aboutsummaryrefslogtreecommitdiff
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c2425
1 files changed, 1392 insertions, 1033 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index a626116af5d..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/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/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>
@@ -33,11 +32,30 @@
#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/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>
@@ -67,6 +85,12 @@
#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
@@ -76,10 +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
@@ -93,25 +115,32 @@ EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
/*
- * this indicates whether you can reboot with ctrl-alt-del: the default is yes
+ * 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
*/
-
-int C_A_D = 1;
-struct pid *cad_pid;
-EXPORT_SYMBOL(cad_pid);
+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;
+}
/*
- * If set, this is used for preparing the system to power off.
+ * set the priority of a task
+ * - the caller must hold the RCU read lock
*/
-
-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)) {
+ if (!set_one_prio_perm(p)) {
error = -EPERM;
goto out;
}
@@ -131,23 +160,26 @@ out:
return error;
}
-asmlinkage long sys_setpriority(int which, int who, int niceval)
+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 < -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);
switch (which) {
case PRIO_PROCESS:
@@ -163,28 +195,30 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
- do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+ do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
- } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+ } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = current->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->user;
if (!who)
- who = current->uid;
- else
- if ((who != current->uid) && !(user = find_user(who)))
- goto out_unlock; /* No processes for this user */
+ 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 (p->uid == who)
+ do_each_thread(g, p) {
+ if (uid_eq(task_uid(p), uid))
error = set_one_prio(p, niceval, error);
- while_each_thread(g, p);
- if (who != current->uid)
+ } 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;
}
@@ -195,16 +229,19 @@ out:
* 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)
+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:
@@ -213,7 +250,7 @@ asmlinkage long sys_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;
}
@@ -223,244 +260,39 @@ asmlinkage long sys_getpriority(int which, int who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
- do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
- niceval = 20 - task_nice(p);
+ do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+ niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
- } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+ } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = current->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->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);
+ 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 (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 != current->uid)
+ } 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;
}
-/**
- * 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);
-
-static 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);
-
-/**
- * kernel_kexec - reboot the system
- *
- * Move into place and start executing a preloaded standalone
- * executable. If nothing was preloaded return an error.
- */
-static void kernel_kexec(void)
-{
-#ifdef CONFIG_KEXEC
- struct kimage *image;
- image = xchg(&kexec_image, NULL);
- if (!image)
- return;
- kernel_restart_prepare(NULL);
- printk(KERN_EMERG "Starting new kernel\n");
- machine_shutdown();
- machine_kexec(image);
-#endif
-}
-
-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;
-
- case LINUX_REBOOT_CMD_KEXEC:
- kernel_kexec();
- unlock_kernel();
- return -EINVAL;
-
-#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)
@@ -479,48 +311,56 @@ void ctrl_alt_del(void)
* 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)
+SYSCALL_DEFINE2(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;
+ struct user_namespace *ns = current_user_ns();
+ const struct cred *old;
+ struct cred *new;
int retval;
+ kgid_t krgid, kegid;
- retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
- if (retval)
- return retval;
+ 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 ((old_rgid == rgid) ||
- (current->egid==rgid) ||
- capable(CAP_SETGID))
- new_rgid = rgid;
+ if (gid_eq(old->gid, krgid) ||
+ gid_eq(old->egid, krgid) ||
+ ns_capable(old->user_ns, CAP_SETGID))
+ new->gid = krgid;
else
- return -EPERM;
+ goto error;
}
if (egid != (gid_t) -1) {
- if ((old_rgid == egid) ||
- (current->egid == egid) ||
- (current->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
- return -EPERM;
- }
- if (new_egid != old_egid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ goto error;
}
+
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;
+ (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;
}
/*
@@ -528,58 +368,64 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
*
* SMP: Same implicit races as above.
