Socket与系统调用深度分析

标签：linux   函数   toc   运行   封装   etc   flags   启动过程   一个   

Socket与系统调用

系统调用是操作系统为用户态进程与硬件设备之间进行交互提供的一组接口，其实现是通过一个软中断(trap）使系统从用户态切换为内核态。
Socket的功能通过调用Socket API来实现，而API(application program interface)实际上是函数接口。API可能直接提供用户态的的服务，也可能通过封装例程(wrapper routine)调用一个或多个系统调用。它们之间的具体关系如下图：

所有socket系统调用的总入口是SYSCALL_DEFINE2,其定义在./net/socket.c中

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;
}

其中用接口编号call进行分支选择，与具体的系统调用对应，接口编号在include/uapi/linux/net.h中定义

gdb追踪系统调用

选择创建socket的函数__sys_socket设立断点，发现其在qemu启动过程中被调用3次，在运行replyhi/hello过程中被调用两次


__sys_socket源代码同样在./net/socket.c中，其功能为创建一个socket，并返回分配的文件描述符，是socket能对系统中的文件进行操作(读、写等）

int __sys_socket(int family, int type, int protocol)
{
    int retval;
    struct socket *sock;
    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));
}

查看__sys_socket汇编码，未发现int 0x80,说明__sys_socket一直在内核态中运行，没有来回切换

如果要查看系统何时从用户态切换到内核态，需要在linux执行int 0x80之前不远处设置断点，暂时还未找到实现这一操作的办法-_-||

Socket与系统调用深度分析

标签：linux   函数   toc   运行   封装   etc   flags   启动过程   一个   

原文地址：https://www.cnblogs.com/ypsupreme/p/12063628.html