(skb, sk);
				tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
			}
 
			//更新延迟回答时钟超时间隔值
			tcp_event_data_recv(sk, skb);
 
			if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
				/* Well, only one small jumplet in fast path... */
				tcp_ack(sk, skb, FLAG_DATA);
				tcp_data_snd_check(sk);
				if (!inet_csk_ack_scheduled(sk))
					goto no_ack;
			}
 
			//收到数据后回复ack确认
			if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
				__tcp_ack_snd_check(sk, 0);
no_ack:
#ifdef CONFIG_NET_DMA
			if (copied_early)
				__skb_queue_tail(&sk->sk_async_wait_queue, skb);
			else
#endif
			if (eaten)
				__kfree_skb(skb);
			else
				//no_ack标签表明套接字已经准备好下一次应用读
				sk->sk_data_ready(sk, 0);
			return 0;
		}
	}
 
slow_path:
	if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb))
		goto csum_error;
 
	/*
	 *	Standard slow path.
	 */
 
	res = tcp_validate_incoming(sk, skb, th, 1);
	if (res <= 0)
		return -res;
 
step5:
	if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
		goto discard;
 
	tcp_rcv_rtt_measure_ts(sk, skb);
 
	/* Process urgent data. */
	//紧急数据段处理
	tcp_urg(sk, skb, th);
 
	/* step 7: process the segment text */
	//根据情况将数据复制到应用层或者
	//将数据加入sk_receive_queue常规队列中
	tcp_data_queue(sk, skb);
 
	tcp_data_snd_check(sk);
	tcp_ack_snd_check(sk);
	return 0;
 
csum_error:
	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 
discard:
	__kfree_skb(skb);
	return 0;
}

tcp_recvmsg

用户进程调用recvfrom读取套接字缓冲区上的数据,实际是调用tcp_recvmsg函数将数据包从内核地址空间复制到用户考地址空间。
所在目录:/linux-5.11.1/net/ipv4/tcp.c。

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)
{
	//获取TCP套接字结构
	struct tcp_sock *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct task_struct *user_recv = NULL;
	int copied_early = 0;
	struct sk_buff *skb;
	u32 urg_hole = 0;
 
	//锁住套接字,其实就是设置sk->sk_lock.owned  = 1
	//当产生软中断调用tcp_v4_rcv获取套接字sock发现
	//sock处于进程上下文,就会把数据包加入到balock_queue队列中
	lock_sock(sk);
 
	TCP_CHECK_TIMER(sk);
 
	err = -ENOTCONN;
	//套接字当前处于监听状态就直接跳出
	if (sk->sk_state == TCP_LISTEN)
		goto out;
 
	//查实时间,如果是非阻塞模式就为0
	timeo = sock_rcvtimeo(sk, nonblock);
 
	//紧急处理数据
	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;
 
	//未读取数据包的开始序列号
	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}
 
	//取len和sk->rcvlowat中的最小值
	//MSG_WAITALL标志是判断是否要接受完整的数据包后再拷贝复制数据包
	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
//配置了DMA可以直接通过访问内存复制数据到用户地址空间
#ifdef CONFIG_NET_DMA
	tp->ucopy.dma_chan = NULL;
	preempt_disable();
	skb = skb_peek_tail(&sk->sk_receive_queue);
	{
		int available = 0;
 
		if (skb)
			available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
		if ((available < target) &&
		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
		    !sysctl_tcp_low_latency &&
		    dma_find_channel(DMA_MEMCPY)) {
			preempt_enable_no_resched();
			tp->ucopy.pinned_list =
					dma_pin_iovec_pages(msg->msg_iov, len);
		} else {
			preempt_enable_no_resched();
		}
	}
#endif
 
	//主循环,复制数据到用户地址空间直到target为0
	do {
		u32 offset;
 
		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		//遇到紧急数据停止处理跳出循环
		if (tp->urg_data && tp->urg_seq == *seq) {
			if (copied)
				break;
			//检测套接字上是否有信号等待处理,确保能处理SIGUSR信号。
			if (signal_pending(current)) {
				//检查是否超时
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}
 
