Release 4.15 kernel/sys.c
// SPDX-License-Identifier: GPL-2.0
/*
* linux/kernel/sys.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/kmod.h>
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.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/personality.h>
#include <linux/ptrace.h>
#include <linux/fs_struct.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/gfp.h>
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>
#include <linux/binfmts.h>
#include <linux/sched.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/stat.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
#include <linux/rcupdate.h>
#include <linux/uidgid.h>
#include <linux/cred.h>
#include <linux/kmsg_dump.h>
/* Move somewhere else to avoid recompiling? */
#include <generated/utsrelease.h>
#include <linux/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
#ifndef MPX_ENABLE_MANAGEMENT
# define MPX_ENABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef MPX_DISABLE_MANAGEMENT
# define MPX_DISABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef GET_FP_MODE
# define GET_FP_MODE(a) (-EINVAL)
#endif
#ifndef SET_FP_MODE
# define SET_FP_MODE(a,b) (-EINVAL)
#endif
#ifndef SVE_SET_VL
# define SVE_SET_VL(a) (-EINVAL)
#endif
#ifndef SVE_GET_VL
# define SVE_GET_VL() (-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;
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
/*
* the same as above, but for filesystems which can only store a 16-bit
* UID and GID. as such, this is needed on all architectures
*/
int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
/*
* Returns true if current's euid is same as p's uid or euid,
* or has CAP_SYS_NICE to p's user_ns.
*
* Called with rcu_read_lock, creds are safe
*/
static bool set_one_prio_perm(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
if (uid_eq(pcred->uid, cred->euid) ||
uid_eq(pcred->euid, cred->euid))
return true;
if (ns_capable(pcred->user_ns, CAP_SYS_NICE))
return true;
return false;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Serge E. Hallyn | 23 | 31.94% | 1 | 12.50% |
| David Howells | 20 | 27.78% | 2 | 25.00% |
| Linus Torvalds (pre-git) | 12 | 16.67% | 2 | 25.00% |
| Ingo Molnar | 9 | 12.50% | 2 | 25.00% |
| Eric W. Biedermann | 8 | 11.11% | 1 | 12.50% |
| Total | 72 | 100.00% | 8 | 100.00% |
/*
* 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)
{
int no_nice;
if (!set_one_prio_perm(p)) {
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Stephen D. Smalley | 38 | 34.55% | 1 | 16.67% |
| Ingo Molnar | 31 | 28.18% | 1 | 16.67% |
| Serge E. Hallyn | 27 | 24.55% | 1 | 16.67% |
| Linus Torvalds (pre-git) | 10 | 9.09% | 2 | 33.33% |
| Matt Mackall | 4 | 3.64% | 1 | 16.67% |
| Total | 110 | 100.00% | 6 | 100.00% |
SYSCALL_DEFINE3(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;
kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
goto out;
/* normalize: avoid signed division (rounding problems) */
error = -ESRCH;
if (niceval < MIN_NICE)
niceval = MIN_NICE;
if (niceval > MAX_NICE)
niceval = MAX_NICE;
rcu_read_lock();
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:
uid = make_kuid(cred->user_ns, who);
user = cred->user;
if (!who)
uid = cred->uid;
else if (!uid_eq(uid, cred->uid)) {
user = find_user(uid);
if (!user)
goto out_unlock; /* No processes for this user */
}
do_each_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p))
error = set_one_prio(p, niceval, error);
} while_each_thread(g, p);
if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
rcu_read_unlock();
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.
*/
SYSCALL_DEFINE2(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;
kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
return -EINVAL;
rcu_read_lock();
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p) {
niceval = nice_to_rlimit(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 = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
user = cred->user;
if (!who)
uid = cred->uid;
else if (!uid_eq(uid, cred->uid)) {
user = find_user(uid);
if (!user)
goto out_unlock; /* No processes for this user */
}
do_each_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) {
niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
} while_each_thread(g, p);
if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
rcu_read_unlock();
return retval;
}
/*
* 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).
