aboutsummaryrefslogtreecommitdiff
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c1090
1 files changed, 558 insertions, 532 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index 6df42624e45..66a751ebf9d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -16,7 +16,6 @@
#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>
@@ -36,6 +35,8 @@
#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>
@@ -45,6 +46,12 @@
#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? */
@@ -108,20 +115,6 @@ EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
/*
- * this indicates whether you can reboot with ctrl-alt-del: the default is yes
- */
-
-int C_A_D = 1;
-struct pid *cad_pid;
-EXPORT_SYMBOL(cad_pid);
-
-/*
- * If set, this is used for preparing the system to power off.
- */
-
-void (*pm_power_off_prepare)(void);
-
-/*
* Returns true if current's euid is same as p's uid or euid,
* or has CAP_SYS_NICE to p's user_ns.
*
@@ -181,10 +174,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
/* 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);
@@ -257,7 +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;
}
@@ -268,7 +261,7 @@ 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);
@@ -284,7 +277,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
do_each_thread(g, p) {
if (uid_eq(task_uid(p), uid)) {
- niceval = 20 - task_nice(p);
+ niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
@@ -300,240 +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)
-{
- kmsg_dump(KMSG_DUMP_EMERG);
- 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;
- usermodehelper_disable();
- device_shutdown();
- syscore_shutdown();
-}
-
-/**
- * register_reboot_notifier - Register function to be called at reboot time
- * @nb: Info about notifier function to be called
- *
- * Registers a function with the list of functions
- * to be called at reboot time.
- *
- * Currently always returns zero, as blocking_notifier_chain_register()
- * always returns zero.
- */
-int register_reboot_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_register(&reboot_notifier_list, nb);
-}
-EXPORT_SYMBOL(register_reboot_notifier);
-
-/**
- * unregister_reboot_notifier - Unregister previously registered reboot notifier
- * @nb: Hook to be unregistered
- *
- * Unregisters a previously registered reboot
- * notifier function.
- *
- * Returns zero on success, or %-ENOENT on failure.
- */
-int unregister_reboot_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
-}
-EXPORT_SYMBOL(unregister_reboot_notifier);
-
-/**
- * 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);
- kmsg_dump(KMSG_DUMP_RESTART);
- 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;
- usermodehelper_disable();
- device_shutdown();
-}
-/**
- * kernel_halt - halt the system
- *
- * Shutdown everything and perform a clean system halt.
- */
-void kernel_halt(void)
-{
- kernel_shutdown_prepare(SYSTEM_HALT);
- syscore_shutdown();
- printk(KERN_EMERG "System halted.\n");
- kmsg_dump(KMSG_DUMP_HALT);
- 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();
- syscore_shutdown();
- printk(KERN_EMERG "Power down.\n");
- kmsg_dump(KMSG_DUMP_POWEROFF);
- 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;
-
- /*
- * If pid namespaces are enabled and the current task is in a child
- * pid_namespace, the command is handled by reboot_pid_ns() which will
- * call do_exit().
- */
- ret = reboot_pid_ns(task_active_pid_ns(current), cmd);
- if (ret)
- return ret;
-
- /* 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)
@@ -577,7 +336,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
if (rgid != (gid_t) -1) {
if (gid_eq(old->gid, krgid) ||
gid_eq(old->egid, krgid) ||
- nsown_capable(CAP_SETGID))
+ ns_capable(old->user_ns, CAP_SETGID))
new->gid = krgid;
else
goto error;
@@ -586,7 +345,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
if (gid_eq(old->gid, kegid) ||
gid_eq(old->egid, kegid) ||
gid_eq(old->sgid, kegid) ||
- nsown_capable(CAP_SETGID))
+ ns_capable(old->user_ns, CAP_SETGID))
new->egid = kegid;
else
goto error;
@@ -627,7 +386,7 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
old = current_cred();
retval = -EPERM;
- if (nsown_capable(CAP_SETGID))
+ 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;
@@ -711,7 +470,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
new->uid = kruid;
if (!uid_eq(old->uid, kruid) &&
!uid_eq(old->euid, kruid) &&
- !nsown_capable(CAP_SETUID))
+ !ns_capable(old->user_ns, CAP_SETUID))
goto error;
}
@@ -720,7 +479,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
if (!uid_eq(old->uid, keuid) &&
!uid_eq(old->euid, keuid) &&
!uid_eq(old->suid, keuid) &&
- !nsown_capable(CAP_SETUID))
+ !ns_capable(old->user_ns, CAP_SETUID))
goto error;
}
@@ -774,7 +533,7 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
old = current_cred();
retval = -EPERM;
- if (nsown_capable(CAP_SETUID)) {
+ if (ns_capable(old->user_ns, CAP_SETUID)) {
new->suid = new->uid = kuid;
if (!uid_eq(kuid, old->uid)) {
retval = set_user(new);
@@ -831,7 +590,7 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
old = current_cred();
retval = -EPERM;
- if (!nsown_capable(CAP_SETUID)) {
+ 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;
@@ -913,7 +672,7 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
old = current_cred();
retval = -EPERM;
- if (!nsown_capable(CAP_SETGID)) {
+ 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;
@@ -984,7 +743,7 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) ||
uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
- nsown_capable(CAP_SETUID)) {
