exit.c

	 */
	debug_check_no_locks_held(tsk);
	/*
	 * We can do this unlocked here. The futex code uses this flag
	 * just to verify whether the pi state cleanup has been done
	 * or not. In the worst case it loops once more.
	 */
	tsk->flags |= PF_EXITPIDONE;

	if (tsk->io_context)
		exit_io_context();

	if (tsk->splice_pipe)
		__free_pipe_info(tsk->splice_pipe);

	preempt_disable();
	/* causes final put_task_struct in finish_task_switch(). */
	tsk->state = TASK_DEAD;
	schedule();
	BUG();
	/* Avoid "noreturn function does return".  */
	for (;;)
		cpu_relax();	/* For when BUG is null */
}

EXPORT_SYMBOL_GPL(do_exit);

NORET_TYPE void complete_and_exit(struct completion *comp, long code)
{
	if (comp)
		complete(comp);

	do_exit(code);
}

EXPORT_SYMBOL(complete_and_exit);

SYSCALL_DEFINE1(exit, int, error_code)
{
	do_exit((error_code&0xff)<<8);
}

/*
 * Take down every thread in the group.  This is called by fatal signals
 * as well as by sys_exit_group (below).
 */
NORET_TYPE void
do_group_exit(int exit_code)
{
	struct signal_struct *sig = current->signal;

	BUG_ON(exit_code & 0x80); /* core dumps don't get here */

	if (signal_group_exit(sig))
		exit_code = sig->group_exit_code;
	else if (!thread_group_empty(current)) {
		struct sighand_struct *const sighand = current->sighand;
		spin_lock_irq(&sighand->siglock);
		if (signal_group_exit(sig))
			/* Another thread got here before we took the lock.  */
			exit_code = sig->group_exit_code;
		else {
			sig->group_exit_code = exit_code;
			sig->flags = SIGNAL_GROUP_EXIT;
			zap_other_threads(current);
		}
		spin_unlock_irq(&sighand->siglock);
	}

	do_exit(exit_code);
	/* NOTREACHED */
}

/*
 * this kills every thread in the thread group. Note that any externally
 * wait4()-ing process will get the correct exit code - even if this
 * thread is not the thread group leader.
 */
SYSCALL_DEFINE1(exit_group, int, error_code)
{
	do_group_exit((error_code & 0xff) << 8);
	/* NOTREACHED */
	return 0;
}

static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
	struct pid *pid = NULL;
	if (type == PIDTYPE_PID)
		pid = task->pids[type].pid;
	else if (type < PIDTYPE_MAX)
		pid = task->group_leader->pids[type].pid;
	return pid;
}

static int eligible_child(enum pid_type type, struct pid *pid, int options,
			  struct task_struct *p)
{
	int err;

	if (type < PIDTYPE_MAX) {
		if (task_pid_type(p, type) != pid)
			return 0;
	}

	/* Wait for all children (clone and not) if __WALL is set;
	 * otherwise, wait for clone children *only* if __WCLONE is
	 * set; otherwise, wait for non-clone children *only*.  (Note:
	 * A "clone" child here is one that reports to its parent
	 * using a signal other than SIGCHLD.) */
	if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
	    && !(options & __WALL))
		return 0;

	err = security_task_wait(p);
	if (err)
		return err;

	return 1;
}

static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
			       int why, int status,
			       struct siginfo __user *infop,
			       struct rusage __user *rusagep)
{
	int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;

	put_task_struct(p);
	if (!retval)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval)
		retval = put_user(0, &infop->si_errno);
	if (!retval)
		retval = put_user((short)why, &infop->si_code);
	if (!retval)
		retval = put_user(pid, &infop->si_pid);
	if (!retval)
		retval = put_user(uid, &infop->si_uid);
	if (!retval)
		retval = put_user(status, &infop->si_status);
	if (!retval)
		retval = pid;
	return retval;
}

