remarkable-linux/kernel/sys.c
Serge Hallyn 18b6e0414e User namespaces: set of cleanups (v2)
The user_ns is moved from nsproxy to user_struct, so that a struct
cred by itself is sufficient to determine access (which it otherwise
would not be).  Corresponding ecryptfs fixes (by David Howells) are
here as well.

Fix refcounting.  The following rules now apply:
        1. The task pins the user struct.
        2. The user struct pins its user namespace.
        3. The user namespace pins the struct user which created it.

User namespaces are cloned during copy_creds().  Unsharing a new user_ns
is no longer possible.  (We could re-add that, but it'll cause code
duplication and doesn't seem useful if PAM doesn't need to clone user
namespaces).

When a user namespace is created, its first user (uid 0) gets empty
keyrings and a clean group_info.

This incorporates a previous patch by David Howells.  Here
is his original patch description:

>I suggest adding the attached incremental patch.  It makes the following
>changes:
>
> (1) Provides a current_user_ns() macro to wrap accesses to current's user
>     namespace.
>
> (2) Fixes eCryptFS.
>
> (3) Renames create_new_userns() to create_user_ns() to be more consistent
>     with the other associated functions and because the 'new' in the name is
>     superfluous.
>
> (4) Moves the argument and permission checks made for CLONE_NEWUSER to the
>     beginning of do_fork() so that they're done prior to making any attempts
>     at allocation.
>
> (5) Calls create_user_ns() after prepare_creds(), and gives it the new creds
>     to fill in rather than have it return the new root user.  I don't imagine
>     the new root user being used for anything other than filling in a cred
>     struct.
>
>     This also permits me to get rid of a get_uid() and a free_uid(), as the
>     reference the creds were holding on the old user_struct can just be
>     transferred to the new namespace's creator pointer.
>
> (6) Makes create_user_ns() reset the UIDs and GIDs of the creds under
>     preparation rather than doing it in copy_creds().
>
>David

>Signed-off-by: David Howells <dhowells@redhat.com>

Changelog:
	Oct 20: integrate dhowells comments
		1. leave thread_keyring alone
		2. use current_user_ns() in set_user()

Signed-off-by: Serge Hallyn <serue@us.ibm.com>
2008-11-24 18:57:41 -05:00

1883 lines
42 KiB
C

/*
* 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/highuid.h>
#include <linux/fs.h>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.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/signal.h>
#include <linux/cn_proc.h>
#include <linux/getcpu.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/seccomp.h>
#include <linux/cpu.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.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
#ifndef GET_ENDIAN
# define GET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef GET_TSC_CTL
# define GET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-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;
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);
/*
* If set, this is used for preparing the system to power off.
*/
void (*pm_power_off_prepare)(void);
/*
* set the priority of a task
* - the caller must hold the RCU read lock
*/
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
int no_nice;
if (pcred->uid != cred->euid &&
pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
error = -EPERM;
goto out;
}
if (niceval < task_nice(p) && !can_nice(p, niceval)) {
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;
const struct cred *cred = current_cred();
int error = -EINVAL;
struct pid *pgrp;
if (which > PRIO_USER || which < PRIO_PROCESS)
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)
p = find_task_by_vpid(who);
else
p = current;
if (p)
error = set_one_prio(p, niceval, error);
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
user = (struct user_struct *) cred->user;
if (!who)
who = cred->uid;
else if ((who != cred->uid) &&
!(user = find_user(who)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (__task_cred(p)->uid == who)
error = set_one_prio(p, niceval, error);
while_each_thread(g, p);
if (who != cred->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;
const struct cred *cred = current_cred();
long niceval, retval = -ESRCH;
struct pid *pgrp;
if (which > PRIO_USER || which < PRIO_PROCESS)
return -EINVAL;
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
user = (struct user_struct *) cred->user;
if (!who)
who = cred->uid;
else if ((who != cred->uid) &&
!(user = find_user(who)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (__task_cred(p)->uid == who) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
while_each_thread(g, p);
if (who != cred->uid)
free_uid(user); /* for find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
return retval;
}
/**
* emergency_restart - reboot the system
*
* Without shutting down any hardware or taking any locks
* reboot the system. This is called when we know we are in
* trouble so this is our best effort to reboot. This is
* safe to call in interrupt context.
