《庖丁解牛Linux网络核心》：源码跟踪HTTP客户端访问github.com

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/jason_holan/article/details/86540116

本实验来自中科大孟宁老师教的《Linux网络程序设计》课程实验部分。
课程通过搭建linux内核调试环境，将编写的http客户端集成到MenuOS中，从linux源码出发 学习网络中的协议具体是如何收发的。
实验代码及参考：
https://github.com/mengning/linuxnet/blob/master/np2018.md

实验内容：

编写一个简单的HTTP客户端访问github.com（此次访问的是科大的主页ustc.edu.cn）并集成到MenuOS里并跟踪分析路由和ARP解析的过程

编写一个简单的客户端通过DNS解析API解析github.com（或其他域名）获得其IP地址
客户端HTTP访问github.com对应的IP地址，能够获取HTTP响应
将前述客户端集成到MenuOS中，能正常输出github.com对应的HTTP响应
跟踪分析MenuOS中前述客户端的运行过程，总从体上分析DNS解析过程UDP在内核中的发送和接收过程， 以及HTTP通信TCP在内核中的发送和接收过程

实验环境：

qemu+linux-3.18.6+MenuOS，主机环境14.04

注意：

每次编译后需将生成的init， 放到rootfs.img中。
过程：
mkdir root
sudo make mount -o loop rootfs.img root
cp init root
sudo umount root

代码如下：

int main()
{
	
    BringUpNetInterface();
    SetDefaultGateway();
    GetRoute();
    PrintMenuOS();
    SetPrompt("MenuOS>>");
    MenuConfig("version","MenuOS V1.0(Based on Linux 3.18.6)",NULL);
    MenuConfig("quit","Quit from MenuOS",Quit);
    MenuConfig("replyhi", "Reply hi TCP Service", StartReplyhi);
    MenuConfig("hello", "Hello TCP Client", Hello);
    MenuConfig("httpReq", "DNS Query github.com", HttpRequest);
    ExecuteMenu();
}

访问其他域名将unsigned char hostname[100] = "www.ustc.edu.cn"; 更改即可。

//Header Files
#include<stdio.h>	//printf
#include<string.h>	//strlen
#include<stdlib.h>	//malloc
#include<sys/socket.h>	//you know what this is for
#include<arpa/inet.h>	//inet_addr , inet_ntoa , ntohs etc
#include<netinet/in.h>
#include<unistd.h>	//getpid

//List of DNS Servers registered on the system
char dns_servers[10][100];
int dns_server_count = 0;
//Types of DNS resource records :)

#define T_A 1 //Ipv4 address
#define T_NS 2 //Nameserver
#define T_CNAME 5 // canonical name
#define T_SOA 6 /* start of authority zone */
#define T_PTR 12 /* domain name pointer */
#define T_MX 15 //Mail server

//Function Prototypes
void ngethostbyname (unsigned char* , int);
void ChangetoDnsNameFormat (unsigned char*,unsigned char*);
unsigned char* ReadName (unsigned char*,unsigned char*,int*);
void get_dns_servers();
int Hellohttp();

//DNS header structure

char ip[20] = {0};

struct DNS_HEADER
{
	unsigned short id; // identification number

	unsigned char rd :1; // recursion desired
	unsigned char tc :1; // truncated message
	unsigned char aa :1; // authoritive answer
	unsigned char opcode :4; // purpose of message
	unsigned char qr :1; // query/response flag

	unsigned char rcode :4; // response code
	unsigned char cd :1; // checking disabled
	unsigned char ad :1; // authenticated data
	unsigned char z :1; // its z! reserved
	unsigned char ra :1; // recursion available

	unsigned short q_count; // number of question entries
	unsigned short ans_count; // number of answer entries
	unsigned short auth_count; // number of authority entries
	unsigned short add_count; // number of resource entries
};

//Constant sized fields of query structure
struct QUESTION
{
	unsigned short qtype;
	unsigned short qclass;
};

//Constant sized fields of the resource record structure
#pragma pack(push, 1)
struct R_DATA
{
	unsigned short type;
	unsigned short _class;
	unsigned int ttl;
	unsigned short data_len;
};
#pragma pack(pop)

//Pointers to resource record contents
struct RES_RECORD
{
	unsigned char *name;
	struct R_DATA *resource;
	unsigned char *rdata;
};

