aboutsummaryrefslogtreecommitdiff
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c1378
1 files changed, 874 insertions, 504 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index 7f5a0cd296a..66a751ebf9d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -4,19 +4,18 @@
* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
-#include <linux/notifier.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/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.h>
#include <linux/device.h>
@@ -36,12 +35,27 @@
#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/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 <asm/uaccess.h>
#include <asm/io.h>
@@ -86,10 +100,8 @@
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
@@ -103,18 +115,22 @@ 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.
+ * 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);
-void (*pm_power_off_prepare)(void);
+ 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;
+}
/*
* set the priority of a task
@@ -122,11 +138,9 @@ void (*pm_power_off_prepare)(void);
*/
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)) {
+ if (!set_one_prio_perm(p)) {
error = -EPERM;
goto out;
}
@@ -153,16 +167,17 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
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 < -20)
- niceval = -20;
- if (niceval > 19)
- niceval = 19;
+ if (niceval < MIN_NICE)
+ niceval = MIN_NICE;
+ if (niceval > MAX_NICE)
+ niceval = MAX_NICE;
rcu_read_lock();
read_lock(&tasklist_lock);
@@ -185,18 +200,19 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = (struct user_struct *) cred->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->user;
if (!who)
- who = cred->uid;
- else if ((who != cred->uid) &&
- !(user = find_user(who)))
+ uid = cred->uid;
+ else if (!uid_eq(uid, cred->uid) &&
+ !(user = find_user(uid)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p) {
- if (__task_cred(p)->uid == who)
+ if (uid_eq(task_uid(p), uid))
error = set_one_prio(p, niceval, error);
} while_each_thread(g, p);
- if (who != cred->uid)
+ if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
@@ -220,6 +236,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
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;
@@ -233,7 +250,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
else
p = current;
if (p) {
- niceval = 20 - task_nice(p);
+ niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
@@ -244,27 +261,28 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
- niceval = 20 - task_nice(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:
- user = (struct user_struct *) cred->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->user;
if (!who)
- who = cred->uid;
- else if ((who != cred->uid) &&
- !(user = find_user(who)))
+ uid = cred->uid;
+ else if (!uid_eq(uid, cred->uid) &&
+ !(user = find_user(uid)))
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 (uid_eq(task_uid(p), uid)) {
+ niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
} while_each_thread(g, p);
- if (who != cred->uid)
+ if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
@@ -275,194 +293,6 @@ out_unlock:
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);
-
-static DEFINE_MUTEX(reboot_mutex);
-
-/*
- * 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.
- */
-SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
- void __user *, arg)
-{
- char buffer[256];
- int ret = 0;
-
- /* 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;
-
- mutex_lock(&reboot_mutex);
- 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();
- do_exit(0);
- panic("cannot halt");
-
- case LINUX_REBOOT_CMD_POWER_OFF:
- kernel_power_off();
- do_exit(0);
- break;
-
- case LINUX_REBOOT_CMD_RESTART2:
- if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
- ret = -EFAULT;
- break;
- }
- buffer[sizeof(buffer) - 1] = '\0';
-
- kernel_restart(buffer);
- break;
-
-#ifdef CONFIG_KEXEC
- case LINUX_REBOOT_CMD_KEXEC:
- ret = kernel_kexec();
- break;
-#endif
-
-#ifdef CONFIG_HIBERNATION
- case LINUX_REBOOT_CMD_SW_SUSPEND:
- ret = hibernate();
- break;
-#endif
-
- default:
- ret = -EINVAL;
- break;
- }
- mutex_unlock(&reboot_mutex);
- return ret;
-}
-
-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)
@@ -483,9 +313,19 @@ void ctrl_alt_del(void)
*/
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)
@@ -494,25 +334,25 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
retval = -EPERM;
if (rgid != (gid_t) -1) {
- if (old->gid == rgid ||
- old->egid == rgid ||
- capable(CAP_SETGID))
- new->gid = rgid;
+ 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 (old->gid == egid ||
- old->egid == egid ||
- old->sgid == egid ||
- capable(CAP_SETGID))
- new->egid = egid;
+ 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 && egid != old->gid))
