1
linux/kernel/sys.c
Frank Mayhar f06febc96b timers: fix itimer/many thread hang
Overview

This patch reworks the handling of POSIX CPU timers, including the
ITIMER_PROF, ITIMER_VIRT timers and rlimit handling.  It was put together
with the help of Roland McGrath, the owner and original writer of this code.

The problem we ran into, and the reason for this rework, has to do with using
a profiling timer in a process with a large number of threads.  It appears
that the performance of the old implementation of run_posix_cpu_timers() was
at least O(n*3) (where "n" is the number of threads in a process) or worse.
Everything is fine with an increasing number of threads until the time taken
for that routine to run becomes the same as or greater than the tick time, at
which point things degrade rather quickly.

This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF."

Code Changes

This rework corrects the implementation of run_posix_cpu_timers() to make it
run in constant time for a particular machine.  (Performance may vary between
one machine and another depending upon whether the kernel is built as single-
or multiprocessor and, in the latter case, depending upon the number of
running processors.)  To do this, at each tick we now update fields in
signal_struct as well as task_struct.  The run_posix_cpu_timers() function
uses those fields to make its decisions.

We define a new structure, "task_cputime," to contain user, system and
scheduler times and use these in appropriate places:

struct task_cputime {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};

This is included in the structure "thread_group_cputime," which is a new
substructure of signal_struct and which varies for uniprocessor versus
multiprocessor kernels.  For uniprocessor kernels, it uses "task_cputime" as
a simple substructure, while for multiprocessor kernels it is a pointer:

struct thread_group_cputime {
	struct task_cputime totals;
};

struct thread_group_cputime {
	struct task_cputime *totals;
};

We also add a new task_cputime substructure directly to signal_struct, to
cache the earliest expiration of process-wide timers, and task_cputime also
replaces the it_*_expires fields of task_struct (used for earliest expiration
of thread timers).  The "thread_group_cputime" structure contains process-wide
timers that are updated via account_user_time() and friends.  In the non-SMP
case the structure is a simple aggregator; unfortunately in the SMP case that
simplicity was not achievable due to cache-line contention between CPUs (in
one measured case performance was actually _worse_ on a 16-cpu system than
the same test on a 4-cpu system, due to this contention).  For SMP, the
thread_group_cputime counters are maintained as a per-cpu structure allocated
using alloc_percpu().  The timer functions update only the timer field in
the structure corresponding to the running CPU, obtained using per_cpu_ptr().

We define a set of inline functions in sched.h that we use to maintain the
thread_group_cputime structure and hide the differences between UP and SMP
implementations from the rest of the kernel.  The thread_group_cputime_init()
function initializes the thread_group_cputime structure for the given task.
The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the
out-of-line function thread_group_cputime_alloc_smp() to allocate and fill
in the per-cpu structures and fields.  The thread_group_cputime_free()
function, also a no-op for UP, in SMP frees the per-cpu structures.  The
thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls
thread_group_cputime_alloc() if the per-cpu structures haven't yet been
allocated.  The thread_group_cputime() function fills the task_cputime
structure it is passed with the contents of the thread_group_cputime fields;
in UP it's that simple but in SMP it must also safely check that tsk->signal
is non-NULL (if it is it just uses the appropriate fields of task_struct) and,
if so, sums the per-cpu values for each online CPU.  Finally, the three
functions account_group_user_time(), account_group_system_time() and
account_group_exec_runtime() are used by timer functions to update the
respective fields of the thread_group_cputime structure.

Non-SMP operation is trivial and will not be mentioned further.

The per-cpu structure is always allocated when a task creates its first new
thread, via a call to thread_group_cputime_clone_thread() from copy_signal().
It is freed at process exit via a call to thread_group_cputime_free() from
cleanup_signal().

All functions that formerly summed utime/stime/sum_sched_runtime values from
from all threads in the thread group now use thread_group_cputime() to
snapshot the values in the thread_group_cputime structure or the values in
the task structure itself if the per-cpu structure hasn't been allocated.

Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit.
The run_posix_cpu_timers() function has been split into a fast path and a
slow path; the former safely checks whether there are any expired thread
timers and, if not, just returns, while the slow path does the heavy lifting.
With the dedicated thread group fields, timers are no longer "rebalanced" and
the process_timer_rebalance() function and related code has gone away.  All
summing loops are gone and all code that used them now uses the
thread_group_cputime() inline.  When process-wide timers are set, the new
task_cputime structure in signal_struct is used to cache the earliest
expiration; this is checked in the fast path.