*/
#ifdef CONFIG_MULTIUSER
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kgid_t krgid, kegid;
krgid = make_kgid(ns, rgid);
kegid = make_kgid(ns, egid);
if ((rgid != (gid_t) -1) && !gid_valid(krgid))
return -EINVAL;
if ((egid != (gid_t) -1) && !gid_valid(kegid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (rgid != (gid_t) -1) {
if (gid_eq(old->gid, krgid) ||
gid_eq(old->egid, krgid) ||
ns_capable(old->user_ns, CAP_SETGID))
new->gid = krgid;
else
goto error;
}
if (egid != (gid_t) -1) {
if (gid_eq(old->gid, kegid) ||
gid_eq(old->egid, kegid) ||
gid_eq(old->sgid, kegid) ||
ns_capable(old->user_ns, CAP_SETGID))
new->egid = kegid;
else
goto error;
}
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && !gid_eq(kegid, 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.
*/
SYSCALL_DEFINE1(setgid, gid_t, gid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kgid_t kgid;
kgid = make_kgid(ns, gid);
if (!gid_valid(kgid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (ns_capable(old->user_ns, CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = kgid;
else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
new->egid = new->fsgid = kgid;
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(new->uid);
if (!new_user)
return -EAGAIN;
/*
* We don't fail in case of NPROC limit excess here because too many
* poorly written programs don't check set*uid() return code, assuming
* it never fails if called by root. We may still enforce NPROC limit
* for programs doing set*uid()+execve() by harmlessly deferring the
* failure to the execve() stage.
*/
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
new_user != INIT_USER)
current->flags |= PF_NPROC_EXCEEDED;
else
current->flags &= ~PF_NPROC_EXCEEDED;
free_uid(new->user);
new->user = new_user;
return 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 33 | 39.29% | 1 | 12.50% |
| Andrew Morton | 16 | 19.05% | 1 | 12.50% |
| Vasiliy Kulikov | 14 | 16.67% | 1 | 12.50% |
| David Howells | 13 | 15.48% | 1 | 12.50% |
| Jiri Slaby | 3 | 3.57% | 1 | 12.50% |
| Linus Torvalds | 2 | 2.38% | 1 | 12.50% |
| Hidehiro Kawai | 2 | 2.38% | 1 | 12.50% |
| Serge E. Hallyn | 1 | 1.19% | 1 | 12.50% |
| Total | 84 | 100.00% | 8 | 100.00% |
/*
* 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.
*/
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kruid, keuid;
kruid = make_kuid(ns, ruid);
keuid = make_kuid(ns, euid);
if ((ruid != (uid_t) -1) && !uid_valid(kruid))
return -EINVAL;
if ((euid != (uid_t) -1) && !uid_valid(keuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (ruid != (uid_t) -1) {
new->uid = kruid;
if (!uid_eq(old->uid, kruid) &&
!uid_eq(old->euid, kruid) &&
!ns_capable(old->user_ns, CAP_SETUID))
goto error;
}
if (euid != (uid_t) -1) {
new->euid = keuid;
if (!uid_eq(old->uid, keuid) &&
!uid_eq(old->euid, keuid) &&
!uid_eq(old->suid, keuid) &&
!ns_capable(old->user_ns, CAP_SETUID))
goto error;
}
if (!uid_eq(new->uid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && !uid_eq(keuid, 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.
*/
SYSCALL_DEFINE1(setuid, uid_t, uid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kuid;
kuid = make_kuid(ns, uid);
if (!uid_valid(kuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (ns_capable(old->user_ns, CAP_SETUID)) {
new->suid = new->uid = kuid;
if (!uid_eq(kuid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
goto error;
}
new->fsuid = new->euid = kuid;
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().
*/
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kruid, keuid, ksuid;
kruid = make_kuid(ns, ruid);
keuid = make_kuid(ns, euid);
ksuid = make_kuid(ns, suid);
if ((ruid != (uid_t) -1) && !uid_valid(kruid))
return -EINVAL;
if ((euid != (uid_t) -1) && !uid_valid(keuid))
return -EINVAL;
if ((suid != (uid_t) -1) && !uid_valid(ksuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (!ns_capable(old->user_ns, CAP_SETUID)) {
if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) &&
!uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
goto error;
if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) &&
!uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
goto error;
if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) &&
!uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
goto error;
}
if (ruid != (uid_t) -1) {
new->uid = kruid;
if (!uid_eq(kruid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
}
if (euid != (uid_t) -1)
new->euid = keuid;
if