*/
-asmlinkage long sys_setgid(gid_t gid)
+SYSCALL_DEFINE1(setgid, gid_t, gid)
{
- int old_egid = current->egid;
+ struct user_namespace *ns = current_user_ns();
+ const struct cred *old;
+ struct cred *new;
int retval;
+ kgid_t kgid;
- retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
- if (retval)
- return retval;
+ kgid = make_kgid(ns, gid);
+ if (!gid_valid(kgid))
+ return -EINVAL;
- 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;
- }
+ 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
- return -EPERM;
+ goto error;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
- return 0;
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
-
-static int set_user(uid_t new_ruid, int dumpclear)
+
+/*
+ * change the user struct in a credentials set to match the new UID
+ */
+static int set_user(struct cred *new)
{
struct user_struct *new_user;
- new_user = alloc_uid(current->nsproxy->user_ns, new_ruid);
+ new_user = alloc_uid(new->uid);
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);
+ /*
+ * 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;
- if (dumpclear) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->uid = new_ruid;
+ free_uid(new->user);
+ new->user = new_user;
return 0;
}
@@ -598,56 +444,65 @@ static int set_user(uid_t new_ruid, int dumpclear)
* 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)
+SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
{
- int old_ruid, old_euid, old_suid, new_ruid, new_euid;
+ struct user_namespace *ns = current_user_ns();
+ const struct cred *old;
+ struct cred *new;
int retval;
+ kuid_t kruid, keuid;
- retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
- if (retval)
- return retval;
+ kruid = make_kuid(ns, ruid);
+ keuid = make_kuid(ns, euid);
- new_ruid = old_ruid = current->uid;
- new_euid = old_euid = current->euid;
- old_suid = current->suid;
+ 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_ruid = ruid;
- if ((old_ruid != ruid) &&
- (current->euid != ruid) &&
- !capable(CAP_SETUID))
- return -EPERM;
+ 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_ruid != euid) &&
- (current->euid != euid) &&
- (current->suid != euid) &&
- !capable(CAP_SETUID))
- return -EPERM;
+ 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_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();
+ if (!uid_eq(new->uid, old->uid)) {
+ retval = set_user(new);
+ if (retval < 0)
+ goto error;
}
- 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;
+ (euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
+ new->suid = new->euid;
+ new->fsuid = new->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);
-}
+ 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
@@ -660,38 +515,46 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
* 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)
+SYSCALL_DEFINE1(setuid, uid_t, uid)
{
- int old_euid = current->euid;
- int old_ruid, old_suid, new_suid;
+ struct user_namespace *ns = current_user_ns();
+ const struct cred *old;
+ struct cred *new;
int retval;
+ kuid_t kuid;
- 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;
+ kuid = make_kuid(ns, uid);
+ if (!uid_valid(kuid))
+ return -EINVAL;
- if (old_euid != uid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ 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;
}
- current->fsuid = current->euid = uid;
- current->suid = new_suid;
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
+ new->fsuid = new->euid = kuid;
+
+ retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
+ if (retval < 0)
+ goto error;
- return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
@@ -699,56 +562,84 @@ asmlinkage long sys_setuid(uid_t uid)
* 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)
+SYSCALL_DEFINE3(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;
+ struct user_namespace *ns = current_user_ns();
+ const struct cred *old;
+ struct cred *new;
int retval;
+ kuid_t kruid, keuid, ksuid;
- retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
- if (retval)
- return retval;
+ kruid = make_kuid(ns, ruid);
+ keuid = make_kuid(ns, euid);
+ ksuid = make_kuid(ns, suid);
- 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) && !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) {
- 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();
+ new->uid = kruid;
+ if (!uid_eq(kruid, old->uid)) {
+ retval = set_user(new);
+ if (retval < 0)
+ goto error;
}
- current->euid = euid;
}
- current->fsuid = current->euid;
+ if (euid != (uid_t) -1)
+ new->euid = keuid;
if (suid != (uid_t) -1)
- current->suid = suid;
+ new->suid = ksuid;
+ new->fsuid = new->euid;
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
+ retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
+ if (retval < 0)
+ goto error;
- return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
-asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
+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(current->uid, ruid)) &&
- !(retval = put_user(current->euid, euid)))
- retval = put_user(current->suid, suid);
+ if (!(retval = put_user(ruid, ruidp)) &&
+ !(retval = put_user(euid, euidp)))
+ retval = put_user(suid, suidp);
return retval;
}
@@ -756,50 +647,71 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us
/*
* Same as above, but for rgid, egid, sgid.