//Structure of a Query
typedef struct
{
	unsigned char *name;
	struct QUESTION *ques;
} QUERY;

//int main( int argc , char *argv[])
int HttpRequest()
{
	unsigned char hostname[100] = "www.ustc.edu.cn";

	//Get the DNS servers from the resolv.conf file
	get_dns_servers();
	
	//Get the hostname from the terminal
	//printf("Enter Hostname to Lookup : ");
	//scanf("%s" , hostname);
	
	//Now get the ip of this hostname , A record
	ngethostbyname(hostname , T_A);
	
	Hellohttp();

	return 0;
}

/*
 * Perform a DNS query by sending a packet
 * */
void ngethostbyname(unsigned char *host , int query_type)
{	
	int jj=0;
	unsigned char buf[65536],*qname,*reader;
	int i , j , stop , s;

	struct sockaddr_in a;

	struct RES_RECORD answers[20],auth[20],addit[20]; //the replies from the DNS server
	struct sockaddr_in dest;

	struct DNS_HEADER *dns = NULL;
	struct QUESTION *qinfo = NULL;

	printf("Resolving %s" , host);

	s = socket(AF_INET , SOCK_DGRAM , IPPROTO_UDP); //UDP packet for DNS queries

	dest.sin_family = AF_INET;
	dest.sin_port = htons(53);
	dest.sin_addr.s_addr = inet_addr(dns_servers[0]); //dns servers

	//Set the DNS structure to standard queries
	dns = (struct DNS_HEADER *)&buf;

	dns->id = (unsigned short) htons(getpid());
	dns->qr = 0; //This is a query
	dns->opcode = 0; //This is a standard query
	dns->aa = 0; //Not Authoritative
	dns->tc = 0; //This message is not truncated
	dns->rd = 1; //Recursion Desired
	dns->ra = 0; //Recursion not available! hey we dont have it (lol)
	dns->z = 0;
	dns->ad = 0;
	dns->cd = 0;
	dns->rcode = 0;
	dns->q_count = htons(1); //we have only 1 question
	dns->ans_count = 0;
	dns->auth_count = 0;
	dns->add_count = 0;

	//point to the query portion
	qname =(unsigned char*)&buf[sizeof(struct DNS_HEADER)];

	ChangetoDnsNameFormat(qname , host);
	qinfo =(struct QUESTION*)&buf[sizeof(struct DNS_HEADER) + (strlen((const char*)qname) + 1)]; //fill it

	qinfo->qtype = htons( query_type ); //type of the query , A , MX , CNAME , NS etc
	qinfo->qclass = htons(1); //its internet (lol)

	printf("\nSending Packet...");
	if( sendto(s,(char*)buf,sizeof(struct DNS_HEADER) + (strlen((const char*)qname)+1) + sizeof(struct QUESTION),0,(struct sockaddr*)&dest,sizeof(dest)) < 0)
	{
		perror("sendto failed");
	}
	printf("Done");
	
	//Receive the answer
	i = sizeof dest;
	printf("\nReceiving answer...");
	if(recvfrom (s,(char*)buf , 65536 , 0 , (struct sockaddr*)&dest , (socklen_t*)&i ) < 0)
	{
		perror("recvfrom failed");
	}
	printf("Done");

	dns = (struct DNS_HEADER*) buf;

	//move ahead of the dns header and the query field
	reader = &buf[sizeof(struct DNS_HEADER) + (strlen((const char*)qname)+1) + sizeof(struct QUESTION)];

	printf("\nThe response contains : ");
	printf("\n %d Questions.",ntohs(dns->q_count));
	printf("\n %d Answers.",ntohs(dns->ans_count));
	printf("\n %d Authoritative Servers.",ntohs(dns->auth_count));
	printf("\n %d Additional records.\n\n",ntohs(dns->add_count));