		/* Next get a buffer. */
 
		//循环变量接受缓冲区队列receive_queue队列
		skb_queue_walk(&sk->sk_receive_queue, skb) {
			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
			     KERN_INFO "recvmsg bug: copied %X "
				       "seq %X rcvnxt %X fl %X\n", *seq,
				       TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
				       flags))
				break;
			//未读取数据包的序列号和已经读取数据包的序列号差
			//如果这个差小于数据包长度skb->len,表示这是我们要找的数据包
			//因为是最小的序列号
			offset = *seq - TCP_SKB_CB(skb)->seq;
			//如果是syn表就跳过
			if (tcp_hdr(skb)->syn)
				offset--;
			//找到了skb,跳转到found_ok_skb处完成复制工作
			if (offset < skb->len)
				goto found_ok_skb;
			//发现是fin包调转到fin处理标签处
			if (tcp_hdr(skb)->fin)
				goto found_fin_ok;
			WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: "
					"copied %X seq %X rcvnxt %X fl %X\n",
					*seq, TCP_SKB_CB(skb)->seq,
					tp->rcv_nxt, flags);
		}
		/* Well, if we have backlog, try to process it now yet. */
		//缓冲区recieve_queue队列中已经没有数据
		//而且backlog_queue队列中也没有数据了就跳出循环
		if (copied >= target && !sk->sk_backlog.tail)
			break;
		if (copied) {
			//检查套接字的状态是否是关闭
			//或者收到远端的断开请求,则要跳出复制循环
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current))
				break;
		} else {
			//copied为0表示应用层没有复制到数据,没有复制到数据有三种可能
			//第一是套接字已经关闭了,第二是缓冲区根本没有数据 
			//第三是其他错误
			if (sock_flag(sk, SOCK_DONE))
				break;
			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;
			if (sk->sk_state == TCP_CLOSE) {
				//当用户关闭套接字会设置SOCK_DON标志
				//连接状态是TCP_CLOSE,SOCK_DONE标志就不会0
				if (!sock_flag(sk, SOCK_DONE)) {
					/* This occurs when user tries to read
					 * from never connected socket.
					 */
					copied = -ENOTCONN;
					break;
				}
				break;
			}
			//查看是否阻塞,不阻塞直接返回
			//返回的错误标志是EAGAIN
			if (!timeo) {
				copied = -EAGAIN;
				break;
			}
			//读取数据失败可能是其他错误
			//返回错误原因
			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}
		//根据已经复制数据长度copied清除recieve_queue队列
		//并且回复对端ack包
		tcp_cleanup_rbuf(sk, copied);
		
		//sk_recieve_queue队列中已无数据需要处理就处理preueue队列上的数据
		//prequeue队列的处理现场是用户进程
		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
			/* Install new reader */
			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
				//复制pre_queue队列的进程是当前进程
				user_recv = current;
				//处理数据的用户进程
				tp->ucopy.task = user_recv;
				//应用层接受数据的缓冲区地址
				tp->ucopy.iov = msg->msg_iov;
			}
			//拷贝数据长度
			tp->ucopy.len = len;
			WARN_ON(tp->copied_seq != tp->rcv_nxt &&
				!(flags & (MSG_PEEK | MSG_TRUNC)));
			 //prequeu队列不为空,必须在释放套接字之前处理这些数据包
			 //如果这个处理没有完成则数据段顺序将会被破坏,接受段处理顺序是
			 //flight中的数据、backlog队列、prequeue队列、sk_receive_queue队列,只有当前队列处理
			 //完成了才会去处理下一个队列。prequeue队列可能在循环结束套接字释放前又
			 //加入数据包,调转到do_prequeue标签处理
			if (!skb_queue_empty(&tp->ucopy.prequeue))
				goto do_prequeue;
			/* __ Set realtime policy in scheduler __ */
		}
#ifdef CONFIG_NET_DMA
		if (tp->ucopy.dma_chan)
			dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
#endif
		//数据包复制完毕
		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			//从backlog队列中复制数据包到sk_receive_queue队列
			release_sock(sk);
			lock_sock(sk);
		} else
			//已经没有数据要处理,将套接字放入等待状态,进程进入睡眠
			//如果有数据段来了tcp_prequeue会唤醒进程,软中断会判断用户进程睡眠
			//如果睡眠就会把数据放到prequeue队列中
			sk_wait_data(sk, &timeo);
#ifdef CONFIG_NET_DMA
		tcp_service_net_dma(sk, false);  /* Don't block */
		tp->ucopy.wakeup = 0;
#endif
 