*/
-asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
+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;
- retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
- if (retval)
- return retval;
+ krgid = make_kgid(ns, rgid);
+ kegid = make_kgid(ns, egid);
+ ksgid = make_kgid(ns, sgid);
- 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;
+ 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)
+ return -ENOMEM;
+ old = current_cred();
+
+ retval = -EPERM;
+ 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 && !gid_eq(kegid, old->gid) &&
+ !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
+ goto error;
+ if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) &&
+ !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
+ goto error;
}
- current->fsgid = current->egid;
+
if (rgid != (gid_t) -1)
- current->gid = rgid;
+ new->gid = krgid;
+ if (egid != (gid_t) -1)
+ new->egid = kegid;
if (sgid != (gid_t) -1)
- current->sgid = sgid;
+ new->sgid = ksgid;
+ new->fsgid = new->egid;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
- return 0;
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
-asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
+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;
+
+ 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(current->gid, rgid)) &&
- !(retval = put_user(current->egid, egid)))
- retval = put_user(current->sgid, sgid);
+ if (!(retval = put_user(rgid, rgidp)) &&
+ !(retval = put_user(egid, egidp)))
+ retval = put_user(sgid, sgidp);
return retval;
}
@@ -811,92 +723,166 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us
* 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)
+SYSCALL_DEFINE1(setfsuid, uid_t, uid)
{
- int old_fsuid;
+ const struct cred *old;
+ struct cred *new;
+ uid_t old_fsuid;
+ kuid_t kuid;
- old_fsuid = current->fsuid;
- if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
+ 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 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();
+ 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;
}
- 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);
+ abort_creds(new);
+ return old_fsuid;
+change_okay:
+ commit_creds(new);
return old_fsuid;
}
/*
* Samma på svenska..
*/
-asmlinkage long sys_setfsgid(gid_t gid)
+SYSCALL_DEFINE1(setfsgid, gid_t, gid)
{
- int old_fsgid;
+ 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);
- old_fsgid = current->fsgid;
- if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
+ kgid = make_kgid(old->user_ns, gid);
+ if (!gid_valid(kgid))
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();
+ new = prepare_creds();
+ if (!new)
+ return old_fsgid;
+
+ 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;
}
- current->fsgid = gid;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
}
+
+ abort_creds(new);
+ return old_fsgid;
+
+change_okay:
+ commit_creds(new);
return old_fsgid;
}
-asmlinkage long sys_times(struct tms __user * tbuf)
+/**
+ * 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_cputime_adjusted(current, &tgutime, &tgstime);
+ cutime = current->signal->cutime;
+ cstime = current->signal->cstime;
+ spin_unlock_irq(&current->sighand->siglock);
+ tms->tms_utime = cputime_to_clock_t(tgutime);
+ tms->tms_stime = cputime_to_clock_t(tgstime);
+ tms->tms_cutime = cputime_to_clock_t(cutime);
+ tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
+SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
{
- /*
- * In the SMP world we might just be unlucky and have one of
- * the times increment as we use it. Since the value is an
- * atomically safe type this is just fine. Conceptually its
- * as if the syscall took an instant longer to occur.