	//Start reading answers
	stop=0;

	for(i=0;i<ntohs(dns->ans_count);i++)
	{
		answers[i].name=ReadName(reader,buf,&stop);
		reader = reader + stop;

		answers[i].resource = (struct R_DATA*)(reader);
		reader = reader + sizeof(struct R_DATA);

		if(ntohs(answers[i].resource->type) == 1) //if its an ipv4 address
		{
			answers[i].rdata = (unsigned char*)malloc(ntohs(answers[i].resource->data_len));

			for(j=0 ; j<ntohs(answers[i].resource->data_len) ; j++)
			{
				answers[i].rdata[j]=reader[j];
			}

			answers[i].rdata[ntohs(answers[i].resource->data_len)] = '\0';

			reader = reader + ntohs(answers[i].resource->data_len);
		}
		else
		{
			answers[i].rdata = ReadName(reader,buf,&stop);
			reader = reader + stop;
		}
	}
	//read authorities
	for(i=0;i<ntohs(dns->auth_count);i++)
	{
		auth[i].name=ReadName(reader,buf,&stop);
		reader+=stop;

		auth[i].resource=(struct R_DATA*)(reader);
		reader+=sizeof(struct R_DATA);

		auth[i].rdata=ReadName(reader,buf,&stop);
		reader+=stop;
	}

	//read additional
	for(i=0;i<ntohs(dns->add_count);i++)
	{
		addit[i].name=ReadName(reader,buf,&stop);
		reader+=stop;

		addit[i].resource=(struct R_DATA*)(reader);
		reader+=sizeof(struct R_DATA);

		if(ntohs(addit[i].resource->type)==1)
		{
			addit[i].rdata = (unsigned char*)malloc(ntohs(addit[i].resource->data_len));
			for(j=0;j<ntohs(addit[i].resource->data_len);j++)
			addit[i].rdata[j]=reader[j];

			addit[i].rdata[ntohs(addit[i].resource->data_len)]='\0';
			reader+=ntohs(addit[i].resource->data_len);
		}
		else
		{
			addit[i].rdata=ReadName(reader,buf,&stop);
			reader+=stop;
		}
	}

	//print answers
	printf("\nAnswer Records : %d \n" , ntohs(dns->ans_count) );
	for(i=0 ; i < ntohs(dns->ans_count) ; i++)
	{
		printf("Name : %s ",answers[i].name);

		if( ntohs(answers[i].resource->type) == T_A) //IPv4 address
		{
			long *p;
			p=(long*)answers[i].rdata;
			a.sin_addr.s_addr=(*p); //working without ntohl
			printf("has IPv4 address : %s",inet_ntoa(a.sin_addr));
			strcpy(ip, (char*)inet_ntoa(a.sin_addr));
			printf("my ustc ip");
		}
		
		if(ntohs(answers[i].resource->type)==5) 
		{
			//Canonical name for an alias
			printf("has alias name : %s",answers[i].rdata);
		}

		printf("\n");
	}

	//print authorities
	printf("\nAuthoritive Records : %d \n" , ntohs(dns->auth_count) );
	for( i=0 ; i < ntohs(dns->auth_count) ; i++)
	{
		
		printf("Name : %s ",auth[i].name);
		if(ntohs(auth[i].resource->type)==2)
		{
			printf("has nameserver : %s",auth[i].rdata);
		}
		printf("\n");
	}

	//print additional resource records
	printf("\nAdditional Records : %d \n" , ntohs(dns->add_count) );
	for(i=0; i < ntohs(dns->add_count) ; i++)
	{
		printf("Name : %s ",addit[i].name);
		if(ntohs(addit[i].resource->type)==1)
		{
			long *p;
			p=(long*)addit[i].rdata;
			a.sin_addr.s_addr=(*p);
			printf("has IPv4 address : %s",inet_ntoa(a.sin_addr));
		}
		printf("\n");
	}
	return;
}

/*
 * 
 * */
u_char* ReadName(unsigned char* reader,unsigned char* buffer,int* count)
{
	unsigned char *name;
	unsigned int p=0,jumped=0,offset;
	int i , j;

	*count = 1;
	name = (unsigned char*)malloc(256);

	name[0]='\0';

	//read the names in 3www6google3com format
	while(*reader!=0)
	{
		if(*reader>=192)
		{
			offset = (*reader)*256 + *(reader+1) - 49152; //49152 = 11000000 00000000 ;)
			reader = buffer + offset - 1;
			jumped = 1; //we have jumped to another location so counting wont go up!
		}
		else
		{
			name[p++]=*reader;
		}

		reader = reader+1;

		if(jumped==0)
		{
			*count = *count + 1; //if we havent jumped to another location then we can count up
		}
	}

	name[p]='\0'; //string complete
	if(jumped==1)
	{
		*count = *count + 1; //number of steps we actually moved forward in the packet
	}

