linux系统调用过程

在用户程序调用read、write等系统调用时，linux内核发生了哪些动作呢。下面以write为例：

调用write系统调用，进入C库执行write函数，就是产生了一个int 0X80的一个中断，这样程序就会进入内核态，中断会根据_NR_name来判断执行那个内核函数，他其实就是int 0X80的一个参数。处理好现场后进入系统调用表：

所以wirte函数，具体的功能就是，触发int80中断，进行系统调用，调用号是__NR_write（#define __NR_write 4），最终会调用数组sys_call_table[4], 也就是sys_write

### int 0x80 - linux系统调用入口点(调用中断int 0x80,eax 中是调用号)
.align 2
system_call:
	cmpl $nr_system_calls-1,%eax    # 调用号如果超出范围的话就在eax中置-1并退出
	ja bad_sys_call
	push %ds                        # 保存原段寄存器值
	push %es
	push %fs
# 一个系统调用最多可带有3个参数，也可以不带参数。下面入栈的ebx、ecx和edx中放着系统
# 调用相应C语言函数的调用函数。这几个寄存器入栈的顺序是由GNU GCC规定的，
# ebx 中可存放第1个参数，ecx中存放第2个参数，edx中存放第3个参数。
# 系统调用语句可参见头文件include/unistd.h中的系统调用宏。
	pushl %edx
	pushl %ecx		# push %ebx,%ecx,%edx as parameters
	pushl %ebx		# to the system call
	movl $0x10,%edx		# set up ds,es to kernel space
	mov %dx,%ds
	mov %dx,%es
# fs指向局部数据段(局部描述符表中数据段描述符)，即指向执行本次系统调用的用户程序的数据段。
# 注意,在Linux 0.11 中内核给任务分配的代码和数据内存段是重叠的，他们的段基址和段限长相同。
	movl $0x17,%edx		# fs points to local data space
	mov %dx,%fs
# 下面这句操作数的含义是：调用地址=[_sys_call_table + %eax * 4]
# sys_call_table[]是一个指针数组，定义在include/linux/sys.h中，该指针数组中设置了所有72
# 个系统调用C处理函数地址。
	call sys_call_table(,%eax,4)        # 间接调用指定功能C函数
	pushl %eax             

//系统调用表
fn_ptr sys_call_table[] = { sys_setup, sys_exit, sys_fork, sys_read,
sys_write, sys_open, sys_close, sys_waitpid, sys_creat, sys_link,
sys_unlink, sys_execve, sys_chdir, sys_time, sys_mknod, sys_chmod,
sys_chown, sys_break, sys_stat, sys_lseek, sys_getpid, sys_mount,
sys_umount, sys_setuid, sys_getuid, sys_stime, sys_ptrace, sys_alarm,
sys_fstat, sys_pause, sys_utime, sys_stty, sys_gtty, sys_access,
sys_nice, sys_ftime, sys_sync, sys_kill, sys_rename, sys_mkdir,
sys_rmdir, sys_dup, sys_pipe, sys_times, sys_prof, sys_brk, sys_setgid,
sys_getgid, sys_signal, sys_geteuid, sys_getegid, sys_acct, sys_phys,
sys_lock, sys_ioctl, sys_fcntl, sys_mpx, sys_setpgid, sys_ulimit,
sys_uname, sys_umask, sys_chroot, sys_ustat, sys_dup2, sys_getppid,
sys_getpgrp, sys_setsid, sys_sigaction, sys_sgetmask, sys_ssetmask,
sys_setreuid,sys_setregid };
#define __NR_setup	0	/* used only by init, to get system going */
#define __NR_exit	1
#define __NR_fork	2
#define __NR_read	3
#define __NR_write	4
#define __NR_open	5
#define __NR_close	6
#define __NR_waitpid	7
#define __NR_creat	8
#define __NR_link	9
#define __NR_unlink	10
#define __NR_execve	11
#define __NR_chdir	12
#define __NR_time	13
#define __NR_mknod	14
#define __NR_chmod	15
#define __NR_chown	16
#define __NR_break	17
#define __NR_stat	18
#define __NR_lseek	19
#define __NR_getpid	20
#define __NR_mount	21
#define __NR_umount	22
#define __NR_setuid	23
#define __NR_getuid	24
#define __NR_stime	25
#define __NR_ptrace	26
#define __NR_alarm	27
#define __NR_fstat	28
#define __NR_pause	29
#define __NR_utime	30
#define __NR_stty	31
#define __NR_gtty	32
#define __NR_access	33
#define __NR_nice	34
#define __NR_ftime	35
#define __NR_sync	36
#define __NR_kill	37
#define __NR_rename	38
#define __NR_mkdir	39
#define __NR_rmdir	40
#define __NR_dup	41
#define __NR_pipe	42
#define __NR_times	43
#define __NR_prof	44
#define __NR_brk	45
#define __NR_setgid	46
#define __NR_getgid	47
#define __NR_signal	48
#define __NR_geteuid	49
#define __NR_getegid	50
#define __NR_acct	51
#define __NR_phys	52
#define __NR_lock	53
#define __NR_ioctl	54
#define __NR_fcntl	55
#define __NR_mpx	56
#define __NR_setpgid	57
#define __NR_ulimit	58
#define __NR_uname	59
#define __NR_umask	60
#define __NR_chroot	61
#define __NR_ustat	62
#define __NR_dup2	63
#define __NR_getppid	64
#define __NR_getpgrp	65
#define __NR_setsid	66
#define __NR_sigaction	67
#define __NR_sgetmask	68
#define __NR_ssetmask	69
#define __NR_setreuid	70
#define __NR_setregid	71

根据参数得到调用的sys_write执行。之后根据fd来找到文件的inode节点，判断是哪种文件，执行相应的操作。

int sys_write(unsigned int fd,char * buf,int count)
{
	struct file * file;
	struct m_inode * inode;
	
	if (fd>=NR_OPEN || count <0 || !(file=current->filp[fd]))
		return -EINVAL;
	if (!count)
		return 0;
	inode=file->f_inode;
	if (inode->i_pipe)
		return (file->f_mode&2)?write_pipe(inode,buf,count):-EIO;
	if (S_ISCHR(inode->i_mode))
		return rw_char(WRITE,inode->i_zone[0],buf,count,&file->f_pos);
	if (S_ISBLK(inode->i_mode))
		return block_write(inode->i_zone[0],&file->f_pos,buf,count);
	if (S_ISREG(inode->i_mode))
		return file_write(inode,file,buf,count);
	printk("(Write)inode->i_mode=%06o\n\r",inode->i_mode);
	return -EINVAL;
}

总结如下图：