		if (user_recv) {
			int chunk;
 
			/* __ Restore normal policy in scheduler __ */
 
			if ((chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
				//更新剩余数据长度
				len -= chunk;
				//更新已经复制的数据长度
				copied += chunk;
			}
 
			//tp->rcv_nxt == tp->copied_seq判断receive_queue队列中释放有数据
			if (tp->rcv_nxt == tp->copied_seq &&
			    !skb_queue_empty(&tp->ucopy.prequeue)) {
do_prequeue:
				//处理prequeue队列
				tcp_prequeue_process(sk);
 
				if ((chunk = len - tp->ucopy.len) != 0) {
					NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
					//更新剩余需要复制数据长度
					len -= chunk;
					//更新复制的数据copied
					copied += chunk;
				}
			}
		}
		if ((flags & MSG_PEEK) &&
		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
			if (net_ratelimit())
				printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
				       current->comm, task_pid_nr(current));
			peek_seq = tp->copied_seq;
		}
		continue;
 
	//处理sk_receive_queue队列中的数据
	found_ok_skb:
		/* Ok so how much can we use? */
		used = skb->len - offset;
		if (len < used)
			used = len;
 
		/* Do we have urgent data here? */
		//首先查看是否有紧急数据需要处理
		//如果设置套接字选项设置了SO_OOBINLINE就不需要处理紧急数据
		//因为有单独处理
		if (tp->urg_data) {
			u32 urg_offset = tp->urg_seq - *seq;
			if (urg_offset < used) {
				if (!urg_offset) {
					if (!sock_flag(sk, SOCK_URGINLINE)) {
						++*seq;
						urg_hole++;
						offset++;
						used--;
						if (!used)
							goto skip_copy;
					}
				} else
					used = urg_offset;
			}
		}
 
		if (!(flags & MSG_TRUNC)) {
#ifdef CONFIG_NET_DMA
			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
				tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 
			if (tp->ucopy.dma_chan) {
				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
					tp->ucopy.dma_chan, skb, offset,
					msg->msg_iov, used,
					tp->ucopy.pinned_list);
 
				if (tp->ucopy.dma_cookie < 0) {
 
					printk(KERN_ALERT "dma_cookie < 0\n");
 
					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}
 
				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
 
				if ((offset + used) == skb->len)
					copied_early = 1;
 
			} else
#endif
			{
				//将数据包从内核地址空间复制到用户地址空间
				err = skb_copy_datagram_iovec(skb, offset,
						msg->msg_iov, used);
				if (err) {
					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}
			}
		}
 
		//更新数据包序列号
		*seq += used;
		//更新已复制的数据长度
		copied += used;
		//更新剩下需要复制的数据长度
		len -= used;
 
		//重新调整tcp接受窗口
		tcp_rcv_space_adjust(sk);
 
skip_copy:
		if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
			tp->urg_data = 0;
			//处理完了紧急数据,调转到Fast Path处理
			tcp_fast_path_check(sk);
		}
		if (used + offset < skb->len)
			continue;
 
		if (tcp_hdr(skb)->fin)
			goto found_fin_ok;
		if (!(flags & MSG_PEEK)) {
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		continue;
 
	//套接字状态是Fin
	found_fin_ok:
		/* Process the FIN. */
		//序列号加1
		++*seq;
		if (!(flags & MSG_PEEK)) {
			//重新计算tcp窗口
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		break;
	} while (len > 0);
 