	//now convert 3www6google3com0 to www.google.com
	for(i=0;i<(int)strlen((const char*)name);i++) 
	{
		p=name[i];
		for(j=0;j<(int)p;j++) 
		{
			name[i]=name[i+1];
			i=i+1;
		}
		name[i]='.';
	}
	name[i-1]='\0'; //remove the last dot
	return name;
}

/*
 * Get the DNS servers from /etc/resolv.conf file on Linux
 * */
void get_dns_servers()
{
	FILE *fp;
	char line[200] , *p;
	if((fp = fopen("/etc/resolv.conf" , "r")) == NULL)
	{
		printf("Failed opening /etc/resolv.conf file \n");
	}
	
	while(fgets(line , 200 , fp))
	{
        printf("%s",line);
		if(line[0] == '#')
		{
			continue;
		}
		if(strncmp(line , "nameserver" , 10) == 0)
		{
			p = strtok(line , " ");
			p = strtok(NULL , " ");
			
			//p now is the dns ip :)
			printf("dns ip:%s",p);
		}
	}
    	
	strcpy(dns_servers[0] , "10.0.2.3");
	strcpy(dns_servers[1] , "208.67.220.220");
}

/*
 * This will convert www.google.com to 3www6google3com 
 * got it :)
 * */
void ChangetoDnsNameFormat(unsigned char* dns,unsigned char* host) 
{
	int lock = 0 , i;
	strcat((char*)host,".");
	
	for(i = 0 ; i < strlen((char*)host) ; i++) 
	{
		if(host[i]=='.') 
		{
			*dns++ = i-lock;
			for(;lock<i;lock++) 
			{
				*dns++=host[lock];
			}
			lock++; //or lock=i+1;
		}
	}
	*dns++='\0';
}

#include<stdio.h>
#include<stdlib.h>
#include<string.h>    //strlen
#include<sys/socket.h>
#include<arpa/inet.h> //inet_addr
#include<netdb.h>
#include<errno.h>
int Hellohttp()
{
    int socket_desc;
    struct sockaddr_in server;
    char *message;
	//char ip[20] = {0};
	int i = 0;
    //Create socket
    socket_desc = socket(AF_INET, SOCK_STREAM , 0);
    if (socket_desc == -1) {
        printf("Could not create socket");
    }   
    printf("Ip rev!");
    //print ip address
    for(i=0;i<=20;i++){
	printf("%c",ip[i]);	
	}
    printf("\n");
    server.sin_addr.s_addr = inet_addr(ip);
    server.sin_family = AF_INET;
    server.sin_port = htons(80);

    printf("%s", ip);
    //Connect to remote server
    if (connect(socket_desc, (struct sockaddr *)&server, sizeof(server)) < 0) {
        printf("connect error： %d", errno);
        return 1;
    }

    puts("Connected\n");

    //Send some data
    //http 协议
    message = "GET /index.html HTTP/1.1\r\nHost: www.ustc.edu.cn\r\n\r\n";

    //向服务器发送数据
    if (send(socket_desc, message, strlen(message) , 0) < 0) {
        puts("Send failed");
        return 1;
    }
    puts("Data Send\n");

    struct timeval timeout = {3, 0};
    setsockopt(socket_desc, SOL_SOCKET, SO_RCVTIMEO, (char *)&timeout, sizeof(struct timeval));

    //Receive a reply from the server
    //loop
    int size_recv, total_size = 0;
    char chunk[512];
    while(1) {
        memset(chunk , 0 , 512); //clear the variable
        //获取数据
        if ((size_recv =  recv(socket_desc, chunk, 512, 0) ) == -1) {
            if (errno == EWOULDBLOCK || errno == EAGAIN) {
                printf("recv timeout ...\n");
                break;
            } else if (errno == EINTR) {
                printf("interrupt by signal...\n");
                continue;
            } else if (errno == ENOENT) {
                printf("recv RST segement...\n");
                break;
            } else {
                printf("unknown error: %d\n", errno);
                exit(1);
            }
        } else if (size_recv == 0) {
            printf("peer closed ...\n");
            break;
        } else {
            total_size += size_recv;
            printf("%s" , chunk);
        }
    }

    printf("Reply received, total_size = %d bytes\n", total_size);
    return 0;
}

通过科大域名发送dns请求，获取ustc.edu.cn的ip地址

并通过ip访问科大主页。代码跟踪左图。
UDP详细的收发过程见：https://blog.csdn.net/jason_holan/article/details/85119483