SUNRPC: Ensure we always bump the backlog queue in xprt_free_slot

[linux-2.6/linux-acpi-2.6/ibm-acpi-2.6.git] / kernel / 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/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/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 <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);

        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.
                 */
                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);
                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);
        }
}

/**
 * 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 */
        current->real_parent = current->parent = kthreadd_task;
        list_move_tail(&current->sibling, &current->real_parent->children);

        /* 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? */
        memcpy(current->signal->rlim, init_task.signal->rlim,
               sizeof(current->signal->rlim));

        atomic_inc(&init_cred.usage);
        commit_creds(&init_cred);
        write_unlock_irq(&tasklist_lock);
}

void __set_special_pids(struct pid *pid)
{
        struct task_struct *curr = current->group_leader;

        if (task_session(curr) != pid)
                change_pid(curr, PIDTYPE_SID, pid);

        if (task_pgrp(curr) != pid)
                change_pid(curr, PIDTYPE_PGID, pid);
}

static void set_special_pids(struct pid *pid)
{
        write_lock_irq(&tasklist_lock);
        __set_special_pids(pid);
        write_unlock_irq(&tasklist_lock);
}

/*
 * 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);

/*
 *      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;
        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 | PF_KTHREAD);

        if (current->nsproxy != &init_nsproxy) {
                get_nsproxy(&init_nsproxy);
                switch_task_namespaces(current, &init_nsproxy);
        }
        set_special_pids(&init_struct_pid);
        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 */

        daemonize_fs_struct();
        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.  But use RCU to shut RCU-lockdep up.
         */
        rcu_read_lock();
        fdt = files_fdtable(files);
        rcu_read_unlock();
        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 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.
                 */
                rcu_read_lock();
                fdt = files_fdtable(files);
                if (fdt != &files->fdtab)
                        kmem_cache_free(files_cachep, files);
                free_fdtable(fdt);
                rcu_read_unlock();
        }
}

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

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

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);
        }
}

#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;
        /*
         * 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;
                        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);
        /* We don't want this task to be frozen prematurely */
        clear_freeze_flag(tsk);
        if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
                atomic_dec(&mm->oom_disable_count);
        task_unlock(tsk);
        mm_update_next_owner(mm);
        mmput(mm);
}

/*
 * 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 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!");

                zap_pid_ns_processes(pid_ns);
                write_lock_irq(&tasklist_lock);
                /*
                 * We can not clear ->child_reaper or leave it alone.
                 * There may by stealth EXIT_DEAD tasks on ->children,
                 * forget_original_parent() must move them somewhere.
                 */
                pid_ns->child_reaper = init_pid_ns.child_reaper;
        }

        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);
        exit_task_namespaces(tsk);

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

        /* Let father know we died
         *
         * Thread signals are configurable, but you aren't going to use
         * that to send signals to arbitrary 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 (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
            (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
             tsk->self_exec_id != tsk->parent_exec_id))
                tsk->exit_signal = SIGCHLD;

        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 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

NORET_TYPE 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_irq_thread();

        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, 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();
        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();
        trace_sched_process_exit(tsk);

        exit_sem(tsk);
        exit_shm(tsk);
        exit_files(tsk);
        exit_fs(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);

        validate_creds_for_do_exit(tsk);

        preempt_disable();
        exit_rcu();
        /* 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;
}

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);
        }
        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 wait_opts *wo, struct task_struct *p)
{
        unsigned long state;
        int retval, status, traced;
        pid_t pid = task_pid_vnr(p);
        uid_t uid = __task_cred(p)->uid;
        struct siginfo __user *infop;

        if (!likely(wo->wo_flags & WEXITED))
                return 0;

        if (unlikely(wo->wo_flags & WNOWAIT)) {
                int exit_code = p->exit_code;
                int why;

                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(wo, p, pid, uid, why, status);
        }

        /*
         * 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);
        /*
         * It can be ptraced but not reparented, check
         * thread_group_leader() to filter out sub-threads.
         */
        if (likely(!traced) && thread_group_leader(p)) {
                struct signal_struct *psig;
                struct signal_struct *sig;
                unsigned long maxrss;
                cputime_t tgutime, tgstime;