	//主循环处理结束后,prequeue队列中还有数据则必须继续处理
	if (user_recv) {
		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
			int chunk;
 
			tp->ucopy.len = copied > 0 ? len : 0;
 
			tcp_prequeue_process(sk);
 
			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
				len -= chunk;
				copied += chunk;
			}
		}
 
		tp->ucopy.task = NULL;
		tp->ucopy.len = 0;
	}
 
#ifdef CONFIG_NET_DMA
	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
	tp->ucopy.dma_chan = NULL;
 
	if (tp->ucopy.pinned_list) {
		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
		tp->ucopy.pinned_list = NULL;
	}
#endif
 
	/* According to UNIX98, msg_name/msg_namelen are ignored
	 * on connected socket. I was just happy when found this 8) --ANK
	 */
 
	/* Clean up data we have read: This will do ACK frames. */
	tcp_cleanup_rbuf(sk, copied);
 
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
 
	if (copied > 0)
		uid_stat_tcp_rcv(current_uid(), copied);
	return copied;
 
out:
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return err;
 
recv_urg:
	//紧急数据处理,复制紧急数据到用户地址空间
	err = tcp_recv_urg(sk, msg, len, flags);
	if (err > 0)
		uid_stat_tcp_rcv(current_uid(), err);
	goto out;
}

数据结构

通过sk_buff * 获得三个协议头的方法。

const struct tcphdr *th = tcp_hdr(skb);
const struct iphdr *ih = ip_hdr(skb);
const struct ethhdr *eh = eth_hdr(skb);

ethhdr

/linux-5.11.1/include/uapi/linux/if_ether.h

struct ethhdr {
	unsigned char	h_dest[ETH_ALEN];	/* destination eth addr	*/
	unsigned char	h_source[ETH_ALEN];	/* source ether addr	*/
	__be16		h_proto;		/* packet type ID field	*/
} __attribute__((packed));

iphdr

\linux-5.11.1\include\uapi\linux\ip.h

struct iphdr {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u8	ihl:4,//首部长度(4位)
		version:4;//版本(4位)
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u8	version:4,
  		ihl:4;
#else
#error	"Please fix "
#endif
	__u8	tos;// 服务类型字段(8位)
	__be16	tot_len;//总长度字段(16位)是指整个IP数据报的长度
	__be16	id;//总长度字段(16位)是指整个IP数据报的长度,
	__be16	frag_off;//分段偏移
	__u8	ttl;//TTL
	__u8	protocol;//协议字段
	__sum16	check;//首部校验和字段
	__be32	saddr;//32源IP地址
	__be32	daddr;//32位目的IP地址
	/*The options start here. */
};

tcphdr

\linux-5.11.1\include\uapi\linux\tcp.h

struct tcphdr {
	__be16	source;//16位源端口
	__be16	dest;//16位源端口
	__be32	seq;//序列号
	__be32	ack_seq;//确认号
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u16	res1:4,// 保留位
		doff:4,//TCP头长度,指明了TCP头部包含了多少个32位的字
		fin:1,//释放一个连接,它表示发送方已经没有数据要传输了。
		syn:1,//同步序号,用来发送一个连接。syn被用于建立连接的过程。
		rst:1,//该位用于重置一个混乱的连接,之所以混乱,可能是因为主机崩溃或者其他原因。
		psh:1,
		ack:1,//ack位被设置为1表示tcphdr->ack_seq是有效的,如果ack为0,则表示该数据段不包含确认信息
		urg:1,//紧急指针有效
		ece:1,
		cwr:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
	__u16	doff:4,
		res1:4,
		cwr:1,
		ece:1,
		urg:1,
		ack:1,
		psh:1,
		rst:1,
		syn:1,
		fin:1;
#else
#error	"Adjust your  defines"
#endif	
	__be16	window;//16位滑动窗口大小,单位为字节,起始于确认序号字段指明的值,这个值是接收端期望接收的字节数,其最大值为63353字节。
	__sum16	check;//校验和,覆盖了整个tcp报文端,是一个强制性的字段,一定是由发送端计算和存储,并由接收端进行验证。
	__be16	urg_ptr;//  这个域被用来指示紧急数据在当前数据段中的为止,它是一个相当于当前序列号的字节偏移量。这个设置可以代替中断信息。
};

