X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=kernel%2Fexit.c;h=29617024d245a36b90e0f1399366485e3594d74b;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=d27b470ec5aa69d0e211795f740e35c178542806;hpb=6a77f38946aaee1cd85eeec6cf4229b204c15071;p=linux-2.6.git diff --git a/kernel/exit.c b/kernel/exit.c index d27b470ec..29617024d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -4,29 +4,50 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include #include #include #include #include #include +#include #include #include #include -#include +#include #include #include #include #include +#include #include #include +#include +#include +#include #include #include #include #include #include +#include +#include +#include #include +#include +#include +#include +#include +#include +#include +#include +#include /* for audit_free() */ +#include +#include #include +#include +#include +#include +#include #include #include @@ -34,47 +55,106 @@ #include extern void sem_exit (void); -extern struct task_struct *child_reaper; -int getrusage(struct task_struct *, int, struct rusage __user *); +static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p) { nr_threads--; - /* tasklist_lock is held, is this sufficient? */ - if (p->vx_info) { - atomic_dec(&p->vx_info->cvirt.nr_threads); - vx_nproc_dec(p); - } detach_pid(p, PIDTYPE_PID); - detach_pid(p, PIDTYPE_TGID); if (thread_group_leader(p)) { detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); - if (p->pid) - __get_cpu_var(process_counts)--; + + list_del_rcu(&p->tasks); + __get_cpu_var(process_counts)--; + } + list_del_rcu(&p->thread_group); + remove_parent(p); +} + +/* + * This function expects the tasklist_lock write-locked. + */ +static void __exit_signal(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct sighand_struct *sighand; + + BUG_ON(!sig); + BUG_ON(!atomic_read(&sig->count)); + + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + spin_lock(&sighand->siglock); + + posix_cpu_timers_exit(tsk); + if (atomic_dec_and_test(&sig->count)) + posix_cpu_timers_exit_group(tsk); + else { + /* + * If there is any task waiting for the group exit + * then notify it: + */ + if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) { + wake_up_process(sig->group_exit_task); + sig->group_exit_task = NULL; + } + 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->min_flt += tsk->min_flt; + sig->maj_flt += tsk->maj_flt; + sig->nvcsw += tsk->nvcsw; + sig->nivcsw += tsk->nivcsw; + sig->sched_time += tsk->sched_time; + sig = NULL; /* Marker for below. */ } - REMOVE_LINKS(p); + __unhash_process(tsk); + + tsk->signal = NULL; + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + + __cleanup_sighand(sighand); + clear_tsk_thread_flag(tsk,TIF_SIGPENDING); + flush_sigqueue(&tsk->pending); + if (sig) { + flush_sigqueue(&sig->shared_pending); + taskstats_tgid_free(sig); + __cleanup_signal(sig); + } +} + +static void delayed_put_task_struct(struct rcu_head *rhp) +{ + put_task_struct(container_of(rhp, struct task_struct, rcu)); } void release_task(struct task_struct * p) { + struct task_struct *leader; int zap_leader; - task_t *leader; - struct dentry *proc_dentry; - -repeat: + int inhibited_leader; +repeat: + tracehook_release_task(p); atomic_dec(&p->user->processes); - spin_lock(&p->proc_lock); - proc_dentry = proc_pid_unhash(p); write_lock_irq(&tasklist_lock); - if (unlikely(p->ptrace)) - __ptrace_unlink(p); - BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); + BUG_ON(tracehook_check_released(p)); __exit_signal(p); - __exit_sighand(p); - __unhash_process(p); /* * If we are the last non-leader member of the thread @@ -82,10 +162,14 @@ repeat: * group leader's parent process. (if it wants notification.) */ zap_leader = 0; + inhibited_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { BUG_ON(leader->exit_signal == -1); - do_notify_parent(leader, leader->exit_signal); + if (tracehook_inhibit_wait_zombie(leader)) + inhibited_leader = 1; + else + 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, @@ -99,31 +183,20 @@ repeat: sched_exit(p); write_unlock_irq(&tasklist_lock); - spin_unlock(&p->proc_lock); - proc_pid_flush(proc_dentry); + proc_flush_task(p); release_thread(p); - if (p->vx_info) - release_vx_info(p->vx_info, p); - put_task_struct(p); + call_rcu(&p->rcu, delayed_put_task_struct); p = leader; if (unlikely(zap_leader)) goto repeat; -} - -/* we are using it only for SMP init */ -void unhash_process(struct task_struct *p) -{ - struct dentry *proc_dentry; - - spin_lock(&p->proc_lock); - proc_dentry = proc_pid_unhash(p); - write_lock_irq(&tasklist_lock); - __unhash_process(p); - write_unlock_irq(&tasklist_lock); - spin_unlock(&p->proc_lock); - proc_pid_flush(proc_dentry); + /* + * If tracing usurps normal reaping of the leader, tracing needs + * to be notified it would normally be reapable now. + */ + if (unlikely(inhibited_leader)) + tracehook_report_delayed_group_leader(leader); } /* @@ -134,21 +207,18 @@ void unhash_process(struct task_struct *p) int session_of_pgrp(int pgrp) { struct task_struct *p; - int sid = -1; + int sid = 0; read_lock(&tasklist_lock); - do_each_task_pid(pgrp, PIDTYPE_PGID, p) { - if (p->signal->session > 0) { - sid = p->signal->session; - goto out; - } - } while_each_task_pid(pgrp, PIDTYPE_PGID, p); - p = find_task_by_pid(pgrp); - if (p) - sid = p->signal->session; -out: + + p = find_task_by_pid_type(PIDTYPE_PGID, pgrp); + if (p == NULL) + p = find_task_by_pid(pgrp); + if (p != NULL) + sid = process_session(p); + read_unlock(&tasklist_lock); - + return sid; } @@ -160,7 +230,7 @@ out: * * "I ask you, have you ever known what it is to be an orphan?" */ -static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) +static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task) { struct task_struct *p; int ret = 1; @@ -168,10 +238,10 @@ static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) do_each_task_pid(pgrp, PIDTYPE_PGID, p) { if (p == ignored_task || p->exit_state - || p->real_parent->pid == 1) + || is_init(p->parent)) continue; - if (process_group(p->real_parent) != pgrp - && p->real_parent->signal->session == p->signal->session) { + if (process_group(p->parent) != pgrp && + process_session(p->parent) == process_session(p)) { ret = 0; break; } @@ -190,7 +260,7 @@ int is_orphaned_pgrp(int pgrp) return retval; } -static inline int has_stopped_jobs(int pgrp) +static int has_stopped_jobs(int pgrp) { int retval = 0; struct task_struct *p; @@ -198,17 +268,6 @@ static inline int has_stopped_jobs(int pgrp) do_each_task_pid(pgrp, PIDTYPE_PGID, p) { if (p->state != TASK_STOPPED) continue; - - /* If p is stopped by a debugger on a signal that won't - stop it, then don't count p as stopped. This isn't - perfect but it's a good approximation. */ - if (unlikely (p->ptrace) - && p->exit_code != SIGSTOP - && p->exit_code != SIGTSTP - && p->exit_code != SIGTTOU - && p->exit_code != SIGTTIN) - continue; - retval = 1; break; } while_each_task_pid(pgrp, PIDTYPE_PGID, p); @@ -216,7 +275,8 @@ static inline int has_stopped_jobs(int pgrp) } /** - * reparent_to_init() - Reparent the calling kernel thread to the init task. + * reparent_to_init - Reparent the calling kernel thread to the init task + * of the pid space that the thread belongs to. * * If a kernel thread is launched as a result of a system call, or if * it ever exits, it should generally reparent itself to init so that @@ -227,22 +287,19 @@ static inline int has_stopped_jobs(int pgrp) * * NOTE that reparent_to_init() gives the caller full capabilities. */ -void reparent_to_init(void) +static void reparent_to_init(void) { write_lock_irq(&tasklist_lock); - ptrace_unlink(current); /* Reparent to init */ - REMOVE_LINKS(current); - /* FIXME handle vchild_reaper/initpid */ - current->parent = child_reaper; - current->real_parent = child_reaper; - SET_LINKS(current); + remove_parent(current); + current->parent = child_reaper(current); + add_parent(current); /* Set the exit signal to SIGCHLD so we signal init on exit */ current->exit_signal = SIGCHLD; - if ((current->policy == SCHED_NORMAL) && (task_nice(current) < 0)) + if (!has_rt_policy(current) && (task_nice(current) < 0)) set_user_nice(current, 0); /* cpus_allowed? */ /* rt_priority? */ @@ -257,11 +314,11 @@ void reparent_to_init(void) void __set_special_pids(pid_t session, pid_t pgrp) { - struct task_struct *curr = current; + struct task_struct *curr = current->group_leader; - if (curr->signal->session != session) { + if (process_session(curr) != session) { detach_pid(curr, PIDTYPE_SID); - curr->signal->session = session; + set_signal_session(curr->signal, session); attach_pid(curr, PIDTYPE_SID, session); } if (process_group(curr) != pgrp) { @@ -271,7 +328,7 @@ void __set_special_pids(pid_t session, pid_t pgrp) } } -void set_special_pids(pid_t session, pid_t pgrp) +static void set_special_pids(pid_t session, pid_t pgrp) { write_lock_irq(&tasklist_lock); __set_special_pids(session, pgrp); @@ -285,7 +342,7 @@ void set_special_pids(pid_t session, pid_t pgrp) */ int allow_signal(int sig) { - if (sig < 1 || sig > _NSIG) + if (!valid_signal(sig) || sig < 1) return -EINVAL; spin_lock_irq(¤t->sighand->siglock); @@ -306,7 +363,7 @@ EXPORT_SYMBOL(allow_signal); int disallow_signal(int sig) { - if (sig < 1 || sig > _NSIG) + if (!valid_signal(sig) || sig < 1) return -EINVAL; spin_lock_irq(¤t->sighand->siglock); @@ -341,9 +398,7 @@ void daemonize(const char *name, ...) exit_mm(current); set_special_pids(1, 1); - down(&tty_sem); - current->signal->tty = NULL; - up(&tty_sem); + proc_clear_tty(current); /* Block and flush all signals */ sigfillset(&blocked); @@ -356,6 +411,11 @@ void daemonize(const char *name, ...) fs = init_task.fs; current->fs = fs; atomic_inc(&fs->count); + + exit_task_namespaces(current); + current->nsproxy = init_task.nsproxy; + get_task_namespaces(current); + exit_files(current); current->files = init_task.files; atomic_inc(¤t->files->count); @@ -365,26 +425,35 @@ void daemonize(const char *name, ...) EXPORT_SYMBOL(daemonize); -static inline void close_files(struct files_struct * files) +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 >= files->max_fdset || i >= files->max_fds) + if (i >= fdt->max_fds) break; - set = files->open_fds->fds_bits[j++]; + set = fdt->open_fds->fds_bits[j++]; while (set) { if (set & 1) { - struct file * file = xchg(&files->fd[i], NULL); + struct file * file = xchg(&fdt->fd[i], NULL); if (file) filp_close(file, files); vx_openfd_dec(i); } i++; set >>= 1; + cond_resched(); } } } @@ -404,23 +473,37 @@ struct files_struct *get_files_struct(struct task_struct *task) void fastcall put_files_struct(struct files_struct *files) { + struct fdtable *fdt; + if (atomic_dec_and_test(&files->count)) { close_files(files); /* * Free the fd and fdset arrays if we expanded them. + * If the fdtable was embedded, pass files for freeing + * at the end of the RCU grace period. Otherwise, + * you can free files immediately. */ - if (files->fd != &files->fd_array[0]) - free_fd_array(files->fd, files->max_fds); - if (files->max_fdset > __FD_SETSIZE) { - free_fdset(files->open_fds, files->max_fdset); - free_fdset(files->close_on_exec, files->max_fdset); - } - kmem_cache_free(files_cachep, files); + fdt = files_fdtable(files); + if (fdt != &files->fdtab) + kmem_cache_free(files_cachep, files); + free_fdtable(fdt); } } EXPORT_SYMBOL(put_files_struct); +void reset_files_struct(struct task_struct *tsk, struct files_struct *files) +{ + struct files_struct *old; + + old = tsk->files; + task_lock(tsk); + tsk->files = files; + task_unlock(tsk); + put_files_struct(old); +} +EXPORT_SYMBOL(reset_files_struct); + static inline void __exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; @@ -450,6 +533,7 @@ static inline void __put_fs_struct(struct fs_struct *fs) dput(fs->altroot); mntput(fs->altrootmnt); } + atomic_dec(&vs_global_fs); kmem_cache_free(fs_cachep, fs); } } @@ -482,7 +566,7 @@ EXPORT_SYMBOL_GPL(exit_fs); * Turn us into a lazy TLB process if we * aren't already.. */ -void exit_mm(struct task_struct * tsk) +static void exit_mm(struct task_struct * tsk) { struct mm_struct *mm = tsk->mm; @@ -508,7 +592,7 @@ void exit_mm(struct task_struct * tsk) down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); - if (mm != tsk->active_mm) BUG(); + BUG_ON(mm != tsk->active_mm); /* more a memory barrier than a real lock */ task_lock(tsk); tsk->mm = NULL; @@ -518,58 +602,52 @@ void exit_mm(struct task_struct * tsk) mmput(mm); } -static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_reaper) +static inline void +choose_new_parent(struct task_struct *p, struct task_struct *reaper) { + /* check for reaper context */ + vxwprintk((p->xid != reaper->xid) && (reaper != child_reaper(p)), + "rogue reaper: %p[%d,#%u] <> %p[%d,#%u]", + p, p->pid, p->xid, reaper, reaper->pid, reaper->xid); + + if (p == reaper) + reaper = vx_child_reaper(p); + /* * Make sure we're not reparenting to ourselves and that * the parent is not a zombie. */ - BUG_ON(p == reaper || reaper->exit_state >= EXIT_ZOMBIE); - p->real_parent = reaper; - if (p->parent == p->real_parent) - BUG(); + BUG_ON(p == reaper || reaper->exit_state); + p->parent = reaper; } -static inline void reparent_thread(task_t *p, task_t *father, int traced) +static void +reparent_thread(struct task_struct *p, struct task_struct *father) { - /* We don't want people slaying init. */ - if (p->exit_signal != -1) - p->exit_signal = SIGCHLD; - if (p->pdeath_signal) /* We already hold the tasklist_lock here. */ - group_send_sig_info(p->pdeath_signal, (void *) 0, p); + group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); /* Move the child from its dying parent to the new one. */ - if (unlikely(traced)) { - /* Preserve ptrace links if someone else is tracing this child. */ - list_del_init(&p->ptrace_list); - if (p->parent != p->real_parent) - list_add(&p->ptrace_list, &p->real_parent->ptrace_children); - } else { - /* If this child is being traced, then we're the one tracing it - * anyway, so let go of it. - */ - p->ptrace = 0; - list_del_init(&p->sibling); - p->parent = p->real_parent; - list_add_tail(&p->sibling, &p->parent->children); + list_move_tail(&p->sibling, &p->parent->children); - /* If we'd notified the old parent about this child's death, - * also notify the new parent. - */ - if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 && - thread_group_empty(p)) - do_notify_parent(p, p->exit_signal); - else if (p->state == TASK_TRACED) { - /* - * If it was at a trace stop, turn it into - * a normal stop since it's no longer being - * traced. - */ - ptrace_untrace(p); - } - } + /* If this is a threaded reparent there is no need to + * notify anyone anything has happened. + */ + if (p->parent->group_leader == father->group_leader) + return; + + /* We don't want people slaying init. */ + if (p->exit_signal != -1) + p->exit_signal = SIGCHLD; + + /* If we'd notified the old parent about this child's death, + * also notify the new parent. + */ + if (!tracehook_inhibit_wait_zombie(p) && + p->exit_state == EXIT_ZOMBIE && + p->exit_signal != -1 && thread_group_empty(p)) + do_notify_parent(p, p->exit_signal); /* * process group orphan check @@ -578,12 +656,13 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * outside, so the child pgrp is now orphaned. */ if ((process_group(p) != process_group(father)) && - (p->signal->session == father->signal->session)) { + (process_session(p) == process_session(father))) { int pgrp = process_group(p); - if (will_become_orphaned_pgrp(pgrp, NULL) && has_stopped_jobs(pgrp)) { - __kill_pg_info(SIGHUP, (void *)1, pgrp); - __kill_pg_info(SIGCONT, (void *)1, pgrp); + if (will_become_orphaned_pgrp(pgrp, NULL) && + has_stopped_jobs(pgrp)) { + __kill_pg_info(SIGHUP, SEND_SIG_PRIV, pgrp); + __kill_pg_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } } @@ -592,65 +671,28 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * 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 global child reaper process (ie "init") + * the child reaper process (ie "init") in our pid + * space. */ -static inline void forget_original_parent(struct task_struct * father, - struct list_head *to_release) +static void +forget_original_parent(struct task_struct *father) { struct task_struct *p, *reaper = father; struct list_head *_p, *_n; - /* FIXME handle vchild_reaper/initpid */ do { reaper = next_thread(reaper); if (reaper == father) { - reaper = child_reaper; + // reaper = child_reaper(father); + reaper = vx_child_reaper(father); break; } } while (reaper->exit_state); - /* - * There are only two places where our children can be: - * - * - in our child list - * - in our ptraced child list - * - * Search them and reparent children. - */ list_for_each_safe(_p, _n, &father->children) { - int ptrace; - p = list_entry(_p,struct task_struct,sibling); - - ptrace = p->ptrace; - - /* if father isn't the real parent, then ptrace must be enabled */ - BUG_ON(father != p->real_parent && !ptrace); - - if (father == p->real_parent) { - /* reparent with a reaper, real father it's us */ - choose_new_parent(p, reaper, child_reaper); - reparent_thread(p, father, 0); - } else { - /* reparent ptraced task to its real parent */ - __ptrace_unlink (p); - if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 && - thread_group_empty(p)) - do_notify_parent(p, p->exit_signal); - } - - /* - * if the ptraced child is a zombie with exit_signal == -1 - * we must collect it before we exit, or it will remain - * zombie forever since we prevented it from self-reap itself - * while it was being traced by us, to be able to see it in wait4. - */ - if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1)) - list_add(&p->ptrace_list, to_release); - } - list_for_each_safe(_p, _n, &father->ptrace_children) { - p = list_entry(_p,struct task_struct,ptrace_list); - choose_new_parent(p, reaper, child_reaper); - reparent_thread(p, father, 1); + p = list_entry(_p, struct task_struct, sibling); + choose_new_parent(p, reaper); + reparent_thread(p, father); } } @@ -662,7 +704,8 @@ static void exit_notify(struct task_struct *tsk) { int state; struct task_struct *t; - struct list_head ptrace_dead, *_p, *_n; + int noreap; + void *cookie; if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT) && !thread_group_empty(tsk)) { @@ -698,10 +741,8 @@ static void exit_notify(struct task_struct *tsk) * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ - INIT_LIST_HEAD(&ptrace_dead); - forget_original_parent(tsk, &ptrace_dead); + forget_original_parent(tsk); BUG_ON(!list_empty(&tsk->children)); - BUG_ON(!list_empty(&tsk->ptrace_children)); /* * Check to see if any process groups have become orphaned @@ -713,14 +754,14 @@ static void exit_notify(struct task_struct *tsk) * is about to become orphaned. */ - t = tsk->real_parent; + t = tsk->parent; if ((process_group(t) != process_group(tsk)) && - (t->signal->session == tsk->signal->session) && + (process_session(t) == process_session(tsk)) && will_become_orphaned_pgrp(process_group(tsk), tsk) && has_stopped_jobs(process_group(tsk))) { - __kill_pg_info(SIGHUP, (void *)1, process_group(tsk)); - __kill_pg_info(SIGCONT, (void *)1, process_group(tsk)); + __kill_pg_info(SIGHUP, SEND_SIG_PRIV, process_group(tsk)); + __kill_pg_info(SIGCONT, SEND_SIG_PRIV, process_group(tsk)); } /* Let father know we died @@ -745,47 +786,22 @@ static void exit_notify(struct task_struct *tsk) && !capable(CAP_KILL)) tsk->exit_signal = SIGCHLD; - - /* If something other than our normal parent is ptracing us, then - * send it a SIGCHLD instead of honoring exit_signal. exit_signal - * only has special meaning to our real parent. - */ - if (tsk->exit_signal != -1 && thread_group_empty(tsk)) { - int signal = tsk->parent == tsk->real_parent ? tsk->exit_signal : SIGCHLD; - do_notify_parent(tsk, signal); - } else if (tsk->ptrace) { - do_notify_parent(tsk, SIGCHLD); - } + if (!tracehook_notify_death(tsk, &noreap, &cookie) + && tsk->exit_signal != -1 && thread_group_empty(tsk)) + do_notify_parent(tsk, tsk->exit_signal); state = EXIT_ZOMBIE; - if (tsk->exit_signal == -1 && - (likely(tsk->ptrace == 0) || - unlikely(tsk->parent->signal->flags & SIGNAL_GROUP_EXIT))) + if (tsk->exit_signal == -1 && !noreap) state = EXIT_DEAD; tsk->exit_state = state; - /* - * Clear these here so that update_process_times() won't try to deliver - * itimer, profile or rlimit signals to this task while it is in late exit. - */ - tsk->it_virt_value = cputime_zero; - tsk->it_prof_value = cputime_zero; - write_unlock_irq(&tasklist_lock); - list_for_each_safe(_p, _n, &ptrace_dead) { - list_del_init(_p); - t = list_entry(_p,struct task_struct,ptrace_list); - release_task(t); - } + tracehook_report_death(tsk, state, cookie); /* If the process is dead, release it - nobody will wait for it */ if (state == EXIT_DEAD) release_task(tsk); - - /* PF_DEAD causes final put_task_struct after we schedule. */ - preempt_disable(); - tsk->flags |= PF_DEAD; } fastcall NORET_TYPE void do_exit(long code) @@ -795,68 +811,137 @@ fastcall NORET_TYPE void