+ (egid != (gid_t) -1 && !gid_eq(kegid, old->gid)))
new->sgid = new->egid;
new->fsgid = new->egid;
@@ -530,9 +370,15 @@ error:
*/
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)
@@ -540,10 +386,10 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
old = current_cred();
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;
+ 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;
@@ -561,15 +407,22 @@ static int set_user(struct cred *new)
{
struct user_struct *new_user;
- new_user = alloc_uid(current_user_ns(), new->uid);
+ 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) {
- free_uid(new_user);
- return -EAGAIN;
- }
+ new_user != INIT_USER)
+ current->flags |= PF_NPROC_EXCEEDED;
+ else
+ current->flags &= ~PF_NPROC_EXCEEDED;
free_uid(new->user);
new->user = new_user;
@@ -593,9 +446,19 @@ static int set_user(struct cred *new)
*/
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)
@@ -604,29 +467,29 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
retval = -EPERM;
if (ruid != (uid_t) -1) {
- new->uid = ruid;
- if (old->uid != ruid &&
- old->euid != ruid &&
- !capable(CAP_SETUID))
+ 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 = euid;
- if (old->uid != euid &&
- old->euid != euid &&
- old->suid != euid &&
- !capable(CAP_SETUID))
+ 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 (new->uid != old->uid) {
+ 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 && euid != old->uid))
+ (euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
new->suid = new->euid;
new->fsuid = new->euid;
@@ -654,9 +517,15 @@ error:
*/
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)
@@ -664,18 +533,18 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
old = current_cred();
retval = -EPERM;
- if (capable(CAP_SETUID)) {
- new->suid = new->uid = uid;
- if (uid != old->uid) {
+ 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 != old->uid && uid != new->suid) {
+ } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
goto error;
}
- new->fsuid = new->euid = uid;
+ new->fsuid = new->euid = kuid;
retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
if (retval < 0)
@@ -695,9 +564,24 @@ error:
*/
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)
@@ -706,30 +590,30 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
old = current_cred();
retval = -EPERM;
- if (!capable(CAP_SETUID)) {
- if (ruid != (uid_t) -1 && ruid != old->uid &&
- ruid != old->euid && ruid != old->suid)
+ 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 && euid != old->uid &&
- euid != old->euid && euid != old->suid)
+ 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 && suid != old->uid &&
- suid != old->euid && suid != old->suid)
+ 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 = ruid;
- if (ruid != old->uid) {
+ 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 = euid;
+ new->euid = keuid;
if (suid != (uid_t) -1)
- new->suid = suid;
+ new->suid = ksuid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
@@ -743,14 +627,19 @@ error:
return retval;
}
-SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
{
const struct cred *cred = current_cred();
int retval;
+ uid_t ruid, euid, suid;
+
+ ruid = from_kuid_munged(cred->user_ns, cred->uid);
+ euid = from_kuid_munged(cred->user_ns, cred->euid);
+ suid = from_kuid_munged(cred->user_ns, cred->suid);
- if (!(retval = put_user(cred->uid, ruid)) &&
- !(retval = put_user(cred->euid, euid)))
- retval = put_user(cred->suid, suid);
+ if (!(retval = put_user(ruid, ruidp)) &&
+ !(retval = put_user(euid, euidp)))
+ retval = put_user(suid, suidp);
return retval;
}
@@ -760,9 +649,22 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u
*/
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kgid_t krgid, kegid, ksgid;
+
+ krgid = make_kgid(ns, rgid);
+ kegid = make_kgid(ns, egid);
+ ksgid = make_kgid(ns, sgid);
+
+ if ((rgid != (gid_t) -1) && !gid_valid(krgid))
+ return -EINVAL;
+ if ((egid != (gid_t) -1) && !gid_valid(kegid))
+ return -EINVAL;
+ if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -770,24 +672,24 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
old = current_cred();
retval = -EPERM;
- if (!capable(CAP_SETGID)) {
- if (rgid != (gid_t) -1 && rgid != old->gid &&
- rgid != old->egid && rgid != old->sgid)
+ if (!ns_capable(old->user_ns, CAP_SETGID)) {
+ if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) &&
+ !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
goto error;
- if (egid != (gid_t) -1 && egid != old->gid &&
- egid != old->egid && egid != old->sgid)
+ if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) &&
+ !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
goto error;
- if (sgid != (gid_t) -1 && sgid != old->gid &&
- sgid != old->egid && sgid != old->sgid)
