/* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h>#include <linux/slab.h>#include <linux/interrupt.h>#include <linux/module.h>#include <linux/capability.h>#include <linux/completion.h>#include <linux/personality.h>#include <linux/tty.h>#include <linux/iocontext.h>#include <linux/key.h>#include <linux/security.h>#include <linux/cpu.h>#include <linux/acct.h>#include <linux/tsacct_kern.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/freezer.h>#include <linux/binfmts.h>#include <linux/nsproxy.h>#include <linux/pid_namespace.h>#include <linux/ptrace.h>#include <linux/profile.h>#include <linux/mount.h>#include <linux/proc_fs.h>#include <linux/kthread.h>#include <linux/mempolicy.h>#include <linux/taskstats_kern.h>#include <linux/delayacct.h>#include <linux/cgroup.h>#include <linux/syscalls.h>#include <linux/signal.h>#include <linux/posix-timers.h>#include <linux/cn_proc.h>#include <linux/mutex.h>#include <linux/futex.h>#include <linux/pipe_fs_i.h>#include <linux/audit.h> /* for audit_free() */#include <linux/resource.h>#include <linux/blkdev.h>#include <linux/task_io_accounting_ops.h>#include <linux/tracehook.h>#include <linux/fs_struct.h>#include <linux/init_task.h>#include <linux/perf_event.h>#include <trace/events/sched.h>#include <linux/hw_breakpoint.h>#include <linux/oom.h>#include <linux/writeback.h>#include <linux/shm.h> #include <asm/uaccess.h>#include <asm/unistd.h>#include <asm/pgtable.h>#include <asm/mmu_context.h> static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p, bool group_dead){ nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node);} /* * This function expects the tasklist_lock write-locked. */static void __exit_signal(struct task_struct *tsk){ struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); cputime_t utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); posix_cpu_timers_exit(tsk); if (group_dead) { posix_cpu_timers_exit_group(tsk); tty = sig->tty; sig->tty = NULL; } else { /* * This can only happen if the caller is de_thread(). * FIXME: this is the temporary hack, we should teach * posix-cpu-timers to handle this case correctly. */ if (unlikely(has_group_leader_pid(tsk))) posix_cpu_timers_exit_group(tsk); /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); /* * Accumulate here the counters for all threads but the * group leader as they die, so they can be added into * the process-wide totals when those are taken. * The group leader stays around as a zombie as long * as there are other threads. When it gets reaped, * the exit.c code will add its counts into these totals. * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ task_cputime(tsk, &utime, &stime); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; } sig->nr_threads--; __unhash_process(tsk, group_dead); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk,TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); }} static void delayed_put_task_struct(struct rcu_head *rhp){ struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk);} void release_task(struct task_struct * p){ struct task_struct *leader; int zap_leader;repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); proc_flush_task(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); release_thread(p); call_rcu(&p->rcu, delayed_put_task_struct); p = leader; if (unlikely(zap_leader)) goto repeat;} /* * This checks not only the pgrp, but falls back on the pid if no * satisfactory pgrp is found. I dunno - gdb doesn't work correctly * without this... * * The caller must hold rcu lock or the tasklist lock. */struct pid *session_of_pgrp(struct pid *pgrp){ struct task_struct *p; struct pid *sid = NULL; p = pid_task(pgrp, PIDTYPE_PGID); if (p == NULL) p = pid_task(pgrp, PIDTYPE_PID); if (p != NULL) sid = task_session(p); return sid;} /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task){ struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1;} int is_current_pgrp_orphaned(void){ int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval;} static bool has_stopped_jobs(struct pid *pgrp){ struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false;} /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */static voidkill_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); }} #ifdef CONFIG_MEMCG/* * 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. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } 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_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */static void exit_mm(struct task_struct * tsk){ struct mm_struct *mm = tsk->mm; struct core_state *core_state; mm_release(tsk, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_sem around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ down_read(&mm->mmap_sem); core_state = mm->core_state; if (core_state) { struct core_thread self; up_read(&mm->mmap_sem); self.task = tsk; self.next = xchg(&core_state->dumper.next, &self); /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_task_state(tsk, TASK_RUNNING); down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); BUG_ON(mm != tsk->active_mm); /* more a memory barrier than a real lock */ task_lock(tsk); tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm);} /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */static struct task_struct *find_new_reaper(struct task_struct *father) __releases(&tasklist_lock) __acquires(&tasklist_lock){ struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *thread; thread = father; while_each_thread(father, thread) { if (thread->flags & PF_EXITING) continue; if (unlikely(pid_ns->child_reaper == father)) pid_ns->child_reaper = thread; return thread; } if (unlikely(pid_ns->child_reaper == father)) { write_unlock_irq(&tasklist_lock); if (unlikely(pid_ns == &init_pid_ns)) { panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); } else if (father->signal->has_child_subreaper) { struct task_struct *reaper; /* * Find the first ancestor marked as child_subreaper. * Note that the code below checks same_thread_group(reaper, * pid_ns->child_reaper). This is what we need to DTRT in a * PID namespace. However we still need the check above, seeLines 1–500 of 1632. Load more
/* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/security.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/pgtable.h> #include <asm/mmu_context.h> static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); cputime_t utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); posix_cpu_timers_exit(tsk); if (group_dead) { posix_cpu_timers_exit_group(tsk); tty = sig->tty; sig->tty = NULL; } else { /* * This can only happen if the caller is de_thread(). * FIXME: this is the temporary hack, we should teach * posix-cpu-timers to handle this case correctly. */ if (unlikely(has_group_leader_pid(tsk))) posix_cpu_timers_exit_group(tsk); /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); /* * Accumulate here the counters for all threads but the * group leader as they die, so they can be added into * the process-wide totals when those are taken. * The group leader stays around as a zombie as long * as there are other threads. When it gets reaped, * the exit.c code will add its counts into these totals. * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ task_cputime(tsk, &utime, &stime); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; } sig->nr_threads--; __unhash_process(tsk, group_dead); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk,TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void release_task(struct task_struct * p) { struct task_struct *leader; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); proc_flush_task(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); release_thread(p); call_rcu(&p->rcu, delayed_put_task_struct); p = leader; if (unlikely(zap_leader)) goto repeat; } /* * This checks not only the pgrp, but falls back on the pid if no * satisfactory pgrp is found. I dunno - gdb doesn't work correctly * without this... * * The caller must hold rcu lock or the tasklist lock. */ struct pid *session_of_pgrp(struct pid *pgrp) { struct task_struct *p; struct pid *sid = NULL; p = pid_task(pgrp, PIDTYPE_PGID); if (p == NULL) p = pid_task(pgrp, PIDTYPE_PID); if (p != NULL) sid = task_session(p); return sid; } /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } #ifdef CONFIG_MEMCG /* * 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. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } 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_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(struct task_struct * tsk) { struct mm_struct *mm = tsk->mm; struct core_state *core_state; mm_release(tsk, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_sem around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ down_read(&mm->mmap_sem); core_state = mm->core_state; if (core_state) { struct core_thread self; up_read(&mm->mmap_sem); self.task = tsk; self.next = xchg(&core_state->dumper.next, &self); /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_task_state(tsk, TASK_RUNNING); down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); BUG_ON(mm != tsk->active_mm); /* more a memory barrier than a real lock */ task_lock(tsk); tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *thread; thread = father; while_each_thread(father, thread) { if (thread->flags & PF_EXITING) continue; if (unlikely(pid_ns->child_reaper == father)) pid_ns->child_reaper = thread; return thread; } if (unlikely(pid_ns->child_reaper == father)) { write_unlock_irq(&tasklist_lock); if (unlikely(pid_ns == &init_pid_ns)) { panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); } else if (father->signal->has_child_subreaper) { struct task_struct *reaper; /* * Find the first ancestor marked as child_subreaper. * Note that the code below checks same_thread_group(reaper, * pid_ns->child_reaper). This is what we need to DTRT in a * PID namespace. However we still need the check above, see