exit.c

/*
 *  linux/kernel/exit.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
#include <linux/mnt_namespace.h>
#include <linux/key.h>
#include <linux/security.h>
#include <linux/cpu.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/file.h>
#include <linux/binfmts.h>
#include <linux/nsproxy.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
#include <linux/kthread.h>
#include <linux/mempolicy.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/freezer.h>
#include <linux/cgroup.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/posix-timers.h>
#include <linux/cn_proc.h>
#include <linux/mutex.h>
#include <linux/futex.h>
#include <linux/compat.h>
#include <linux/pipe_fs_i.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/blkdev.h>
#include <linux/task_io_accounting_ops.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>

extern void sem_exit (void);

static void exit_mm(struct task_struct * tsk);

static void __unhash_process(struct task_struct *p)
{
	nr_threads--;
	detach_pid(p, PIDTYPE_PID);
	if (thread_group_leader(p)) {
		detach_pid(p, PIDTYPE_PGID);
		detach_pid(p, PIDTYPE_SID);

		list_del_rcu(&p->tasks);
		__get_cpu_var(process_counts)--;
	}
	list_del_rcu(&p->thread_group);
	remove_parent(p);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
static void __exit_signal(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;
	struct sighand_struct *sighand;

	BUG_ON(!sig);
	BUG_ON(!atomic_read(&sig->count));

	rcu_read_lock();
	sighand = rcu_dereference(tsk->sighand);
	spin_lock(&sighand->siglock);

	posix_cpu_timers_exit(tsk);
	if (atomic_dec_and_test(&sig->count))
		posix_cpu_timers_exit_group(tsk);
	else {
		/*
		 * If there is any task waiting for the group exit
		 * then notify it:
		 */
		if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count)
			wake_up_process(sig->group_exit_task);

		if (tsk == sig->curr_target)
			sig->curr_target = next_thread(tsk);
		/*
		 * Accumulate here the counters for all threads but the
		 * group leader as they die, so they can be added into
		 * the process-wide totals when those are taken.
		 * The group leader stays around as a zombie as long
		 * as there are other threads.  When it gets reaped,
		 * the exit.c code will add its counts into these totals.
		 * We won't ever get here for the group leader, since it
		 * will have been the last reference on the signal_struct.
		 */
		sig->utime = cputime_add(sig->utime, tsk->utime);
		sig->stime = cputime_add(sig->stime, tsk->stime);
		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
		sig->min_flt += tsk->min_flt;
		sig->maj_flt += tsk->maj_flt;
		sig->nvcsw += tsk->nvcsw;
		sig->nivcsw += tsk->nivcsw;
		sig->inblock += task_io_get_inblock(tsk);
		sig->oublock += task_io_get_oublock(tsk);
		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
		sig = NULL; /* Marker for below. */
	}

	__unhash_process(tsk);

	tsk->signal = NULL;
	tsk->sighand = NULL;
	spin_unlock(&sighand->siglock);
	rcu_read_unlock();

	__cleanup_sighand(sighand);
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	flush_sigqueue(&tsk->pending);
	if (sig) {
		flush_sigqueue(&sig->shared_pending);
		taskstats_tgid_free(sig);
		__cleanup_signal(sig);
	}
}

static void delayed_put_task_struct(struct rcu_head *rhp)
{
	put_task_struct(container_of(rhp, struct task_struct, rcu));
}

void release_task(struct task_struct * p)
{
	struct task_struct *leader;
	int zap_leader;
repeat:
	atomic_dec(&p->user->processes);
	write_lock_irq(&tasklist_lock);
	ptrace_unlink(p);
	BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
	__exit_signal(p);

	/*
	 * If we are the last non-leader member of the thread
	 * group, and the leader is zombie, then notify the
	 * group leader's parent process. (if it wants notification.)
	 */
	zap_leader = 0;
	leader = p->group_leader;
	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
		BUG_ON(leader->exit_signal == -1);
		do_notify_parent(leader, leader->exit_signal);
		/*
		 * If we were the last child thread and the leader has
		 * exited already, and the leader's parent ignores SIGCHLD,
		 * then we are the one who should release the leader.
		 *
		 * do_notify_parent() will have marked it self-reaping in
		 * that case.
		 */
		zap_leader = (leader->exit_signal == -1);
	}

	write_unlock_irq(&tasklist_lock);
	proc_flush_task(p);
	release_thread(p);
	call_rcu(&p->rcu, delayed_put_task_struct);

