1. TCP协议头tcphdr

TCP协议头描述了TCP数据段发送的源地址、目标地址、数据段传送管理和连接管理的信息，是TCP协议实现的重要数据结构之一。

struct tcphdr {__be16    source;__be16   dest;__be32 seq;__be32  ack_seq;
#if defined(__LITTLE_ENDIAN_BITFIELD)__u16  res1:4,doff:4,fin:1,syn:1,rst:1,psh:1,ack:1,urg:1,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 <asm/byteorder.h> defines"
#endif  __be16  window;__sum16  check;__be16    urg_ptr;
};

2. TCP的控制缓冲区tcp_skb_cb

TCP是完全异步的协议，实际数据段的传送独立于所有来自套接字层的写操作。
TCP层分配Socket Buffer来存放应用层写入套接字的数据，但应用程序控制管理数据包的信息存放在TCP的控制缓冲区中。
TCP控制缓冲区由struct tcp_skb_cb数据结构描述。
可以看到TCP控制缓冲区中的信息与TCP协议头的信息有部分重合，当数据从应用程序复制到TCP层的Socket Buffer时，函数需要用TCP控制缓冲区中TCP协议头的信息，来设置struct tcphdr数据结构中的相关数据域。

/* This is what the send packet queuing engine uses to pass* TCP per-packet control information to the transmission* code.  We also store the host-order sequence numbers in* here too.  This is 36 bytes on 32-bit architectures,* 40 bytes on 64-bit machines, if this grows please adjust* skbuff.h:skbuff->cb[xxx] size appropriately.*/
struct tcp_skb_cb {union {struct inet_skb_parm  h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)struct inet6_skb_parm   h6;
#endif} header; /* For incoming frames      */__u32     seq;        /* Starting sequence number */__u32     end_seq;    /* SEQ + FIN + SYN + datalen */__u32     when;       /* used to compute rtt's   */__u8      flags;      /* TCP header flags.        *//* NOTE: These must match up to the flags byte in a*       real TCP header.*/
#define TCPCB_FLAG_FIN      0x01
#define TCPCB_FLAG_SYN      0x02
#define TCPCB_FLAG_RST      0x04
#define TCPCB_FLAG_PSH      0x08
#define TCPCB_FLAG_ACK      0x10
#define TCPCB_FLAG_URG      0x20
#define TCPCB_FLAG_ECE      0x40
#define TCPCB_FLAG_CWR      0x80__u8        sacked;     /* State flags for SACK/FACK.   */
#define TCPCB_SACKED_ACKED  0x01    /* SKB ACK'd by a SACK block   */
#define TCPCB_SACKED_RETRANS    0x02    /* SKB retransmitted        */
#define TCPCB_LOST      0x04    /* SKB is lost          */
#define TCPCB_TAGBITS       0x07    /* All tag bits         */#define TCPCB_EVER_RETRANS    0x80    /* Ever retransmitted frame */
#define TCPCB_RETRANS       (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)__u32      ack_seq;    /* Sequence number ACK'd   */
};

3. TCP套接字的数据结构

TCP套接字的数据结构中包含了管理TCP协议各方面的信息，如发送和接收序列号、TCP窗口尺寸、避免网络阻塞等。

这些管理信息由TCP套接字的数据结构struct tcp_sock描述。struct tcp_sock是一个庞大的数据结构，其中包含了TCP层管理数据传送需要的所有信息。

