Socket与系统调用深度分析

• Socket API编程接口之上可以编写基于不同网络协议的应用程序；
• Socket接口在用户态通过系统调用机制进入内核；
• 内核中将系统调用作为一个特殊的中断来处理，以socket相关系统调用为例进行分析；
• socket相关系统调用的内核处理函数内部通过“多态机制”对不同的网络协议进行的封装方法；

请将Socket API编程接口、系统调用机制及内核中系统调用相关源代码、 socket相关系统调用的内核处理函数结合起来分析，并在X86 64环境下Linux5.0以上的内核中进一步跟踪验证。

完成一篇图文并茂、逻辑严谨、代码详实的实验报告

为了完成本次实验，首先我们要知道linux x86-64系统是通过int 80调用系统调用中断来进入内核态

进入内核的代码：

SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
{
unsigned long a[AUDITSC_ARGS];
unsigned long a0, a1;
int err;
unsigned int len;
if (call < 1 || call > SYS_SENDMMSG)
return -EINVAL;
call = array_index_nospec(call, SYS_SENDMMSG + 1);
len = nargs[call];
if (len > sizeof(a))
return -EINVAL;
/* copy_from_user should be SMP safe. */
if (copy_from_user(a, args, len))
return -EFAULT;
err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);
if (err)
return err;
a0 = a[0];
a1 = a[1];
switch (call) {
case SYS_SOCKET:
err = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
err = __sys_listen(a0, a1);
break;
case SYS_ACCEPT:
err = __sys_accept4(a0, (struct sockaddr __user *)a1,
(int __user *)a[2], 0);
break;
case SYS_GETSOCKNAME:
err =
__sys_getsockname(a0, (struct sockaddr __user *)a1,
(int __user *)a[2]);
break;
case SYS_GETPEERNAME:
err =
__sys_getpeername(a0, (struct sockaddr __user *)a1,
(int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
break;
case SYS_SEND:
err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
NULL, 0);
break;
case SYS_SENDTO:
err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
(struct sockaddr __user *)a[4], a[5]);
break;
case SYS_RECV:
err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
NULL, NULL);
break;
case SYS_RECVFROM:
err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
(struct sockaddr __user *)a[4],
(int __user *)a[5]);
break;
case SYS_SHUTDOWN:
err = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3],
a[4]);
break;
case SYS_GETSOCKOPT:
err =
__sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
(int __user *)a[4]);
break;
case SYS_SENDMSG:
err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1,
a[2], true);
break;
case SYS_SENDMMSG:
err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2],
a[3], true);
break;
case SYS_RECVMSG:
err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1,
a[2], true);
break;
case SYS_RECVMMSG:
if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME))
err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1,
a[2], a[3],
(struct __kernel_timespec __user *)a[4],
NULL);
else
err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1,
a[2], a[3], NULL,
(struct old_timespec32 __user *)a[4]);
break;
case SYS_ACCEPT4:
err = __sys_accept4(a0, (struct sockaddr __user *)a1,
(int __user *)a[2], a[3]);
break;
default:
err = -EINVAL;
break;
}
return err;
}

socket 抽象层的多态机制：

int __sys_socket(int family, int type, int protocol)
{
    int retval;
    struct socket *sock;  // socket位关键的数据结构
    int flags;

    /* Check the SOCK_* constants for consistency.  */
    BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
    BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
    BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
    BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);

    flags = type & ~SOCK_TYPE_MASK;
    if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
        return -EINVAL;
    type &= SOCK_TYPE_MASK;

    if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
        flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

    retval = sock_create(family, type, protocol, &sock);
    if (retval < 0)
        return retval;

    return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
}

<net.h>
struct socket {
    socket_state        state;
    short           type;
    unsigned long       flags;
    struct socket_wq    *wq;
    struct file     *file;
    struct sock     *sk;
    const struct proto_ops  *ops;  // ***
};

<net.h>
struct proto_ops {
    int     family;
    struct module   *owner;
    int     (*release)   (struct socket *sock);
    int     (*bind)      (struct socket *sock,
                      struct sockaddr *myaddr,
                      int sockaddr_len);
    int     (*connect)   (struct socket *sock,
                      struct sockaddr *vaddr,
                      int sockaddr_len, int flags);
    int     (*socketpair)(struct socket *sock1,
                      struct socket *sock2);
    int     (*accept)    (struct socket *sock,
                      struct socket *newsock, int flags, bool kern);
  //...