	p = leader;
	if (unlikely(zap_leader))
		goto repeat;
}

/*
 * This checks not only the pgrp, but falls back on the pid if no
 * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
 * without this...
 *
 * The caller must hold rcu lock or the tasklist lock.
 */
struct pid *session_of_pgrp(struct pid *pgrp)
{
	struct task_struct *p;
	struct pid *sid = NULL;

	p = pid_task(pgrp, PIDTYPE_PGID);
	if (p == NULL)
		p = pid_task(pgrp, PIDTYPE_PID);
	if (p != NULL)
		sid = task_session(p);

	return sid;
}

/*
 * Determine if a process group is "orphaned", according to the POSIX
 * definition in 2.2.2.52.  Orphaned process groups are not to be affected
 * by terminal-generated stop signals.  Newly orphaned process groups are
 * to receive a SIGHUP and a SIGCONT.
 *
 * "I ask you, have you ever known what it is to be an orphan?"
 */
static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
{
	struct task_struct *p;
	int ret = 1;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if (p == ignored_task
				|| p->exit_state
				|| is_global_init(p->real_parent))
			continue;
		if (task_pgrp(p->real_parent) != pgrp &&
		    task_session(p->real_parent) == task_session(p)) {
			ret = 0;
			break;
		}
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
	return ret;	/* (sighing) "Often!" */
}

int is_current_pgrp_orphaned(void)
{
	int retval;

	read_lock(&tasklist_lock);
	retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
	read_unlock(&tasklist_lock);

	return retval;
}

static int has_stopped_jobs(struct pid *pgrp)
{
	int retval = 0;
	struct task_struct *p;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if (p->state != TASK_STOPPED)
			continue;
		retval = 1;
		break;
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
	return retval;
}

/**
 * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
 *
 * If a kernel thread is launched as a result of a system call, or if
 * it ever exits, it should generally reparent itself to kthreadd so it
 * isn't in the way of other processes and is correctly cleaned up on exit.
 *
 * The various task state such as scheduling policy and priority may have
 * been inherited from a user process, so we reset them to sane values here.
 *
 * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
 */
static void reparent_to_kthreadd(void)
{
	write_lock_irq(&tasklist_lock);

	ptrace_unlink(current);
	/* Reparent to init */
	remove_parent(current);
	current->real_parent = current->parent = kthreadd_task;
	add_parent(current);

	/* Set the exit signal to SIGCHLD so we signal init on exit */
	current->exit_signal = SIGCHLD;

	if (task_nice(current) < 0)
		set_user_nice(current, 0);
	/* cpus_allowed? */
	/* rt_priority? */
	/* signals? */
	security_task_reparent_to_init(current);
	memcpy(current->signal->rlim, init_task.signal->rlim,
	       sizeof(current->signal->rlim));
	atomic_inc(&(INIT_USER->__count));
	write_unlock_irq(&tasklist_lock);
	switch_uid(INIT_USER);
}

void __set_special_pids(pid_t session, pid_t pgrp)
{
	struct task_struct *curr = current->group_leader;

	if (task_session_nr(curr) != session) {
		detach_pid(curr, PIDTYPE_SID);
		set_task_session(curr, session);
		attach_pid(curr, PIDTYPE_SID, find_pid(session));
	}
	if (task_pgrp_nr(curr) != pgrp) {
		detach_pid(curr, PIDTYPE_PGID);
		curr->signal->pgrp = pgrp;
		attach_pid(curr, PIDTYPE_PGID, find_pid(pgrp));
	}
}

static void set_special_pids(pid_t session, pid_t pgrp)
{
	write_lock_irq(&tasklist_lock);
	__set_special_pids(session, pgrp);
	write_unlock_irq(&tasklist_lock);
}

/*
 * Let kernel threads use this to say that they
 * allow a certain signal (since daemonize() will
 * have disabled all of them by default).
 */
int allow_signal(int sig)
{
	if (!valid_signal(sig) || sig < 1)
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
	sigdelset(&current->blocked, sig);
	if (!current->mm) {
		/* Kernel threads handle their own signals.
		   Let the signal code know it'll be handled, so
		   that they don't get converted to SIGKILL or
		   just silently dropped */
		current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
	}
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	return 0;
}

EXPORT_SYMBOL(allow_signal);

int disallow_signal(int sig)
{
	if (!valid_signal(sig) || sig < 1)
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
	current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	return 0;
}

EXPORT_SYMBOL(disallow_signal);