+ if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) &&
+ !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
goto error;
}
if (rgid != (gid_t) -1)
- new->gid = rgid;
+ new->gid = krgid;
if (egid != (gid_t) -1)
- new->egid = egid;
+ new->egid = kegid;
if (sgid != (gid_t) -1)
- new->sgid = sgid;
+ new->sgid = ksgid;
new->fsgid = new->egid;
return commit_creds(new);
@@ -797,14 +699,19 @@ error:
return retval;
}
-SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
{
const struct cred *cred = current_cred();
int retval;
+ gid_t rgid, egid, sgid;
- if (!(retval = put_user(cred->gid, rgid)) &&
- !(retval = put_user(cred->egid, egid)))
- retval = put_user(cred->sgid, sgid);
+ rgid = from_kgid_munged(cred->user_ns, cred->gid);
+ egid = from_kgid_munged(cred->user_ns, cred->egid);
+ sgid = from_kgid_munged(cred->user_ns, cred->sgid);
+
+ if (!(retval = put_user(rgid, rgidp)) &&
+ !(retval = put_user(egid, egidp)))
+ retval = put_user(sgid, sgidp);
return retval;
}
@@ -821,18 +728,24 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
const struct cred *old;
struct cred *new;
uid_t old_fsuid;
+ kuid_t kuid;
+
+ old = current_cred();
+ old_fsuid = from_kuid_munged(old->user_ns, old->fsuid);
+
+ kuid = make_kuid(old->user_ns, uid);
+ if (!uid_valid(kuid))
+ return old_fsuid;
new = prepare_creds();
if (!new)
- return current_fsuid();
- old = current_cred();
- old_fsuid = old->fsuid;
+ return old_fsuid;
- if (uid == old->uid || uid == old->euid ||
- uid == old->suid || uid == old->fsuid ||
- capable(CAP_SETUID)) {
- if (uid != old_fsuid) {
- new->fsuid = uid;
+ if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) ||
+ uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
+ ns_capable(old->user_ns, CAP_SETUID)) {
+ if (!uid_eq(kuid, old->fsuid)) {
+ new->fsuid = kuid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
goto change_okay;
}
@@ -854,18 +767,24 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
const struct cred *old;
struct cred *new;
gid_t old_fsgid;
+ kgid_t kgid;
+
+ old = current_cred();
+ old_fsgid = from_kgid_munged(old->user_ns, old->fsgid);
+
+ kgid = make_kgid(old->user_ns, gid);
+ if (!gid_valid(kgid))
+ return old_fsgid;
new = prepare_creds();
if (!new)
- return current_fsgid();
- old = current_cred();
- old_fsgid = old->fsgid;
+ return old_fsgid;
- if (gid == old->gid || gid == old->egid ||
- gid == old->sgid || gid == old->fsgid ||
- capable(CAP_SETGID)) {
- if (gid != old_fsgid) {
- new->fsgid = gid;
+ if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) ||
+ gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
+ ns_capable(old->user_ns, CAP_SETGID)) {
+ if (!gid_eq(kgid, old->fsgid)) {
+ new->fsgid = kgid;
goto change_okay;
}
}
@@ -878,12 +797,73 @@ change_okay:
return old_fsgid;
}
+/**
+ * sys_getpid - return the thread group id of the current process
+ *
+ * Note, despite the name, this returns the tgid not the pid. The tgid and
+ * the pid are identical unless CLONE_THREAD was specified on clone() in
+ * which case the tgid is the same in all threads of the same group.
+ *
+ * This is SMP safe as current->tgid does not change.
+ */
+SYSCALL_DEFINE0(getpid)
+{
+ return task_tgid_vnr(current);
+}
+
+/* Thread ID - the internal kernel "pid" */
+SYSCALL_DEFINE0(gettid)
+{
+ return task_pid_vnr(current);
+}
+
+/*
+ * Accessing ->real_parent is not SMP-safe, it could
+ * change from under us. However, we can use a stale
+ * value of ->real_parent under rcu_read_lock(), see
+ * release_task()->call_rcu(delayed_put_task_struct).
+ */
+SYSCALL_DEFINE0(getppid)
+{
+ int pid;
+
+ rcu_read_lock();
+ pid = task_tgid_vnr(rcu_dereference(current->real_parent));
+ rcu_read_unlock();
+
+ return pid;
+}
+
+SYSCALL_DEFINE0(getuid)
+{
+ /* Only we change this so SMP safe */
+ return from_kuid_munged(current_user_ns(), current_uid());
+}
+
+SYSCALL_DEFINE0(geteuid)
+{
+ /* Only we change this so SMP safe */
+ return from_kuid_munged(current_user_ns(), current_euid());
+}
+
+SYSCALL_DEFINE0(getgid)
+{
+ /* Only we change this so SMP safe */
+ return from_kgid_munged(current_user_ns(), current_gid());
+}
+
+SYSCALL_DEFINE0(getegid)
+{
+ /* Only we change this so SMP safe */
+ return from_kgid_munged(current_user_ns(), current_egid());
+}
+
void do_sys_times(struct tms *tms)
{
cputime_t tgutime, tgstime, cutime, cstime;
spin_lock_irq(&current->sighand->siglock);
- thread_group_times(current, &tgutime, &tgstime);
+ thread_group_cputime_adjusted(current, &tgutime, &tgstime);
cutime = current->signal->cutime;
cstime = current->signal->cstime;
spin_unlock_irq(&current->sighand->siglock);
@@ -915,8 +895,7 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
* 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
+ * !PF_FORKNOEXEC check to conform completely to POSIX.