udphdr

\linux-5.11.1\include\uapi\linux\udp.h

struct udphdr {
	__be16	source;//源端口号
	__be16	dest;//目的端口号
	__be16	len;//整个UDP数据报的长度 = 报头+载荷。
	__sum16	check;//检测UDP数据(包含头部和数据部分)报在传输中是否有错,有错则丢弃
};

socket

传输层的socket结构体,这个结构体表征BSD套接字的通用特性。
\linux-5.11.1\include\linux\net.h

/**
 *  struct socket - general BSD socket
 *  @state: socket state (%SS_CONNECTED, etc)
 *  @type: socket type (%SOCK_STREAM, etc)
 *  @flags: socket flags (%SOCK_NOSPACE, etc)
 *  @ops: protocol specific socket operations
 *  @file: File back pointer for gc
 *  @sk: internal networking protocol agnostic socket representation
 *  @wq: wait queue for several uses
 */
struct socket {
	socket_state		state;	//连接状态

	short			type;//套接字类型,如SOCK_STREAM

	unsigned long		flags;

	struct file		*file;//套接字对应的文件指针
	struct sock		*sk;//网络层的套接字
	const struct proto_ops	*ops;//协议相关的一系列套接字操作

	struct socket_wq	wq;//等待队列
};

sock

\linux-5.11.1\include\net\sock.h
sock属于网络层,即IP层,该结构体sock中包含了一个基本结构体sock_common。

struct sock { 
    struct sock_common    __sk_common;       // 网络层套接字通用结构体
......
    socket_lock_t        sk_lock;           // 套接字同步锁
    atomic_t        sk_drops;               // IP/UDP包丢包统计
    int            sk_rcvlowat;               // SO_RCVLOWAT标记位
......
    struct sk_buff_head    sk_receive_queue;    // 收到的数据包队列
......
    int            sk_rcvbuf;                  // 接收缓存大小
......
    union { 
        struct socket_wq __rcu    *sk_wq;        // 等待队列
        struct socket_wq    *sk_wq_raw;
    };
......
    int            sk_sndbuf;                   // 发送缓存大小
    /* ===== cache line for TX ===== */
    int            sk_wmem_queued;               // 传输队列大小
    refcount_t        sk_wmem_alloc;            // 已确认的传输字节数
    unsigned long        sk_tsq_flags;        // TCP Small Queue标记位
    union { 
        struct sk_buff    *sk_send_head;        // 发送队列对首
        struct rb_root    tcp_rtx_queue;         
    };
    struct sk_buff_head    sk_write_queue;         // 发送队列
......
    u32            sk_pacing_status; /* see enum sk_pacing 发包速率控制状态*/ 
    long            sk_sndtimeo;            // SO_SNDTIMEO 标记位
    struct timer_list    sk_timer;            // 套接字清空计时器
    __u32            sk_priority;            // SO_PRIORITY 标记位
......
    unsigned long        sk_pacing_rate; /* bytes per second 发包速率*/
    unsigned long        sk_max_pacing_rate;  // 最大发包速率
    struct page_frag    sk_frag;            // 缓存页帧
......
    struct proto        *sk_prot_creator;
    rwlock_t        sk_callback_lock;
    int            sk_err,                      // 上次错误
                sk_err_soft;              // “软”错误:不会导致失败的错误
    u32            sk_ack_backlog;               // ack队列长度
    u32            sk_max_ack_backlog;           // 最大ack队列长度
    kuid_t            sk_uid;                  // user id
    struct pid        *sk_peer_pid;           // 套接字对应的peer的id
......
    long            sk_rcvtimeo;          // 接收超时
    ktime_t            sk_stamp;              // 时间戳
......
    struct socket        *sk_socket;           // Identd协议报告IO信号
    void            *sk_user_data;          // RPC层私有信息
......
    struct sock_cgroup_data    sk_cgrp_data;   // cgroup数据
    struct mem_cgroup    *sk_memcg;           // 内存cgroup关联
    void            (*sk_state_change)(struct sock *sk);    // 状态变化回调函数
    void            (*sk_data_ready)(struct sock *sk);        // 数据处理回调函数
    void            (*sk_write_space)(struct sock *sk);        // 写空间可用回调函数
    void            (*sk_error_report)(struct sock *sk);    // 错误报告回调函数
    int            (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb);    // 处理存储区回调函数
......
    void                    (*sk_destruct)(struct sock *sk);    // 析构回调函数
    struct sock_reuseport __rcu    *sk_reuseport_cb;               // group容器重用回调函数
......
};