/*
 * Handle sys_wait4 work for one task in state EXIT_ZOMBIE.  We hold
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_zombie(struct task_struct *p, int options,
			    struct siginfo __user *infop,
			    int __user *stat_addr, struct rusage __user *ru)
{
	unsigned long state;
	int retval, status, traced;
	pid_t pid = task_pid_vnr(p);
	uid_t uid = __task_cred(p)->uid;

	if (!likely(options & WEXITED))
		return 0;

	if (unlikely(options & WNOWAIT)) {
		int exit_code = p->exit_code;
		int why, status;

		get_task_struct(p);
		read_unlock(&tasklist_lock);
		if ((exit_code & 0x7f) == 0) {
			why = CLD_EXITED;
			status = exit_code >> 8;
		} else {
			why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
			status = exit_code & 0x7f;
		}
		return wait_noreap_copyout(p, pid, uid, why,
					   status, infop, ru);
	}

	/*
	 * Try to move the task's state to DEAD
	 * only one thread is allowed to do this:
	 */
	state = xchg(&p->exit_state, EXIT_DEAD);
	if (state != EXIT_ZOMBIE) {
		BUG_ON(state != EXIT_DEAD);
		return 0;
	}

	traced = ptrace_reparented(p);

	if (likely(!traced)) {
		struct signal_struct *psig;
		struct signal_struct *sig;
		struct task_cputime cputime;

		/*
		 * The resource counters for the group leader are in its
		 * own task_struct.  Those for dead threads in the group
		 * are in its signal_struct, as are those for the child
		 * processes it has previously reaped.  All these
		 * accumulate in the parent's signal_struct c* fields.
		 *
		 * We don't bother to take a lock here to protect these
		 * p->signal fields, because they are only touched by
		 * __exit_signal, which runs with tasklist_lock
		 * write-locked anyway, and so is excluded here.  We do
		 * need to protect the access to p->parent->signal fields,
		 * as other threads in the parent group can be right
		 * here reaping other children at the same time.
		 *
		 * We use thread_group_cputime() to get times for the thread
		 * group, which consolidates times for all threads in the
		 * group including the group leader.
		 */
		thread_group_cputime(p, &cputime);
		spin_lock_irq(&p->parent->sighand->siglock);
		psig = p->parent->signal;
		sig = p->signal;
		psig->cutime =
			cputime_add(psig->cutime,
			cputime_add(cputime.utime,
				    sig->cutime));
		psig->cstime =
			cputime_add(psig->cstime,
			cputime_add(cputime.stime,
				    sig->cstime));
		psig->cgtime =
			cputime_add(psig->cgtime,
			cputime_add(p->gtime,
			cputime_add(sig->gtime,
				    sig->cgtime)));
		psig->cmin_flt +=
			p->min_flt + sig->min_flt + sig->cmin_flt;
		psig->cmaj_flt +=
			p->maj_flt + sig->maj_flt + sig->cmaj_flt;
		psig->cnvcsw +=
			p->nvcsw + sig->nvcsw + sig->cnvcsw;
		psig->cnivcsw +=
			p->nivcsw + sig->nivcsw + sig->cnivcsw;
		psig->cinblock +=
			task_io_get_inblock(p) +
			sig->inblock + sig->cinblock;
		psig->coublock +=
			task_io_get_oublock(p) +
			sig->oublock + sig->coublock;
		task_io_accounting_add(&psig->ioac, &p->ioac);
		task_io_accounting_add(&psig->ioac, &sig->ioac);
		spin_unlock_irq(&p->parent->sighand->siglock);
	}

	/*
	 * Now we are sure this task is interesting, and no other
	 * thread can reap it because we set its state to EXIT_DEAD.
	 */
	read_unlock(&tasklist_lock);

	/*
	 * Flush inherited counters to the parent - before the parent
	 * gets woken up by child-exit notifications.
	 */
	perf_counter_exit_task(p);