- */
if (tbuf) {
struct tms tmp;
- struct task_struct *tsk = current;
- struct task_struct *t;
- cputime_t utime, stime, cutime, cstime;
-
- spin_lock_irq(&tsk->sighand->siglock);
- utime = tsk->signal->utime;
- stime = tsk->signal->stime;
- t = tsk;
- do {
- utime = cputime_add(utime, t->utime);
- stime = cputime_add(stime, t->stime);
- t = next_thread(t);
- } while (t != tsk);
-
- cutime = tsk->signal->cutime;
- cstime = tsk->signal->cstime;
- spin_unlock_irq(&tsk->sighand->siglock);
-
- tmp.tms_utime = cputime_to_clock_t(utime);
- tmp.tms_stime = cputime_to_clock_t(stime);
- tmp.tms_cutime = cputime_to_clock_t(cutime);
- tmp.tms_cstime = cputime_to_clock_t(cstime);
+
+ do_sys_times(&tmp);
if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
return -EFAULT;
}
+ force_successful_syscall_return();
return (long) jiffies_64_to_clock_t(get_jiffies_64());
}
@@ -909,10 +895,9 @@ asmlinkage long sys_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.
*/
-asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
+SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
{
struct task_struct *p;
struct task_struct *group_leader = current->group_leader;
@@ -925,6 +910,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
+ rcu_read_lock();
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
@@ -945,7 +931,7 @@ asmlinkage long sys_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;
@@ -971,72 +957,94 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
if (err)
goto out;
- if (task_pgrp(p) != pgrp) {
- detach_pid(p, PIDTYPE_PGID);
- attach_pid(p, PIDTYPE_PGID, pgrp);
- set_task_pgrp(p, pid_nr(pgrp));
- }
+ if (task_pgrp(p) != pgrp)
+ change_pid(p, PIDTYPE_PGID, pgrp);
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
+ rcu_read_unlock();
return err;
}
-asmlinkage long sys_getpgid(pid_t pid)
+SYSCALL_DEFINE1(getpgid, pid_t, pid)
{
+ struct task_struct *p;
+ struct pid *grp;
+ int retval;
+
+ rcu_read_lock();
if (!pid)
- return task_pgrp_vnr(current);
+ grp = task_pgrp(current);
else {
- int retval;
- struct task_struct *p;
-
- read_lock(&tasklist_lock);
- p = find_task_by_vpid(pid);
retval = -ESRCH;
- if (p) {
- retval = security_task_getpgid(p);
- if (!retval)
- retval = task_pgrp_vnr(p);
- }
- read_unlock(&tasklist_lock);
- return retval;
+ 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)
+SYSCALL_DEFINE0(getpgrp)
{
- /* SMP - assuming writes are word atomic this is fine */
- return task_pgrp_vnr(current);
+ return sys_getpgid(0);
}
#endif
-asmlinkage long sys_getsid(pid_t pid)
+SYSCALL_DEFINE1(getsid, pid_t, pid)
{
+ struct task_struct *p;
+ struct pid *sid;
+ int retval;
+
+ rcu_read_lock();
if (!pid)
- return task_session_vnr(current);
+ sid = task_session(current);
else {
- int retval;
- struct task_struct *p;
-
- rcu_read_lock();
- p = find_task_by_vpid(pid);
retval = -ESRCH;
- if (p) {
- retval = security_task_getsid(p);
- if (!retval)
- retval = task_session_vnr(p);
- }
- rcu_read_unlock();
- return retval;
+ 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)
+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;
struct pid *sid = task_pid(group_leader);
@@ -1055,304 +1063,154 @@ asmlinkage long sys_setsid(void)
goto out;
group_leader->signal->leader = 1;
- __set_special_pids(sid);
+ set_special_pids(sid);
- spin_lock(&group_leader->sighand->siglock);
- group_leader->signal->tty = NULL;
- spin_unlock(&group_leader->sighand->siglock);
+ proc_clear_tty(group_leader);
err = session;
out:
write_unlock_irq(&tasklist_lock);
- return err;
-}
-
-/*
- * Supplementary group IDs
- */
-
-/* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
-
-struct group_info *groups_alloc(int gidsetsize)
-{
- struct group_info *group_info;
- int nblocks;
- int i;
-
- nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
- /* Make sure we always allocate at least one indirect block pointer */
- nblocks = nblocks ? : 1;
- group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
- if (!group_info)
- return NULL;
- group_info->ngroups = gidsetsize;
- group_info->nblocks = nblocks;
