#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
* and the like.
*/
-static struct notifier_block *reboot_notifier_list;
-static DEFINE_RWLOCK(notifier_lock);
+static BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
+
+/*
+ * Notifier chain core routines. The exported routines below
+ * are layered on top of these, with appropriate locking added.
+ */
+
+static int notifier_chain_register(struct notifier_block **nl,
+ struct notifier_block *n)
+{
+ while ((*nl) != NULL) {
+ if (n->priority > (*nl)->priority)
+ break;
+ nl = &((*nl)->next);
+ }
+ n->next = *nl;
+ rcu_assign_pointer(*nl, n);
+ return 0;
+}
+
+static int notifier_chain_unregister(struct notifier_block **nl,
+ struct notifier_block *n)
+{
+ while ((*nl) != NULL) {
+ if ((*nl) == n) {
+ rcu_assign_pointer(*nl, n->next);
+ return 0;
+ }
+ nl = &((*nl)->next);
+ }
+ return -ENOENT;
+}
+
+static int __kprobes notifier_call_chain(struct notifier_block **nl,
+ unsigned long val, void *v)
+{
+ int ret = NOTIFY_DONE;
+ struct notifier_block *nb;
+
+ nb = rcu_dereference(*nl);
+ while (nb) {
+ ret = nb->notifier_call(nb, val, v);
+ if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK)
+ break;
+ nb = rcu_dereference(nb->next);
+ }
+ return ret;
+}
+
+/*
+ * Atomic notifier chain routines. Registration and unregistration
+ * use a mutex, and call_chain is synchronized by RCU (no locks).
+ */
/**
- * notifier_chain_register - Add notifier to a notifier chain
- * @list: Pointer to root list pointer
+ * atomic_notifier_chain_register - Add notifier to an atomic notifier chain
+ * @nh: Pointer to head of the atomic notifier chain
* @n: New entry in notifier chain
*
- * Adds a notifier to a notifier chain.
+ * Adds a notifier to an atomic notifier chain.
*
* Currently always returns zero.
*/
+
+int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
+ struct notifier_block *n)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&nh->lock, flags);
+ ret = notifier_chain_register(&nh->head, n);
+ spin_unlock_irqrestore(&nh->lock, flags);
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
+
+/**
+ * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
+ * @nh: Pointer to head of the atomic notifier chain
+ * @n: Entry to remove from notifier chain
+ *
+ * Removes a notifier from an atomic notifier chain.
+ *
+ * Returns zero on success or %-ENOENT on failure.
+ */
+int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
+ struct notifier_block *n)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&nh->lock, flags);
+ ret = notifier_chain_unregister(&nh->head, n);
+ spin_unlock_irqrestore(&nh->lock, flags);
+ synchronize_rcu();
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
+
+/**
+ * atomic_notifier_call_chain - Call functions in an atomic notifier chain
+ * @nh: Pointer to head of the atomic notifier chain
+ * @val: Value passed unmodified to notifier function
+ * @v: Pointer passed unmodified to notifier function
+ *
+ * Calls each function in a notifier chain in turn. The functions
+ * run in an atomic context, so they must not block.
+ * This routine uses RCU to synchronize with changes to the chain.
+ *
+ * If the return value of the notifier can be and'ed
+ * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain
+ * will return immediately, with the return value of
+ * the notifier function which halted execution.
+ * Otherwise the return value is the return value
+ * of the last notifier function called.
+ */
-int notifier_chain_register(struct notifier_block **list, struct notifier_block *n)
+int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+ unsigned long val, void *v)
{
- write_lock(¬ifier_lock);
- while(*list)
- {
- if(n->priority > (*list)->priority)
- break;
- list= &((*list)->next);
- }
- n->next = *list;
- *list=n;
- write_unlock(¬ifier_lock);
- return 0;
+ int ret;
+
+ rcu_read_lock();
+ ret = notifier_call_chain(&nh->head, val, v);
+ rcu_read_unlock();
+ return ret;
}
-EXPORT_SYMBOL(notifier_chain_register);
+EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
+
+/*
+ * Blocking notifier chain routines. All access to the chain is
+ * synchronized by an rwsem.