	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
	status = (p->signal->flags & SIGNAL_GROUP_EXIT)
		? p->signal->group_exit_code : p->exit_code;
	if (!retval && stat_addr)
		retval = put_user(status, stat_addr);
	if (!retval && infop)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval && infop)
		retval = put_user(0, &infop->si_errno);
	if (!retval && infop) {
		int why;

		if ((status & 0x7f) == 0) {
			why = CLD_EXITED;
			status >>= 8;
		} else {
			why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
			status &= 0x7f;
		}
		retval = put_user((short)why, &infop->si_code);
		if (!retval)
			retval = put_user(status, &infop->si_status);
	}
	if (!retval && infop)
		retval = put_user(pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(uid, &infop->si_uid);
	if (!retval)
		retval = pid;

	if (traced) {
		write_lock_irq(&tasklist_lock);
		/* We dropped tasklist, ptracer could die and untrace */
		ptrace_unlink(p);
		/*
		 * If this is not a detached task, notify the parent.
		 * If it's still not detached after that, don't release
		 * it now.
		 */
		if (!task_detached(p)) {
			do_notify_parent(p, p->exit_signal);
			if (!task_detached(p)) {
				p->exit_state = EXIT_ZOMBIE;
				p = NULL;
			}
		}
		write_unlock_irq(&tasklist_lock);
	}
	if (p != NULL)
		release_task(p);

	return retval;
}

static int *task_stopped_code(struct task_struct *p, bool ptrace)
{
	if (ptrace) {
		if (task_is_stopped_or_traced(p))
			return &p->exit_code;
	} else {
		if (p->signal->flags & SIGNAL_STOP_STOPPED)
			return &p->signal->group_exit_code;
	}
	return NULL;
}

/*
 * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_stopped(int ptrace, struct task_struct *p,
			     int options, struct siginfo __user *infop,
			     int __user *stat_addr, struct rusage __user *ru)
{
	int retval, exit_code, *p_code, why;
	uid_t uid = 0; /* unneeded, required by compiler */
	pid_t pid;

	if (!(options & WUNTRACED))
		return 0;

	exit_code = 0;
	spin_lock_irq(&p->sighand->siglock);

	p_code = task_stopped_code(p, ptrace);
	if (unlikely(!p_code))
		goto unlock_sig;

	exit_code = *p_code;
	if (!exit_code)
		goto unlock_sig;

	if (!unlikely(options & WNOWAIT))
		*p_code = 0;

	/* don't need the RCU readlock here as we're holding a spinlock */
	uid = __task_cred(p)->uid;
unlock_sig:
	spin_unlock_irq(&p->sighand->siglock);
	if (!exit_code)
		return 0;

	/*
	 * Now we are pretty sure this task is interesting.
	 * Make sure it doesn't get reaped out from under us while we
	 * give up the lock and then examine it below.  We don't want to
	 * keep holding onto the tasklist_lock while we call getrusage and
	 * possibly take page faults for user memory.
	 */
	get_task_struct(p);
	pid = task_pid_vnr(p);
	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
	read_unlock(&tasklist_lock);

	if (unlikely(options & WNOWAIT))
		return wait_noreap_copyout(p, pid, uid,
					   why, exit_code,
					   infop, ru);

	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
	if (!retval && stat_addr)
		retval = put_user((exit_code << 8) | 0x7f, stat_addr);
	if (!retval && infop)
		retval = put_user(SIGCHLD, &infop->si_signo);
	if (!retval && infop)
		retval = put_user(0, &infop->si_errno);
	if (!retval && infop)
		retval = put_user((short)why, &infop->si_code);
	if (!retval && infop)
		retval = put_user(exit_code, &infop->si_status);
	if (!retval && infop)
		retval = put_user(pid, &infop->si_pid);
	if (!retval && infop)
		retval = put_user(uid, &infop->si_uid);
	if (!retval)
		retval = pid;
	put_task_struct(p);

	BUG_ON(!retval);
	return retval;
}

/*
 * Handle do_wait work for one task in a live, non-stopped state.
 * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
 * the lock and this task is uninteresting.  If we return nonzero, we have
 * released the lock and the system call should return.
 */
static int wait_task_continued(struct task_struct *p, int options,
			       struct siginfo __user *infop,
			       int __user *stat_addr, struct rusage __user *ru)
{
	int retval;
	pid_t pid;
	uid_t uid;

	if (!unlikely(options & WCONTINUED))
		return 0;

