Linux-2.6.12-rc2

[net-next-2.6.git] / kernel / sys.c

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

#include <linux/config.h>
#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 <linux/fs.h>
#include <linux/workqueue.h>
#include <linux/device.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
#include <linux/dcookies.h>
#include <linux/suspend.h>
#include <linux/tty.h>

#include <linux/compat.h>
#include <linux/syscalls.h>

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

#ifndef SET_UNALIGN_CTL
# define SET_UNALIGN_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_UNALIGN_CTL
# define GET_UNALIGN_CTL(a,b)	(-EINVAL)
#endif
#ifndef SET_FPEMU_CTL
# define SET_FPEMU_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_FPEMU_CTL
# define GET_FPEMU_CTL(a,b)	(-EINVAL)
#endif
#ifndef SET_FPEXC_CTL
# define SET_FPEXC_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_FPEXC_CTL
# define GET_FPEXC_CTL(a,b)	(-EINVAL)
#endif

/*
 * 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;

#ifdef CONFIG_UID16
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
#endif

/*
 * 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;

EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);

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

int C_A_D = 1;
int cad_pid = 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;
static DEFINE_RWLOCK(notifier_lock);

/**
 *	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;
}

EXPORT_SYMBOL(notifier_chain_register);

/**
 *	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;
}

EXPORT_SYMBOL(notifier_chain_unregister);

/**
 *	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;
}

EXPORT_SYMBOL(notifier_call_chain);

/**
 *	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);
}

EXPORT_SYMBOL(register_reboot_notifier);

/**
 *	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);
}

EXPORT_SYMBOL(unregister_reboot_notifier);

static int set_one_prio(struct task_struct *p, int niceval, int error)
{
	int no_nice;

	if (p->uid != current->euid &&
		p->euid != current->euid && !capable(CAP_SYS_NICE)) {
		error = -EPERM;
		goto out;
	}
	if (niceval < task_nice(p) && !capable(CAP_SYS_NICE)) {
		error = -EACCES;
		goto out;
	}
	no_nice = security_task_setnice(p, niceval);
	if (no_nice) {
		error = no_nice;
		goto out;
	}
	if (error == -ESRCH)
		error = 0;
	set_user_nice(p, niceval);
out:
	return error;
}

asmlinkage long sys_setpriority(int which, int who, int niceval)
{
	struct task_struct *g, *p;
	struct user_struct *user;
	int error = -EINVAL;

	if (which > 2 || which < 0)
		goto out;

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

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
			if (!who)
				who = current->pid;
			p = find_task_by_pid(who);
			if (p)
				error = set_one_prio(p, niceval, error);
			break;
		case PRIO_PGRP:
			if (!who)
				who = process_group(current);
			do_each_task_pid(who, PIDTYPE_PGID, p) {
				error = set_one_prio(p, niceval, error);
			} while_each_task_pid(who, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = current->user;
			if (!who)
				who = current->uid;
			else
				if ((who != current->uid) && !(user = find_user(who)))
					goto out_unlock;	/* No processes for this user */

			do_each_thread(g, p)
				if (p->uid == who)
					error = set_one_prio(p, niceval, error);
			while_each_thread(g, p);
			if (who != current->uid)
				free_uid(user);		/* For find_user() */
			break;
	}
out_unlock:
	read_unlock(&tasklist_lock);
out:
	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 *g, *p;
	struct user_struct *user;
	long niceval, retval = -ESRCH;

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

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
			if (!who)
				who = current->pid;
			p = find_task_by_pid(who);
			if (p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			}
			break;
		case PRIO_PGRP:
			if (!who)
				who = process_group(current);
			do_each_task_pid(who, PIDTYPE_PGID, p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			} while_each_task_pid(who, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = current->user;
			if (!who)
				who = current->uid;
			else
				if ((who != current->uid) && !(user = find_user(who)))
					goto out_unlock;	/* No processes for this user */

			do_each_thread(g, p)
				if (p->uid == who) {
					niceval = 20 - task_nice(p);
					if (niceval > retval)
						retval = niceval;
				}
			while_each_thread(g, p);
			if (who != current->uid)
				free_uid(user);		/* for find_user() */
			break;
	}
out_unlock:
	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 __user * 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 &&
	                magic2 != LINUX_REBOOT_MAGIC2C))
		return -EINVAL;

	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
		system_state = SYSTEM_RESTART;
		device_shutdown();
		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);
		system_state = SYSTEM_HALT;
		device_shutdown();
		printk(KERN_EMERG "System halted.\n");
		machine_halt();
		unlock_kernel();
		do_exit(0);
		break;