- atomic_set(&group_info->usage, 1);
-
- if (gidsetsize <= NGROUPS_SMALL)
- group_info->blocks[0] = group_info->small_block;
- else {
- for (i = 0; i < nblocks; i++) {
- gid_t *b;
- b = (void *)__get_free_page(GFP_USER);
- if (!b)
- goto out_undo_partial_alloc;
- group_info->blocks[i] = b;
- }
- }
- return group_info;
-
-out_undo_partial_alloc:
- while (--i >= 0) {
- free_page((unsigned long)group_info->blocks[i]);
+ if (err > 0) {
+ proc_sid_connector(group_leader);
+ sched_autogroup_create_attach(group_leader);
}
- 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);
+ return err;
}
-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;
+DECLARE_RWSEM(uts_sem);
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
- }
- return 0;
-}
+#ifdef COMPAT_UTS_MACHINE
+#define override_architecture(name) \
+ (personality(current->personality) == PER_LINUX32 && \
+ copy_to_user(name->machine, COMPAT_UTS_MACHINE, \
+ sizeof(COMPAT_UTS_MACHINE)))
+#else
+#define override_architecture(name) 0
+#endif
-/* 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)
+/*
+ * 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 i;
- unsigned int count = group_info->ngroups;
+ int ret = 0;
- 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 (current->personality & UNAME26) {
+ const char *rest = UTS_RELEASE;
+ char buf[65] = { 0 };
+ int ndots = 0;
+ unsigned v;
+ size_t copy;
- 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;
+ while (*rest) {
+ if (*rest == '.' && ++ndots >= 3)
+ break;
+ if (!isdigit(*rest) && *rest != '.')
+ break;
+ rest++;
}
- 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;
+ 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 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;
+ return ret;
}
-EXPORT_SYMBOL(set_current_groups);
-
-asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
{
- int i = 0;
-
- /*
- * SMP: Nobody else can change our grouplist. Thus we are
- * safe.
- */
+ int errno = 0;
- if (gidsetsize < 0)
- return -EINVAL;
+ down_read(&uts_sem);
+ if (copy_to_user(name, utsname(), sizeof *name))
+ errno = -EFAULT;
+ up_read(&uts_sem);
- /* 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;
+ if (!errno && override_release(name->release, sizeof(name->release)))
+ errno = -EFAULT;
+ if (!errno && override_architecture(name))
+ errno = -EFAULT;
+ return errno;
}
+#ifdef __ARCH_WANT_SYS_OLD_UNAME
/*
- * SMP: Our groups are copy-on-write. We can set them safely
- * without another task interfering.
+ * Old cruft
*/
-
-asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
{
- 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;
- }
+ int error = 0;
- retval = set_current_groups(group_info);
- put_group_info(group_info);
+ if (!name)
+ return -EFAULT;
- return retval;
-}
+ down_read(&uts_sem);
+ if (copy_to_user(name, utsname(), sizeof(*name)))
+ error = -EFAULT;
+ up_read(&uts_sem);
-/*
- * 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;
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
+ if (!error && override_architecture(name))
+ error = -EFAULT;
+ return error;
}
-EXPORT_SYMBOL(in_group_p);
-
-int in_egroup_p(gid_t grp)
+SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
{
- 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);
-
-EXPORT_SYMBOL(uts_sem);
+ int error;
-asmlinkage long sys_newuname(struct new_utsname __user * name)
-{
- int errno = 0;
+ if (!name)
+ return -EFAULT;
+ if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
+ return -EFAULT;
down_read(&uts_sem);
- if (copy_to_user(name, utsname(), sizeof *name))
- errno = -EFAULT;
+ error = __copy_to_user(&name->sysname, &utsname()->sysname,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->nodename, &utsname()->nodename,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->nodename + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->release, &utsname()->release,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->release + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->version, &utsname()->version,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->version + __OLD_UTS_LEN);