do_exit(long code) profile_task_exit(tsk); + WARN_ON(atomic_read(&tsk->fs_excl)); + if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); - if (unlikely(tsk->pid == 1)) - panic("Attempted to kill init!"); - if (tsk->io_context) - exit_io_context(); + if (unlikely(tsk == child_reaper(tsk))) { + if (tsk->nsproxy->pid_ns != &init_pid_ns) + tsk->nsproxy->pid_ns->child_reaper = init_pid_ns.child_reaper; + else + panic("Attempted to kill init!"); + } + - if (unlikely(current->ptrace & PT_TRACE_EXIT)) { - current->ptrace_message = code; - ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); + 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"); + if (tsk->io_context) + exit_io_context(); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); } tsk->flags |= PF_EXITING; - del_timer_sync(&tsk->real_timer); + + ptrace_exit(tsk); if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, current->pid, preempt_count()); - acct_update_integrals(); - update_mem_hiwater(); + 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) - acct_process(code); + if (group_dead) { + hrtimer_cancel(&tsk->signal->real_timer); + exit_itimers(tsk->signal); + } + acct_collect(code, group_dead); + if (unlikely(tsk->robust_list)) + exit_robust_list(tsk); +#if defined(CONFIG_FUTEX) && defined(CONFIG_COMPAT) + if (unlikely(tsk->compat_robust_list)) + compat_exit_robust_list(tsk); +#endif + if (unlikely(tsk->audit_context)) + audit_free(tsk); + + taskstats_exit(tsk, group_dead); + exit_mm(tsk); + if (group_dead) + acct_process(); exit_sem(tsk); __exit_files(tsk); __exit_fs(tsk); - exit_namespace(tsk); exit_thread(); + cpuset_exit(tsk); exit_keys(tsk); if (group_dead && tsk->signal->leader) disassociate_ctty(1); - module_put(tsk->thread_info->exec_domain->module); + module_put(task_thread_info(tsk)->exec_domain->module); if (tsk->binfmt) module_put(tsk->binfmt->module); tsk->exit_code = code; + proc_exit_connector(tsk); + exit_task_namespaces(tsk); + // ns = exit_task_namespaces_early(tsk); + /* needs to stay before exit_notify() */ + exit_vx_info_early(tsk, code); exit_notify(tsk); + // exit_task_namespaces(tsk, ns); #ifdef CONFIG_NUMA mpol_free(tsk->mempolicy); tsk->mempolicy = NULL; #endif + /* + * This must happen late, after the PID is not + * hashed anymore: + */ + if (unlikely(!list_empty(&tsk->pi_state_list))) + exit_pi_state_list(tsk); + if (unlikely(current->pi_state_cache)) + kfree(current->pi_state_cache); + /* + * Make sure we are holding no locks: + */ + debug_check_no_locks_held(tsk); + + if (tsk->io_context) + exit_io_context(); + + if (tsk->splice_pipe) + __free_pipe_info(tsk->splice_pipe); + + /* needs to stay after exit_notify() */ + exit_vx_info(tsk, code); + exit_nx_info(tsk); + + preempt_disable(); + /* causes final put_task_struct in finish_task_switch(). */ + tsk->state = TASK_DEAD; - BUG_ON(!(current->flags & PF_DEAD)); schedule(); BUG(); /* Avoid "noreturn function does return". */ - for (;;) ; + 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); } @@ -867,13 +952,6 @@ asmlinkage long sys_exit(int error_code) do_exit((error_code&0xff)<<8); } -task_t fastcall *next_thread(const task_t *p) -{ - return pid_task(p->pids[PIDTYPE_TGID].pid_list.next, PIDTYPE_TGID); -} - -EXPORT_SYMBOL(next_thread); - /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). @@ -888,18 +966,15 @@ do_group_exit(int exit_code) else if (!thread_group_empty(current)) { struct signal_struct *const sig = current->signal; struct sighand_struct *const sighand = current->sighand; - read_lock(&tasklist_lock); spin_lock_irq(&sighand->siglock); if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { - sig->flags = SIGNAL_GROUP_EXIT; sig->group_exit_code = exit_code; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); - read_unlock(&tasklist_lock); } do_exit(exit_code); @@ -916,7 +991,7 @@ asmlinkage void sys_exit_group(int error_code) do_group_exit((error_code & 0xff) << 8); } -static int eligible_child(pid_t pid, int options, task_t *p) +static int eligible_child(pid_t pid, int options, struct task_struct *p) { if (pid > 0) { if (p->pid != pid) @@ -930,10 +1005,9 @@ static int eligible_child(pid_t pid, int options, task_t *p) } /* - * Do not consider