*/
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
{
@@ -952,7 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
- if (p->did_exec)
+ if (!(p->flags & PF_FORKNOEXEC))
goto out;
} else {
err = -ESRCH;
@@ -1054,6 +1033,17 @@ out:
return retval;
}
+static void set_special_pids(struct pid *pid)
+{
+ struct task_struct *curr = current->group_leader;
+
+ if (task_session(curr) != pid)
+ change_pid(curr, PIDTYPE_SID, pid);
+
+ if (task_pgrp(curr) != pid)
+ change_pid(curr, PIDTYPE_PGID, pid);
+}
+
SYSCALL_DEFINE0(setsid)
{
struct task_struct *group_leader = current->group_leader;
@@ -1073,15 +1063,17 @@ SYSCALL_DEFINE0(setsid)
goto out;
group_leader->signal->leader = 1;
- __set_special_pids(sid);
+ set_special_pids(sid);
proc_clear_tty(group_leader);
err = session;
out:
write_unlock_irq(&tasklist_lock);
- if (err > 0)
+ if (err > 0) {
proc_sid_connector(group_leader);
+ sched_autogroup_create_attach(group_leader);
+ }
return err;
}
@@ -1096,6 +1088,36 @@ DECLARE_RWSEM(uts_sem);
#define override_architecture(name) 0
#endif
+/*
+ * Work around broken programs that cannot handle "Linux 3.0".
+ * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ */
+static int override_release(char __user *release, size_t len)
+{
+ int ret = 0;
+
+ if (current->personality & UNAME26) {
+ const char *rest = UTS_RELEASE;
+ char buf[65] = { 0 };
+ int ndots = 0;
+ unsigned v;
+ size_t copy;
+
+ while (*rest) {
+ if (*rest == '.' && ++ndots >= 3)
+ break;
+ if (!isdigit(*rest) && *rest != '.')
+ break;
+ rest++;
+ }
+ v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+ copy = clamp_t(size_t, len, 1, sizeof(buf));
+ copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
+ ret = copy_to_user(release, buf, copy + 1);
+ }
+ return ret;
+}
+
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
{
int errno = 0;
@@ -1105,6 +1127,8 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
errno = -EFAULT;
up_read(&uts_sem);
+ if (!errno && override_release(name->release, sizeof(name->release)))
+ errno = -EFAULT;
if (!errno && override_architecture(name))
errno = -EFAULT;
return errno;
@@ -1126,6 +1150,8 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
error = -EFAULT;
up_read(&uts_sem);
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
if (!error && override_architecture(name))
error = -EFAULT;
return error;
@@ -1160,6 +1186,8 @@ SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
if (!error && override_architecture(name))
error = -EFAULT;
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
return error ? -EFAULT : 0;
}
#endif
@@ -1169,8 +1197,9 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
+
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
@@ -1181,6 +1210,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
memcpy(u->nodename, tmp, len);
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
+ uts_proc_notify(UTS_PROC_HOSTNAME);
}
up_write(&uts_sem);
return errno;
@@ -1218,7 +1248,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
@@ -1231,6 +1261,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
memcpy(u->domainname, tmp, len);
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
+ uts_proc_notify(UTS_PROC_DOMAINNAME);
}
up_write(&uts_sem);
return errno;
@@ -1333,6 +1364,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource,
rlim = tsk->signal->rlim + resource;
task_lock(tsk->group_leader);
if (new_rlim) {
+ /* Keep the capable check against init_user_ns until
+ cgroups can contain all limits */
if (new_rlim->rlim_max > rlim->rlim_max &&
!capable(CAP_SYS_RESOURCE))
retval = -EPERM;
@@ -1376,18 +1409,21 @@ static int check_prlimit_permission(struct task_struct *task)
{
const struct cred *cred = current_cred(), *tcred;
- tcred = __task_cred(task);
- if ((cred->uid != tcred->euid ||
- cred->uid != tcred->suid ||
- cred->uid != tcred->uid ||
- cred->gid != tcred->egid ||
- cred->gid != tcred->sgid ||
- cred->gid != tcred->gid) &&
- !capable(CAP_SYS_RESOURCE)) {
- return -EPERM;
- }
+ if (current == task)
+ return 0;
- return 0;
+ tcred = __task_cred(task);
+ if (uid_eq(cred->uid, tcred->euid) &&
+ uid_eq(cred->uid, tcred->suid) &&
+ uid_eq(cred->uid, tcred->uid) &&
+ gid_eq(cred->gid, tcred->egid) &&
+ gid_eq(cred->gid, tcred->sgid) &&
+ gid_eq(cred->gid, tcred->gid))
+ return 0;
+ if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