+ error |= __copy_to_user(&name->machine, &utsname()->machine,
+ __OLD_UTS_LEN);
+ error |= __put_user(0, name->machine + __OLD_UTS_LEN);
up_read(&uts_sem);
- return errno;
+
+ if (!error && override_architecture(name))
+ error = -EFAULT;
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
+ return error ? -EFAULT : 0;
}
+#endif
-asmlinkage long sys_sethostname(char __user *name, int len)
+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);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- memcpy(utsname()->nodename, tmp, len);
- utsname()->nodename[len] = 0;
+ struct new_utsname *u = utsname();
+
+ 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;
@@ -1360,18 +1218,20 @@ asmlinkage long sys_sethostname(char __user *name, int len)
#ifdef __ARCH_WANT_SYS_GETHOSTNAME
-asmlinkage long sys_gethostname(char __user *name, int len)
+SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
{
int i, errno;
+ struct new_utsname *u;
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
- i = 1 + strlen(utsname()->nodename);
+ u = utsname();
+ i = 1 + strlen(u->nodename);
if (i > len)
i = len;
errno = 0;
- if (copy_to_user(name, utsname()->nodename, i))
+ if (copy_to_user(name, u->nodename, i))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
@@ -1383,12 +1243,12 @@ asmlinkage long sys_gethostname(char __user *name, int len)
* Only setdomainname; getdomainname can be implemented by calling
* uname()
*/
-asmlinkage long sys_setdomainname(char __user *name, int len)
+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;
@@ -1396,25 +1256,27 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- memcpy(utsname()->domainname, tmp, len);
- utsname()->domainname[len] = 0;
+ struct new_utsname *u = utsname();
+
+ 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;
}
-asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(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;
- }
+ struct rlimit value;
+ int ret;
+
+ ret = do_prlimit(current, resource, NULL, &value);
+ if (!ret)
+ ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+
+ return ret;
}
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
@@ -1423,7 +1285,8 @@ asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
* Back compatibility for getrlimit. Needed for some apps.
*/
-asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+ struct rlimit __user *, rlim)
{
struct rlimit x;
if (resource >= RLIM_NLIMITS)
@@ -1441,45 +1304,91 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
#endif
-asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
+static inline bool rlim64_is_infinity(__u64 rlim64)
{
- struct rlimit new_rlim, *old_rlim;
- unsigned long it_prof_secs;
- int retval;
+#if BITS_PER_LONG < 64
+ return rlim64 >= ULONG_MAX;
+#else
+ return rlim64 == RLIM64_INFINITY;
+#endif
+}
+
+static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64)
+{
+ if (rlim->rlim_cur == RLIM_INFINITY)
+ rlim64->rlim_cur = RLIM64_INFINITY;
+ else
+ rlim64->rlim_cur = rlim->rlim_cur;
+ if (rlim->rlim_max == RLIM_INFINITY)
+ rlim64->rlim_max = RLIM64_INFINITY;
+ else
+ rlim64->rlim_max = rlim->rlim_max;
+}
+
+static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
+{
+ if (rlim64_is_infinity(rlim64->rlim_cur))
+ rlim->rlim_cur = RLIM_INFINITY;
+ else
+ rlim->rlim_cur = (unsigned long)rlim64->rlim_cur;
+ if (rlim64_is_infinity(rlim64->rlim_max))
+ rlim->rlim_max = RLIM_INFINITY;
+ else
+ rlim->rlim_max = (unsigned long)rlim64->rlim_max;
+}
+
+/* make sure you are allowed to change @tsk limits before calling this */
+int do_prlimit(struct task_struct *tsk, unsigned int resource,
+ struct rlimit *new_rlim, struct rlimit *old_rlim)
+{
+ struct rlimit *rlim;
+ int retval = 0;
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;
+ if (new_rlim) {
+ if (new_rlim->rlim_cur > new_rlim->rlim_max)
+ return -EINVAL;
+ if (resource == RLIMIT_NOFILE &&
+ new_rlim->rlim_max > sysctl_nr_open)
+ return -EPERM;
}
- task_lock(current->group_leader);
- *old_rlim = new_rlim;
- task_unlock(current->group_leader);
-