*/
void emergency_restart(void)
{
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
void kernel_restart_prepare(char *cmd)
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
device_shutdown();
sysdev_shutdown();
}
/**
* kernel_restart - reboot the system
* @cmd: pointer to buffer containing command to execute for restart
* or %NULL
*
* Shutdown everything and perform a clean reboot.
* This is not safe to call in interrupt context.
*/
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
if (!cmd)
printk(KERN_EMERG "Restarting system.\n");
else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
static void kernel_shutdown_prepare(enum system_states state)
{
blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
system_state = state;
device_shutdown();
}
/**
* kernel_halt - halt the system
*
* Shutdown everything and perform a clean system halt.
*/
void kernel_halt(void)
{
kernel_shutdown_prepare(SYSTEM_HALT);
sysdev_shutdown();
printk(KERN_EMERG "System halted.\n");
machine_halt();
}
EXPORT_SYMBOL_GPL(kernel_halt);
/**
* kernel_power_off - power_off the system
*
* Shutdown everything and perform a clean system power_off.
*/
void kernel_power_off(void)
{
kernel_shutdown_prepare(SYSTEM_POWER_OFF);
if (pm_power_off_prepare)
pm_power_off_prepare();
disable_nonboot_cpus();
sysdev_shutdown();
printk(KERN_EMERG "Power down.\n");
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
/*
* 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;
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
lock_kernel();
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_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:
kernel_halt();
unlock_kernel();
do_exit(0);
break;
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_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';
kernel_restart(buffer);
break;
#ifdef CONFIG_KEXEC
case LINUX_REBOOT_CMD_KEXEC:
{
int ret;
ret = kernel_kexec();
unlock_kernel();
return ret;
}
#endif
#ifdef CONFIG_HIBERNATION
case LINUX_REBOOT_CMD_SW_SUSPEND:
{
int ret = hibernate();
unlock_kernel();
return ret;
}
#endif
default:
unlock_kernel();
return -EINVAL;
}
unlock_kernel();
return 0;
}
static void deferred_cad(struct work_struct *dummy)
{
kernel_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);
if (C_A_D)
schedule_work(&cad_work);
else
kill_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)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
if (retval)
goto error;
retval = -EPERM;
if (rgid != (gid_t) -1) {
if (old->gid == rgid ||
old->egid == rgid ||
capable(CAP_SETGID))
new->gid = rgid;
else
goto error;
}
if (egid != (gid_t) -1) {
if (old->gid == egid ||
old->egid == egid ||
old->sgid == egid ||
capable(CAP_SETGID))
new->egid = egid;
else
goto error;
}
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && egid != old->gid))
new->sgid = new->egid;
new->fsgid = new->egid;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* setgid() is implemented like SysV w/ SAVED_IDS
*
* SMP: Same implicit races as above.