+ */
/**
- * notifier_chain_unregister - Remove notifier from a notifier chain
- * @nl: Pointer to root list pointer
+ * blocking_notifier_chain_register - Add notifier to a blocking notifier chain
+ * @nh: Pointer to head of the blocking notifier chain
* @n: New entry in notifier chain
*
- * Removes a notifier from a notifier chain.
+ * Adds a notifier to a blocking notifier chain.
+ * Must be called in process context.
*
- * Returns zero on success, or %-ENOENT on failure.
+ * Currently always returns zero.
*/
-int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n)
+int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
+ struct notifier_block *n)
{
- write_lock(¬ifier_lock);
- while((*nl)!=NULL)
- {
- if((*nl)==n)
- {
- *nl=n->next;
- write_unlock(¬ifier_lock);
- return 0;
- }
- nl=&((*nl)->next);
- }
- write_unlock(¬ifier_lock);
- return -ENOENT;
+ int ret;
+
+ /*
+ * This code gets used during boot-up, when task switching is
+ * not yet working and interrupts must remain disabled. At
+ * such times we must not call down_write().
+ */
+ if (unlikely(system_state == SYSTEM_BOOTING))
+ return notifier_chain_register(&nh->head, n);
+
+ down_write(&nh->rwsem);
+ ret = notifier_chain_register(&nh->head, n);
+ up_write(&nh->rwsem);
+ return ret;
}
-EXPORT_SYMBOL(notifier_chain_unregister);
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
/**
- * notifier_call_chain - Call functions in a notifier chain
- * @n: Pointer to root pointer of notifier chain
+ * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
+ * @nh: Pointer to head of the blocking notifier chain
+ * @n: Entry to remove from notifier chain
+ *
+ * Removes a notifier from a blocking notifier chain.
+ * Must be called from process context.
+ *
+ * Returns zero on success or %-ENOENT on failure.
+ */
+int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
+ struct notifier_block *n)
+{
+ int ret;
+
+ /*
+ * This code gets used during boot-up, when task switching is
+ * not yet working and interrupts must remain disabled. At
+ * such times we must not call down_write().
+ */
+ if (unlikely(system_state == SYSTEM_BOOTING))
+ return notifier_chain_unregister(&nh->head, n);
+
+ down_write(&nh->rwsem);
+ ret = notifier_chain_unregister(&nh->head, n);
+ up_write(&nh->rwsem);
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
+
+/**
+ * blocking_notifier_call_chain - Call functions in a blocking notifier chain
+ * @nh: Pointer to head of the blocking notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
- * Calls each function in a notifier chain in turn.
+ * Calls each function in a notifier chain in turn. The functions
+ * run in a process context, so they are allowed to block.
*
- * If the return value of the notifier can be and'd
- * with %NOTIFY_STOP_MASK, then notifier_call_chain
+ * If the return value of the notifier can be and'ed
+ * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain
* will return immediately, with the return value of
* the notifier function which halted execution.
- * Otherwise, the return value is the return value
+ * Otherwise the return value is the return value
* of the last notifier function called.
*/
-int __kprobes notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
+int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
+ unsigned long val, void *v)
{
- int ret=NOTIFY_DONE;
- struct notifier_block *nb = *n;
+ int ret;
- while(nb)
- {
- ret=nb->notifier_call(nb,val,v);
- if(ret&NOTIFY_STOP_MASK)
- {
- return ret;
- }
- nb=nb->next;
- }
+ down_read(&nh->rwsem);
+ ret = notifier_call_chain(&nh->head, val, v);
+ up_read(&nh->rwsem);
return ret;
}
-EXPORT_SYMBOL(notifier_call_chain);
+EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
+
+/*
+ * Raw notifier chain routines. There is no protection;
+ * the caller must provide it. Use at your own risk!
