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/iocontext.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/fdtable.h>
#include <linux/freezer.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/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/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 <linux/tracehook.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
#include <linux/perf_event.h>
#include <trace/events/sched.h>
#include <linux/hw_breakpoint.h>
#include <linux/oom.h>
#include <linux/writeback.h>
#include <linux/shm.h>

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

static void exit_mm(struct task_struct * tsk);

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

		list_del_rcu(&p->tasks);
		list_del_init(&p->sibling);
		__this_cpu_dec(process_counts);
	}
	list_del_rcu(&p->thread_group);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
static void __exit_signal(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;
	bool group_dead = thread_group_leader(tsk);
	struct sighand_struct *sighand;
	struct tty_struct *uninitialized_var(tty);
	cputime_t utime, stime;

	sighand = rcu_dereference_check(tsk->sighand,
					lockdep_tasklist_lock_is_held());
	spin_lock(&sighand->siglock);

	posix_cpu_timers_exit(tsk);
	if (group_dead) {
		posix_cpu_timers_exit_group(tsk);
		tty = sig->tty;
		sig->tty = NULL;
	} else {
		/*
		 * This can only happen if the caller is de_thread().
		 * FIXME: this is the temporary hack, we should teach
		 * posix-cpu-timers to handle this case correctly.
		 */
		if (unlikely(has_group_leader_pid(tsk)))
			posix_cpu_timers_exit_group(tsk);

		/*
		 * If there is any task waiting for the group exit
		 * then notify it:
		 */
		if (sig->notify_count > 0 && !--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.
		 */
		task_cputime(tsk, &utime, &stime);
		sig->utime += utime;
		sig->stime += stime;
		sig->gtime += task_gtime(tsk);
		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);
		task_io_accounting_add(&sig->ioac, &tsk->ioac);
		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
	}

	sig->nr_threads--;
	__unhash_process(tsk, group_dead);

	/*
	 * Do this under ->siglock, we can race with another thread
	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
	 */
	flush_sigqueue(&tsk->pending);
	tsk->sighand = NULL;
	spin_unlock(&sighand->siglock);

	__cleanup_sighand(sighand);
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	if (group_dead) {
		flush_sigqueue(&sig->shared_pending);
		tty_kref_put(tty);
	}
}

static void delayed_put_task_struct(struct rcu_head *rhp)
{
	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);

	perf_event_delayed_put(tsk);
	trace_sched_process_free(tsk);
	put_task_struct(tsk);
}


void release_task(struct task_struct * p)
{
	struct task_struct *leader;
	int zap_leader;
repeat:
	/* don't need to get the RCU readlock here - the process is dead and
	 * can't be modifying its own credentials. But shut RCU-lockdep up */
	rcu_read_lock();
	atomic_dec(&__task_cred(p)->user->processes);
	rcu_read_unlock();

	proc_flush_task(p);

	write_lock_irq(&tasklist_lock);
	ptrace_release_task(p);
	__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) {
		/*
		 * 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.
		 */
		zap_leader = do_notify_parent(leader, leader->exit_signal);
		if (zap_leader)
			leader->exit_state = EXIT_DEAD;
	}

	write_unlock_irq(&tasklist_lock);
	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;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if ((p == ignored_task) ||
		    (p->exit_state && thread_group_empty(p)) ||
		    is_global_init(p->real_parent))
			continue;

		if (task_pgrp(p->real_parent) != pgrp &&
		    task_session(p->real_parent) == task_session(p))
			return 0;
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);

	return 1;
}

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 bool has_stopped_jobs(struct pid *pgrp)
{
	struct task_struct *p;

	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
		if (p->signal->flags & SIGNAL_STOP_STOPPED)
			return true;
	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);

	return false;
}

/*
 * 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)
 */
static void
kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
{
	struct pid *pgrp = task_pgrp(tsk);
	struct task_struct *ignored_task = tsk;

	if (!parent)
		 /* exit: our father is in a different pgrp than
		  * we are and we were the only connection outside.
		  */
		parent = tsk->real_parent;
	else
		/* reparent: our child is in a different pgrp than
		 * we are, and it was the only connection outside.
		 */
		ignored_task = NULL;