/*
 *	Put all the gunge required to become a kernel thread without
 *	attached user resources in one place where it belongs.
 */

void daemonize(const char *name, ...)
{
	va_list args;
	struct fs_struct *fs;
	sigset_t blocked;

	va_start(args, name);
	vsnprintf(current->comm, sizeof(current->comm), name, args);
	va_end(args);

	/*
	 * If we were started as result of loading a module, close all of the
	 * user space pages.  We don't need them, and if we didn't close them
	 * they would be locked into memory.
	 */
	exit_mm(current);
	/*
	 * We don't want to have TIF_FREEZE set if the system-wide hibernation
	 * or suspend transition begins right now.
	 */
	current->flags |= PF_NOFREEZE;

	set_special_pids(1, 1);
	proc_clear_tty(current);

	/* Block and flush all signals */
	sigfillset(&blocked);
	sigprocmask(SIG_BLOCK, &blocked, NULL);
	flush_signals(current);

	/* Become as one with the init task */

	exit_fs(current);	/* current->fs->count--; */
	fs = init_task.fs;
	current->fs = fs;
	atomic_inc(&fs->count);

	if (current->nsproxy != init_task.nsproxy) {
		get_nsproxy(init_task.nsproxy);
		switch_task_namespaces(current, init_task.nsproxy);
	}

	exit_files(current);
	current->files = init_task.files;
	atomic_inc(&current->files->count);

	reparent_to_kthreadd();
}

EXPORT_SYMBOL(daemonize);

static void close_files(struct files_struct * files)
{
	int i, j;
	struct fdtable *fdt;

	j = 0;

	/*
	 * It is safe to dereference the fd table without RCU or
	 * ->file_lock because this is the last reference to the
	 * files structure.
	 */
	fdt = files_fdtable(files);
	for (;;) {
		unsigned long set;
		i = j * __NFDBITS;
		if (i >= fdt->max_fds)
			break;
		set = fdt->open_fds->fds_bits[j++];
		while (set) {
			if (set & 1) {
				struct file * file = xchg(&fdt->fd[i], NULL);
				if (file) {
					filp_close(file, files);
					cond_resched();
				}
			}
			i++;
			set >>= 1;
		}
	}
}

struct files_struct *get_files_struct(struct task_struct *task)
{
	struct files_struct *files;

	task_lock(task);
	files = task->files;
	if (files)
		atomic_inc(&files->count);
	task_unlock(task);

	return files;
}

void fastcall put_files_struct(struct files_struct *files)
{
	struct fdtable *fdt;

	if (atomic_dec_and_test(&files->count)) {
		close_files(files);
		/*
		 * Free the fd and fdset arrays if we expanded them.
		 * If the fdtable was embedded, pass files for freeing
		 * at the end of the RCU grace period. Otherwise,
		 * you can free files immediately.
		 */
		fdt = files_fdtable(files);
		if (fdt != &files->fdtab)
			kmem_cache_free(files_cachep, files);
		free_fdtable(fdt);
	}
}

EXPORT_SYMBOL(put_files_struct);

void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
{
	struct files_struct *old;

	old = tsk->files;
	task_lock(tsk);
	tsk->files = files;
	task_unlock(tsk);
	put_files_struct(old);
}
EXPORT_SYMBOL(reset_files_struct);

static inline void __exit_files(struct task_struct *tsk)
{
	struct files_struct * files = tsk->files;

	if (files) {
		task_lock(tsk);
		tsk->files = NULL;
		task_unlock(tsk);
		put_files_struct(files);
	}
}

void exit_files(struct task_struct *tsk)
{
	__exit_files(tsk);
}

static inline void __put_fs_struct(struct fs_struct *fs)
{
	/* No need to hold fs->lock if we are killing it */
	if (atomic_dec_and_test(&fs->count)) {
		dput(fs->root);
		mntput(fs->rootmnt);
		dput(fs->pwd);
		mntput(fs->pwdmnt);
		if (fs->altroot) {
			dput(fs->altroot);
			mntput(fs->altrootmnt);
		}
		kmem_cache_free(fs_cachep, fs);
	}
}

void put_fs_struct(struct fs_struct *fs)
{
	__put_fs_struct(fs);
}

static inline void __exit_fs(struct task_struct *tsk)
{
	struct fs_struct * fs = tsk->fs;

	if (fs) {
		task_lock(tsk);
		tsk->fs = NULL;
		task_unlock(tsk);
		__put_fs_struct(fs);
	}
}

void exit_fs(struct task_struct *tsk)
{
	__exit_fs(tsk);
}

EXPORT_SYMBOL_GPL(exit_fs);