sock_common

\linux-5.11.1\include\net\sock.h
sock_common是套接口在网络层的最小表示,即最基本的网络层套接字信息。

struct sock_common { 
    /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned * address on 64bit arches : cf INET_MATCH() */
    union { 
        __addrpair    skc_addrpair;
        struct { 
            __be32    skc_daddr;        // 外部/目的IPV4地址
            __be32    skc_rcv_saddr;    // 本地绑定IPV4地址
        };
    };
    union  { 
        unsigned int    skc_hash;    // 根据协议查找表获取的哈希值
        __u16        skc_u16hashes[2]; // 2个16位哈希值,UDP专用
    };
    /* skc_dport && skc_num must be grouped as well */
    union { 
        __portpair    skc_portpair;    // 
        struct { 
            __be16    skc_dport;        // inet_dport占位符
            __u16    skc_num;        // inet_num占位符
        };
    };
    unsigned short        skc_family;          // 网络地址family
    volatile unsigned char    skc_state;    // 连接状态
    unsigned char        skc_reuse:4;      // SO_REUSEADDR 标记位
    unsigned char        skc_reuseport:1;  // SO_REUSEPORT 标记位
    unsigned char        skc_ipv6only:1;   // IPV6标记位
    unsigned char        skc_net_refcnt:1; // 该套接字网络名字空间内引用数
    int            skc_bound_dev_if;         // 绑定设备索引
    union { 
        struct hlist_node    skc_bind_node;     // 不同协议查找表组成的绑定哈希表
        struct hlist_node    skc_portaddr_node; // UDP/UDP-Lite protocol二级哈希表
    };
    struct proto        *skc_prot;              // 协议回调函数,根据协议不同而不同
......
    union {                                     
        struct hlist_node    skc_node;            // 不同协议查找表组成的主哈希表
        struct hlist_nulls_node skc_nulls_node;  // UDP/UDP-Lite protocol主哈希表
    };
    unsigned short        skc_tx_queue_mapping;    // 该连接的传输队列
    unsigned short        skc_rx_queue_mapping;    // 该连接的接受队列
......
    union { 
        int        skc_incoming_cpu; // 多核下处理该套接字数据包的CPU编号
        u32        skc_rcv_wnd;      // 接收窗口大小
        u32        skc_tw_rcv_nxt; /* struct tcp_timewait_sock */
    };
    refcount_t        skc_refcnt;   // 套接字引用计数
......
};

sk_buff

\linux-5.11.1\include\linux\skbuff.h
struct sk_buff这一结构体在各层协议中都会被用到。该结构体存储了网络数据报的所有信息。包括各层的头部以及 payload,以及必要的各层实现相关的信息。

struct sk_buff {
//sk_buff可以被组织成两种数据结构:双向链表和红黑树。且一个sk_buff不是在双向链表中,就是在红黑树中,因此,采用了 union 来节约空间。
	union {
		struct {
			/* These two members must be first. */
			struct sk_buff		*next;
			struct sk_buff		*prev;
			//next 和 prev 两个域是用于双向链表的结构体,而 rbnode 是红黑树相关的结构
			union {
				struct net_device	*dev;/* 与该包关联的网络设备 */
				/* Some protocols might use this space to store information,
				 * while device pointer would be NULL.
				 * UDP receive path is one user.
				 */
				unsigned long		dev_scratch;
			};
		};
		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
		struct list_head	list;
	};

