X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;ds=sidebyside;f=kernel%2Fexit.c;h=208cbfa0987723699534ede7b6786ea111b0c53a;hb=64ba3f394c830ec48a1c31b53dcae312c56f1604;hp=37faf083e6f6e5b5d1d80f17839866ced5be8f5b;hpb=9213980e6a70d8473e0ffd4b39ab5b6caaba9ff5;p=linux-2.6.git diff --git a/kernel/exit.c b/kernel/exit.c index 37faf083e..208cbfa09 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -10,11 +10,14 @@ #include #include #include +#include #include #include #include #include +#include #include +#include #include #include #include @@ -23,7 +26,15 @@ #include #include #include +#include +#include +#include +#include +#include #include +#include +#include +#include #include #include @@ -35,15 +46,11 @@ 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->cacct.nr_threads); - vx_nproc_dec(p->vx_info); - // atomic_dec(&p->vx_info->limit.res[RLIMIT_NPROC]); - } detach_pid(p, PIDTYPE_PID); detach_pid(p, PIDTYPE_TGID); if (thread_group_leader(p)) { @@ -63,8 +70,6 @@ void release_task(struct task_struct * p) struct dentry *proc_dentry; repeat: - BUG_ON(p->state < TASK_ZOMBIE); - atomic_dec(&p->user->processes); spin_lock(&p->proc_lock); proc_dentry = proc_pid_unhash(p); @@ -73,7 +78,11 @@ repeat: __ptrace_unlink(p); BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); __exit_signal(p); - __exit_sighand(p); + /* + * Note that the fastpath in sys_times depends on __exit_signal having + * updated the counters before a task is removed from the tasklist of + * the process by __unhash_process. + */ __unhash_process(p); /* @@ -83,7 +92,7 @@ repeat: */ zap_leader = 0; leader = p->group_leader; - if (leader != p && thread_group_empty(leader) && leader->state == TASK_ZOMBIE) { + 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); /* @@ -97,12 +106,6 @@ repeat: zap_leader = (leader->exit_signal == -1); } - p->parent->cutime += p->utime + p->cutime; - p->parent->cstime += p->stime + p->cstime; - p->parent->cmin_flt += p->min_flt + p->cmin_flt; - p->parent->cmaj_flt += p->maj_flt + p->cmaj_flt; - p->parent->cnvcsw += p->nvcsw + p->cnvcsw; - p->parent->cnivcsw += p->nivcsw + p->cnivcsw; sched_exit(p); write_unlock_irq(&tasklist_lock); spin_unlock(&p->proc_lock); @@ -138,16 +141,15 @@ void unhash_process(struct task_struct *p) int session_of_pgrp(int pgrp) { struct task_struct *p; - struct list_head *l; - struct pid *pid; int sid = -1; read_lock(&tasklist_lock); - for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid) + 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; @@ -168,13 +170,11 @@ out: static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) { struct task_struct *p; - struct list_head *l; - struct pid *pid; int ret = 1; - for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid) { + do_each_task_pid(pgrp, PIDTYPE_PGID, p) { if (p == ignored_task - || p->state >= TASK_ZOMBIE + || p->exit_state || p->real_parent->pid == 1) continue; if (process_group(p->real_parent) != pgrp @@ -182,7 +182,7 @@ static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) ret = 0; break; } - } + } while_each_task_pid(pgrp, PIDTYPE_PGID, p); return ret; /* (sighing) "Often!" */ } @@ -197,14 +197,12 @@ 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; - struct list_head *l; - struct pid *pid; - for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid) { + do_each_task_pid(pgrp, PIDTYPE_PGID, p) { if (p->state != TASK_STOPPED) continue; @@ -220,12 +218,12 @@ static inline int has_stopped_jobs(int pgrp) retval = 1; break; - } + } while_each_task_pid(pgrp, PIDTYPE_PGID, p); return retval; } /** - * reparent_to_init() - Reparent the calling kernel thread to the init task. + * reparent_to_init - Reparent the calling kernel thread to the init task. * * 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 @@ -236,14 +234,13 @@ 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); @@ -251,22 +248,24 @@ void