/*
 * Turn us into a lazy TLB process if we
 * aren't already..
 */
static void exit_mm(struct task_struct * tsk)
{
	struct mm_struct *mm = tsk->mm;

	mm_release(tsk, mm);
	if (!mm)
		return;
	/*
	 * Serialize with any possible pending coredump.
	 * We must hold mmap_sem around checking core_waiters
	 * and clearing tsk->mm.  The core-inducing thread
	 * will increment core_waiters for each thread in the
	 * group with ->mm != NULL.
	 */
	down_read(&mm->mmap_sem);
	if (mm->core_waiters) {
		up_read(&mm->mmap_sem);
		down_write(&mm->mmap_sem);
		if (!--mm->core_waiters)
			complete(mm->core_startup_done);
		up_write(&mm->mmap_sem);

		wait_for_completion(&mm->core_done);
		down_read(&mm->mmap_sem);
	}
	atomic_inc(&mm->mm_count);
	BUG_ON(mm != tsk->active_mm);
	/* more a memory barrier than a real lock */
	task_lock(tsk);
	tsk->mm = NULL;
	up_read(&mm->mmap_sem);
	enter_lazy_tlb(mm, current);
	/* We don't want this task to be frozen prematurely */
	clear_freeze_flag(tsk);
	task_unlock(tsk);
	mmput(mm);
}

static void
reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
{
	if (p->pdeath_signal)
		/* We already hold the tasklist_lock here.  */
		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);

	/* Move the child from its dying parent to the new one.  */
	if (unlikely(traced)) {
		/* Preserve ptrace links if someone else is tracing this child.  */
		list_del_init(&p->ptrace_list);
		if (p->parent != p->real_parent)
			list_add(&p->ptrace_list, &p->real_parent->ptrace_children);
	} else {
		/* If this child is being traced, then we're the one tracing it
		 * anyway, so let go of it.
		 */
		p->ptrace = 0;
		remove_parent(p);
		p->parent = p->real_parent;
		add_parent(p);

		if (p->state == TASK_TRACED) {
			/*
			 * If it was at a trace stop, turn it into
			 * a normal stop since it's no longer being
			 * traced.
			 */
			ptrace_untrace(p);
		}
	}

	/* If this is a threaded reparent there is no need to
	 * notify anyone anything has happened.
	 */
	if (p->real_parent->group_leader == father->group_leader)
		return;

	/* We don't want people slaying init.  */
	if (p->exit_signal != -1)
		p->exit_signal = SIGCHLD;

	/* If we'd notified the old parent about this child's death,
	 * also notify the new parent.
	 */
	if (!traced && p->exit_state == EXIT_ZOMBIE &&
	    p->exit_signal != -1 && thread_group_empty(p))
		do_notify_parent(p, p->exit_signal);

	/*
	 * process group orphan check
	 * Case ii: Our child is in a different pgrp
	 * than we are, and it was the only connection
	 * outside, so the child pgrp is now orphaned.
	 */
	if ((task_pgrp(p) != task_pgrp(father)) &&
	    (task_session(p) == task_session(father))) {
		struct pid *pgrp = task_pgrp(p);

		if (will_become_orphaned_pgrp(pgrp, NULL) &&
		    has_stopped_jobs(pgrp)) {
			__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
			__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
		}
	}
}

/*
 * When we die, we re-parent all our children.
 * Try to give them to another thread in our thread
 * group, and if no such member exists, give it to
 * the child reaper process (ie "init") in our pid
 * space.
 */
static void
forget_original_parent(struct task_struct *father, struct list_head *to_release)
{
	struct task_struct *p, *n, *reaper = father;

	do {
		reaper = next_thread(reaper);
		if (reaper == father) {
			reaper = task_child_reaper(father);
			break;
		}
	} while (reaper->exit_state);

	/*
	 * There are only two places where our children can be:
	 *
	 * - in our child list
	 * - in our ptraced child list
	 *
	 * Search them and reparent children.
	 */
	list_for_each_entry_safe(p, n, &father->children, sibling) {
		int ptrace;

		ptrace = p->ptrace;

		/* if father isn't the real parent, then ptrace must be enabled */
		BUG_ON(father != p->real_parent && !ptrace);

		if (father == p->real_parent) {
			/* reparent with a reaper, real father it's us */
			p->real_parent = reaper;
			reparent_thread(p, father, 0);
		} else {
			/* reparent ptraced task to its real parent */
			__ptrace_unlink (p);
			if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 &&
			    thread_group_empty(p))
				do_notify_parent(p, p->exit_signal);
		}