*/
asmlinkage long sys_setgid(gid_t gid)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
if (retval)
goto error;
retval = -EPERM;
if (capable(CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = gid;
else if (gid == old->gid || gid == old->sgid)
new->egid = new->fsgid = gid;
else
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* change the user struct in a credentials set to match the new UID
*/
static int set_user(struct cred *new)
{
struct user_struct *new_user;
new_user = alloc_uid(current_user_ns(), new->uid);
if (!new_user)
return -EAGAIN;
if (atomic_read(&new_user->processes) >=
current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
new_user != INIT_USER) {
free_uid(new_user);
return -EAGAIN;
}
free_uid(new->user);
new->user = new_user;
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)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
if (retval)
goto error;
retval = -EPERM;
if (ruid != (uid_t) -1) {
new->uid = ruid;
if (old->uid != ruid &&
old->euid != ruid &&
!capable(CAP_SETUID))
goto error;
}
if (euid != (uid_t) -1) {
new->euid = euid;
if (old->uid != euid &&
old->euid != euid &&
old->suid != euid &&
!capable(CAP_SETUID))
goto error;
}
retval = -EAGAIN;
if (new->uid != old->uid && set_user(new) < 0)
goto error;
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && euid != old->uid))
new->suid = new->euid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* 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)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
if (retval)
goto error;
retval = -EPERM;
if (capable(CAP_SETUID)) {
new->suid = new->uid = uid;
if (uid != old->uid && set_user(new) < 0) {
retval = -EAGAIN;
goto error;
}
} else if (uid != old->uid && uid != new->suid) {
goto error;
}
new->fsuid = new->euid = uid;
retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* 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)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
if (retval)
goto error;
old = current_cred();
retval = -EPERM;
if (!capable(CAP_SETUID)) {
if (ruid != (uid_t) -1 && ruid != old->uid &&
ruid != old->euid && ruid != old->suid)
goto error;
if (euid != (uid_t) -1 && euid != old->uid &&
euid != old->euid && euid != old->suid)
goto error;
if (suid != (uid_t) -1 && suid != old->uid &&
suid != old->euid && suid != old->suid)
goto error;
}
retval = -EAGAIN;
if (ruid != (uid_t) -1) {
new->uid = ruid;
if (ruid != old->uid && set_user(new) < 0)
goto error;
}
if (euid != (uid_t) -1)
new->euid = euid;
if (suid != (uid_t) -1)
new->suid = suid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
{
const struct cred *cred = current_cred();
int retval;
if (!(retval = put_user(cred->uid, ruid)) &&
!(retval = put_user(cred->euid, euid)))
retval = put_user(cred->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)
{
const struct cred *old;
struct cred *new;
int retval;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
if (retval)
goto error;
retval = -EPERM;
if (!capable(CAP_SETGID)) {
if (rgid != (gid_t) -1 && rgid != old->gid &&
rgid != old->egid && rgid != old->sgid)
goto error;
if (egid != (gid_t) -1 && egid != old->gid &&
egid != old->egid && egid != old->sgid)
goto error;
if (sgid != (gid_t) -1 && sgid != old->gid &&
sgid != old->egid && sgid != old->sgid)
goto error;
}
if (rgid != (gid_t) -1)
new->gid = rgid;
if (egid != (gid_t) -1)
new->egid = egid;
if (sgid != (gid_t) -1)
new->sgid = sgid;
new->fsgid = new->egid;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
{
const struct cred *cred = current_cred();
int retval;
if (!(retval = put_user(cred->gid, rgid)) &&
!(retval = put_user(cred->egid, egid)))
retval = put_user(cred->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)
{
const struct cred *old;
struct cred *new;
uid_t old_fsuid;
new = prepare_creds();
if (!new)
return current_fsuid();
old = current_cred();
old_fsuid = old->fsuid;
if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
goto error;
if (uid == old->uid || uid == old->euid ||
uid == old->suid || uid == old->fsuid ||
capable(CAP_SETUID)) {
if (uid != old_fsuid) {
new->fsuid = uid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
goto change_okay;
}
}
error:
abort_creds(new);
return old_fsuid;
change_okay:
commit_creds(new);
return old_fsuid;
}
/*
* Samma på svenska..