reparent_to_init(void) /* 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 ((current->policy == SCHED_NORMAL || + current->policy == SCHED_BATCH) + && (task_nice(current) < 0)) set_user_nice(current, 0); /* cpus_allowed? */ /* rt_priority? */ /* signals? */ security_task_reparent_to_init(current); - memcpy(current->rlim, init_task.rlim, sizeof(*(current->rlim))); + memcpy(current->signal->rlim, init_task.signal->rlim, + sizeof(current->signal->rlim)); atomic_inc(&(INIT_USER->__count)); - switch_uid(INIT_USER); - write_unlock_irq(&tasklist_lock); + switch_uid(INIT_USER); } 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) { detach_pid(curr, PIDTYPE_SID); @@ -294,7 +293,7 @@ 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); @@ -304,7 +303,7 @@ int allow_signal(int sig) 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 *)2; + current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; } recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); @@ -315,7 +314,7 @@ 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); @@ -350,7 +349,9 @@ void daemonize(const char *name, ...) exit_mm(current); set_special_pids(1, 1); + down(&tty_sem); current->signal->tty = NULL; + up(&tty_sem); /* Block and flush all signals */ sigfillset(&blocked); @@ -363,6 +364,9 @@ void daemonize(const char *name, ...) fs = init_task.fs; current->fs = fs; atomic_inc(&fs->count); + exit_namespace(current); + current->namespace = init_task.namespace; + get_namespace(current->namespace); exit_files(current); current->files = init_task.files; atomic_inc(¤t->files->count); @@ -372,20 +376,28 @@ 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_fdset || 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); @@ -411,18 +423,22 @@ 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) + fdt->free_files = files; + else + kmem_cache_free(files_cachep, files); + free_fdtable(fdt); } } @@ -489,7 +505,7 @@ EXPORT_SYMBOL_GPL(exit_fs); * Turn us into a lazy TLB process if we * aren't already.. */ -static inline void __exit_mm(struct task_struct * tsk) +static void exit_mm(struct task_struct * tsk) { struct mm_struct *mm = tsk->mm; @@ -525,37 +541,30 @@ static inline void __exit_mm(struct task_struct * tsk) mmput(mm); } -void exit_mm(struct task_struct *tsk) +static inline void choose_new_parent(task_t *p, task_t *reaper) { - __exit_mm(tsk); -} - -EXPORT_SYMBOL(exit_mm); + /* check for reaper context */ + vxwprintk((p->xid != reaper->xid) && (reaper != child_reaper), + "rogue reaper: %p[%d,#%u] <> %p[%d,#%u]", + p, p->pid, p->xid, reaper, reaper->pid, reaper->xid); -static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_reaper) -{ /* * Make sure we're not reparenting to ourselves and that * the parent is not a zombie. */ - if (p == reaper || reaper->state >= TASK_ZOMBIE) - p->real_parent = child_reaper; - else - p->real_parent = reaper; - if (p->parent == p->real_parent) - BUG(); + BUG_ON(p == reaper || reaper->exit_state >= EXIT_ZOMBIE); + p->real_parent = reaper; } -static inline void reparent_thread(task_t *p, task_t *father, int traced) +static void reparent_thread(task_t *p, task_t *father, int traced) { /* We don't want people slaying init. */ if (p->exit_signal != -1) p->exit_signal = SIGCHLD; - p->self_exec_id++; 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)) { @@ -575,9 +584,17 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) /* If we'd notified the old parent about this child's death, * also notify the new parent. */ - if (p->state == TASK_ZOMBIE && p->exit_signal != -1 && + 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); + } } /* @@ -591,8 +608,8 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) 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); + __kill_pg_info(SIGHUP, SEND_SIG_PRIV, pgrp); + __kill_pg_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } } @@ -603,15 +620,19 