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

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

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

#ifdef CONFIG_SOFTWARE_SUSPEND
	case LINUX_REBOOT_CMD_SW_SUSPEND:
		{
			int ret = software_suspend();
			unlock_kernel();
			return ret;
		}
#endif

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

static void deferred_cad(void *dummy)
{
	notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
	machine_restart(NULL);
}

/*
 * 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)
{
	static DECLARE_WORK(cad_work, deferred_cad, NULL);

	if (C_A_D)
		schedule_work(&cad_work);
	else
		kill_proc(cad_pid, 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
 * 100% compatible with POSIX with saved IDs. 
 *
 * SMP: There are not races, the GIDs are checked only by filesystem
 *      operations (as far as semantic preservation is concerned).
 */
asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
{
	int old_rgid = current->gid;
	int old_egid = current->egid;
	int new_rgid = old_rgid;
	int new_egid = old_egid;
	int retval;

	retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
	if (retval)
		return retval;

	if (rgid != (gid_t) -1) {
		if ((old_rgid == rgid) ||
		    (current->egid==rgid) ||
		    capable(CAP_SETGID))
			new_rgid = rgid;
		else
			return -EPERM;
	}
	if (egid != (gid_t) -1) {
		if ((old_rgid == egid) ||
		    (current->egid == egid) ||
		    (current->sgid == egid) ||
		    capable(CAP_SETGID))
			new_egid = egid;
		else {
			return -EPERM;
		}
	}
	if (new_egid != old_egid)
	{
		current->mm->dumpable = 0;
		wmb();
	}
	if (rgid != (gid_t) -1 ||
	    (egid != (gid_t) -1 && egid != old_rgid))
		current->sgid = new_egid;
	current->fsgid = new_egid;
	current->egid = new_egid;
	current->gid = new_rgid;
	key_fsgid_changed(current);
	return 0;
}

/*
 * setgid() is implemented like SysV w/ SAVED_IDS 
 *
 * SMP: Same implicit races as above.
 */
asmlinkage long sys_setgid(gid_t gid)
{
	int old_egid = current->egid;
	int retval;

	retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
	if (retval)
		return retval;

	if (capable(CAP_SETGID))
	{
		if(old_egid != gid)
		{
			current->mm->dumpable=0;
			wmb();
		}
		current->gid = current->egid = current->sgid = current->fsgid = gid;
	}
	else if ((gid == current->gid) || (gid == current->sgid))
	{
		if(old_egid != gid)
		{
			current->mm->dumpable=0;
			wmb();
		}
		current->egid = current->fsgid = gid;
	}
	else
		return -EPERM;

	key_fsgid_changed(current);
	return 0;
}
  
static int set_user(uid_t new_ruid, int dumpclear)
{
	struct user_struct *new_user;

	new_user = alloc_uid(new_ruid);
	if (!new_user)
		return -EAGAIN;

	if (atomic_read(&new_user->processes) >=
				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
			new_user != &root_user) {
		free_uid(new_user);
		return -EAGAIN;
	}

	switch_uid(new_user);

	if(dumpclear)
	{
		current->mm->dumpable = 0;
		wmb();
	}
	current->uid = new_ruid;
	return 0;
}

/*
 * Unprivileged users may change the real uid to the effective uid
 * or vice versa.  (BSD-style)
 *
 * If you set the real uid at all, or set the effective uid to a value not
 * equal to the real uid, then the saved uid is set to the new effective uid.
 *
 * This makes it possible for a setuid 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 setreuid() will be
 * 100% compatible with BSD.  A program which uses just setuid() will be
 * 100% compatible with POSIX with saved IDs. 
 */
asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
{
	int old_ruid, old_euid, old_suid, new_ruid, new_euid;
	int retval;

	retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
	if (retval)
		return retval;

	new_ruid = old_ruid = current->uid;
	new_euid = old_euid = current->euid;
	old_suid = current->suid;

	if (ruid != (uid_t) -1) {
		new_ruid = ruid;
		if ((old_ruid != ruid) &&
		    (current->euid != ruid) &&
		    !capable(CAP_SETUID))
			return -EPERM;
	}

	if (euid != (uid_t) -1) {
		new_euid = euid;
		if ((old_ruid != euid) &&
		    (current->euid != euid) &&
		    (current->suid != euid) &&
		    !capable(CAP_SETUID))
			return -EPERM;
	}

	if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
		return -EAGAIN;

	if (new_euid != old_euid)
	{
		current->mm->dumpable=0;
		wmb();
	}
	current->fsuid = current->euid = new_euid;
	if (ruid != (uid_t) -1 ||
	    (euid != (uid_t) -1 && euid != old_ruid))
		current->suid = current->euid;
	current->fsuid = current->euid;

	key_fsuid_changed(current);

