Linux内核学习（2)——系统调用

kernel中的系统调用入口：

linux/arch/arm/kernel/calls.S

被文件linux/arch/arm/kernel/entry-common.S调用

/*
 * Let's declare a second syscall table for old ABI binaries
 * using the compatibility syscall entries.
 */
#define ABI(native, compat) compat
#define OBSOLETE(syscall) syscall

	.type	sys_oabi_call_table, #object
ENTRY(sys_oabi_call_table)
#include "calls.S"
#undef ABI
#undef OBSOLETE

#endif

对应socket的接口如下：

CALL(OBSOLETE(ABI(sys_socketcall, sys_oabi_socketcall)))     /*102*/

最后

asmlinkage long sys_oabi_socketcall(int call, unsigned long __user *args)
{
	unsigned long r = -EFAULT, a[6];

	switch (call) {
	case SYS_BIND:
		if (copy_from_user(a, args, 3 * sizeof(long)) == 0)
			r = sys_oabi_bind(a[0], (struct sockaddr __user *)a[1], a[2]);
		break;
	case SYS_CONNECT:
		if (copy_from_user(a, args, 3 * sizeof(long)) == 0)
			r = sys_oabi_connect(a[0], (struct sockaddr __user *)a[1], a[2]);
		break;
	case SYS_SENDTO:
		if (copy_from_user(a, args, 6 * sizeof(long)) == 0)
			r = sys_oabi_sendto(a[0], (void __user *)a[1], a[2], a[3],
					    (struct sockaddr __user *)a[4], a[5]);
		break;
	case SYS_SENDMSG:
		if (copy_from_user(a, args, 3 * sizeof(long)) == 0)
			r = sys_oabi_sendmsg(a[0], (struct user_msghdr __user *)a[1], a[2]);
		break;
	default:
		r = sys_socketcall(call, args);
	}

	return r;
}

例如创建socket，那么调用sys_socketcall，这个函数定义在net/socket.c

#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)

#define SYSCALL_DEFINEx(x, sname, ...)                \
    SYSCALL_METADATA(sname, x, __VA_ARGS__)            \  这个可以忽略
    __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)

最后变成

#define __SYSCALL_DEFINEx(x, name, ...)                    \
    asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))    \
        __attribute__((alias(__stringify(SyS##name))));        \
    static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));    \
    asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));    \
    asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))    \
    {                                \
        long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));    \
        __MAP(x,__SC_TEST,__VA_ARGS__);                \
        __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));    \
        return ret;                        \
    }                                \
    static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))

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;

	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_send(a0, (void __user *)a1, a[2], a[3]);
		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_recv(a0, (void __user *)a1, a[2], a[3]);
		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]);
		break;
	case SYS_SENDMMSG:
		err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]);
		break;
	case SYS_RECVMSG:
		err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]);
		break;
	case SYS_RECVMMSG:
		err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3],
				   (struct timespec __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;
}

#define __SYSCALL_DEFINEx(x, name, ...)					\
	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
		__attribute__((alias(__stringify(SyS##name))));		\
	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
	{								\
		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
		__MAP(x,__SC_TEST,__VA_ARGS__);				\
		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
		return ret;						\
	}								\
	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))

通过对宏定义的展开，就可以看到外部的系统调用，会进入到这里，

这样，我们就了解了系统调用的顺序，

首先外部app通过c库的socket，进入调用，这个调用会调用到102 (entry-common.S), 在这里调用到sys_oabi_socketcall，

在里面调用到sys_socketcall，这个函数用宏定义来完成，具体实际就是

SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)

从这里开始，拷贝参数到内核，进入到具体的内核工作。