		/*
		 * if the ptraced child is a zombie with exit_signal == -1
		 * we must collect it before we exit, or it will remain
		 * zombie forever since we prevented it from self-reap itself
		 * while it was being traced by us, to be able to see it in wait4.
		 */
		if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1))
			list_add(&p->ptrace_list, to_release);
	}
	list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) {
		p->real_parent = reaper;
		reparent_thread(p, father, 1);
	}
}

/*
 * Send signals to all our closest relatives so that they know
 * to properly mourn us..
 */
static void exit_notify(struct task_struct *tsk)
{
	int state;
	struct task_struct *t;
	struct list_head ptrace_dead, *_p, *_n;
	struct pid *pgrp;

	if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT)
	    && !thread_group_empty(tsk)) {
		/*
		 * This occurs when there was a race between our exit
		 * syscall and a group signal choosing us as the one to
		 * wake up.  It could be that we are the only thread
		 * alerted to check for pending signals, but another thread
		 * should be woken now to take the signal since we will not.
		 * Now we'll wake all the threads in the group just to make
		 * sure someone gets all the pending signals.
		 */
		spin_lock_irq(&tsk->sighand->siglock);
		for (t = next_thread(tsk); t != tsk; t = next_thread(t))
			if (!signal_pending(t) && !(t->flags & PF_EXITING))
				recalc_sigpending_and_wake(t);
		spin_unlock_irq(&tsk->sighand->siglock);
	}

	write_lock_irq(&tasklist_lock);

	/*
	 * This does two things:
	 *
  	 * A.  Make init inherit all the child processes
	 * B.  Check to see if any process groups have become orphaned
	 *	as a result of our exiting, and if they have any stopped
	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
	 */

	INIT_LIST_HEAD(&ptrace_dead);
	forget_original_parent(tsk, &ptrace_dead);
	BUG_ON(!list_empty(&tsk->children));
	BUG_ON(!list_empty(&tsk->ptrace_children));

	/*
	 * Check to see if any process groups have become orphaned
	 * as a result of our exiting, and if they have any stopped
	 * jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
	 *
	 * Case i: Our father is in a different pgrp than we are
	 * and we were the only connection outside, so our pgrp
	 * is about to become orphaned.
	 */
	t = tsk->real_parent;

	pgrp = task_pgrp(tsk);
	if ((task_pgrp(t) != pgrp) &&
	    (task_session(t) == task_session(tsk)) &&
	    will_become_orphaned_pgrp(pgrp, tsk) &&
	    has_stopped_jobs(pgrp)) {
		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
	}

	/* Let father know we died
	 *
	 * Thread signals are configurable, but you aren't going to use
	 * that to send signals to arbitary processes.
	 * That stops right now.
	 *
	 * If the parent exec id doesn't match the exec id we saved
	 * when we started then we know the parent has changed security
	 * domain.
	 *
	 * If our self_exec id doesn't match our parent_exec_id then
	 * we have changed execution domain as these two values started
	 * the same after a fork.
	 */
	if (tsk->exit_signal != SIGCHLD && tsk->exit_signal != -1 &&
	    ( tsk->parent_exec_id != t->self_exec_id  ||
	      tsk->self_exec_id != tsk->parent_exec_id)
	    && !capable(CAP_KILL))
		tsk->exit_signal = SIGCHLD;


	/* If something other than our normal parent is ptracing us, then
	 * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
	 * only has special meaning to our real parent.
	 */
	if (tsk->exit_signal != -1 && thread_group_empty(tsk)) {
		int signal = tsk->parent == tsk->real_parent ? tsk->exit_signal : SIGCHLD;
		do_notify_parent(tsk, signal);
	} else if (tsk->ptrace) {
		do_notify_parent(tsk, SIGCHLD);
	}

	state = EXIT_ZOMBIE;
	if (tsk->exit_signal == -1 && likely(!tsk->ptrace))
		state = EXIT_DEAD;
	tsk->exit_state = state;

	if (thread_group_leader(tsk) &&
	    tsk->signal->notify_count < 0 &&
	    tsk->signal->group_exit_task)
		wake_up_process(tsk->signal->group_exit_task);

	write_unlock_irq(&tasklist_lock);

	list_for_each_safe(_p, _n, &ptrace_dead) {
		list_del_init(_p);
		t = list_entry(_p, struct task_struct, ptrace_list);
		release_task(t);
	}