detached threads that are - * not ptraced: + * Do not consider detached threads. */ - if (p->exit_signal == -1 && !p->ptrace) + if (p->exit_signal == -1) return 0; /* Wait for all children (clone and not) if __WALL is set; @@ -948,7 +1022,7 @@ static int eligible_child(pid_t pid, int options, task_t *p) * Do not consider thread group leaders that are * in a non-empty thread group: */ - if (current->tgid != p->tgid && delay_group_leader(p)) + if (delay_group_leader(p)) return 2; if (security_task_wait(p)) @@ -957,12 +1031,13 @@ static int eligible_child(pid_t pid, int options, task_t *p) return 1; } -static int wait_noreap_copyout(task_t *p, pid_t pid, uid_t uid, +static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, int why, int status, struct siginfo __user *infop, struct rusage __user *rusagep) { int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + put_task_struct(p); if (!retval) retval = put_user(SIGCHLD, &infop->si_signo); @@ -987,7 +1062,7 @@ static int wait_noreap_copyout(task_t *p, pid_t pid, uid_t uid, * 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(task_t *p, int noreap, +static int wait_task_zombie(struct task_struct *p, int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1003,7 +1078,7 @@ static int wait_task_zombie(task_t *p, int noreap, if (unlikely(p->exit_state != EXIT_ZOMBIE)) return 0; - if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) + if (unlikely(p->exit_signal == -1)) return 0; get_task_struct(p); read_unlock(&tasklist_lock); @@ -1027,15 +1102,12 @@ static int wait_task_zombie(task_t *p, int noreap, BUG_ON(state != EXIT_DEAD); return 0; } - if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) { - /* - * This can only happen in a race with a ptraced thread - * dying on another processor. - */ - return 0; - } + BUG_ON(p->exit_signal == -1); + + if (likely(p->signal)) { + struct signal_struct *psig; + struct signal_struct *sig; - if (likely(p->real_parent == p->parent) && likely(p->signal)) { /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group @@ -1052,24 +1124,26 @@ static int wait_task_zombie(task_t *p, int noreap, * here reaping other children at the same time. */ spin_lock_irq(&p->parent->sighand->siglock); - p->parent->signal->cutime = - cputime_add(p->parent->signal->cutime, + psig = p->parent->signal; + sig = p->signal; + psig->cutime = + cputime_add(psig->cutime, cputime_add(p->utime, - cputime_add(p->signal->utime, - p->signal->cutime))); - p->parent->signal->cstime = - cputime_add(p->parent->signal->cstime, + cputime_add(sig->utime, + sig->cutime))); + psig->cstime = + cputime_add(psig->cstime, cputime_add(p->stime, - cputime_add(p->signal->stime, - p->signal->cstime))); - p->parent->signal->cmin_flt += - p->min_flt + p->signal->min_flt + p->signal->cmin_flt; - p->parent->signal->cmaj_flt += - p->maj_flt + p->signal->maj_flt + p->signal->cmaj_flt; - p->parent->signal->cnvcsw += - p->nvcsw + p->signal->nvcsw + p->signal->cnvcsw; - p->parent->signal->cnivcsw += - p->nivcsw + p->signal->nivcsw + p->signal->cnivcsw; + cputime_add(sig->stime, + sig->cstime))); + 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; spin_unlock_irq(&p->parent->sighand->siglock); } @@ -1112,28 +1186,8 @@ static int wait_task_zombie(task_t *p, int noreap, return retval; } retval = p->pid; - if (p->real_parent != p->parent) { - write_lock_irq(&tasklist_lock); - /* Double-check with lock held. */ - if (p->real_parent != p->parent) { - __ptrace_unlink(p); - // TODO: is this safe? - p->exit_state = EXIT_ZOMBIE; - /* - * If this is not a detached task, notify the parent. - * If it's still not detached after that, don't release - * it now. - */ - if (p->exit_signal != -1) { - do_notify_parent(p, p->exit_signal); - if (p->exit_signal != -1) - p = NULL; - } - } - write_unlock_irq(&tasklist_lock); - } - if (p != NULL) - release_task(p); + release_task(p); + BUG_ON(!retval); return retval; } @@ -1144,15 +1198,15 @@ static int wait_task_zombie(task_t *p, int noreap, * 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_stopped(task_t *p, int delayed_group_leader, int noreap, - struct siginfo __user *infop, +static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, + int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code; if (!p->exit_code) return 0; - if (delayed_group_leader && !