* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
-#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/tty.h>
#include <linux/signal.h>
#include <linux/cn_proc.h>
+#include <linux/getcpu.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#ifndef GET_FPEXC_CTL
# define GET_FPEXC_CTL(a,b) (-EINVAL)
#endif
+#ifndef GET_ENDIAN
+# define GET_ENDIAN(a,b) (-EINVAL)
+#endif
+#ifndef SET_ENDIAN
+# define SET_ENDIAN(a,b) (-EINVAL)
+#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
unsigned long val, void *v)
{
int ret = NOTIFY_DONE;
- struct notifier_block *nb;
+ struct notifier_block *nb, *next_nb;
nb = rcu_dereference(*nl);
while (nb) {
+ next_nb = rcu_dereference(nb->next);
ret = nb->notifier_call(nb, val, v);
if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK)
break;
- nb = rcu_dereference(nb->next);
+ nb = next_nb;
}
return ret;
}
}
EXPORT_SYMBOL_GPL(emergency_restart);
-void kernel_restart_prepare(char *cmd)
+static void kernel_restart_prepare(char *cmd)
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
- if (!cmd) {
+ if (!cmd)
printk(KERN_EMERG "Restarting system.\n");
- } else {
+ else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
- }
- printk(".\n");
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.
*/
-void kernel_kexec(void)
+static void kernel_kexec(void)
{
#ifdef CONFIG_KEXEC
struct kimage *image;
image = xchg(&kexec_image, NULL);
- if (!image) {
+ if (!image)
return;
- }
kernel_restart_prepare(NULL);
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
machine_kexec(image);
#endif
}
-EXPORT_SYMBOL_GPL(kernel_kexec);
void kernel_shutdown_prepare(enum system_states state)
{
(current->sgid == egid) ||
capable(CAP_SETGID))
new_egid = egid;
- else {
+ else
return -EPERM;
- }
}
- if (new_egid != old_egid)
- {
+ if (new_egid != old_egid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
if (retval)
return retval;
- if (capable(CAP_SETGID))
- {
- if(old_egid != gid)
- {
+ if (capable(CAP_SETGID)) {
+ if (old_egid != gid) {
current->mm->dumpable = 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)
- {
+ } else if ((gid == current->gid) || (gid == current->sgid)) {
+ if (old_egid != gid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
switch_uid(new_user);
- if(dumpclear)
- {
+ if (dumpclear) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
return -EAGAIN;
- if (new_euid != old_euid)
- {
+ if (new_euid != old_euid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
} else if ((uid != current->uid) && (uid != new_suid))
return -EPERM;
- if (old_euid != uid)
- {
+ if (old_euid != uid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
return -EAGAIN;
}
if (euid != (uid_t) -1) {
- if (euid != current->euid)
- {
+ if (euid != current->euid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
return -EPERM;
}
if (egid != (gid_t) -1) {
- if (egid != current->egid)
- {
+ if (egid != current->egid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
if (uid == current->uid || uid == current->euid ||
uid == current->suid || uid == current->fsuid ||
- capable(CAP_SETUID))
- {
- if (uid != old_fsuid)
- {
+ capable(CAP_SETUID)) {
+ if (uid != old_fsuid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
if (gid == current->gid || gid == current->egid ||
gid == current->sgid || gid == current->fsgid ||
- capable(CAP_SETGID))
- {
- if (gid != old_fsgid)
- {
+ capable(CAP_SETGID)) {
+ if (gid != old_fsgid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
asmlinkage long sys_getpgid(pid_t pid)
{
- if (!pid) {
+ if (!pid)
return process_group(current);
- } else {
+ else {
int retval;
struct task_struct *p;
asmlinkage long sys_getsid(pid_t pid)
{
- if (!pid) {
+ if (!pid)
return current->signal->session;
- } else {
+ else {
int retval;
struct task_struct *p;
p = find_task_by_pid(pid);
retval = -ESRCH;
- if(p) {
+ if (p) {
retval = security_task_getsid(p);
if (!retval)
retval = p->signal->session;
group_info->nblocks = nblocks;
atomic_set(&group_info->usage, 1);
- if (gidsetsize <= NGROUPS_SMALL) {
+ if (gidsetsize <= NGROUPS_SMALL)
group_info->blocks[0] = group_info->small_block;
- } else {
+ else {
for (i = 0; i < nblocks; i++) {
gid_t *b;
b = (void *)__get_free_page(GFP_USER);
/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
- {
+{
int i;
int count = group_info->ngroups;
int in_group_p(gid_t grp)
{
int retval = 1;
- if (grp != current->fsgid) {
+ if (grp != current->fsgid)
retval = groups_search(current->group_info, grp);
- }
return retval;
}
int in_egroup_p(gid_t grp)
{
int retval = 1;
- if (grp != current->egid) {
+ if (grp != current->egid)
retval = groups_search(current->group_info, grp);
- }
return retval;
}
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
- if(x.rlim_cur > 0x7FFFFFFF)
+ if (x.rlim_cur > 0x7FFFFFFF)
x.rlim_cur = 0x7FFFFFFF;
- if(x.rlim_max > 0x7FFFFFFF)
+ if (x.rlim_max > 0x7FFFFFFF)
x.rlim_max = 0x7FFFFFFF;
return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}
* fields when reaping, so a sample either gets all the additions of a
* given child after it's reaped, or none so this sample is before reaping.