                /*
                 * 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 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_times() to get times for the thread
                 * group, which consolidates times for all threads in the
                 * group including the group leader.
                 */
                thread_group_times(p, &tgutime, &tgstime);
                spin_lock_irq(&p->real_parent->sighand->siglock);
                psig = p->real_parent->signal;
                sig = p->signal;
                psig->cutime =
                        cputime_add(psig->cutime,
                        cputime_add(tgutime,
                                    sig->cutime));
                psig->cstime =
                        cputime_add(psig->cstime,
                        cputime_add(tgstime,
                                    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;
                maxrss = max(sig->maxrss, sig->cmaxrss);
                if (psig->cmaxrss < maxrss)
                        psig->cmaxrss = maxrss;
                task_io_accounting_add(&psig->ioac, &p->ioac);
                task_io_accounting_add(&psig->ioac, &sig->ioac);
                spin_unlock_irq(&p->real_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);

        retval = wo->wo_rusage
                ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
        status = (p->signal->flags & SIGNAL_GROUP_EXIT)
                ? p->signal->group_exit_code : p->exit_code;
        if (!retval && wo->wo_stat)
                retval = put_user(status, wo->wo_stat);

        infop = wo->wo_info;
        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 sub-thread, notify the parent.
                 * If parent wants a zombie, don't release it now.
                 */
                if (thread_group_leader(p) &&
                    !do_notify_parent(p, p->exit_signal)) {
                        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) &&
                    !(p->jobctl & JOBCTL_LISTENING))
                        return &p->exit_code;
        } else {
                if (p->signal->flags & SIGNAL_STOP_STOPPED)
                        return &p->signal->group_exit_code;
        }
        return NULL;
}

/**
 * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED
 * @wo: wait options
 * @ptrace: is the wait for ptrace
 * @p: task to wait for
 *
 * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED.
 *
 * CONTEXT:
 * read_lock(&tasklist_lock), which is released if return value is
 * non-zero.  Also, grabs and releases @p->sighand->siglock.
 *
 * RETURNS:
 * 0 if wait condition didn't exist and search for other wait conditions
 * should continue.  Non-zero return, -errno on failure and @p's pid on
 * success, implies that tasklist_lock is released and wait condition
 * search should terminate.
 */
static int wait_task_stopped(struct wait_opts *wo,
                                int ptrace, struct task_struct *p)
{
        struct siginfo __user *infop;
        int retval, exit_code, *p_code, why;
        uid_t uid = 0; /* unneeded, required by compiler */
        pid_t pid;

        /*
         * Traditionally we see ptrace'd stopped tasks regardless of options.
         */
        if (!ptrace && !(wo->wo_flags & WUNTRACED))
                return 0;

        if (!task_stopped_code(p, ptrace))
                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(wo->wo_flags & WNOWAIT))
                *p_code = 0;

        uid = task_uid(p);
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(wo->wo_flags & WNOWAIT))
                return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);

        retval = wo->wo_rusage
                ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
        if (!retval && wo->wo_stat)
                retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat);

        infop = wo->wo_info;
        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 wait_opts *wo, struct task_struct *p)
{
        int retval;
        pid_t pid;
        uid_t uid;

        if (!unlikely(wo->wo_flags & 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(wo->wo_flags & WNOWAIT))
                p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
        uid = task_uid(p);
        spin_unlock_irq(&p->sighand->siglock);

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

        if (!wo->wo_info) {
                retval = wo->wo_rusage
                        ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
                put_task_struct(p);
                if (!retval && wo->wo_stat)
                        retval = put_user(0xffff, wo->wo_stat);
                if (!retval)
                        retval = pid;
        } else {
                retval = wait_noreap_copyout(wo, p, pid, uid,
                                             CLD_CONTINUED, SIGCONT);
                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 wait_opts *wo, int ptrace,
                                struct task_struct *p)
{
        int ret = eligible_child(wo, p);
        if (!ret)
                return ret;

        ret = security_task_wait(p);
        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 (wo->notask_error)
                        wo->notask_error = ret;
                return 0;
        }

        /* dead body doesn't have much to contribute */
        if (p->exit_state == EXIT_DEAD)
                return 0;

        /* slay zombie? */
        if (p->exit_state == EXIT_ZOMBIE) {
                /*
                 * A zombie ptracee is only visible to its ptracer.
                 * Notification and reaping will be cascaded to the real
                 * parent when the ptracer detaches.
                 */
                if (likely(!ptrace) && unlikely(p->ptrace)) {
                        /* it will become visible, clear notask_error */
                        wo->notask_error = 0;
                        return 0;
                }

                /* we don't reap group leaders with subthreads */
                if (!delay_group_leader(p))
                        return wait_task_zombie(wo, p);

                /*
                 * Allow access to stopped/continued state via zombie by
                 * falling through.  Clearing of notask_error is complex.
                 *
                 * When !@ptrace:
                 *
                 * If WEXITED is set, notask_error should naturally be
                 * cleared.  If not, subset of WSTOPPED|WCONTINUED is set,
                 * so, if there are live subthreads, there are events to
                 * wait for.  If all subthreads are dead, it's still safe
                 * to clear - this function will be called again in finite
                 * amount time once all the subthreads are released and
                 * will then return without clearing.
                 *
                 * When @ptrace:
                 *
                 * Stopped state is per-task and thus can't change once the
                 * target task dies.  Only continued and exited can happen.
                 * Clear notask_error if WCONTINUED | WEXITED.
                 */
                if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED)))
                        wo->notask_error = 0;
        } else {
                /*
                 * If @p is ptraced by a task in its real parent's group,
                 * hide group stop/continued state when looking at @p as
                 * the real parent; otherwise, a single stop can be
                 * reported twice as group and ptrace stops.
                 *
                 * If a ptracer wants to distinguish the two events for its
                 * own children, it should create a separate process which
                 * takes the role of real parent.
                 */
                if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
                        return 0;