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * group, and if no such member exists, give it to * the global child reaper process (ie "init") */ -static inline void forget_original_parent(struct task_struct * father) +static void forget_original_parent(struct task_struct * father, + struct list_head *to_release) { struct task_struct *p, *reaper = father; struct list_head *_p, *_n; - /* FIXME handle vchild_reaper/initpid */ - reaper = father->group_leader; - if (reaper == father) - reaper = child_reaper; + do { + reaper = next_thread(reaper); + if (reaper == father) { + reaper = vx_child_reaper(father); + break; + } + } while (reaper->exit_state); /* * There are only two places where our children can be: @@ -622,20 +643,39 @@ static inline void forget_original_parent(struct task_struct * father) * 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) { - choose_new_parent(p, reaper, child_reaper); + /* reparent with a reaper, real father it's us */ + choose_new_parent(p, vx_child_reaper(p)); reparent_thread(p, father, 0); } else { - ptrace_unlink (p); - if (p->state == TASK_ZOMBIE && p->exit_signal != -1 && + /* 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); + + choose_new_parent(p, reaper); reparent_thread(p, father, 1); } } @@ -648,8 +688,9 @@ static void exit_notify(struct task_struct *tsk) { int state; struct task_struct *t; + struct list_head ptrace_dead, *_p, *_n; - if (signal_pending(tsk) && !tsk->signal->group_exit + if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT) && !thread_group_empty(tsk)) { /* * This occurs when there was a race between our exit @@ -683,8 +724,10 @@ static void exit_notify(struct task_struct *tsk) * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ - forget_original_parent(tsk); + INIT_LIST_HEAD(&ptrace_dead); + forget_original_parent(tsk, &ptrace_dead); BUG_ON(!list_empty(&tsk->children)); + BUG_ON(!list_empty(&tsk->ptrace_children)); /* * Check to see if any process groups have become orphaned @@ -702,8 +745,8 @@ static void exit_notify(struct task_struct *tsk) (t->signal->session == tsk->signal->session) && 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 @@ -740,44 +783,34 @@ static void exit_notify(struct task_struct *tsk) do_notify_parent(tsk, SIGCHLD); } - state = TASK_ZOMBIE; - if (tsk->exit_signal == -1 && tsk->ptrace == 0) - state = TASK_DEAD; - tsk->state = state; - tsk->flags |= PF_DEAD; + state = EXIT_ZOMBIE; + if (tsk->exit_signal == -1 && + (likely(tsk->ptrace == 0) || + unlikely(tsk->parent->signal->flags & SIGNAL_GROUP_EXIT))) + 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 = 0; - tsk->it_prof_value = 0; - tsk->rlim[RLIMIT_CPU].rlim_cur = RLIM_INFINITY; + write_unlock_irq(&tasklist_lock); - /* - * In the preemption case it must be impossible for the task - * to get runnable again, so use "_raw_" unlock to keep - * preempt_count elevated until we schedule(). - * - * To avoid deadlock on SMP, interrupts must be unmasked. If we - * don't, subsequently called functions (e.g, wait_task_inactive() - * via release_task()) will spin, with interrupt flags - * unwittingly blocked, until the other task sleeps. That task - * may itself be waiting for smp_call_function() to answer and - * complete, and with interrupts blocked that will never happen. - */ - _raw_write_unlock(&tasklist_lock); - local_irq_enable(); + list_for_each_safe(_p, _n, &ptrace_dead) { + list_del_init(_p); + t = list_entry(_p,struct task_struct,ptrace_list); + release_task(t); + } /* If the process is dead, release it - nobody will wait for it */ - if (state == TASK_DEAD) + if (state == EXIT_DEAD) release_task(tsk); - } -asmlinkage NORET_TYPE void do_exit(long code) +fastcall 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!"); @@ -787,48 +820,89 @@ asmlinkage NORET_TYPE void do_exit(long code) panic("Attempted to kill init!"); if (tsk->io_context) exit_io_context(); + + if (unlikely(current->ptrace & PT_TRACE_EXIT)) { + current->ptrace_message = code; + ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); + } + + /* + * 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"); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + } + tsk->flags |= PF_EXITING; - del_timer_sync(&tsk->real_timer); if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, current->pid, preempt_count()); - profile_exit_task(tsk); - - if (unlikely(current->ptrace & PT_TRACE_EXIT)) { - current->ptrace_message = code; - ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); + acct_update_integrals(tsk); + if (tsk->mm) { + update_hiwater_rss(tsk->mm); + update_hiwater_vm(tsk->mm); } - - acct_process(code); - __exit_mm(tsk); + group_dead = atomic_dec_and_test(&tsk->signal->live); + if (group_dead) { + hrtimer_cancel(&tsk->signal->real_timer); + exit_itimers(tsk->signal); + acct_process(code); + } + exit_mm(tsk); exit_sem(tsk); __exit_files(tsk); __exit_fs(tsk); exit_namespace(tsk); exit_thread(); -#ifdef CONFIG_NUMA - mpol_free(tsk->mempolicy); -#endif + cpuset_exit(tsk); + exit_keys(tsk); - if (tsk->signal->leader) + 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); + /* needs to stay before exit_notify() */ + exit_vx_info_early(tsk, code); exit_notify(tsk); +#ifdef CONFIG_NUMA + mpol_free(tsk->mempolicy); + tsk->mempolicy = NULL; +#endif + /* + * If DEBUG_MUTEXES is on, make sure we are holding no locks: + */ + mutex_debug_check_no_locks_held(tsk); + + /* needs to stay after exit_notify() */ + exit_vx_info(tsk, code); + exit_nx_info(tsk); + + /* PF_DEAD causes final put_task_struct after we schedule. */ + preempt_disable(); + BUG_ON(tsk->flags & PF_DEAD); + tsk->flags |= PF_DEAD; + schedule(); BUG(); /* Avoid "noreturn function does return". */ for (;;) ; } +EXPORT_SYMBOL_GPL(do_exit); + NORET_TYPE void complete_and_exit(struct completion *comp, long code) { if (comp) @@ -844,23 +918,9 @@ asmlinkage long sys_exit(int error_code) do_exit((error_code&0xff)<<8); } -task_t fastcall *next_thread(task_t *p) +task_t fastcall *next_thread(const task_t *p) { - struct pid_link *link = p->pids + PIDTYPE_TGID; - struct list_head *tmp, *head = &link->pidptr->task_list; - -#ifdef CONFIG_SMP - if (!p->sighand) - BUG(); - if (!spin_is_locked(&p->sighand->siglock) && - !rwlock_is_locked(&tasklist_lock)) - BUG(); -#endif - tmp = link->pid_chain.next; - if (tmp == head) - tmp = head->next; - - return pid_task(tmp, PIDTYPE_TGID); + return pid_task(p->pids[PIDTYPE_TGID].pid_list.next, PIDTYPE_TGID); } EXPORT_SYMBOL(next_thread); @@ -874,18 +934,17 @@ do_group_exit(int exit_code) { BUG_ON(exit_code & 0x80); /* core dumps don't get here */ - if (current->signal->group_exit) + if (current->signal->flags & SIGNAL_GROUP_EXIT) exit_code = current->signal->group_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->group_exit) + if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { - sig->group_exit = 1; sig->group_exit_code = exit_code; zap_other_threads(current); } @@ -948,48 +1007,163 @@ 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, + 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); + if (!retval) + retval = put_user(0, &infop->si_errno); + if (!retval) + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(pid, &infop->si_pid); + if (!retval) + retval = put_user(uid, &infop->si_uid); + if (!retval) + retval = put_user(status, &infop->si_status); + if (!retval) + retval = pid; + return retval; +} + /* - * Handle sys_wait4 work for one task in state TASK_ZOMBIE. We hold + * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_zombie(task_t *p, unsigned int __user *stat_addr, struct rusage __user *ru) +static int wait_task_zombie(task_t *p, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) { unsigned long state; int retval; + int status; + + if (unlikely(noreap)) { + pid_t pid = p->pid; + uid_t