+ return 0;
+
+ return -EPERM;
}
SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
@@ -1492,10 +1528,10 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
- utime = stime = cputime_zero;
+ utime = stime = 0;
if (who == RUSAGE_THREAD) {
- task_times(current, &utime, &stime);
+ task_cputime_adjusted(current, &utime, &stime);
accumulate_thread_rusage(p, r);
maxrss = p->signal->maxrss;
goto out;
@@ -1521,9 +1557,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
break;
case RUSAGE_SELF:
- thread_group_times(p, &tgutime, &tgstime);
- utime = cputime_add(utime, tgutime);
- stime = cputime_add(stime, tgstime);
+ thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+ utime += tgutime;
+ stime += tgstime;
r->ru_nvcsw += p->signal->nvcsw;
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
@@ -1535,8 +1571,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
t = p;
do {
accumulate_thread_rusage(t, r);
- t = next_thread(t);
- } while (t != p);
+ } while_each_thread(p, t);
break;
default:
@@ -1573,12 +1608,231 @@ SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
return getrusage(current, who, ru);
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru)
+{
+ struct rusage r;
+
+ if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
+ who != RUSAGE_THREAD)
+ return -EINVAL;
+
+ k_getrusage(current, who, &r);
+ return put_compat_rusage(&r, ru);
+}
+#endif
+
SYSCALL_DEFINE1(umask, int, mask)
{
mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
return mask;
}
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
+{
+ struct fd exe;
+ struct inode *inode;
+ int err;
+
+ exe = fdget(fd);
+ if (!exe.file)
+ return -EBADF;
+
+ inode = file_inode(exe.file);
+
+ /*
+ * Because the original mm->exe_file points to executable file, make
+ * sure that this one is executable as well, to avoid breaking an
+ * overall picture.
+ */
+ err = -EACCES;
+ if (!S_ISREG(inode->i_mode) ||
+ exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+ goto exit;
+
+ err = inode_permission(inode, MAY_EXEC);
+ if (err)
+ goto exit;
+
+ down_write(&mm->mmap_sem);
+
+ /*
+ * Forbid mm->exe_file change if old file still mapped.
+ */
+ err = -EBUSY;
+ if (mm->exe_file) {
+ struct vm_area_struct *vma;
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next)
+ if (vma->vm_file &&
+ path_equal(&vma->vm_file->f_path,
+ &mm->exe_file->f_path))
+ goto exit_unlock;
+ }
+
+ /*
+ * The symlink can be changed only once, just to disallow arbitrary
+ * transitions malicious software might bring in. This means one
+ * could make a snapshot over all processes running and monitor
+ * /proc/pid/exe changes to notice unusual activity if needed.
+ */
+ err = -EPERM;
+ if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+ goto exit_unlock;
+
+ err = 0;
+ set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */
+exit_unlock:
+ up_write(&mm->mmap_sem);
+
+exit:
+ fdput(exe);
+ return err;
+}
+
+static int prctl_set_mm(int opt, unsigned long addr,
+ unsigned long arg4, unsigned long arg5)
+{
+ unsigned long rlim = rlimit(RLIMIT_DATA);
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int error;
+
+ if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (opt == PR_SET_MM_EXE_FILE)
+ return prctl_set_mm_exe_file(mm, (unsigned int)addr);
+
+ if (addr >= TASK_SIZE || addr < mmap_min_addr)
+ return -EINVAL;
+
+ error = -EINVAL;
+
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+
+ switch (opt) {
+ case PR_SET_MM_START_CODE:
+ mm->start_code = addr;
+ break;
+ case PR_SET_MM_END_CODE:
+ mm->end_code = addr;
+ break;
+ case PR_SET_MM_START_DATA:
+ mm->start_data = addr;
+ break;
+ case PR_SET_MM_END_DATA:
+ mm->end_data = addr;
+ break;
+
+ case PR_SET_MM_START_BRK:
+ if (addr <= mm->end_data)
+ goto out;
+
+ if (rlim < RLIM_INFINITY &&
+ (mm->brk - addr) +
+ (mm->end_data - mm->start_data) > rlim)
+ goto out;
+
+ mm->start_brk = addr;
+ break;
+
+ case PR_SET_MM_BRK:
+ if (addr <= mm->end_data)
+ goto out;
+
+ if (rlim < RLIM_INFINITY &&
+ (addr - mm->start_brk) +
+ (mm->end_data - mm->start_data) > rlim)
+ goto out;
+
+ mm->brk = addr;
+ break;
+
+ /*
+ * If command line arguments and environment
+ * are placed somewhere else on stack, we can
+ * set them up here, ARG_START/END to setup
+ * command line argumets and ENV_START/END
+ * for environment.