*/
asmlinkage long sys_setfsgid(gid_t gid)
{
const struct cred *old;
struct cred *new;
gid_t old_fsgid;
new = prepare_creds();
if (!new)
return current_fsgid();
old = current_cred();
old_fsgid = old->fsgid;
if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
goto error;
if (gid == old->gid || gid == old->egid ||
gid == old->sgid || gid == old->fsgid ||
capable(CAP_SETGID)) {
if (gid != old_fsgid) {
new->fsgid = gid;
goto change_okay;
}
}
error:
abort_creds(new);
return old_fsgid;
change_okay:
commit_creds(new);
return old_fsgid;
}
void do_sys_times(struct tms *tms)
{
struct task_cputime cputime;
cputime_t cutime, cstime;
spin_lock_irq(&current->sighand->siglock);
thread_group_cputime(current, &cputime);
cutime = current->signal->cutime;
cstime = current->signal->cstime;
spin_unlock_irq(&current->sighand->siglock);
tms->tms_utime = cputime_to_clock_t(cputime.utime);
tms->tms_stime = cputime_to_clock_t(cputime.stime);
tms->tms_cutime = cputime_to_clock_t(cutime);
tms->tms_cstime = cputime_to_clock_t(cstime);
}
asmlinkage long sys_times(struct tms __user * tbuf)
{
if (tbuf) {
struct tms tmp;
do_sys_times(&tmp);
if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
return -EFAULT;
}
return (long) jiffies_64_to_clock_t(get_jiffies_64());
}
/*
* This needs some heavy checking ...
* I just haven't the stomach for it. I also don't fully
* understand sessions/pgrp etc. Let somebody who does explain it.
*
* OK, I think I have the protection semantics right.... this is really
* only important on a multi-user system anyway, to make sure one user
* can't send a signal to a process owned by another. -TYT, 12/12/91
*
* Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
* LBT 04.03.94
*/
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
struct task_struct *group_leader = current->group_leader;
struct pid *pgrp;
int err;
if (!pid)
pid = task_pid_vnr(group_leader);
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
write_lock_irq(&tasklist_lock);
err = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
err = -EINVAL;
if (!thread_group_leader(p))
goto out;
if (same_thread_group(p->real_parent, group_leader)) {
err = -EPERM;
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
if (p != group_leader)
goto out;
}
err = -EPERM;
if (p->signal->leader)
goto out;
pgrp = task_pid(p);
if (pgid != pid) {
struct task_struct *g;
pgrp = find_vpid(pgid);
g = pid_task(pgrp, PIDTYPE_PGID);
if (!g || task_session(g) != task_session(group_leader))
goto out;
}
err = security_task_setpgid(p, pgid);
if (err)
goto out;
if (task_pgrp(p) != pgrp) {
change_pid(p, PIDTYPE_PGID, pgrp);
set_task_pgrp(p, pid_nr(pgrp));
}
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
return err;
}
asmlinkage long sys_getpgid(pid_t pid)
{
struct task_struct *p;
struct pid *grp;
int retval;
rcu_read_lock();
if (!pid)
grp = task_pgrp(current);
else {
retval = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
grp = task_pgrp(p);
if (!grp)
goto out;
retval = security_task_getpgid(p);
if (retval)
goto out;
}
retval = pid_vnr(grp);
out:
rcu_read_unlock();
return retval;
}
#ifdef __ARCH_WANT_SYS_GETPGRP
asmlinkage long sys_getpgrp(void)
{
return sys_getpgid(0);
}
#endif
asmlinkage long sys_getsid(pid_t pid)
{
struct task_struct *p;
struct pid *sid;
int retval;
rcu_read_lock();
if (!pid)
sid = task_session(current);
else {
retval = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
sid = task_session(p);
if (!sid)
goto out;
retval = security_task_getsid(p);
if (retval)
goto out;
}
retval = pid_vnr(sid);
out:
rcu_read_unlock();
return retval;
}
asmlinkage long sys_setsid(void)
{
struct task_struct *group_leader = current->group_leader;
struct pid *sid = task_pid(group_leader);
pid_t session = pid_vnr(sid);
int err = -EPERM;
write_lock_irq(&tasklist_lock);
/* Fail if I am already a session leader */
if (group_leader->signal->leader)
goto out;
/* Fail if a process group id already exists that equals the
* proposed session id.