	/* If the process is dead, release it - nobody will wait for it */
	if (state == EXIT_DEAD)
		release_task(tsk);
}

#ifdef CONFIG_DEBUG_STACK_USAGE
static void check_stack_usage(void)
{
	static DEFINE_SPINLOCK(low_water_lock);
	static int lowest_to_date = THREAD_SIZE;
	unsigned long *n = end_of_stack(current);
	unsigned long free;

	while (*n == 0)
		n++;
	free = (unsigned long)n - (unsigned long)end_of_stack(current);

	if (free >= lowest_to_date)
		return;

	spin_lock(&low_water_lock);
	if (free < lowest_to_date) {
		printk(KERN_WARNING "%s used greatest stack depth: %lu bytes "
				"left\n",
				current->comm, free);
		lowest_to_date = free;
	}
	spin_unlock(&low_water_lock);
}
#else
static inline void check_stack_usage(void) {}
#endif

static inline void exit_child_reaper(struct task_struct *tsk)
{
	if (likely(tsk->group_leader != task_child_reaper(tsk)))
		return;

	panic("Attempted to kill init!");
}

fastcall NORET_TYPE void do_exit(long code)
{
	struct task_struct *tsk = current;
	int group_dead;

	profile_task_exit(tsk);

	WARN_ON(atomic_read(&tsk->fs_excl));

	if (unlikely(in_interrupt()))
		panic("Aiee, killing interrupt handler!");
	if (unlikely(!tsk->pid))
		panic("Attempted to kill the idle task!");

	if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
		current->ptrace_message = code;
		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
	}

	/*
	 * We're taking recursive faults here in do_exit. Safest is to just
	 * leave this task alone and wait for reboot.
	 */
	if (unlikely(tsk->flags & PF_EXITING)) {
		printk(KERN_ALERT
			"Fixing recursive fault but reboot is needed!\n");
		/*
		 * 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. We pretend that the cleanup was
		 * done as there is no way to return. Either the
		 * OWNER_DIED bit is set by now or we push the blocked
		 * task into the wait for ever nirwana as well.
		 */
		tsk->flags |= PF_EXITPIDONE;
		if (tsk->io_context)
			exit_io_context();
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule();
	}

	tsk->flags |= PF_EXITING;
	/*
	 * tsk->flags are checked in the futex code to protect against
	 * an exiting task cleaning up the robust pi futexes.
	 */
	smp_mb();
	spin_unlock_wait(&tsk->pi_lock);

	if (unlikely(in_atomic()))
		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
				current->comm, current->pid,
				preempt_count());

	acct_update_integrals(tsk);
	if (tsk->mm) {
		update_hiwater_rss(tsk->mm);
		update_hiwater_vm(tsk->mm);
	}
	group_dead = atomic_dec_and_test(&tsk->signal->live);
	if (group_dead) {
		exit_child_reaper(tsk);
		hrtimer_cancel(&tsk->signal->real_timer);
		exit_itimers(tsk->signal);
	}
	acct_collect(code, group_dead);
#ifdef CONFIG_FUTEX
	if (unlikely(tsk->robust_list))
		exit_robust_list(tsk);
#ifdef CONFIG_COMPAT
	if (unlikely(tsk->compat_robust_list))
		compat_exit_robust_list(tsk);
#endif
#endif
	if (group_dead)
		tty_audit_exit();
	if (unlikely(tsk->audit_context))
		audit_free(tsk);

	tsk->exit_code = code;
	taskstats_exit(tsk, group_dead);

	exit_mm(tsk);

	if (group_dead)
		acct_process();
	exit_sem(tsk);
	__exit_files(tsk);
	__exit_fs(tsk);
	check_stack_usage();
	exit_thread();
	cgroup_exit(tsk, 1);
	exit_keys(tsk);

	if (group_dead && tsk->signal->leader)
		disassociate_ctty(1);

	module_put(task_thread_info(tsk)->exec_domain->module);
	if (tsk->binfmt)
		module_put(tsk->binfmt->module);

	proc_exit_connector(tsk);
	exit_task_namespaces(tsk);
	exit_notify(tsk);
#ifdef CONFIG_NUMA
	mpol_free(tsk->mempolicy);
	tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
	/*
	 * This must happen late, after the PID is not
	 * hashed anymore:
	 */
	if (unlikely(!list_empty(&tsk->pi_state_list)))
		exit_pi_state_list(tsk);
	if (unlikely(current->pi_state_cache))
		kfree(current->pi_state_cache);
#endif
	/*