Performance

The fix appears not to add significant overhead to existing operations.  It
generally performs the same as the current code except in two cases, one in
which it performs slightly worse (Case 5 below) and one in which it performs
very significantly better (Case 2 below).  Overall it's a wash except in those
two cases.

I've since done somewhat more involved testing on a dual-core Opteron system.

Case 1: With no itimer running, for a test with 100,000 threads, the fixed
	kernel took 1428.5 seconds, 513 seconds more than the unfixed system,
	all of which was spent in the system.  There were twice as many
	voluntary context switches with the fix as without it.

Case 2: With an itimer running at .01 second ticks and 4000 threads (the most
	an unmodified kernel can handle), the fixed kernel ran the test in
	eight percent of the time (5.8 seconds as opposed to 70 seconds) and
	had better tick accuracy (.012 seconds per tick as opposed to .023
	seconds per tick).

Case 3: A 4000-thread test with an initial timer tick of .01 second and an
	interval of 10,000 seconds (i.e. a timer that ticks only once) had
	very nearly the same performance in both cases:  6.3 seconds elapsed
	for the fixed kernel versus 5.5 seconds for the unfixed kernel.

With fewer threads (eight in these tests), the Case 1 test ran in essentially
the same time on both the modified and unmodified kernels (5.2 seconds versus
5.8 seconds).  The Case 2 test ran in about the same time as well, 5.9 seconds
versus 5.4 seconds but again with much better tick accuracy, .013 seconds per
tick versus .025 seconds per tick for the unmodified kernel.

Since the fix affected the rlimit code, I also tested soft and hard CPU limits.

Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer
	running), the modified kernel was very slightly favored in that while
	it killed the process in 19.997 seconds of CPU time (5.002 seconds of
	wall time), only .003 seconds of that was system time, the rest was
	user time.  The unmodified kernel killed the process in 20.001 seconds
	of CPU (5.014 seconds of wall time) of which .016 seconds was system
	time.  Really, though, the results were too close to call.  The results
	were essentially the same with no itimer running.

Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds
	(where the hard limit would never be reached) and an itimer running,
	the modified kernel exhibited worse tick accuracy than the unmodified
	kernel: .050 seconds/tick versus .028 seconds/tick.  Otherwise,
	performance was almost indistinguishable.  With no itimer running this
	test exhibited virtually identical behavior and times in both cases.

In times past I did some limited performance testing.  those results are below.

On a four-cpu Opteron system without this fix, a sixteen-thread test executed
in 3569.991 seconds, of which user was 3568.435s and system was 1.556s.  On
the same system with the fix, user and elapsed time were about the same, but
system time dropped to 0.007 seconds.  Performance with eight, four and one
thread were comparable.  Interestingly, the timer ticks with the fix seemed
more accurate:  The sixteen-thread test with the fix received 149543 ticks
for 0.024 seconds per tick, while the same test without the fix received 58720
for 0.061 seconds per tick.  Both cases were configured for an interval of
0.01 seconds.  Again, the other tests were comparable.  Each thread in this
test computed the primes up to 25,000,000.

I also did a test with a large number of threads, 100,000 threads, which is
impossible without the fix.  In this case each thread computed the primes only
up to 10,000 (to make the runtime manageable).  System time dominated, at
1546.968 seconds out of a total 2176.906 seconds (giving a user time of
629.938s).  It received 147651 ticks for 0.015 seconds per tick, still quite
accurate.  There is obviously no comparable test without the fix.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-14 16:25:35 +02:00