struct tcp_sock数据结构是SOCK_STREAM类的套接字数据结构stuct sock中的一部分，在分配套接字的同时也分配内存空间。

struct tcp_sock {/* inet_connection_sock has to be the first member of tcp_sock */struct inet_connection_sock    inet_conn;u16   tcp_header_len; /* Bytes of tcp header to send      */u16   xmit_size_goal_segs; /* Goal for segmenting output packets *//**    Header prediction flags*    0x5?10 << 16 + snd_wnd in net byte order*/__be32 pred_flags;/**  RFC793 variables by their proper names. This means you can* read the code and the spec side by side (and laugh ...)*    See RFC793 and RFC1122. The RFC writes these in capitals.*/u32  rcv_nxt;    /* What we want to receive next     */u32   copied_seq; /* Head of yet unread data      */u32   rcv_wup;    /* rcv_nxt on last window update sent   */u32   snd_nxt;    /* Next sequence we send        */u32   snd_una;    /* First byte we want an ack for    */u32   snd_sml;    /* Last byte of the most recently transmitted small packet */u32    rcv_tstamp; /* timestamp of last received ACK (for keepalives) */u32    lsndtime;   /* timestamp of last sent data packet (for restart window) *//* Data for direct copy to user */struct {struct sk_buff_head  prequeue;struct task_struct *task;struct iovec      *iov;int            memory;int          len;
#ifdef CONFIG_NET_DMA/* members for async copy */struct dma_chan        *dma_chan;int           wakeup;struct dma_pinned_list   *pinned_list;dma_cookie_t       dma_cookie;
#endif} ucopy;u32   snd_wl1;    /* Sequence for window update       */u32   snd_wnd;    /* The window we expect to receive  */u32   max_window; /* Maximal window ever seen from peer   */u32   mss_cache;  /* Cached effective mss, not including SACKS */u32  window_clamp;   /* Maximal window to advertise      */u32   rcv_ssthresh;   /* Current window clamp         */u32   frto_highmark;  /* snd_nxt when RTO occurred */u16  advmss;     /* Advertised MSS           */u8    frto_counter;   /* Number of new acks after RTO */u8    nonagle     : 4,/* Disable Nagle algorithm?             */thin_lto    : 1,/* Use linear timeouts for thin streams */thin_dupack : 1,/* Fast retransmit on first dupack      */unused      : 2;/* RTT measurement */u32  srtt;       /* smoothed round trip time << 3  */u32   mdev;       /* medium deviation         */u32   mdev_max;   /* maximal mdev for the last rtt period */u32   rttvar;     /* smoothed mdev_max            */u32   rtt_seq;    /* sequence number to update rttvar */u32   packets_out;    /* Packets which are "in flight"  */u32   retrans_out;    /* Retransmitted packets out        */u16   urg_data;   /* Saved octet of OOB data and control flags */u8   ecn_flags;  /* ECN status bits.         */u8    reordering; /* Packet reordering metric.        */u32   snd_up;     /* Urgent pointer       */u8    keepalive_probes; /* num of allowed keep alive probes   */
/**      Options received (usually on last packet, some only on SYN packets).*/struct tcp_options_received rx_opt;/**   Slow start and congestion control (see also Nagle, and Karn & Partridge)*/u32   snd_ssthresh;   /* Slow start size threshold        */u32   snd_cwnd;   /* Sending congestion window        */u32   snd_cwnd_cnt;   /* Linear increase counter      */u32   snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */u32   snd_cwnd_used;u32   snd_cwnd_stamp;u32  rcv_wnd;    /* Current receiver window      */u32   write_seq;  /* Tail(+1) of data held in tcp send buffer */u32  pushed_seq; /* Last pushed seq, required to talk to windows */u32   lost_out;   /* Lost packets         */u32   sacked_out; /* SACK'd packets          */u32   fackets_out;    /* FACK'd packets          */u32   tso_deferred;u32    bytes_acked;    /* Appropriate Byte Counting - RFC3465 *//* from STCP, retrans queue hinting */struct sk_buff* lost_skb_hint;struct sk_buff *scoreboard_skb_hint;struct sk_buff *retransmit_skb_hint;struct sk_buff_head    out_of_order_queue; /* Out of order segments go here *//* SACKs data, these 2 need to be together (see tcp_build_and_update_options) */struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/struct tcp_sack_block recv_sack_cache[4];struct sk_buff *highest_sack;   /* highest skb with SACK received* (validity guaranteed only if* sacked_out > 0)*/int     lost_cnt_hint;u32     retransmit_high;    /* L-bits may be on up to this seqno */u32  lost_retrans_low;   /* Sent seq after any rxmit (lowest) */u32  prior_ssthresh; /* ssthresh saved at recovery start */u32   high_seq;   /* snd_nxt at onset of congestion   */u32   retrans_stamp;  /* Timestamp of the last retransmit,* also used in SYN-SENT to remember stamp of* the first SYN. */u32  undo_marker;    /* tracking retrans started here. */int undo_retrans;   /* number of undoable retransmissions. */u32    total_retrans;  /* Total retransmits for entire connection */u32    urg_seq;    /* Seq of received urgent pointer */unsigned int        keepalive_time;   /* time before keep alive takes place */unsigned int      keepalive_intvl;  /* time interval between keep alive probes */int          linger2;/* Receiver side RTT estimation */struct {u32   rtt;u32 seq;u32 time;} rcv_rtt_est;/* Receiver queue space */struct {int    space;u32   seq;u32 time;} rcvq_space;/* TCP-specific MTU probe information. */struct {u32        probe_seq_start;u32         probe_seq_end;} mtu_probe;#ifdef CONFIG_TCP_MD5SIG
/* TCP AF-Specific parts; only used by MD5 Signature support so far */const struct tcp_sock_af_ops  *af_specific;/* TCP MD5 Signature Option information */struct tcp_md5sig_info   *md5sig_info;
#endif/* When the cookie options are generated and exchanged, then this* object holds a reference to them (cookie_values->kref).  Also* contains related tcp_cookie_transactions fields.*/struct tcp_cookie_values  *cookie_values;
};