+ */
+
+/**
+ * raw_notifier_chain_register - Add notifier to a raw notifier chain
+ * @nh: Pointer to head of the raw notifier chain
+ * @n: New entry in notifier chain
+ *
+ * Adds a notifier to a raw notifier chain.
+ * All locking must be provided by the caller.
+ *
+ * Currently always returns zero.
+ */
+
+int raw_notifier_chain_register(struct raw_notifier_head *nh,
+ struct notifier_block *n)
+{
+ return notifier_chain_register(&nh->head, n);
+}
+
+EXPORT_SYMBOL_GPL(raw_notifier_chain_register);
+
+/**
+ * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain
+ * @nh: Pointer to head of the raw notifier chain
+ * @n: Entry to remove from notifier chain
+ *
+ * Removes a notifier from a raw notifier chain.
+ * All locking must be provided by the caller.
+ *
+ * Returns zero on success or %-ENOENT on failure.
+ */
+int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
+ struct notifier_block *n)
+{
+ return notifier_chain_unregister(&nh->head, n);
+}
+
+EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
+
+/**
+ * raw_notifier_call_chain - Call functions in a raw notifier chain
+ * @nh: Pointer to head of the raw notifier chain
+ * @val: Value passed unmodified to notifier function
+ * @v: Pointer passed unmodified to notifier function
+ *
+ * Calls each function in a notifier chain in turn. The functions
+ * run in an undefined context.
+ * All locking must be provided by the caller.
+ *
+ * If the return value of the notifier can be and'ed
+ * with %NOTIFY_STOP_MASK then raw_notifier_call_chain
+ * will return immediately, with the return value of
+ * the notifier function which halted execution.
+ * Otherwise the return value is the return value
+ * of the last notifier function called.
+ */
+
+int raw_notifier_call_chain(struct raw_notifier_head *nh,
+ unsigned long val, void *v)
+{
+ return notifier_call_chain(&nh->head, val, v);
+}
+
+EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
/**
* register_reboot_notifier - Register function to be called at reboot time
* Registers a function with the list of functions
* to be called at reboot time.
*
- * Currently always returns zero, as notifier_chain_register
+ * Currently always returns zero, as blocking_notifier_chain_register
* always returns zero.
*/
int register_reboot_notifier(struct notifier_block * nb)
{
- return notifier_chain_register(&reboot_notifier_list, nb);
+ return blocking_notifier_chain_register(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(register_reboot_notifier);
int unregister_reboot_notifier(struct notifier_block * nb)
{
- return notifier_chain_unregister(&reboot_notifier_list, nb);
+ return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(unregister_reboot_notifier);
-#ifndef CONFIG_SECURITY
-int capable(int cap)
-{
- if (cap_raised(current->cap_effective, cap)) {
- current->flags |= PF_SUPERPRIV;
- return 1;
- }
- return 0;
-}
-EXPORT_SYMBOL(capable);
-#endif
-
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
int no_nice;
void kernel_restart_prepare(char *cmd)
{
- notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
+ blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
device_shutdown();
}
void kernel_shutdown_prepare(enum system_states state)
{
- notifier_call_chain(&reboot_notifier_list,
+ blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
system_state = state;
device_shutdown();
*/
if (tbuf) {
struct tms tmp;
+ struct task_struct *tsk = current;
+ struct task_struct *t;
cputime_t utime, stime, cutime, cstime;
-#ifdef CONFIG_SMP
- if (thread_group_empty(current)) {
- /*
- * Single thread case without the use of any locks.
- *
- * We may race with release_task if two threads are
- * executing. However, release task first adds up the
- * counters (__exit_signal) before removing the task
- * from the process tasklist (__unhash_process).
- * __exit_signal also acquires and releases the
- * siglock which results in the proper memory ordering
- * so that the list modifications are always visible
- * after the counters have been updated.