*/
if (pid_task(sid, PIDTYPE_PGID))
goto out;
group_leader->signal->leader = 1;
__set_special_pids(sid);
proc_clear_tty(group_leader);
err = session;
out:
write_unlock_irq(&tasklist_lock);
return err;
}
/*
* Supplementary group IDs
*/
/* init to 2 - one for init_task, one to ensure it is never freed */
struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
struct group_info *groups_alloc(int gidsetsize)
{
struct group_info *group_info;
int nblocks;
int i;
nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
/* Make sure we always allocate at least one indirect block pointer */
nblocks = nblocks ? : 1;
group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
if (!group_info)
return NULL;
group_info->ngroups = gidsetsize;
group_info->nblocks = nblocks;
atomic_set(&group_info->usage, 1);
if (gidsetsize <= NGROUPS_SMALL)
group_info->blocks[0] = group_info->small_block;
else {
for (i = 0; i < nblocks; i++) {
gid_t *b;
b = (void *)__get_free_page(GFP_USER);
if (!b)
goto out_undo_partial_alloc;
group_info->blocks[i] = b;
}
}
return group_info;
out_undo_partial_alloc:
while (--i >= 0) {
free_page((unsigned long)group_info->blocks[i]);
}
kfree(group_info);
return NULL;
}
EXPORT_SYMBOL(groups_alloc);
void groups_free(struct group_info *group_info)
{
if (group_info->blocks[0] != group_info->small_block) {
int i;
for (i = 0; i < group_info->nblocks; i++)
free_page((unsigned long)group_info->blocks[i]);
}
kfree(group_info);
}
EXPORT_SYMBOL(groups_free);
/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
const struct group_info *group_info)
{
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
unsigned int len = cp_count * sizeof(*grouplist);
if (copy_to_user(grouplist, group_info->blocks[i], len))
return -EFAULT;
grouplist += NGROUPS_PER_BLOCK;
count -= cp_count;
}
return 0;
}
/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
{
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
unsigned int len = cp_count * sizeof(*grouplist);
if (copy_from_user(group_info->blocks[i], grouplist, len))
return -EFAULT;
grouplist += NGROUPS_PER_BLOCK;
count -= cp_count;
}
return 0;
}
/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
int base, max, stride;
int gidsetsize = group_info->ngroups;
for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
; /* nothing */
stride /= 3;
while (stride) {
max = gidsetsize - stride;
for (base = 0; base < max; base++) {
int left = base;
int right = left + stride;
gid_t tmp = GROUP_AT(group_info, right);
while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
GROUP_AT(group_info, right) =
GROUP_AT(group_info, left);
right = left;
left -= stride;
}
GROUP_AT(group_info, right) = tmp;
}
stride /= 3;
}
}
/* a simple bsearch */
int groups_search(const struct group_info *group_info, gid_t grp)
{
unsigned int left, right;
if (!group_info)
return 0;
left = 0;
right = group_info->ngroups;
while (left < right) {
unsigned int mid = (left+right)/2;
int cmp = grp - GROUP_AT(group_info, mid);
if (cmp > 0)
left = mid + 1;
else if (cmp < 0)
right = mid;
else
return 1;
}
return 0;
}
/**
* set_groups - Change a group subscription in a set of credentials
* @new: The newly prepared set of credentials to alter
* @group_info: The group list to install
*
* Validate a group subscription and, if valid, insert it into a set
* of credentials.
*/
int set_groups(struct cred *new, struct group_info *group_info)
{
int retval;
retval = security_task_setgroups(group_info);
if (retval)
return retval;
put_group_info(new->group_info);
groups_sort(group_info);
get_group_info(group_info);
new->group_info = group_info;
return 0;
}
EXPORT_SYMBOL(set_groups);
/**
* set_current_groups - Change current's group subscription
* @group_info: The group list to impose
*
* Validate a group subscription and, if valid, impose it upon current's task
* security record.