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

/*
 * Let kernel threads use this to say that they allow a certain signal.
 * Must not be used if kthread was cloned with CLONE_SIGHAND.
 */
int allow_signal(int sig)
{
	if (!valid_signal(sig) || sig < 1)
		return -EINVAL;

	spin_lock_irq(&current->sighand->siglock);
	/* This is only needed for daemonize()'ed kthreads */
	sigdelset(&current->blocked, sig);
	/*
	 * 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);

#ifdef CONFIG_MM_OWNER
/*
 * A task is exiting.   If it owned this mm, find a new owner for the mm.
 */
void mm_update_next_owner(struct mm_struct *mm)
{
	struct task_struct *c, *g, *p = current;

retry:
	/*
	 * If the exiting or execing task is not the owner, it's
	 * someone else's problem.
	 */
	if (mm->owner != p)
		return;
	/*
	 * The current owner is exiting/execing and there are no other
	 * candidates.  Do not leave the mm pointing to a possibly
	 * freed task structure.
	 */
	if (atomic_read(&mm->mm_users) <= 1) {
		mm->owner = NULL;
		return;
	}

	read_lock(&tasklist_lock);
	/*
	 * Search in the children
	 */
	list_for_each_entry(c, &p->children, sibling) {
		if (c->mm == mm)
			goto assign_new_owner;
	}

	/*
	 * Search in the siblings
	 */
	list_for_each_entry(c, &p->real_parent->children, sibling) {
		if (c->mm == mm)
			goto assign_new_owner;
	}

	/*
	 * Search through everything else. We should not get
	 * here often
	 */
	do_each_thread(g, c) {
		if (c->mm == mm)
			goto assign_new_owner;
	} while_each_thread(g, c);

	read_unlock(&tasklist_lock);
	/*
	 * We found no owner yet mm_users > 1: this implies that we are
	 * most likely racing with swapoff (try_to_unuse()) or /proc or
	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
	 */
	mm->owner = NULL;
	return;

assign_new_owner:
	BUG_ON(c == p);
	get_task_struct(c);
	/*
	 * The task_lock protects c->mm from changing.
	 * We always want mm->owner->mm == mm
	 */
	task_lock(c);
	/*
	 * Delay read_unlock() till we have the task_lock()
	 * to ensure that c does not slip away underneath us
	 */
	read_unlock(&tasklist_lock);
	if (c->mm != mm) {
		task_unlock(c);
		put_task_struct(c);
		goto retry;
	}
	mm->owner = c;
	task_unlock(c);
	put_task_struct(c);
}
#endif /* CONFIG_MM_OWNER */

/*
 * 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;
	struct core_state *core_state;

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

		self.task = tsk;
		self.next = xchg(&core_state->dumper.next, &self);
		/*
		 * Implies mb(), the result of xchg() must be visible
		 * to core_state->dumper.
		 */
		if (atomic_dec_and_test(&core_state->nr_threads))
			complete(&core_state->startup);

		for (;;) {
			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
			if (!self.task) /* see coredump_finish() */
				break;
			freezable_schedule();
		}
		__set_task_state(tsk, TASK_RUNNING);
		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);
	task_unlock(tsk);
	mm_update_next_owner(mm);
	mmput(mm);
}

/*
 * When we die, we re-parent all our children, and try to:
 * 1. give them to another thread in our thread group, if such a member exists
 * 2. give it to the first ancestor process which prctl'd itself as a
 *    child_subreaper for its children (like a service manager)
 * 3. give it to the init process (PID 1) in our pid namespace
 */
static struct task_struct *find_new_reaper(struct task_struct *father)
	__releases(&tasklist_lock)
	__acquires(&tasklist_lock)
{
	struct pid_namespace *pid_ns = task_active_pid_ns(father);
	struct task_struct *thread;

	thread = father;
	while_each_thread(father, thread) {
		if (thread->flags & PF_EXITING)
			continue;
		if (unlikely(pid_ns->child_reaper == father))
			pid_ns->child_reaper = thread;
		return thread;
	}

	if (unlikely(pid_ns->child_reaper == father)) {
		write_unlock_irq(&tasklist_lock);
		if (unlikely(pid_ns == &init_pid_ns)) {
			panic("Attempted to kill init! exitcode=0x%08x\n",
				father->signal->group_exit_code ?:
					father->exit_code);
		}

		zap_pid_ns_processes(pid_ns);
		write_lock_irq(&tasklist_lock);
	} else if (father->signal->has_child_subreaper) {
		struct task_struct *reaper;