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
}


		
/*
 * setuid() is implemented like SysV with SAVED_IDS 
 * 
 * Note that SAVED_ID's is deficient in that a setuid root program
 * like sendmail, for example, cannot set its uid to be a normal 
 * user and then switch back, because if you're root, setuid() sets
 * the saved uid too.  If you don't like this, blame the bright people
 * in the POSIX committee and/or USG.  Note that the BSD-style setreuid()
 * will allow a root program to temporarily drop privileges and be able to
 * regain them by swapping the real and effective uid.  
 */
asmlinkage long sys_setuid(uid_t uid)
{
	int old_euid = current->euid;
	int old_ruid, old_suid, new_ruid, new_suid;
	int retval;

	retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
	if (retval)
		return retval;

	old_ruid = new_ruid = current->uid;
	old_suid = current->suid;
	new_suid = old_suid;
	
	if (capable(CAP_SETUID)) {
		if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
			return -EAGAIN;
		new_suid = uid;
	} else if ((uid != current->uid) && (uid != new_suid))
		return -EPERM;

	if (old_euid != uid)
	{
		current->mm->dumpable = 0;
		wmb();
	}
	current->fsuid = current->euid = uid;
	current->suid = new_suid;

	key_fsuid_changed(current);

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
}


/*
 * This function implements a generic ability to update ruid, euid,
 * and suid.  This allows you to implement the 4.4 compatible seteuid().
 */
asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
{
	int old_ruid = current->uid;
	int old_euid = current->euid;
	int old_suid = current->suid;
	int retval;

	retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
	if (retval)
		return retval;

	if (!capable(CAP_SETUID)) {
		if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
		    (ruid != current->euid) && (ruid != current->suid))
			return -EPERM;
		if ((euid != (uid_t) -1) && (euid != current->uid) &&
		    (euid != current->euid) && (euid != current->suid))
			return -EPERM;
		if ((suid != (uid_t) -1) && (suid != current->uid) &&
		    (suid != current->euid) && (suid != current->suid))
			return -EPERM;
	}
	if (ruid != (uid_t) -1) {
		if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
			return -EAGAIN;
	}
	if (euid != (uid_t) -1) {
		if (euid != current->euid)
		{
			current->mm->dumpable = 0;
			wmb();
		}
		current->euid = euid;
	}
	current->fsuid = current->euid;
	if (suid != (uid_t) -1)
		current->suid = suid;

	key_fsuid_changed(current);

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
}

asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
{
	int retval;

	if (!(retval = put_user(current->uid, ruid)) &&
	    !(retval = put_user(current->euid, euid)))
		retval = put_user(current->suid, suid);

	return retval;
}

/*
 * Same as above, but for rgid, egid, sgid.
 */
asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
{
	int retval;

	retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
	if (retval)
		return retval;

	if (!capable(CAP_SETGID)) {
		if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
		    (rgid != current->egid) && (rgid != current->sgid))
			return -EPERM;
		if ((egid != (gid_t) -1) && (egid != current->gid) &&
		    (egid != current->egid) && (egid != current->sgid))
			return -EPERM;
		if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
		    (sgid != current->egid) && (sgid != current->sgid))
			return -EPERM;
	}
	if (egid != (gid_t) -1) {
		if (egid != current->egid)
		{
			current->mm->dumpable = 0;
			wmb();
		}
		current->egid = egid;
	}
	current->fsgid = current->egid;
	if (rgid != (gid_t) -1)
		current->gid = rgid;
	if (sgid != (gid_t) -1)
		current->sgid = sgid;

	key_fsgid_changed(current);
	return 0;
}

asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
{
	int retval;

	if (!(retval = put_user(current->gid, rgid)) &&
	    !(retval = put_user(current->egid, egid)))
		retval = put_user(current->sgid, sgid);

	return retval;
}


/*
 * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
 * is used for "access()" and for the NFS daemon (letting nfsd stay at
 * whatever uid it wants to). It normally shadows "euid", except when
 * explicitly set by setfsuid() or for access..
 */
asmlinkage long sys_setfsuid(uid_t uid)
{
	int old_fsuid;

	old_fsuid = current->fsuid;
	if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
		return old_fsuid;

	if (uid == current->uid || uid == current->euid ||
	    uid == current->suid || uid == current->fsuid || 
	    capable(CAP_SETUID))
	{
		if (uid != old_fsuid)
		{
			current->mm->dumpable = 0;
			wmb();
		}
		current->fsuid = uid;
	}

	key_fsuid_changed(current);

	security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);

	return old_fsuid;
}

/*