+ */
+ case PR_SET_MM_START_STACK:
+ case PR_SET_MM_ARG_START:
+ case PR_SET_MM_ARG_END:
+ case PR_SET_MM_ENV_START:
+ case PR_SET_MM_ENV_END:
+ if (!vma) {
+ error = -EFAULT;
+ goto out;
+ }
+ if (opt == PR_SET_MM_START_STACK)
+ mm->start_stack = addr;
+ else if (opt == PR_SET_MM_ARG_START)
+ mm->arg_start = addr;
+ else if (opt == PR_SET_MM_ARG_END)
+ mm->arg_end = addr;
+ else if (opt == PR_SET_MM_ENV_START)
+ mm->env_start = addr;
+ else if (opt == PR_SET_MM_ENV_END)
+ mm->env_end = addr;
+ break;
+
+ /*
+ * This doesn't move auxiliary vector itself
+ * since it's pinned to mm_struct, but allow
+ * to fill vector with new values. It's up
+ * to a caller to provide sane values here
+ * otherwise user space tools which use this
+ * vector might be unhappy.
+ */
+ case PR_SET_MM_AUXV: {
+ unsigned long user_auxv[AT_VECTOR_SIZE];
+
+ if (arg4 > sizeof(user_auxv))
+ goto out;
+ up_read(&mm->mmap_sem);
+
+ if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
+ return -EFAULT;
+
+ /* Make sure the last entry is always AT_NULL */
+ user_auxv[AT_VECTOR_SIZE - 2] = 0;
+ user_auxv[AT_VECTOR_SIZE - 1] = 0;
+
+ BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+
+ task_lock(current);
+ memcpy(mm->saved_auxv, user_auxv, arg4);
+ task_unlock(current);
+
+ return 0;
+ }
+ default:
+ goto out;
+ }
+
+ error = 0;
+out:
+ up_read(&mm->mmap_sem);
+ return error;
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return put_user(me->clear_child_tid, tid_addr);
+}
+#else
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return -EINVAL;
+}
+#endif
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -1592,144 +1846,174 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
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);
+ case PR_SET_PDEATHSIG:
+ if (!valid_signal(arg2)) {
+ error = -EINVAL;
break;
- case PR_SET_ENDIAN:
- error = SET_ENDIAN(me, arg2);
+ }
+ me->pdeath_signal = arg2;
+ 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 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) {
+ error = -EINVAL;
break;
+ }
+ set_dumpable(me->mm, 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_TASK_PERF_EVENTS_DISABLE:
- error = perf_event_task_disable();
- break;
- case PR_TASK_PERF_EVENTS_ENABLE:
- error = perf_event_task_enable();
- break;
- case PR_GET_TIMERSLACK:
- error = current->timer_slack_ns;
- break;
- case PR_SET_TIMERSLACK:
- if (arg2 <= 0)
- current->timer_slack_ns =
+ 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;
+ 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);
+ proc_comm_connector(me);
+ break;
+ case PR_GET_NAME:
+ get_task_comm(comm, me);
+ if (copy_to_user((char __user *)arg2, comm, sizeof(comm)))
+ return -EFAULT;
+ break;
+ 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, (char __user *)arg3);
+ break;
+ case PR_GET_TSC:
+ error = GET_TSC_CTL(arg2);
+ break;
+ case PR_SET_TSC:
+ error = SET_TSC_CTL(arg2);
+ break;
+ case PR_TASK_PERF_EVENTS_DISABLE:
+ error = perf_event_task_disable();
+ break;
+ case PR_TASK_PERF_EVENTS_ENABLE:
+ error = perf_event_task_enable();
+ 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;
- case PR_MCE_KILL:
- if (arg4 | arg5)
- return -EINVAL;
- switch (arg2) {
- case PR_MCE_KILL_CLEAR:
- if (arg3 != 0)
- return -EINVAL;
- current->flags &= ~PF_MCE_PROCESS;
- break;
- case PR_MCE_KILL_SET:
- current->flags |= PF_MCE_PROCESS;
- if (arg3 == PR_MCE_KILL_EARLY)
- current->flags |= PF_MCE_EARLY;
- else if (arg3 == PR_MCE_KILL_LATE)
- current->flags &= ~PF_MCE_EARLY;
- else if (arg3 == PR_MCE_KILL_DEFAULT)
- current->flags &=
- ~(PF_MCE_EARLY|PF_MCE_PROCESS);
- else
- return -EINVAL;
- break;
- default:
+ else
+ current->timer_slack_ns = arg2;
+ break;
+ case PR_MCE_KILL:
+ if (arg4 | arg5)
+ return -EINVAL;
+ switch (arg2) {
+ case PR_MCE_KILL_CLEAR:
+ if (arg3 != 0)
return -EINVAL;
- }
- error = 0;
+ current->flags &= ~PF_MCE_PROCESS;
break;
- case PR_MCE_KILL_GET:
- if (arg2 | arg3 | arg4 | arg5)
- return -EINVAL;
- if (current->flags & PF_MCE_PROCESS)
- error = (current->flags & PF_MCE_EARLY) ?
- PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
+ case PR_MCE_KILL_SET:
+ current->flags |= PF_MCE_PROCESS;
+ if (arg3 == PR_MCE_KILL_EARLY)
+ current->flags |= PF_MCE_EARLY;
+ else if (arg3 == PR_MCE_KILL_LATE)
+ current->flags &= ~PF_MCE_EARLY;
+ else if (arg3 == PR_MCE_KILL_DEFAULT)
+ current->flags &=
+ ~(PF_MCE_EARLY|PF_MCE_PROCESS);
else
- error = PR_MCE_KILL_DEFAULT;
+ return -EINVAL;
break;
default:
- error = -EINVAL;
- break;
+ return -EINVAL;
+ }
+ break;
+ case PR_MCE_KILL_GET:
+ if (arg2 | arg3 | arg4 | arg5)
+ return -EINVAL;
+ if (current->flags & PF_MCE_PROCESS)
+ error = (current->flags & PF_MCE_EARLY) ?
+ PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
+ else
+ error = PR_MCE_KILL_DEFAULT;
+ break;
+ case PR_SET_MM:
+ error = prctl_set_mm(arg2, arg3, arg4, arg5);
+ break;
+ case PR_GET_TID_ADDRESS:
+ error = prctl_get_tid_address(me, (int __user **)arg2);
+ break;
+ case PR_SET_CHILD_SUBREAPER:
+ me->signal->is_child_subreaper = !!arg2;
+ break;
+ case PR_GET_CHILD_SUBREAPER:
+ error = put_user(me->signal->is_child_subreaper,
+ (int __user *)arg2);
+ break;
+ case PR_SET_NO_NEW_PRIVS:
+ if (arg2 != 1 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ current->no_new_privs = 1;
+ break;
+ case PR_GET_NO_NEW_PRIVS:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ return current->no_new_privs ? 1 : 0;
+ case PR_GET_THP_DISABLE:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+ break;
+ case PR_SET_THP_DISABLE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ down_write(&me->mm->mmap_sem);
+ if (arg2)
+ me->mm->def_flags |= VM_NOHUGEPAGE;
+ else
+ me->mm->def_flags &= ~VM_NOHUGEPAGE;
+ up_write(&me->mm->mmap_sem);
+ break;
+ default:
+ error = -EINVAL;
+ break;
}
return error;
}
@@ -1746,60 +2030,146 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
return err ? -EFAULT : 0;
}
-char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
-
-static void argv_cleanup(struct subprocess_info *info)
-{
- argv_free(info->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.