4. 应用层传送给传输层信息的数据结构

struct msghdr数据结构中包含了来自应用层数据的信息。

它将作为参数从套接字传送给TCP协议实例的传送处理函数，在传送处理函数中应用数据从套接字复制到内核地址空间的SocketBuffer中。


/** As we do 4.4BSD message passing we use a 4.4BSD message passing*    system, not 4.3. Thus msg_accrights(len) are now missing. They* belong in an obscure libc emulation or the bin.*/struct msghdr {void    *   msg_name;   /* Socket name          */int       msg_namelen;    /* Length of name       */struct iovec *    msg_iov;    /* Data blocks          */__kernel_size_t   msg_iovlen; /* Number of blocks     */void  *   msg_control;    /* Per protocol magic (eg BSD file descriptor passing) */__kernel_size_t    msg_controllen; /* Length of cmsg list */unsigned   msg_flags;
};

Linux内核中TCP协议实现的关键数据结构相关推荐

linux内核中TCP接收的实现
linux内核中TCP接收的实现入口函数是tcp_v4_rcv 1. 数据包检查处理一开始做一些数据包详细检查处理,一旦出错,可能导致内核挂掉 int tcp_v4_rcv(struct sk_bu ...
linux做预警机制,预警通告：Linux内核中TCP SACK机制远程DoS
漏洞描述 2019年6月18日,RedHat官网发布报告:安全研究人员在Linux内核处理TCP SACK数据包模块中发现了三个漏洞,CVE编号为CVE-2019-11477.CVE-2019-114 ...
linux内核中TCP发送的实现
TCP发送功能是指将从应用层通过打开的套接字写入的数据移入内核,通过TCP/IP协议栈,最终通过网络设备发送到远端接收主机. TCP传送的特点如下: 异步传送:TCP的实际传送独立于应用层. 汇集从套 ...
linux程序获取透传参数,Linux内核中TCP SACK处理流程分析
frankzfz2014-07-27 17:32 demo121:frankzfz您好: 我想请教一个问题,就是将写好的GenericApp项目(没有配置工具),我加入zigbee协议栈的配置工具后还 ...
Linux内核中的算法和数据结构
算法和数据结构纷繁复杂,但是对于Linux Kernel开发人员来说重点了解Linux内核中使用到的算法和数据结构很有必要. 在一个国外问答平台stackexchange.com的Theoretica ...
linux下IPROTO_TCP,TCP/IP协议栈在Linux内核中的运行时序分析
可选题目三:TCP/IP协议栈在Linux内核中的运行时序分析在深入理解Linux内核任务调度(中断处理.softirg.tasklet.wq.内核线程等)机制的基础上,分析梳理send和recv过 ...
TCP/IP协议栈在Linux内核中的运行时序分析
本文主要是讲解TCP/IP协议栈在Linux内核中的运行时序,文章较长,里面有配套的视频讲解,建议收藏观看. 1 Linux概述 1.1 Linux操作系统架构简介 Linux操作系统总体上由Linu ...
TCP三次握手在linux内核中的实现
TCP三次握手在linux内核中的实现以下基于linux内核2.4.0源码(转自www.yuanma.org/) 以前一直使用的网络通讯的函数都是工作在阻塞模式.在看connect实现源码时,突然想 ...
TCP/IP网络协议栈在Linux内核中的如何使用丨内核开发丨驱动开发丨操作系统丨内核源码
TCP/IP网络协议栈在Linux内核中的如何使用视频讲解如下,点击观看: TCP/IP网络协议栈在Linux内核中的如何使用丨内核开发丨驱动开发丨操作系统丨内核源码 C/C++Linux服务器开发 ...

Linux内核中TCP协议实现的关键数据结构

1. TCP协议头tcphdr

2. TCP的控制缓冲区tcp_skb_cb

3. TCP套接字的数据结构

4. 应用层传送给传输层信息的数据结构

Linux内核中TCP协议实现的关键数据结构相关推荐

最新文章

热门文章