(p->ptrace & PT_PTRACED) && + if (delayed_group_leader && p->signal && p->signal->group_stop_count > 0) /* * A group stop is in progress and this is the group leader. @@ -1173,14 +1227,13 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap, if (unlikely(noreap)) { pid_t pid = p->pid; uid_t uid = p->uid; - int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; exit_code = p->exit_code; if (unlikely(!exit_code) || - unlikely(p->state > TASK_STOPPED)) + unlikely(p->state & TASK_TRACED)) goto bail_ref; - return wait_noreap_copyout(p, pid, uid, - why, (exit_code << 8) | 0x7f, + return wait_noreap_copyout(p, pid, uid, CLD_STOPPED, + (exit_code << 8) | 0x7f, infop, ru); } @@ -1224,7 +1277,7 @@ bail_ref: /* move to end of parent's list to avoid starvation */ remove_parent(p); - add_parent(p, p->parent); + add_parent(p); write_unlock_irq(&tasklist_lock); @@ -1236,9 +1289,7 @@ bail_ref: if (!retval && infop) retval = put_user(0, &infop->si_errno); if (!retval && infop) - retval = put_user((short)((p->ptrace & PT_PTRACED) - ? CLD_TRAPPED : CLD_STOPPED), - &infop->si_code); + retval = put_user((short)CLD_STOPPED, &infop->si_code); if (!retval && infop) retval = put_user(exit_code, &infop->si_status); if (!retval && infop) @@ -1259,7 +1310,7 @@ bail_ref: * 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(task_t *p, int noreap, +static int wait_task_continued(struct task_struct *p, int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1306,22 +1357,6 @@ static int wait_task_continued(task_t *p, int noreap, } -static inline int my_ptrace_child(struct task_struct *p) -{ - if (!(p->ptrace & PT_PTRACED)) - return 0; - if (!(p->ptrace & PT_ATTACHED)) - return 1; - /* - * This child was PTRACE_ATTACH'd. We should be seeing it only if - * we are the attacher. If we are the real parent, this is a race - * inside ptrace_attach. It is waiting for the tasklist_lock, - * which we have to switch the parent links, but has already set - * the flags in p->ptrace. - */ - return (p->parent != p->real_parent); -} - static long do_wait(pid_t pid, int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1345,7 +1380,7 @@ repeat: int ret; list_for_each(_p,&tsk->children) { - p = list_entry(_p,struct task_struct,sibling); + p = list_entry(_p, struct task_struct, sibling); ret = eligible_child(pid, options, p); if (!ret) @@ -1353,17 +1388,17 @@ repeat: switch (p->state) { case TASK_TRACED: - if (!my_ptrace_child(p)) - continue; - /*FALLTHROUGH*/ + flag = 1; + continue; case TASK_STOPPED: /* * It's stopped now, so it might later * continue, exit, or stop again. */ flag = 1; - if (!(options & WUNTRACED) && - !my_ptrace_child(p)) + if (!(options & WUNTRACED)) + continue; + if (tracehook_inhibit_wait_stopped(p)) continue; retval = wait_task_stopped(p, ret == 2, (options & WNOWAIT), @@ -1388,6 +1423,10 @@ repeat: goto check_continued; if (!likely(options & WEXITED)) continue; + if (tracehook_inhibit_wait_zombie(p)) { + flag = 1; + continue; + } retval = wait_task_zombie( p, (options & WNOWAIT), infop, stat_addr, ru); @@ -1404,6 +1443,8 @@ check_continued: flag = 1; if (!unlikely(options & WCONTINUED)) continue; + if (tracehook_inhibit_wait_continued(p)) + continue; retval = wait_task_continued( p, (options & WNOWAIT), infop, stat_addr, ru); @@ -1412,21 +1453,19 @@ check_continued: break; } } - if (!flag) { - list_for_each(_p, &tsk->ptrace_children) { - p = list_entry(_p, struct task_struct, - ptrace_list); - if (!eligible_child(pid, options, p)) - continue; - flag = 1; - break; - } + + retval = ptrace_do_wait(tsk, pid, options, + infop, stat_addr, ru); + if (retval != -ECHILD) { + flag = 1; + if (retval != 0) /* He released the lock. */ + goto end; } + if (options & __WNOTHREAD) break; tsk = next_thread(tsk); - if (tsk->signal != current->signal) - BUG(); + BUG_ON(tsk->signal != current->signal); } while (tsk != current); read_unlock(&tasklist_lock); @@ -1446,7 +1485,7 @@ end: remove_wait_queue(¤t->signal->wait_chldexit,&wait); if (infop) { if (retval > 0) - retval = 0; + retval = 0; else { /* * For a WNOHANG return, clear out all the fields