	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
		return 0;

	spin_lock_irq(&p->sighand->siglock);
	/* Re-check with the lock held.  */
	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
		spin_unlock_irq(&p->sighand->siglock);
		return 0;
	}
	if (!unlikely(options & WNOWAIT))
		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
	uid = __task_cred(p)->uid;
	spin_unlock_irq(&p->sighand->siglock);

	pid = task_pid_vnr(p);
	get_task_struct(p);
	read_unlock(&tasklist_lock);

	if (!infop) {
		retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
		put_task_struct(p);
		if (!retval && stat_addr)
			retval = put_user(0xffff, stat_addr);
		if (!retval)
			retval = pid;
	} else {
		retval = wait_noreap_copyout(p, pid, uid,
					     CLD_CONTINUED, SIGCONT,
					     infop, ru);
		BUG_ON(retval == 0);
	}

	return retval;
}

/*
 * Consider @p for a wait by @parent.
 *
 * -ECHILD should be in *@notask_error before the first call.
 * Returns nonzero for a final return, when we have unlocked tasklist_lock.
 * Returns zero if the search for a child should continue;
 * then *@notask_error is 0 if @p is an eligible child,
 * or another error from security_task_wait(), or still -ECHILD.
 */
static int wait_consider_task(struct task_struct *parent, int ptrace,
			      struct task_struct *p, int *notask_error,
			      enum pid_type type, struct pid *pid, int options,
			      struct siginfo __user *infop,
			      int __user *stat_addr, struct rusage __user *ru)
{
	int ret = eligible_child(type, pid, options, p);
	if (!ret)
		return ret;

	if (unlikely(ret < 0)) {
		/*
		 * If we have not yet seen any eligible child,
		 * then let this error code replace -ECHILD.
		 * A permission error will give the user a clue
		 * to look for security policy problems, rather
		 * than for mysterious wait bugs.
		 */
		if (*notask_error)
			*notask_error = ret;
	}

	if (likely(!ptrace) && unlikely(p->ptrace)) {
		/*
		 * This child is hidden by ptrace.
		 * We aren't allowed to see it now, but eventually we will.
		 */
		*notask_error = 0;
		return 0;
	}

	if (p->exit_state == EXIT_DEAD)
		return 0;

	/*
	 * We don't reap group leaders with subthreads.
	 */
	if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
		return wait_task_zombie(p, options, infop, stat_addr, ru);

	/*
	 * It's stopped or running now, so it might
	 * later continue, exit, or stop again.
	 */
	*notask_error = 0;

	if (task_stopped_code(p, ptrace))
		return wait_task_stopped(ptrace, p, options,
					 infop, stat_addr, ru);

	return wait_task_continued(p, options, infop, stat_addr, ru);
}

/*
 * Do the work of do_wait() for one thread in the group, @tsk.
 *
 * -ECHILD should be in *@notask_error before the first call.
 * Returns nonzero for a final return, when we have unlocked tasklist_lock.
 * Returns zero if the search for a child should continue; then
 * *@notask_error is 0 if there were any eligible children,
 * or another error from security_task_wait(), or still -ECHILD.
 */
static int do_wait_thread(struct task_struct *tsk, int *notask_error,
			  enum pid_type type, struct pid *pid, int options,
			  struct siginfo __user *infop, int __user *stat_addr,
			  struct rusage __user *ru)
{
	struct task_struct *p;

	list_for_each_entry(p, &tsk->children, sibling) {
		/*
		 * Do not consider detached threads.
		 */
		if (!task_detached(p)) {
			int ret = wait_consider_task(tsk, 0, p, notask_error,
						     type, pid, options,
						     infop, stat_addr, ru);
			if (ret)
				return ret;
		}
	}

	return 0;
}

static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
			  enum pid_type type, struct pid *pid, int options,
			  struct siginfo __user *infop, int __user *stat_addr,
			  struct rusage __user *ru)
{
	struct task_struct *p;

	/*
	 * Traditionally we see ptrace'd stopped tasks regardless of options.
	 */
	options |= WUNTRACED;