+ 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)
@@ -1023,7 +782,7 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) ||
gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
- nsown_capable(CAP_SETGID)) {
+ ns_capable(old->user_ns, CAP_SETGID)) {
if (!gid_eq(kgid, old->fsgid)) {
new->fsgid = kgid;
goto change_okay;
@@ -1038,12 +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);
@@ -1075,8 +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)
{
@@ -1112,7 +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;
@@ -1214,6 +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;
@@ -1233,7 +1063,7 @@ SYSCALL_DEFINE0(setsid)
goto out;
group_leader->signal->leader = 1;
- __set_special_pids(sid);
+ set_special_pids(sid);
proc_clear_tty(group_leader);
@@ -1262,15 +1092,16 @@ DECLARE_RWSEM(uts_sem);
* 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, int len)
+static int override_release(char __user *release, size_t len)
{
int ret = 0;
- char buf[65];
if (current->personality & UNAME26) {
- char *rest = UTS_RELEASE;
+ const char *rest = UTS_RELEASE;
+ char buf[65] = { 0 };
int ndots = 0;
unsigned v;
+ size_t copy;
while (*rest) {
if (*rest == '.' && ++ndots >= 3)
@@ -1280,8 +1111,9 @@ static int override_release(char __user *release, int len)
rest++;
}
v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
- snprintf(buf, len, "2.6.%u%s", v, rest);
- ret = copy_to_user(release, buf, len);
+ 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;
}
@@ -1378,8 +1210,8 @@ 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);
}
- uts_proc_notify(UTS_PROC_HOSTNAME);
up_write(&uts_sem);
return errno;
}
@@ -1429,8 +1261,8 @@ 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);
}
- uts_proc_notify(UTS_PROC_DOMAINNAME);
up_write(&uts_sem);
return errno;
}
@@ -1699,7 +1531,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
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;
@@ -1725,7 +1557,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
break;
case RUSAGE_SELF:
- thread_group_times(p, &tgutime, &tgstime);
+ thread_group_cputime_adjusted(p, &tgutime, &tgstime);
utime += tgutime;
stime += tgstime;
r->ru_nvcsw += p->signal->nvcsw;
@@ -1739,8 +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:
@@ -1777,84 +1608,125 @@ 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;
}
-#ifdef CONFIG_CHECKPOINT_RESTORE
+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);
- unsigned long vm_req_flags;
- unsigned long vm_bad_flags;
- struct vm_area_struct *vma;
- int error = 0;
struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int error;
- if (arg4 | arg5)
+ if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
return -EINVAL;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
- if (addr >= TASK_SIZE)
+ 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);
- if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
- /* It must be existing VMA */
- if (!vma || vma->vm_start > addr)
- goto out;
- }
-
- error = -EINVAL;
switch (opt) {
case PR_SET_MM_START_CODE:
+ mm->start_code = addr;
+ break;
case PR_SET_MM_END_CODE:
- vm_req_flags = VM_READ | VM_EXEC;
- vm_bad_flags = VM_WRITE | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_CODE)
- mm->start_code = addr;
- else
- mm->end_code = addr;
+ mm->end_code = addr;
break;
-
case PR_SET_MM_START_DATA:
- case PR_SET_MM_END_DATA:
- vm_req_flags = VM_READ | VM_WRITE;
- vm_bad_flags = VM_EXEC | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_DATA)
- mm->start_data = addr;
- else
- mm->end_data = addr;
+ mm->start_data = addr;
break;
-
- case PR_SET_MM_START_STACK:
-
-#ifdef CONFIG_STACK_GROWSUP
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
-#else
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
-#endif
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
- goto out;
-
- mm->start_stack = addr;
+ case PR_SET_MM_END_DATA:
+ mm->end_data = addr;
break;
case PR_SET_MM_START_BRK:
@@ -1881,21 +1753,81 @@ static int prctl_set_mm(int opt, unsigned long addr,
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:
- error = -EINVAL;
goto out;
}
error = 0;
-
out:
up_read(&mm->mmap_sem);
-
return error;
}
-#else /* CONFIG_CHECKPOINT_RESTORE */
-static int prctl_set_mm(int opt, unsigned long addr,
- unsigned long arg4, unsigned long arg5)
+
+#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;
}
@@ -1914,166 +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);
- proc_comm_connector(me);
- 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, (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 =
+ 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;
- break;
- case PR_SET_MM:
- error = prctl_set_mm(arg2, arg3, arg4, arg5);
- break;
- case PR_SET_CHILD_SUBREAPER:
- me->signal->is_child_subreaper = !!arg2;
- error = 0;
- 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;
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;
}
@@ -2090,60 +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);
- info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
- if (info == NULL) {
- argv_free(argv);
+ /*
+ * 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_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);
- ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
+ if (copy_to_user(info, &val, sizeof(struct sysinfo)))
+ return -EFAULT;
- out:
- if (ret && force) {
- printk(KERN_WARNING "Failed to start orderly shutdown: "
- "forcing the issue\n");
+ return 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();
+#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 2025-12-05 20:14:06 +0000