*/
int set_current_groups(struct group_info *group_info)
{
struct cred *new;
int ret;
new = prepare_creds();
if (!new)
return -ENOMEM;
ret = set_groups(new, group_info);
if (ret < 0) {
abort_creds(new);
return ret;
}
return commit_creds(new);
}
EXPORT_SYMBOL(set_current_groups);
asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
const struct cred *cred = current_cred();
int i;
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
i = cred->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups_to_user(grouplist, cred->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
return i;
}
/*
* SMP: Our groups are copy-on-write. We can set them safely
* without another task interfering.
*/
asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
{
struct group_info *group_info;
int retval;
if (!capable(CAP_SETGID))
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
group_info = groups_alloc(gidsetsize);
if (!group_info)
return -ENOMEM;
retval = groups_from_user(group_info, grouplist);
if (retval) {
put_group_info(group_info);
return retval;
}
retval = set_current_groups(group_info);
put_group_info(group_info);
return retval;
}
/*
* Check whether we're fsgid/egid or in the supplemental group..
*/
int in_group_p(gid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
if (grp != cred->fsgid)
retval = groups_search(cred->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_group_p);
int in_egroup_p(gid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
if (grp != cred->egid)
retval = groups_search(cred->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_egroup_p);
DECLARE_RWSEM(uts_sem);
asmlinkage long sys_newuname(struct new_utsname __user * name)
{
int errno = 0;
down_read(&uts_sem);
if (copy_to_user(name, utsname(), sizeof *name))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
}
asmlinkage long sys_sethostname(char __user *name, int len)
{
int errno;
char tmp[__NEW_UTS_LEN];
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u = utsname();
memcpy(u->nodename, tmp, len);
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
}
up_write(&uts_sem);
return errno;
}
#ifdef __ARCH_WANT_SYS_GETHOSTNAME
asmlinkage long sys_gethostname(char __user *name, int len)
{
int i, errno;
struct new_utsname *u;
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
u = utsname();
i = 1 + strlen(u->nodename);
if (i > len)
i = len;
errno = 0;
if (copy_to_user(name, u->nodename, i))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
}
#endif
/*
* Only setdomainname; getdomainname can be implemented by calling
* uname()
*/
asmlinkage long sys_setdomainname(char __user *name, int len)
{
int errno;
char tmp[__NEW_UTS_LEN];
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u = utsname();
memcpy(u->domainname, tmp, len);
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
}
up_write(&uts_sem);
return errno;
}
asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
if (resource >= RLIM_NLIMITS)
return -EINVAL;
else {
struct rlimit value;
task_lock(current->group_leader);
value = current->signal->rlim[resource];
task_unlock(current->group_leader);
return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
}
}
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
/*
* Back compatibility for getrlimit. Needed for some apps.
*/
asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit x;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
if (x.rlim_cur > 0x7FFFFFFF)
x.rlim_cur = 0x7FFFFFFF;
if (x.rlim_max > 0x7FFFFFFF)
x.rlim_max = 0x7FFFFFFF;
return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}
#endif
asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit new_rlim, *old_rlim;
int retval;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
return -EFAULT;
old_rlim = current->signal->rlim + resource;
if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (resource == RLIMIT_NOFILE) {
if (new_rlim.rlim_max == RLIM_INFINITY)
new_rlim.rlim_max = sysctl_nr_open;
if (new_rlim.rlim_cur == RLIM_INFINITY)
new_rlim.rlim_cur = sysctl_nr_open;
if (new_rlim.rlim_max > sysctl_nr_open)
return -EPERM;
}
if (new_rlim.rlim_cur > new_rlim.rlim_max)
return -EINVAL;
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
return retval;
if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
/*
* The caller is asking for an immediate RLIMIT_CPU
* expiry. But we use the zero value to mean "it was
* never set". So let's cheat and make it one second
* instead
*/
new_rlim.rlim_cur = 1;
}
task_lock(current->group_leader);
*old_rlim = new_rlim;
task_unlock(current->group_leader);
if (resource != RLIMIT_CPU)
goto out;
/*
* RLIMIT_CPU handling. Note that the kernel fails to return an error
* code if it rejected the user's attempt to set RLIMIT_CPU. This is a
* very long-standing error, and fixing it now risks breakage of
* applications, so we live with it
*/
if (new_rlim.rlim_cur == RLIM_INFINITY)
goto out;
update_rlimit_cpu(new_rlim.rlim_cur);
out:
return 0;
}
/*
* It would make sense to put struct rusage in the task_struct,
* except that would make the task_struct be *really big*. After
* task_struct gets moved into malloc'ed memory, it would
* make sense to do this. It will make moving the rest of the information
* a lot simpler! (Which we're not doing right now because we're not
* measuring them yet).