*
- * tasklist_lock locking optimisation:
- * If we are current and single threaded, we do not need to take the tasklist
- * lock or the siglock. No one else can take our signal_struct away,
- * no one else can reap the children to update signal->c* counters, and
- * no one else can race with the signal-> fields.
- * If we do not take the tasklist_lock, the signal-> fields could be read
- * out of order while another thread was just exiting. So we place a
- * read memory barrier when we avoid the lock. On the writer side,
- * write memory barrier is implied in __exit_signal as __exit_signal releases
- * the siglock spinlock after updating the signal-> fields.
- *
- * We don't really need the siglock when we access the non c* fields
- * of the signal_struct (for RUSAGE_SELF) even in multithreaded
- * case, since we take the tasklist lock for read and the non c* signal->
- * fields are updated only in __exit_signal, which is called with
- * tasklist_lock taken for write, hence these two threads cannot execute
- * concurrently.
+ * Locking:
+ * We need to take the siglock for CHILDEREN, SELF and BOTH
+ * for the cases current multithreaded, non-current single threaded
+ * non-current multithreaded. Thread traversal is now safe with
+ * the siglock held.
+ * Strictly speaking, we donot need to take the siglock if we are current and
+ * single threaded, as no one else can take our signal_struct away, no one
+ * else can reap the children to update signal->c* counters, and no one else
+ * can race with the signal-> fields. If we do not take any lock, the
+ * signal-> fields could be read out of order while another thread was just
+ * exiting. So we should place a read memory barrier when we avoid the lock.
+ * On the writer side, write memory barrier is implied in __exit_signal
+ * as __exit_signal releases the siglock spinlock after updating the signal->
+ * fields. But we don't do this yet to keep things simple.
*
*/
struct task_struct *t;
unsigned long flags;
cputime_t utime, stime;
- int need_lock = 0;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
- if (p != current || !thread_group_empty(p))
- need_lock = 1;
-
- if (need_lock) {
- read_lock(&tasklist_lock);
- if (unlikely(!p->signal)) {
- read_unlock(&tasklist_lock);
- return;
- }
- } else
- /* See locking comments above */
- smp_rmb();
+ rcu_read_lock();
+ if (!lock_task_sighand(p, &flags)) {
+ rcu_read_unlock();
+ return;
+ }
switch (who) {
case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
- spin_lock_irqsave(&p->sighand->siglock, flags);
utime = p->signal->cutime;
stime = p->signal->cstime;
r->ru_nvcsw = p->signal->cnvcsw;
r->ru_nivcsw = p->signal->cnivcsw;
r->ru_minflt = p->signal->cmin_flt;
r->ru_majflt = p->signal->cmaj_flt;
- spin_unlock_irqrestore(&p->sighand->siglock, flags);
if (who == RUSAGE_CHILDREN)
break;
BUG();
}
- if (need_lock)
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(p, &flags);
+ rcu_read_unlock();
+
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
}
error = current->mm->dumpable;
break;
case PR_SET_DUMPABLE:
- if (arg2 < 0 || arg2 > 2) {
+ if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
return -EFAULT;
return 0;
}
+ case PR_GET_ENDIAN:
+ error = GET_ENDIAN(current, arg2);
+ break;
+ case PR_SET_ENDIAN:
+ error = SET_ENDIAN(current, arg2);
+ break;
+
default:
error = -EINVAL;
break;
}
return error;
}
+
+asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
+ struct getcpu_cache __user *cache)
+{
+ int err = 0;
+ int cpu = raw_smp_processor_id();
+ if (cpup)
+ err |= put_user(cpu, cpup);
+ if (nodep)
+ err |= put_user(cpu_to_node(cpu), nodep);
+ if (cache) {
+ /*
+ * The cache is not needed for this implementation,
+ * but make sure user programs pass something
+ * valid. vsyscall implementations can instead make
+ * good use of the cache. Only use t0 and t1 because
+ * these are available in both 32bit and 64bit ABI (no
+ * need for a compat_getcpu). 32bit has enough
+ * padding
+ */
+ unsigned long t0, t1;
+ get_user(t0, &cache->blob[0]);
+ get_user(t1, &cache->blob[1]);
+ t0++;
+ t1++;
+ put_user(t0, &cache->blob[0]);
+ put_user(t1, &cache->blob[1]);
+ }
+ return err ? -EFAULT : 0;
+}