Version:  2.6.24 2.6.25 2.6.26 2.6.27 2.6.28

Architecture:  x86 m68k m68knommu mips powerpc sh blackfin

   /*
    *  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/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 <trace/sched.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 inline int task_detached(struct task_struct *p)
  {
          return p->exit_signal == -1;
  }
  
  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);
          list_del_init(&p->sibling);
  }
  
  /*
   * 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));
  
          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->gtime = cputime_add(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 = NULL; /* Marker for below. */
         }
 
         __unhash_process(tsk);
 
         /*
          * Do this under ->siglock, we can race with another thread
          * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
          */
         flush_sigqueue(&tsk->pending);
 
         tsk->signal = NULL;
         tsk->sighand = NULL;
         spin_unlock(&sighand->siglock);
 
         __cleanup_sighand(sighand);
         clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
         if (sig) {
                 flush_sigqueue(&sig->shared_pending);
                 taskstats_tgid_free(sig);
                 /*
                  * Make sure ->signal can't go away under rq->lock,
                  * see account_group_exec_runtime().
                  */
                 task_rq_unlock_wait(tsk);
                 __cleanup_signal(sig);
         }
 }
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
         struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
         trace_sched_process_free(tsk);
         put_task_struct(tsk);
 }
 
 
 void release_task(struct task_struct * p)
 {
         struct task_struct *leader;
         int zap_leader;
 repeat:
         tracehook_prepare_release_task(p);
         atomic_dec(&p->user->processes);
         proc_flush_task(p);
         write_lock_irq(&tasklist_lock);
         tracehook_finish_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) {
                 BUG_ON(task_detached(leader));
                 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 = task_detached(leader);
 
                 /*
                  * This maintains the invariant that release_task()
                  * only runs on a task in EXIT_DEAD, just for sanity.
                  */
                 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 int has_stopped_jobs(struct pid *pgrp)
 {
         int retval = 0;
         struct task_struct *p;
 
         do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
                 if (!task_is_stopped(p))
                         continue;
                 retval = 1;
                 break;
         } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
         return retval;
 }
 
 /*
  * 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? */
         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(struct pid *pid)
 {
         struct task_struct *curr = current->group_leader;
         pid_t nr = pid_nr(pid);
 
         if (task_session(curr) != pid) {
                 change_pid(curr, PIDTYPE_SID, pid);
                 set_task_session(curr, nr);
         }
         if (task_pgrp(curr) != pid) {
                 change_pid(curr, PIDTYPE_PGID, pid);
                 set_task_pgrp(curr, nr);
         }
 }
 
 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 (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 | 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 */
 
         exit_fs(current);       /* current->fs->count--; */
         fs = init_task.fs;
         current->fs = fs;
         atomic_inc(&fs->count);
 
         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 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);
         }
 }
 
 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);
         }
 }
 
 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)) {
                 path_put(&fs->root);
                 path_put(&fs->pwd);
                 kmem_cache_free(fs_cachep, fs);
         }
 }
 
 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);
         }
 }
 
 EXPORT_SYMBOL_GPL(exit_fs);
 
 #ifdef CONFIG_MM_OWNER
 /*
  * Task p is exiting and it owned mm, lets find a new owner for it
  */
 static inline int
 mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
 {
         /*
          * If there are other users of the mm and the owner (us) is exiting
          * we need to find a new owner to take on the responsibility.
          */
         if (atomic_read(&mm->mm_users) <= 1)
                 return 0;
         if (mm->owner != p)
                 return 0;
         return 1;
 }
 
 void mm_update_next_owner(struct mm_struct *mm)
 {
         struct task_struct *c, *g, *p = current;
 
 retry:
         if (!mm_need_new_owner(mm, p))
                 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->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,
          * so that subsystems can understand the callback and take action.
          */
         down_write(&mm->mmap_sem);
         cgroup_mm_owner_callbacks(mm->owner, NULL);
         mm->owner = NULL;
         up_write(&mm->mmap_sem);
         return;
 
 assign_new_owner:
         BUG_ON(c == p);
         get_task_struct(c);
         read_unlock(&tasklist_lock);
         down_write(&mm->mmap_sem);
         /*
          * The task_lock protects c->mm from changing.
          * We always want mm->owner->mm == mm
          */
         task_lock(c);
         if (c->mm != mm) {
                 task_unlock(c);
                 up_write(&mm->mmap_sem);
                 put_task_struct(c);
                 goto retry;
         }
         cgroup_mm_owner_callbacks(mm->owner, c);
         mm->owner = c;
         task_unlock(c);
         up_write(&mm->mmap_sem);
         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);
         task_unlock(tsk);
         mm_update_next_owner(mm);
         mmput(mm);
 }
 
 /*
  * Return nonzero if @parent's children should reap themselves.
  *
  * Called with write_lock_irq(&tasklist_lock) held.
  */
 static int ignoring_children(struct task_struct *parent)
 {
         int ret;
         struct sighand_struct *psig = parent->sighand;
         unsigned long flags;
         spin_lock_irqsave(&psig->siglock, flags);
         ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
                (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
         spin_unlock_irqrestore(&psig->siglock, flags);
         return ret;
 }
 