*
* When sampling multiple threads for RUSAGE_SELF, under SMP we might have
* races with threads incrementing their own counters. But since word
* reads are atomic, we either get new values or old values and we don't
* care which for the sums. We always take the siglock to protect reading
* the c* fields from p->signal from races with exit.c updating those
* fields when reaping, so a sample either gets all the additions of a
* given child after it's reaped, or none so this sample is before reaping.
*
* Locking:
* We need to take the siglock for CHILDEREN, SELF and BOTH
* for the cases current multithreaded, non-current single threaded
* non-current multithreaded. Thread traversal is now safe with
* the siglock held.
* Strictly speaking, we donot need to take the siglock if we are current and
* single threaded, as no one else can take our signal_struct away, no one
* else can reap the children to update signal->c* counters, and no one else
* can race with the signal-> fields. If we do not take any lock, the
* signal-> fields could be read out of order while another thread was just
* exiting. So we should place a read memory barrier when we avoid the lock.
* On the writer side, write memory barrier is implied in __exit_signal
* as __exit_signal releases the siglock spinlock after updating the signal->
* fields. But we don't do this yet to keep things simple.
*
*/
static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
{
r->ru_nvcsw += t->nvcsw;
r->ru_nivcsw += t->nivcsw;
r->ru_minflt += t->min_flt;
r->ru_majflt += t->maj_flt;
r->ru_inblock += task_io_get_inblock(t);
r->ru_oublock += task_io_get_oublock(t);
}
static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
struct task_struct *t;
unsigned long flags;
cputime_t utime, stime;
struct task_cputime cputime;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
if (who == RUSAGE_THREAD) {
accumulate_thread_rusage(p, r);
goto out;
}
if (!lock_task_sighand(p, &flags))
return;
switch (who) {
case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
utime = p->signal->cutime;
stime = p->signal->cstime;
r->ru_nvcsw = p->signal->cnvcsw;
r->ru_nivcsw = p->signal->cnivcsw;
r->ru_minflt = p->signal->cmin_flt;
r->ru_majflt = p->signal->cmaj_flt;
r->ru_inblock = p->signal->cinblock;
r->ru_oublock = p->signal->coublock;
if (who == RUSAGE_CHILDREN)
break;
case RUSAGE_SELF:
thread_group_cputime(p, &cputime);
utime = cputime_add(utime, cputime.utime);
stime = cputime_add(stime, cputime.stime);
r->ru_nvcsw += p->signal->nvcsw;
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
r->ru_majflt += p->signal->maj_flt;
r->ru_inblock += p->signal->inblock;
r->ru_oublock += p->signal->oublock;
t = p;
do {
accumulate_thread_rusage(t, r);
t = next_thread(t);
} while (t != p);
break;
default:
BUG();
}
unlock_task_sighand(p, &flags);
out:
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
}
int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
{
struct rusage r;
k_getrusage(p, who, &r);
return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
}
asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
{
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
who != RUSAGE_THREAD)
return -EINVAL;
return getrusage(current, who, ru);
}
asmlinkage long sys_umask(int mask)
{
mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
return mask;
}
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
struct task_struct *me = current;
unsigned char comm[sizeof(me->comm)];
long error;