                /*
                 * @p is alive and it's gonna stop, continue or exit, so
                 * there always is something to wait for.
                 */
                wo->notask_error = 0;
        }

        /*
         * Wait for stopped.  Depending on @ptrace, different stopped state
         * is used and the two don't interact with each other.
         */
        ret = wait_task_stopped(wo, ptrace, p);
        if (ret)
                return ret;

        /*
         * Wait for continued.  There's only one continued state and the
         * ptracer can consume it which can confuse the real parent.  Don't
         * use WCONTINUED from ptracer.  You don't need or want it.
         */
        return wait_task_continued(wo, p);
}

/*
 * 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 wait_opts *wo, struct task_struct *tsk)
{
        struct task_struct *p;

        list_for_each_entry(p, &tsk->children, sibling) {
                int ret = wait_consider_task(wo, 0, p);
                if (ret)
                        return ret;
        }

        return 0;
}

static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
{
        struct task_struct *p;

        list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
                int ret = wait_consider_task(wo, 1, p);
                if (ret)
                        return ret;
        }

        return 0;
}

static int child_wait_callback(wait_queue_t *wait, unsigned mode,
                                int sync, void *key)
{
        struct wait_opts *wo = container_of(wait, struct wait_opts,
                                                child_wait);
        struct task_struct *p = key;

        if (!eligible_pid(wo, p))
                return 0;

        if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
                return 0;

        return default_wake_function(wait, mode, sync, key);
}

void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
{
        __wake_up_sync_key(&parent->signal->wait_chldexit,
                                TASK_INTERRUPTIBLE, 1, p);
}

static long do_wait(struct wait_opts *wo)
{
        struct task_struct *tsk;
        int retval;

        trace_sched_process_wait(wo->wo_pid);

        init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
        wo->child_wait.private = current;
        add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
repeat:
        /*
         * If there is nothing that can match our critiera just get out.
         * We will clear ->notask_error to zero if we see any child that
         * might later match our criteria, even if we are not able to reap
         * it yet.
         */
        wo->notask_error = -ECHILD;
        if ((wo->wo_type < PIDTYPE_MAX) &&
           (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
                goto notask;

        set_current_state(TASK_INTERRUPTIBLE);
        read_lock(&tasklist_lock);
        tsk = current;
        do {
                retval = do_wait_thread(wo, tsk);
                if (retval)
                        goto end;

                retval = ptrace_do_wait(wo, tsk);
                if (retval)
                        goto end;

                if (wo->wo_flags & __WNOTHREAD)
                        break;
        } while_each_thread(current, tsk);
        read_unlock(&tasklist_lock);

notask:
        retval = wo->notask_error;
        if (!retval && !(wo->wo_flags & WNOHANG)) {
                retval = -ERESTARTSYS;
                if (!signal_pending(current)) {
                        schedule();
                        goto repeat;
                }
        }
end:
        __set_current_state(TASK_RUNNING);
        remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
        return retval;
}

SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
                infop, int, options, struct rusage __user *, ru)
{
        struct wait_opts wo;
        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);

        wo.wo_type      = type;
        wo.wo_pid       = pid;
        wo.wo_flags     = options;
        wo.wo_info      = infop;
        wo.wo_stat      = NULL;
        wo.wo_rusage    = ru;
        ret = do_wait(&wo);

        if (ret > 0) {
                ret = 0;
        } else if (infop) {
                /*
                 * For a WNOHANG return, clear out all the fields
                 * we would set so the user can easily tell the
                 * difference.
                 */
                if (!ret)
                        ret = put_user(0, &infop->si_signo);
                if (!ret)
                        ret = put_user(0, &infop->si_errno);
                if (!ret)
                        ret = put_user(0, &infop->si_code);
                if (!ret)
                        ret = put_user(0, &infop->si_pid);
                if (!ret)
                        ret = put_user(0, &infop->si_uid);
                if (!ret)
                        ret = put_user(0, &infop->si_status);
        }

        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 wait_opts wo;
        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);
        }

        wo.wo_type      = type;
        wo.wo_pid       = pid;
        wo.wo_flags     = options | WEXITED;
        wo.wo_info      = NULL;
        wo.wo_stat      = stat_addr;
        wo.wo_rusage    = ru;
        ret = do_wait(&wo);
        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