 /*
  * Detach all tasks we were using ptrace on.
  * Any that need to be release_task'd are put on the @dead list.
  *
  * Called with write_lock(&tasklist_lock) held.
  */
 static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
 {
         struct task_struct *p, *n;
         int ign = -1;
 
         list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
                 __ptrace_unlink(p);
 
                 if (p->exit_state != EXIT_ZOMBIE)
                         continue;
 
                 /*
                  * If it's a zombie, our attachedness prevented normal
                  * parent notification or self-reaping.  Do notification
                  * now if it would have happened earlier.  If it should
                  * reap itself, add it to the @dead list.  We can't call
                  * release_task() here because we already hold tasklist_lock.
                  *
                  * If it's our own child, there is no notification to do.
                  * But if our normal children self-reap, then this child
                  * was prevented by ptrace and we must reap it now.
                  */
                 if (!task_detached(p) && thread_group_empty(p)) {
                         if (!same_thread_group(p->real_parent, parent))
                                 do_notify_parent(p, p->exit_signal);
                         else {
                                 if (ign < 0)
                                         ign = ignoring_children(parent);
                                 if (ign)
                                         p->exit_signal = -1;
                         }
                 }
 
                 if (task_detached(p)) {
                         /*
                          * Mark it as in the process of being reaped.
                          */
                         p->exit_state = EXIT_DEAD;
                         list_add(&p->ptrace_entry, dead);
                 }
         }
 }
 
 /*
  * Finish up exit-time ptrace cleanup.
  *
  * Called without locks.
  */
 static void ptrace_exit_finish(struct task_struct *parent,
                                struct list_head *dead)
 {
         struct task_struct *p, *n;
 
         BUG_ON(!list_empty(&parent->ptraced));
 
         list_for_each_entry_safe(p, n, dead, ptrace_entry) {
                 list_del_init(&p->ptrace_entry);
                 release_task(p);
         }
 }
 
 static void reparent_thread(struct task_struct *p, struct task_struct *father)
 {
         if (p->pdeath_signal)
                 /* We already hold the tasklist_lock here.  */
                 group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
 
         list_move_tail(&p->sibling, &p->real_parent->children);
 
         /* 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.  */
         if (!task_detached(p))
                 p->exit_signal = SIGCHLD;
 
         /* If we'd notified the old parent about this child's death,
          * also notify the new parent.
          */
         if (!ptrace_reparented(p) &&
             p->exit_state == EXIT_ZOMBIE &&
             !task_detached(p) && thread_group_empty(p))
                 do_notify_parent(p, p->exit_signal);
 
         kill_orphaned_pgrp(p, father);
 }
 
 /*
  * 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)
 {
         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;
 }
 
 static void forget_original_parent(struct task_struct *father)
 {
         struct task_struct *p, *n, *reaper;
         LIST_HEAD(ptrace_dead);
 
         write_lock_irq(&tasklist_lock);
         reaper = find_new_reaper(father);
         /*
          * First clean up ptrace if we were using it.
          */
         ptrace_exit(father, &ptrace_dead);
 
         list_for_each_entry_safe(p, n, &father->children, sibling) {
                 p->real_parent = reaper;
                 if (p->parent == father) {
                         BUG_ON(p->ptrace);
                         p->parent = p->real_parent;
                 }
                 reparent_thread(p, father);
         }
 
         write_unlock_irq(&tasklist_lock);
         BUG_ON(!list_empty(&father->children));
 
         ptrace_exit_finish(father, &ptrace_dead);
 }
 
 /*
  * 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)
 {
         int signal;
         void *cookie;
 
         /*
          * 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 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 && !task_detached(tsk) &&
             (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
              tsk->self_exec_id != tsk->parent_exec_id) &&
             !capable(CAP_KILL))
                 tsk->exit_signal = SIGCHLD;
 
         signal = tracehook_notify_death(tsk, &cookie, group_dead);
         if (signal >= 0)
                 signal = do_notify_parent(tsk, signal);
 
         tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
 
         /* mt-exec, de_thread() is waiting for us */
         if (thread_group_leader(tsk) &&
             tsk->signal->group_exit_task &&
             tsk->signal->notify_count < 0)
                 wake_up_process(tsk->signal->group_exit_task);
 
         write_unlock_irq(&tasklist_lock);
 
         tracehook_report_death(tsk, signal, cookie, group_dead);
 
         /* If the process is dead, release it - nobody will wait for it */
         if (signal == DEATH_REAP)
                 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
 
 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!");
 
         tracehook_report_exit(&code);
 
         /*
          * 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();
         }
 
         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();
         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);
         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) {
                 hrtimer_cancel(&tsk->signal->real_timer);
                 exit_itimers(tsk->signal);
         }
         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_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_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
         mpol_put(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)))