- if (resource != RLIMIT_CPU)
+ /* protect tsk->signal and tsk->sighand from disappearing */
+ read_lock(&tasklist_lock);
+ if (!tsk->sighand) {
+ retval = -ESRCH;
goto out;
+ }
+
+ 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;
+ if (!retval)
+ retval = security_task_setrlimit(tsk->group_leader,
+ resource, new_rlim);
+ 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;
+ }
+ }
+ if (!retval) {
+ if (old_rlim)
+ *old_rlim = *rlim;
+ if (new_rlim)
+ *rlim = *new_rlim;
+ }
+ task_unlock(tsk->group_leader);
/*
* RLIMIT_CPU handling. Note that the kernel fails to return an error
@@ -1487,23 +1396,85 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
* 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;
+ if (!retval && new_rlim && resource == RLIMIT_CPU &&
+ new_rlim->rlim_cur != RLIM_INFINITY)
+ update_rlimit_cpu(tsk, new_rlim->rlim_cur);
+out:
+ read_unlock(&tasklist_lock);
+ return retval;
+}
+
+/* rcu lock must be held */
+static int check_prlimit_permission(struct task_struct *task)
+{
+ const struct cred *cred = current_cred(), *tcred;
- it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
- if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
- unsigned long rlim_cur = new_rlim.rlim_cur;
- cputime_t cputime;
-
- cputime = secs_to_cputime(rlim_cur);
- read_lock(&tasklist_lock);
- spin_lock_irq(&current->sighand->siglock);
- set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
- spin_unlock_irq(&current->sighand->siglock);
- read_unlock(&tasklist_lock);
+ if (current == task)
+ 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,
+ const struct rlimit64 __user *, new_rlim,
+ struct rlimit64 __user *, old_rlim)
+{
+ struct rlimit64 old64, new64;
+ struct rlimit old, new;
+ struct task_struct *tsk;
+ int ret;
+
+ if (new_rlim) {
+ if (copy_from_user(&new64, new_rlim, sizeof(new64)))
+ return -EFAULT;
+ rlim64_to_rlim(&new64, &new);
}
-out:
- return 0;
+
+ rcu_read_lock();
+ tsk = pid ? find_task_by_vpid(pid) : current;
+ if (!tsk) {
+ rcu_read_unlock();
+ return -ESRCH;
+ }
+ ret = check_prlimit_permission(tsk);
+ if (ret) {
+ rcu_read_unlock();
+ return ret;
+ }
+ get_task_struct(tsk);
+ rcu_read_unlock();
+
+ ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
+ old_rlim ? &old : NULL);
+
+ if (!ret && old_rlim) {
+ rlim_to_rlim64(&old, &old64);
+ if (copy_to_user(old_rlim, &old64, sizeof(old64)))
+ ret = -EFAULT;
+ }
+
+ put_task_struct(tsk);
+ return ret;
+}
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+ struct rlimit new_rlim;
+
+ if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+ return -EFAULT;
+ return do_prlimit(current, resource, &new_rlim, NULL);
}
/*
@@ -1539,21 +1510,36 @@ out:
*
*/
+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;
+ cputime_t tgutime, tgstime, utime, stime;
+ unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
- utime = stime = cputime_zero;
+ utime = stime = 0;
- rcu_read_lock();
- if (!lock_task_sighand(p, &flags)) {
- rcu_read_unlock();
- return;
+ if (who == RUSAGE_THREAD) {
+ task_cputime_adjusted(current, &utime, &stime);
+ accumulate_thread_rusage(p, r);
+ maxrss = p->signal->maxrss;
+ goto out;
}
+ if (!lock_task_sighand(p, &flags))
+ return;
+
switch (who) {
case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
@@ -1565,42 +1551,46 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
r->ru_majflt = p->signal->cmaj_flt;
r->ru_inblock = p->signal->cinblock;
r->ru_oublock = p->signal->coublock;
+ maxrss = p->signal->cmaxrss;
if (who == RUSAGE_CHILDREN)
break;
case RUSAGE_SELF:
- utime = cputime_add(utime, p->signal->utime);
- stime = cputime_add(stime, p->signal->stime);
+ 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;
r->ru_majflt += p->signal->maj_flt;
r->ru_inblock += p->signal->inblock;
r->ru_oublock += p->signal->oublock;
+ if (maxrss < p->signal->maxrss)
+ maxrss = p->signal->maxrss;
t = p;
do {
- utime = cputime_add(utime, t->utime);
- stime = cputime_add(stime, t->stime);
- 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);
- t = next_thread(t);
- } while (t != p);