error = security_task_prctl(option, arg2, arg3, arg4, arg5);
if (error != -ENOSYS)
return error;
error = 0;
switch (option) {
case PR_SET_PDEATHSIG:
if (!valid_signal(arg2)) {
error = -EINVAL;
break;
}
me->pdeath_signal = arg2;
error = 0;
break;
case PR_GET_PDEATHSIG:
error = put_user(me->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
error = get_dumpable(me->mm);
break;
case PR_SET_DUMPABLE:
if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
set_dumpable(me->mm, arg2);
error = 0;
break;
case PR_SET_UNALIGN:
error = SET_UNALIGN_CTL(me, arg2);
break;
case PR_GET_UNALIGN:
error = GET_UNALIGN_CTL(me, arg2);
break;
case PR_SET_FPEMU:
error = SET_FPEMU_CTL(me, arg2);
break;
case PR_GET_FPEMU:
error = GET_FPEMU_CTL(me, arg2);
break;
case PR_SET_FPEXC:
error = SET_FPEXC_CTL(me, arg2);
break;
case PR_GET_FPEXC:
error = GET_FPEXC_CTL(me, arg2);
break;
case PR_GET_TIMING:
error = PR_TIMING_STATISTICAL;
break;
case PR_SET_TIMING:
if (arg2 != PR_TIMING_STATISTICAL)
error = -EINVAL;
else
error = 0;
break;
case PR_SET_NAME:
comm[sizeof(me->comm)-1] = 0;
if (strncpy_from_user(comm, (char __user *)arg2,
sizeof(me->comm) - 1) < 0)
return -EFAULT;
set_task_comm(me, comm);
return 0;
case PR_GET_NAME:
get_task_comm(comm, me);
if (copy_to_user((char __user *)arg2, comm,
sizeof(comm)))
return -EFAULT;
return 0;
case PR_GET_ENDIAN:
error = GET_ENDIAN(me, arg2);
break;
case PR_SET_ENDIAN:
error = SET_ENDIAN(me, arg2);
break;
case PR_GET_SECCOMP:
error = prctl_get_seccomp();
break;
case PR_SET_SECCOMP:
error = prctl_set_seccomp(arg2);
break;
case PR_GET_TSC:
error = GET_TSC_CTL(arg2);
break;
case PR_SET_TSC:
error = SET_TSC_CTL(arg2);
break;
case PR_GET_TIMERSLACK:
error = current->timer_slack_ns;
break;
case PR_SET_TIMERSLACK:
if (arg2 <= 0)
current->timer_slack_ns =
current->default_timer_slack_ns;
else
current->timer_slack_ns = arg2;
error = 0;
break;
default:
error = -EINVAL;
break;
}
return error;
}
asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
struct getcpu_cache __user *unused)
{
int err = 0;
int cpu = raw_smp_processor_id();
if (cpup)
err |= put_user(cpu, cpup);
if (nodep)
err |= put_user(cpu_to_node(cpu), nodep);
return err ? -EFAULT : 0;
}
char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
static void argv_cleanup(char **argv, char **envp)
{
argv_free(argv);
}
/**
* orderly_poweroff - Trigger an orderly system poweroff
* @force: force poweroff if command execution fails
*
* This may be called from any context to trigger a system shutdown.
* If the orderly shutdown fails, it will force an immediate shutdown.
*/
int orderly_poweroff(bool force)
{
int argc;
char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
static char *envp[] = {
"HOME=/",
"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
NULL
};
int ret = -ENOMEM;
struct subprocess_info *info;
if (argv == NULL) {
printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
__func__, poweroff_cmd);
goto out;
}
info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
if (info == NULL) {
argv_free(argv);
goto out;
}
call_usermodehelper_setcleanup(info, argv_cleanup);
ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
out:
if (ret && force) {
printk(KERN_WARNING "Failed to start orderly shutdown: "
"forcing the issue\n");
/* I guess this should try to kick off some daemon to
sync and poweroff asap. Or not even bother syncing
if we're doing an emergency shutdown? */
emergency_sync();
kernel_power_off();
}
return ret;
}
EXPORT_SYMBOL_GPL(orderly_poweroff);