sys.c

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

/*
 *  linux/kernel/sys.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/init.h>
#include <linux/highuid.h>

#include <asm/uaccess.h>
#include <asm/io.h>

/*
 * this is where the system-wide overflow UID and GID are defined, for
 * architectures that now have 32-bit UID/GID but didn't in the past
 */

int overflowuid = DEFAULT_OVERFLOWUID;
int overflowgid = DEFAULT_OVERFLOWGID;

/*
 * the same as above, but for filesystems which can only store a 16-bit
 * UID and GID. as such, this is needed on all architectures
 */

int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;

/*
 * this indicates whether you can reboot with ctrl-alt-del: the default is yes
 */

int C_A_D = 1;


/*
 *	Notifier list for kernel code which wants to be called
 *	at shutdown. This is used to stop any idling DMA operations
 *	and the like. 
 */

static struct notifier_block *reboot_notifier_list;
rwlock_t notifier_lock = RW_LOCK_UNLOCKED;

/**
 *	notifier_chain_register	- Add notifier to a notifier chain
 *	@list: Pointer to root list pointer
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a notifier chain.
 *
 *	Currently always returns zero.
 */
 
int notifier_chain_register(struct notifier_block **list, struct notifier_block *n)
{
	write_lock(&notifier_lock);
	while(*list)
	{
		if(n->priority > (*list)->priority)
			break;
		list= &((*list)->next);
	}
	n->next = *list;
	*list=n;
	write_unlock(&notifier_lock);
	return 0;
}

/**
 *	notifier_chain_unregister - Remove notifier from a notifier chain
 *	@nl: Pointer to root list pointer
 *	@n: New entry in notifier chain
 *
 *	Removes a notifier from a notifier chain.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
 
int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n)
{
	write_lock(&notifier_lock);
	while((*nl)!=NULL)
	{
		if((*nl)==n)
		{
			*nl=n->next;
			write_unlock(&notifier_lock);
			return 0;
		}
		nl=&((*nl)->next);
	}
	write_unlock(&notifier_lock);
	return -ENOENT;
}

/**
 *	notifier_call_chain - Call functions in a notifier chain
 *	@n: Pointer to root pointer of notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *
 *	Calls each function in a notifier chain in turn.
 *
 *	If the return value of the notifier can be and'd
 *	with %NOTIFY_STOP_MASK, then notifier_call_chain
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise, the return value is the return value
 *	of the last notifier function called.
 */
 
int notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
{
	int ret=NOTIFY_DONE;
	struct notifier_block *nb = *n;

	while(nb)
	{
		ret=nb->notifier_call(nb,val,v);
		if(ret&NOTIFY_STOP_MASK)
		{
			return ret;
		}
		nb=nb->next;
	}
	return ret;
}

/**
 *	register_reboot_notifier - Register function to be called at reboot time
 *	@nb: Info about notifier function to be called
 *
 *	Registers a function with the list of functions
 *	to be called at reboot time.
 *
 *	Currently always returns zero, as notifier_chain_register
 *	always returns zero.
 */
 
int register_reboot_notifier(struct notifier_block * nb)
{
	return notifier_chain_register(&reboot_notifier_list, nb);
}

/**
 *	unregister_reboot_notifier - Unregister previously registered reboot notifier
 *	@nb: Hook to be unregistered
 *
 *	Unregisters a previously registered reboot
 *	notifier function.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
 
int unregister_reboot_notifier(struct notifier_block * nb)
{
	return notifier_chain_unregister(&reboot_notifier_list, nb);
}

asmlinkage long sys_ni_syscall(void)
{
	return -ENOSYS;
}

static int proc_sel(struct task_struct *p, int which, int who)
{
	if(p->pid)
	{
		switch (which) {
			case PRIO_PROCESS:
				if (!who && p == current)
					return 1;
				return(p->pid == who);
			case PRIO_PGRP:
				if (!who)
					who = current->pgrp;
				return(p->pgrp == who);
			case PRIO_USER:
				if (!who)
					who = current->uid;
				return(p->uid == who);
		}
	}
	return 0;
}

asmlinkage long sys_setpriority(int which, int who, int niceval)
{
	struct task_struct *p;
	int error;

	if (which > 2 || which < 0)
		return -EINVAL;