- *
- * If the counters have been updated by the second thread
- * but the thread has not yet been removed from the list
- * then the other branch will be executing which will
- * block on tasklist_lock until the exit handling of the
- * other task is finished.
- *
- * This also implies that the sighand->siglock cannot
- * be held by another processor. So we can also
- * skip acquiring that lock.
- */
- utime = cputime_add(current->signal->utime, current->utime);
- stime = cputime_add(current->signal->utime, current->stime);
- cutime = current->signal->cutime;
- cstime = current->signal->cstime;
- } else
-#endif
- {
-
- /* Process with multiple threads */
- struct task_struct *tsk = current;
- struct task_struct *t;
+ 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);
- read_lock(&tasklist_lock);
- 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);
- /*
- * While we have tasklist_lock read-locked, no dying thread
- * can be updating current->signal->[us]time. Instead,
- * we got their counts included in the live thread loop.
- * However, another thread can come in right now and
- * do a wait call that updates current->signal->c[us]time.
- * To make sure we always see that pair updated atomically,
- * we take the siglock around fetching them.
- */
- spin_lock_irq(&tsk->sighand->siglock);
- cutime = tsk->signal->cutime;
- cstime = tsk->signal->cstime;
- spin_unlock_irq(&tsk->sighand->siglock);
- read_unlock(&tasklist_lock);
- }
tmp.tms_utime = cputime_to_clock_t(utime);
tmp.tms_stime = cputime_to_clock_t(stime);
tmp.tms_cutime = cputime_to_clock_t(cutime);
asmlinkage long sys_setsid(void)
{
struct task_struct *group_leader = current->group_leader;
- struct pid *pid;
+ pid_t session;
int err = -EPERM;
mutex_lock(&tty_mutex);
write_lock_irq(&tasklist_lock);
- pid = find_pid(PIDTYPE_PGID, group_leader->pid);
- if (pid)
+ /* Fail if I am already a session leader */
+ if (group_leader->signal->leader)
+ goto out;
+
+ session = group_leader->pid;
+ /* Fail if a process group id already exists that equals the
+ * proposed session id.
+ *
+ * Don't check if session id == 1 because kernel threads use this
+ * session id and so the check will always fail and make it so
+ * init cannot successfully call setsid.
+ */
+ if (session > 1 && find_task_by_pid_type(PIDTYPE_PGID, session))
goto out;
group_leader->signal->leader = 1;
- __set_special_pids(group_leader->pid, group_leader->pid);
+ __set_special_pids(session, session);
group_leader->signal->tty = NULL;
group_leader->signal->tty_old_pgrp = 0;
err = process_group(group_leader);
/* a simple bsearch */
int groups_search(struct group_info *group_info, gid_t grp)
{
- int left, right;
+ unsigned int left, right;
if (!group_info)
return 0;
left = 0;
right = group_info->ngroups;
while (left < right) {
- int mid = (left+right)/2;
+ unsigned int mid = (left+right)/2;
int cmp = grp - GROUP_AT(group_info, mid);
if (cmp > 0)
left = mid + 1;
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
- get_group_info(current->group_info);
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
}
}
out:
- put_group_info(current->group_info);
return i;
}
{
int retval = 1;
if (grp != current->fsgid) {
- get_group_info(current->group_info);
retval = groups_search(current->group_info, grp);
- put_group_info(current->group_info);
}
return retval;
}
{
int retval = 1;
if (grp != current->egid) {
- get_group_info(current->group_info);
retval = groups_search(current->group_info, grp);
- put_group_info(current->group_info);
}
return retval;
}
if (resource != RLIMIT_CPU)
goto out;
+
+ /*
+ * RLIMIT_CPU handling. Note that the kernel fails to return an error
+ * code if it rejected the user's attempt to set RLIMIT_CPU. This is a
+ * 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;
* 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);
}
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;