+ accumulate_thread_rusage(t, r);
+ } while_each_thread(p, t);
break;
default:
BUG();
}
-
unlock_task_sighand(p, &flags);
- rcu_read_unlock();
+out:
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
+
+ if (who != RUSAGE_CHILDREN) {
+ struct mm_struct *mm = get_task_mm(p);
+ if (mm) {
+ setmax_mm_hiwater_rss(&maxrss, mm);
+ mmput(mm);
+ }
+ }
+ r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
}
int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
@@ -1610,143 +1600,426 @@ int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
}
-asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
+SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
{
- if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
+ if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
+ who != RUSAGE_THREAD)
return -EINVAL;
return getrusage(current, who, ru);
}
-asmlinkage long sys_umask(int mask)
+#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;
}
-asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
- unsigned long arg4, unsigned long arg5)
+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)
+{
+ struct task_struct *me = current;
+ unsigned char comm[sizeof(me->comm)];
long error;
error = security_task_prctl(option, arg2, arg3, arg4, arg5);
- if (error)
+ if (error != -ENOSYS)
return error;
+ error = 0;
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);
+ case PR_SET_PDEATHSIG:
+ if (!valid_signal(arg2)) {
+ error = -EINVAL;
break;
- case PR_SET_DUMPABLE:
- if (arg2 < 0 || arg2 > 1) {
- error = -EINVAL;
- break;
- }
- set_dumpable(current->mm, 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_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;
+ 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;
+ 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_SET_TIMING:
- if (arg2 == PR_TIMING_STATISTICAL)
- error = 0;
+ 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 = -EINVAL;
- break;
-
- case PR_GET_KEEPCAPS:
- if (current->keep_capabilities)
- error = 1;
- break;
- case PR_SET_KEEPCAPS:
- if (arg2 != 0 && arg2 != 1) {
- error = -EINVAL;
- break;
- }
- current->keep_capabilities = arg2;
+ return -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;
+ default:
+ return -EINVAL;
}
- 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_CAPBSET_READ:
- if (!cap_valid(arg2))
- return -EINVAL;
- return !!cap_raised(current->cap_bset, arg2);
- case PR_CAPBSET_DROP:
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
- return cap_prctl_drop(arg2);
-#else
+ 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;
-#endif
- default:
- error = -EINVAL;
- break;
+ 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;
}
-asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
- struct getcpu_cache __user *unused)
+SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
+ struct getcpu_cache __user *, unused)
{
int err = 0;
int cpu = raw_smp_processor_id();
@@ -1757,60 +2030,146 @@ asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *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.
+ * 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));
- info = call_usermodehelper_setup(argv[0], argv, envp);
- if (info == NULL) {
- argv_free(argv);
+ 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>
+ */
+
+ 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_setcleanup(info, argv_cleanup);
+ /*
+ * 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...
+ */
- ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
+ 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:
- if (ret && force) {
- printk(KERN_WARNING "Failed to start orderly shutdown: "
- "forcing the issue\n");
+out:
+ return 0;
+}
+
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
+{
+ struct sysinfo val;
+
+ do_sysinfo(&val);
- /* 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();
+ if (copy_to_user(info, &val, sizeof(struct sysinfo)))
+ return -EFAULT;
+
+ return 0;
+}
+
+#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;
+
+ 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 2025-11-10 15:57:16 +0000