	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
		int ret = wait_consider_task(tsk, 1, p, notask_error,
					     type, pid, options,
					     infop, stat_addr, ru);
		if (ret)
			return ret;
	}

	return 0;
}

static long do_wait(enum pid_type type, struct pid *pid, int options,
		    struct siginfo __user *infop, int __user *stat_addr,
		    struct rusage __user *ru)
{
	DECLARE_WAITQUEUE(wait, current);
	struct task_struct *tsk;
	int retval;

	trace_sched_process_wait(pid);

	add_wait_queue(&current->signal->wait_chldexit,&wait);
repeat:
	/*
	 * If there is nothing that can match our critiera just get out.
	 * We will clear @retval to zero if we see any child that might later
	 * match our criteria, even if we are not able to reap it yet.
	 */
	retval = -ECHILD;
	if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
		goto end;

	current->state = TASK_INTERRUPTIBLE;
	read_lock(&tasklist_lock);
	tsk = current;
	do {
		int tsk_result = do_wait_thread(tsk, &retval,
						type, pid, options,
						infop, stat_addr, ru);
		if (!tsk_result)
			tsk_result = ptrace_do_wait(tsk, &retval,
						    type, pid, options,
						    infop, stat_addr, ru);
		if (tsk_result) {
			/*
			 * tasklist_lock is unlocked and we have a final result.
			 */
			retval = tsk_result;
			goto end;
		}

		if (options & __WNOTHREAD)
			break;
		tsk = next_thread(tsk);
		BUG_ON(tsk->signal != current->signal);
	} while (tsk != current);
	read_unlock(&tasklist_lock);

	if (!retval && !(options & WNOHANG)) {
		retval = -ERESTARTSYS;
		if (!signal_pending(current)) {
			schedule();
			goto repeat;
		}
	}

end:
	current->state = TASK_RUNNING;
	remove_wait_queue(&current->signal->wait_chldexit,&wait);
	if (infop) {
		if (retval > 0)
			retval = 0;
		else {
			/*
			 * For a WNOHANG return, clear out all the fields
			 * we would set so the user can easily tell the
			 * difference.
			 */
			if (!retval)
				retval = put_user(0, &infop->si_signo);
			if (!retval)
				retval = put_user(0, &infop->si_errno);
			if (!retval)
				retval = put_user(0, &infop->si_code);
			if (!retval)
				retval = put_user(0, &infop->si_pid);
			if (!retval)
				retval = put_user(0, &infop->si_uid);
			if (!retval)
				retval = put_user(0, &infop->si_status);
		}
	}
	return retval;
}

SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
		infop, int, options, struct rusage __user *, ru)
{
	struct pid *pid = NULL;
	enum pid_type type;
	long ret;

	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
		return -EINVAL;
	if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
		return -EINVAL;

	switch (which) {
	case P_ALL:
		type = PIDTYPE_MAX;
		break;
	case P_PID:
		type = PIDTYPE_PID;
		if (upid <= 0)
			return -EINVAL;
		break;
	case P_PGID:
		type = PIDTYPE_PGID;
		if (upid <= 0)
			return -EINVAL;
		break;
	default:
		return -EINVAL;
	}

	if (type < PIDTYPE_MAX)
		pid = find_get_pid(upid);
	ret = do_wait(type, pid, options, infop, NULL, ru);
	put_pid(pid);

	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(5, ret, which, upid, infop, options, ru);
	return ret;
}

SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
		int, options, struct rusage __user *, ru)
{
	struct pid *pid = NULL;
	enum pid_type type;
	long ret;

	if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
			__WNOTHREAD|__WCLONE|__WALL))
		return -EINVAL;

	if (upid == -1)
		type = PIDTYPE_MAX;
	else if (upid < 0) {
		type = PIDTYPE_PGID;
		pid = find_get_pid(-upid);
	} else if (upid == 0) {
		type = PIDTYPE_PGID;
		pid = get_task_pid(current, PIDTYPE_PGID);
	} else /* upid > 0 */ {
		type = PIDTYPE_PID;
		pid = find_get_pid(upid);
	}

	ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
	put_pid(pid);

	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(4, ret, upid, stat_addr, options, ru);
	return ret;
}

#ifdef __ARCH_WANT_SYS_WAITPID

/*
 * sys_waitpid() remains for compatibility. waitpid() should be
 * implemented by calling sys_wait4() from libc.a.
 */
SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
{
	return sys_wait4(pid, stat_addr, options, NULL);
}

#endif