+ * do_sysinfo - fill in sysinfo struct
+ * @info: pointer to buffer to fill
*/
-int orderly_poweroff(bool force)
+static int do_sysinfo(struct sysinfo *info)
{
- 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;
- }
+ unsigned long mem_total, sav_total;
+ unsigned int mem_unit, bitcount;
+ struct timespec tp;
+
+ memset(info, 0, sizeof(struct sysinfo));
+
+ get_monotonic_boottime(&tp);
+ info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
+
+ get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
+
+ info->procs = nr_threads;
+
+ si_meminfo(info);
+ si_swapinfo(info);
+
+ /*
+ * If the sum of all the available memory (i.e. ram + swap)
+ * is less than can be stored in a 32 bit unsigned long then
+ * we can be binary compatible with 2.2.x kernels. If not,
+ * well, in that case 2.2.x was broken anyways...
+ *
+ * -Erik Andersen <andersee@debian.org>
+ */
- info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
- if (info == NULL) {
- argv_free(argv);
+ mem_total = info->totalram + info->totalswap;
+ if (mem_total < info->totalram || mem_total < info->totalswap)
goto out;
+ bitcount = 0;
+ mem_unit = info->mem_unit;
+ while (mem_unit > 1) {
+ bitcount++;
+ mem_unit >>= 1;
+ sav_total = mem_total;
+ mem_total <<= 1;
+ if (mem_total < sav_total)
+ goto out;
}
- call_usermodehelper_setfns(info, NULL, argv_cleanup, NULL);
+ /*
+ * If mem_total did not overflow, multiply all memory values by
+ * info->mem_unit and set it to 1. This leaves things compatible
+ * with 2.2.x, and also retains compatibility with earlier 2.4.x
+ * kernels...
+ */
+
+ info->mem_unit = 1;
+ info->totalram <<= bitcount;
+ info->freeram <<= bitcount;
+ info->sharedram <<= bitcount;
+ info->bufferram <<= bitcount;
+ info->totalswap <<= bitcount;
+ info->freeswap <<= bitcount;
+ info->totalhigh <<= bitcount;
+ info->freehigh <<= bitcount;
+
+out:
+ return 0;
+}
+
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
+{
+ struct sysinfo val;
+
+ do_sysinfo(&val);
+
+ if (copy_to_user(info, &val, sizeof(struct sysinfo)))
+ return -EFAULT;
- ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
+ return 0;
+}
- out:
- if (ret && force) {
- printk(KERN_WARNING "Failed to start orderly shutdown: "
- "forcing the issue\n");
+#ifdef CONFIG_COMPAT
+struct compat_sysinfo {
+ s32 uptime;
+ u32 loads[3];
+ u32 totalram;
+ u32 freeram;
+ u32 sharedram;
+ u32 bufferram;
+ u32 totalswap;
+ u32 freeswap;
+ u16 procs;
+ u16 pad;
+ u32 totalhigh;
+ u32 freehigh;
+ u32 mem_unit;
+ char _f[20-2*sizeof(u32)-sizeof(int)];
+};
+
+COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
+{
+ struct sysinfo s;
+
+ do_sysinfo(&s);
+
+ /* Check to see if any memory value is too large for 32-bit and scale
+ * down if needed
+ */
+ if ((s.totalram >> 32) || (s.totalswap >> 32)) {
+ int bitcount = 0;
- /* 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();
+ while (s.mem_unit < PAGE_SIZE) {
+ s.mem_unit <<= 1;
+ bitcount++;
+ }
+
+ s.totalram >>= bitcount;
+ s.freeram >>= bitcount;
+ s.sharedram >>= bitcount;
+ s.bufferram >>= bitcount;
+ s.totalswap >>= bitcount;
+ s.freeswap >>= bitcount;
+ s.totalhigh >>= bitcount;
+ s.freehigh >>= bitcount;
}
- return ret;
+ if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) ||
+ __put_user(s.uptime, &info->uptime) ||
+ __put_user(s.loads[0], &info->loads[0]) ||
+ __put_user(s.loads[1], &info->loads[1]) ||
+ __put_user(s.loads[2], &info->loads[2]) ||
+ __put_user(s.totalram, &info->totalram) ||
+ __put_user(s.freeram, &info->freeram) ||
+ __put_user(s.sharedram, &info->sharedram) ||
+ __put_user(s.bufferram, &info->bufferram) ||
+ __put_user(s.totalswap, &info->totalswap) ||
+ __put_user(s.freeswap, &info->freeswap) ||
+ __put_user(s.procs, &info->procs) ||
+ __put_user(s.totalhigh, &info->totalhigh) ||
+ __put_user(s.freehigh, &info->freehigh) ||
+ __put_user(s.mem_unit, &info->mem_unit))
+ return -EFAULT;
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(orderly_poweroff);
+#endif /* CONFIG_COMPAT */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 07:14:04 +0000