		/*
		 * Find the first ancestor marked as child_subreaper.
		 * Note that the code below checks same_thread_group(reaper,
		 * pid_ns->child_reaper).  This is what we need to DTRT in a
		 * PID namespace. However we still need the check above, see
		 * http://marc.info/?l=linux-kernel&m=131385460420380
		 */
		for (reaper = father->real_parent;
		     reaper != &init_task;
		     reaper = reaper->real_parent) {
			if (same_thread_group(reaper, pid_ns->child_reaper))
				break;
			if (!reaper->signal->is_child_subreaper)
				continue;
			thread = reaper;
			do {
				if (!(thread->flags & PF_EXITING))
					return reaper;
			} while_each_thread(reaper, thread);
		}
	}

	return pid_ns->child_reaper;
}

/*
* Any that need to be release_task'd are put on the @dead list.
 */
static void reparent_leader(struct task_struct *father, struct task_struct *p,
				struct list_head *dead)
{
	list_move_tail(&p->sibling, &p->real_parent->children);

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

	/* We don't want people slaying init.  */
	p->exit_signal = SIGCHLD;

	/* If it has exited notify the new parent about this child's death. */
	if (!p->ptrace &&
	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
		if (do_notify_parent(p, p->exit_signal)) {
			p->exit_state = EXIT_DEAD;
			list_move_tail(&p->sibling, dead);
		}
	}

	kill_orphaned_pgrp(p, father);
}

static void forget_original_parent(struct task_struct *father)
{
	struct task_struct *p, *n, *reaper;
	LIST_HEAD(dead_children);

	write_lock_irq(&tasklist_lock);
	/*
	 * Note that exit_ptrace() and find_new_reaper() might
	 * drop tasklist_lock and reacquire it.
	 */
	exit_ptrace(father);
	reaper = find_new_reaper(father);

	list_for_each_entry_safe(p, n, &father->children, sibling) {
		struct task_struct *t = p;
		do {
			t->real_parent = reaper;
			if (t->parent == father) {
				BUG_ON(t->ptrace);
				t->parent = t->real_parent;
			}
			if (t->pdeath_signal)
				group_send_sig_info(t->pdeath_signal,
						    SEND_SIG_NOINFO, t);
		} while_each_thread(p, t);
		reparent_leader(father, p, &dead_children);
	}
	write_unlock_irq(&tasklist_lock);

	BUG_ON(!list_empty(&father->children));

	list_for_each_entry_safe(p, n, &dead_children, sibling) {
		list_del_init(&p->sibling);
		release_task(p);
	}
}

/*
 * Send signals to all our closest relatives so that they know
 * to properly mourn us..
 */
static void exit_notify(struct task_struct *tsk, int group_dead)
{
	bool autoreap;

	/*
	 * 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)
	 */
	forget_original_parent(tsk);

	write_lock_irq(&tasklist_lock);
	if (group_dead)
		kill_orphaned_pgrp(tsk->group_leader, NULL);

	if (unlikely(tsk->ptrace)) {
		int sig = thread_group_leader(tsk) &&
				thread_group_empty(tsk) &&
				!ptrace_reparented(tsk) ?
			tsk->exit_signal : SIGCHLD;
		autoreap = do_notify_parent(tsk, sig);
	} else if (thread_group_leader(tsk)) {
		autoreap = thread_group_empty(tsk) &&
			do_notify_parent(tsk, tsk->exit_signal);
	} else {
		autoreap = true;
	}

	tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;

	/* mt-exec, de_thread() is waiting for group leader */
	if (unlikely(tsk->signal->notify_count < 0))
		wake_up_process(tsk->signal->group_exit_task);
	write_unlock_irq(&tasklist_lock);

	/* If the process is dead, release it - nobody will wait for it */
	if (autoreap)
		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 free;

	free = stack_not_used(current);

	if (free >= lowest_to_date)
		return;

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

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

	profile_task_exit(tsk);