1783 lines
41 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);
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) && !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;
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 = 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;
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 = 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;
}
/**
* 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)
{
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) {
set_dumpable(current->mm, suid_dumpable);
smp_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);
proc_id_connector(current, PROC_EVENT_GID);
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) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->gid = current->egid = current->sgid = current->fsgid = gid;
} else if ((gid == current->gid) || (gid == current->sgid)) {
if (old_egid != gid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->egid = current->fsgid = gid;
}
else
return -EPERM;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
static int set_user(uid_t new_ruid, int dumpclear)
{
struct user_struct *new_user;
new_user = alloc_uid(current->nsproxy->user_ns, new_ruid);
if (!new_user)
return -EAGAIN;
if (atomic_read(&new_user->processes) >=
current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
new_user != current->nsproxy->user_ns->root_user) {
free_uid(new_user);
return -EAGAIN;
}
switch_uid(new_user);
if (dumpclear) {
set_dumpable(current->mm, suid_dumpable);
smp_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) {
set_dumpable(current->mm, suid_dumpable);
smp_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);
proc_id_connector(current, PROC_EVENT_UID);
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_suid;
int retval;
retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
if (retval)
return retval;
old_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) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsuid = current->euid = uid;
current->suid = new_suid;
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
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) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->euid = euid;
}
current->fsuid = current->euid;
if (suid != (uid_t) -1)
current->suid = suid;
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
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) {
set_dumpable(current->mm, suid_dumpable);
smp_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);
proc_id_connector(current, PROC_EVENT_GID);
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) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsuid = uid;
}
key_fsuid_changed(current);
proc_id_connector(current, PROC_EVENT_UID);
security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
return old_fsuid;
}
/*
* Samma på svenska..
*/
asmlinkage long sys_setfsgid(gid_t gid)
{
int old_fsgid;
old_fsgid = current->fsgid;
if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
return old_fsgid;
if (gid == current->gid || gid == current->egid ||
gid == current->sgid || gid == current->fsgid ||
capable(CAP_SETGID)) {
if (gid != old_fsgid) {
set_dumpable(current->mm, suid_dumpable);
smp_wmb();
}
current->fsgid = gid;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
}
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);
spin_lock(&group_leader->sighand->siglock);
group_leader->signal->tty = NULL;
spin_unlock(&group_leader->sighand->siglock);
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,
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(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;
}
/* validate and set current->group_info */
int set_current_groups(struct group_info *group_info)
{
int retval;
struct group_info *old_info;
retval = security_task_setgroups(group_info);
if (retval)
return retval;
groups_sort(group_info);
get_group_info(group_info);
task_lock(current);
old_info = current->group_info;
current->group_info = group_info;
task_unlock(current);
put_group_info(old_info);
return 0;
}
EXPORT_SYMBOL(set_current_groups);
asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
int i = 0;
/*
* SMP: Nobody else can change our grouplist. Thus we are
* safe.
*/
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups_to_user(grouplist, current->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)
{
int retval = 1;
if (grp != current->fsgid)
retval = groups_search(current->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_group_p);
int in_egroup_p(gid_t grp)
{
int retval = 1;
if (grp != current->egid)
retval = groups_search(current->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)) {
memcpy(utsname()->nodename, tmp, len);
utsname()->nodename[len] = 0;
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;
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
i = 1 + strlen(utsname()->nodename);
if (i > len)
i = len;
errno = 0;
if (copy_to_user(name, utsname()->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)) {
memcpy(utsname()->domainname, tmp, len);
utsname()->domainname[len] = 0;
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;
if (new_rlim.rlim_cur > new_rlim.rlim_max)
return -EINVAL;
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 && new_rlim.rlim_max > sysctl_nr_open)
return -EPERM;
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)
{
long error = 0;
if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
return error;
switch (option) {
case PR_SET_PDEATHSIG:
if (!valid_signal(arg2)) {
error = -EINVAL;
break;
}
current->pdeath_signal = arg2;
break;
case PR_GET_PDEATHSIG:
error = put_user(current->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
error = get_dumpable(current->mm);
break;
case PR_SET_DUMPABLE:
if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
set_dumpable(current->mm, arg2);
break;
case PR_SET_UNALIGN:
error = SET_UNALIGN_CTL(current, arg2);
break;
case PR_GET_UNALIGN:
error = GET_UNALIGN_CTL(current, arg2);
break;
case PR_SET_FPEMU:
error = SET_FPEMU_CTL(current, arg2);
break;
case PR_GET_FPEMU:
error = GET_FPEMU_CTL(current, arg2);
break;
case PR_SET_FPEXC:
error = SET_FPEXC_CTL(current, arg2);
break;
case PR_GET_FPEXC:
error = GET_FPEXC_CTL(current, arg2);
break;
case PR_GET_TIMING:
error = PR_TIMING_STATISTICAL;
break;
case PR_SET_TIMING:
if (arg2 != PR_TIMING_STATISTICAL)
error = -EINVAL;
break;
case PR_SET_NAME: {
struct task_struct *me = current;
unsigned char ncomm[sizeof(me->comm)];
ncomm[sizeof(me->comm)-1] = 0;
if (strncpy_from_user(ncomm, (char __user *)arg2,
sizeof(me->comm)-1) < 0)
return -EFAULT;
set_task_comm(me, ncomm);
return 0;
}
case PR_GET_NAME: {
struct task_struct *me = current;
unsigned char tcomm[sizeof(me->comm)];
get_task_comm(tcomm, me);
if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
return -EFAULT;
return 0;
}
case PR_GET_ENDIAN:
error = GET_ENDIAN(current, arg2);
break;
case PR_SET_ENDIAN:
error = SET_ENDIAN(current, 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;
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);