	/* normalize: avoid signed division (rounding problems) */
	error = -ESRCH;
	if (niceval < -20)
		niceval = -20;
	if (niceval > 19)
		niceval = 19;

	read_lock(&tasklist_lock);
	for_each_task(p) {
		if (!proc_sel(p, which, who))
			continue;
		if (p->uid != current->euid &&
			p->uid != current->uid && !capable(CAP_SYS_NICE)) {
			error = -EPERM;
			continue;
		}
		if (error == -ESRCH)
			error = 0;
		if (niceval < p->nice && !capable(CAP_SYS_NICE))
			error = -EACCES;
		else
			p->nice = niceval;
	}
	read_unlock(&tasklist_lock);

	return error;
}

/*
 * Ugh. To avoid negative return values, "getpriority()" will
 * not return the normal nice-value, but a negated value that
 * has been offset by 20 (ie it returns 40..1 instead of -20..19)
 * to stay compatible.
 */
asmlinkage long sys_getpriority(int which, int who)
{
	struct task_struct *p;
	long retval = -ESRCH;

	if (which > 2 || which < 0)
		return -EINVAL;

	read_lock(&tasklist_lock);
	for_each_task (p) {
		long niceval;
		if (!proc_sel(p, which, who))
			continue;
		niceval = 20 - p->nice;
		if (niceval > retval)
			retval = niceval;
	}
	read_unlock(&tasklist_lock);

	return retval;
}


/*
 * Reboot system call: for obvious reasons only root may call it,
 * and even root needs to set up some magic numbers in the registers
 * so that some mistake won't make this reboot the whole machine.
 * You can also set the meaning of the ctrl-alt-del-key here.
 *
 * reboot doesn't sync: do that yourself before calling this.
 */
asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void * arg)
{
	char buffer[256];

	/* We only trust the superuser with rebooting the system. */
	if (!capable(CAP_SYS_BOOT))
		return -EPERM;

	/* For safety, we require "magic" arguments. */
	if (magic1 != LINUX_REBOOT_MAGIC1 ||
	    (magic2 != LINUX_REBOOT_MAGIC2 && magic2 != LINUX_REBOOT_MAGIC2A &&
			magic2 != LINUX_REBOOT_MAGIC2B))
		return -EINVAL;

	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
		printk(KERN_EMERG "Restarting system.\n");
		machine_restart(NULL);
		break;

	case LINUX_REBOOT_CMD_CAD_ON:
		C_A_D = 1;
		break;

	case LINUX_REBOOT_CMD_CAD_OFF:
		C_A_D = 0;
		break;

	case LINUX_REBOOT_CMD_HALT:
		notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL);
		printk(KERN_EMERG "System halted.\n");
		machine_halt();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_POWER_OFF:
		notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL);
		printk(KERN_EMERG "Power down.\n");
		machine_power_off();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_RESTART2:
		if (strncpy_from_user(&buffer[0], (char *)arg, sizeof(buffer) - 1) < 0) {
			unlock_kernel();
			return -EFAULT;
		}
		buffer[sizeof(buffer) - 1] = '\0';

		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, buffer);
		printk(KERN_EMERG "Restarting system with command '%s'.\n", buffer);
		machine_restart(buffer);
		break;

	default:
		unlock_kernel();
		return -EINVAL;
	}
	unlock_kernel();
	return 0;
}

/*
 * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
 * As it's called within an interrupt, it may NOT sync: the only choice
 * is whether to reboot at once, or just ignore the ctrl-alt-del.
 */
void ctrl_alt_del(void)
{
	if (C_A_D) {
		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
		machine_restart(NULL);
	} else
		kill_proc(1, SIGINT, 1);
}
	

/*
 * Unprivileged users may change the real gid to the effective gid
 * or vice versa.  (BSD-style)
 *
 * If you set the real gid at all, or set the effective gid to a value not
 * equal to the real gid, then the saved gid is set to the new effective gid.
 *
 * This makes it possible for a setgid program to completely drop its
 * privileges, which is often a useful assertion to make when you are doing
 * a security audit over a program.
 *
 * The general idea is that a program which uses just setregid() will be
 * 100% compatible with BSD.  A program which uses just setgid() will be