	WARN_ON(blk_needs_flush_plug(tsk));

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

	/*
	 * If do_exit is called because this processes oopsed, it's possible
	 * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
	 * continuing. Amongst other possible reasons, this is to prevent
	 * mm_release()->clear_child_tid() from writing to a user-controlled
	 * kernel address.
	 */
	set_fs(USER_DS);

	ptrace_event(PTRACE_EVENT_EXIT, code);

	validate_creds_for_do_exit(tsk);

	/*
	 * 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;
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule();
	}

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

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

	acct_update_integrals(tsk);
	/* sync mm's RSS info before statistics gathering */
	if (tsk->mm)
		sync_mm_rss(tsk->mm);
	group_dead = atomic_dec_and_test(&tsk->signal->live);
	if (group_dead) {
		hrtimer_cancel(&tsk->signal->real_timer);
		exit_itimers(tsk->signal);
		if (tsk->mm)
			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
	}
	acct_collect(code, group_dead);
	if (group_dead)
		tty_audit_exit();
	audit_free(tsk);

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

	exit_mm(tsk);

	if (group_dead)
		acct_process();
	trace_sched_process_exit(tsk);

	exit_sem(tsk);
	exit_shm(tsk);
	exit_files(tsk);
	exit_fs(tsk);
	exit_task_namespaces(tsk);
	exit_task_work(tsk);
	check_stack_usage();
	exit_thread();

	/*
	 * Flush inherited counters to the parent - before the parent
	 * gets woken up by child-exit notifications.
	 *
	 * because of cgroup mode, must be called before cgroup_exit()
	 */
	perf_event_exit_task(tsk);

	cgroup_exit(tsk, 1);

	if (group_dead)
		disassociate_ctty(1);

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

	proc_exit_connector(tsk);

	/*
	 * FIXME: do that only when needed, using sched_exit tracepoint
	 */
	ptrace_put_breakpoints(tsk);

	exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
	task_lock(tsk);
	mpol_put(tsk->mempolicy);
	tsk->mempolicy = NULL;
	task_unlock(tsk);
#endif
#ifdef CONFIG_FUTEX
	if (unlikely(current->pi_state_cache))
		kfree(current->pi_state_cache);
#endif
	/*
	 * Make sure we are holding no locks:
	 */
	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(tsk);

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

	if (tsk->task_frag.page)
		put_page(tsk->task_frag.page);

	validate_creds_for_do_exit(tsk);

	preempt_disable();
	if (tsk->nr_dirtied)
		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
	exit_rcu();

	/*
	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
	 * when the following two conditions become true.
	 *   - There is race condition of mmap_sem (It is acquired by
	 *     exit_mm()), and
	 *   - SMI occurs before setting TASK_RUNINNG.
	 *     (or hypervisor of virtual machine switches to other guest)
	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
	 *
	 * To avoid it, we have to wait for releasing tsk->pi_lock which
	 * is held by try_to_wake_up()
	 */
	smp_mb();
	raw_spin_unlock_wait(&tsk->pi_lock);

	/* causes final put_task_struct in finish_task_switch(). */
	tsk->state = TASK_DEAD;
	tsk->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
	schedule();
	BUG();
	/* Avoid "noreturn function does return".  */
	for (;;)
		cpu_relax();	/* For when BUG is null */
}

EXPORT_SYMBOL_GPL(do_exit);

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).
 */
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;
}

struct wait_opts {
	enum pid_type		wo_type;
	int			wo_flags;
	struct pid		*wo_pid;

	struct siginfo __user	*wo_info;
	int __user		*wo_stat;
	struct rusage __user	*wo_rusage;

	wait_queue_t		child_wait;
	int			notask_error;
};

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

static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
	return	wo->wo_type == PIDTYPE_MAX ||
		task_pid_type(p, wo->wo_type) == wo->wo_pid;
}

static int eligible_child(struct wait_opts *wo, struct task_struct *p)
{
	if (!eligible_pid(wo, p))
		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) ^ !!(wo->wo_flags & __WCLONE))
	    && !(wo->wo_flags & __WALL))
		return 0;

	return 1;
}

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

	put_task_struct(p);
	infop = wo->wo_info;
	if (infop) {
		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);