	union {
		struct sock		*sk;/* 拥有该 sk_buff 的套接字的指针 */
		int			ip_defrag_offset;
	};

	union {
		ktime_t		tstamp;
		u64		skb_mstamp_ns; /* earliest departure time */
	};
	/*
	 * This is the control buffer. It is free to use for every
	 * layer. Please put your private variables there. If you
	 * want to keep them across layers you have to do a skb_clone()
	 * first. This is owned by whoever has the skb queued ATM.
	 */
	char			cb[48] __aligned(8);/* 控制用的缓冲区,用于存放各层的私有数据 */

	union {
		struct {
			unsigned long	_skb_refdst;/* 存放了目的地项的引用计数 */
			void		(*destructor)(struct sk_buff *skb);/* 析构函数 */
		};
		struct list_head	tcp_tsorted_anchor;
	};

#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	unsigned long		 _nfct;
#endif
	unsigned int		len,//代表 buffer 中的数据报总长度(含各协议的头部),以及分片长度。
				data_len;//代表分片中的数据的长度
	__u16			mac_len,//MAC 层头部的长度
				hdr_len;//克隆出来的可写的头部的长度

	/* Following fields are _not_ copied in __copy_skb_header()
	 * Note that queue_mapping is here mostly to fill a hole.
	 */
	__u16			queue_mapping;/* 对于多队列设备的队列关系映射 */

/* if you move cloned around you also must adapt those constants */
#ifdef __BIG_ENDIAN_BITFIELD
#define CLONED_MASK	(1 << 7)
#else
#define CLONED_MASK	1
#endif
#define CLONED_OFFSET()		offsetof(struct sk_buff, __cloned_offset)

	/* private: */
	__u8			__cloned_offset[0];
	/* public: */
	__u8			cloned:1,/* 是否被克隆 */
				nohdr:1,/* 只引用了负载 */
				fclone:2,/* skbuff 克隆的情况 */
				peeked:1,/* peeked 表明该包已经被统计过了,无需再次统计 */
				head_frag:1,
				pfmemalloc:1;
#ifdef CONFIG_SKB_EXTENSIONS
	__u8			active_extensions;
#endif
	/* fields enclosed in headers_start/headers_end are copied
	 * using a single memcpy() in __copy_skb_header()
	 */
	/* private: */
	//一个包的头部,这一部分再次使用了类似上面的方法,用了两个零长度的数组 headers_start和headers_end来标明头部的起始和终止地址
	//在 __copy_skb_header() 中,只需使用一个 memcpy() 即可将 headers_start/end 之间的部分克隆一份
	__u32			headers_start[0];
	/* public: */

/* if you move pkt_type around you also must adapt those constants */
#ifdef __BIG_ENDIAN_BITFIELD
#define PKT_TYPE_MAX	(7 << 5)
#else
#define PKT_TYPE_MAX	7
#endif
#define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)

	/* private: */
	__u8			__pkt_type_offset[0];
	/* public: */
	__u8			pkt_type:3;/* 该包的类型 */
	__u8			ignore_df:1;/* 是否允许本地分片 (local fragmentation) */
	__u8			nf_trace:1;/* netfilter 包追踪标记 */
	__u8			ip_summed:2;/* 驱动(硬件)给出来的 checksum */
	__u8			ooo_okay:1;/* 允许该 socket 到队列的对应关系发生变更 */

	__u8			l4_hash:1;/* 表明哈希值字段 hash 是一个典型的 4 元组的通过传输端口的哈希 */
	__u8			sw_hash:1;/* 表明哈希值字段 hash 是通过软件栈计算出来的 */
	__u8			wifi_acked_valid:1;/* 表明 wifi_acked 是否被设置了 */
	__u8			wifi_acked:1;/* 表明帧是否在 wifi 上被确认了 */
	__u8			no_fcs:1;/* 请求 NIC 将最后的 4 个字节作为以太网 FCS 来对待 */
	/* Indicates the inner headers are valid in the skbuff. */
	__u8			encapsulation:1;
	__u8			encap_hdr_csum:1;
	__u8			csum_valid:1;

#ifdef __BIG_ENDIAN_BITFIELD
#define PKT_VLAN_PRESENT_BIT	7
#else
#define PKT_VLAN_PRESENT_BIT	0
#endif
#define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, __pkt_vlan_present_offset)
	/* private: */
	__u8			__pkt_vlan_present_offset[0];
	/* public: */
	__u8			vlan_present:1;
	__u8			csum_complete_sw:1;
	__u8			csum_level:2;
	__u8			csum_not_inet:1;
	__u8			dst_pending_confirm:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
	__u8			ndisc_nodetype:2;/* 路由类型(来自链路层) */
#endif

	__u8			ipvs_property:1;/* 标明该 skbuff 是否被 ipvs 拥有 */
	__u8			inner_protocol_type:1;
	__u8			remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV
	__u8			offload_fwd_mark:1;
	__u8			offload_l3_fwd_mark:1;
#endif
#ifdef CONFIG_NET_CLS_ACT
	__u8			tc_skip_classify:1;
	__u8			tc_at_ingress:1;
#endif
#ifdef CONFIG_NET_REDIRECT
	__u8			redirected:1;
	__u8			from_ingress:1;
#endif
#ifdef CONFIG_TLS_DEVICE
	__u8			decrypted:1;
#endif

#ifdef CONFIG_NET_SCHED
	__u16			tc_index;	/* traffic control index */
#endif

	union {
		__wsum		csum;/* 校验码 */
		struct {
			__u16	csum_start;/* 从 skb->head 开始到应当计算校验码的起始位置的偏移 */
			__u16	csum_offset;/* 从 csum_start 开始到存储校验码的位置的偏移 */
		};
	};
	__u32			priority;/* 包队列的优先级 */
	int			skb_iif;/* 到达的设备的序号 */
	__u32			hash;/* 包的哈希值 */
	__be16			vlan_proto;/* vlan 包装协议 */
	__u16			vlan_tci;/* vlan tag 控制信息 */
#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
	union {
		unsigned int	napi_id;/* 表明该 skb 来源的 NAPI 结构体的 id */
		unsigned int	sender_cpu;
	};
#endif
#ifdef CONFIG_NETWORK_SECMARK
	__u32		secmark;/* 安全标记 */
#endif

	union {
		__u32		mark;/* 通用的包的标记位 */
		__u32		reserved_tailroom;
	};

	union {
		__be16		inner_protocol;/* 协议(封装好的) */
		__u8		inner_ipproto;
	};

	__u16			inner_transport_header;/* 已封装的内部传输层头部 */
	__u16			inner_network_header;/* 已封装的内部网络层头部 */
	__u16			inner_mac_header;/* 已封装的内部链路层头部 */

	__be16			protocol;/* 驱动(硬件)给出的包的协议类型 */
	__u16			transport_header;/* 传输层头部 */
	__u16			network_header;/* 网络层头部 */
	__u16			mac_header;/* 数据链路层头部 */

#ifdef CONFIG_KCOV
	u64			kcov_handle;
#endif

	/* private: */
	__u32			headers_end[0];
	/* public: */

	/* These elements must be at the end, see alloc_skb() for details.  */
	//最后是一组是管理相关的字段。其中,head和end 代表被分配的内存的起始位置和终止位置。而data和tail 则是实际数据的起始和终止位置。
	sk_buff_data_t		tail;
	sk_buff_data_t		end;
	unsigned char		*head,
				*data;
	unsigned int		truesize;//数据报的真实大小。
	refcount_t		users;//是引用计数,所以是个原子的

#ifdef CONFIG_SKB_EXTENSIONS
	/* only useable after checking ->active_extensions != 0 */
	struct skb_ext		*extensions;
#endif
}

你可能感兴趣的:(C/C++,linux/嵌入式,tcp/ip,linux,网络)