uid = p->uid; + int exit_code = p->exit_code; + int why, status; + + if (unlikely(p->exit_state != EXIT_ZOMBIE)) + return 0; + if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) + return 0; + get_task_struct(p); + read_unlock(&tasklist_lock); + if ((exit_code & 0x7f) == 0) { + why = CLD_EXITED; + status = exit_code >> 8; + } else { + why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; + status = exit_code & 0x7f; + } + return wait_noreap_copyout(p, pid, uid, why, + status, infop, ru); + } /* * Try to move the task's state to DEAD * only one thread is allowed to do this: */ - state = xchg(&p->state, TASK_DEAD); - if (state != TASK_ZOMBIE) { - BUG_ON(state != TASK_DEAD); + state = xchg(&p->exit_state, EXIT_DEAD); + if (state != EXIT_ZOMBIE) { + BUG_ON(state != EXIT_DEAD); return 0; } - if (unlikely(p->exit_signal == -1 && p->ptrace == 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; + } + + if (likely(p->real_parent == p->parent) && likely(p->signal)) { + struct signal_struct *psig; + struct signal_struct *sig; + + /* + * The resource counters for the group leader are in its + * own task_struct. Those for dead threads in the group + * are in its signal_struct, as are those for the child + * processes it has previously reaped. All these + * accumulate in the parent's signal_struct c* fields. + * + * We don't bother to take a lock here to protect these + * p->signal fields, because they are only touched by + * __exit_signal, which runs with tasklist_lock + * write-locked anyway, and so is excluded here. We do + * need to protect the access to p->parent->signal fields, + * as other threads in the parent group can be right + * here reaping other children at the same time. + */ + spin_lock_irq(&p->parent->sighand->siglock); + psig = p->parent->signal; + sig = p->signal; + psig->cutime = + cputime_add(psig->cutime, + cputime_add(p->utime, + cputime_add(sig->utime, + sig->cutime))); + psig->cstime = + cputime_add(psig->cstime, + cputime_add(p->stime, + 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); + } /* * Now we are sure this task is interesting, and no other - * thread can reap it because we set its state to TASK_DEAD. + * thread can reap it because we set its state to EXIT_DEAD. */ read_unlock(&tasklist_lock); retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; - if (!retval && stat_addr) { - if (p->signal->group_exit) - retval = put_user(p->signal->group_exit_code, stat_addr); - else - retval = put_user(p->exit_code, stat_addr); + status = (p->signal->flags & SIGNAL_GROUP_EXIT) + ? p->signal->group_exit_code : p->exit_code; + if (!retval && stat_addr) + retval = put_user(status, stat_addr); + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) { + int why; + + if ((status & 0x7f) == 0) { + why = CLD_EXITED; + status >>= 8; + } else { + why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; + status &= 0x7f; + } + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(status, &infop->si_status); } + if (!retval && infop) + retval = put_user(p->pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(p->uid, &infop->si_uid); if (retval) { - p->state = TASK_ZOMBIE; + // TODO: is this safe? + p->exit_state = EXIT_ZOMBIE; return retval; } retval = p->pid; @@ -998,21 +1172,20 @@ static int wait_task_zombie(task_t *p, unsigned int __user *stat_addr, struct ru /* Double-check with lock held. */ if (p->real_parent != p->parent) { __ptrace_unlink(p); - p->state = TASK_ZOMBIE; - /* If this is a detached thread, this is where it goes away. */ - if (p->exit_signal == -1) { - /* release_task takes the lock itself. */ - write_unlock_irq(&tasklist_lock); - release_task (p); - } - else { + // 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); - write_unlock_irq(&tasklist_lock); + if (p->exit_signal != -1) + p = NULL; } - p = NULL; } - else - write_unlock_irq(&tasklist_lock); + write_unlock_irq(&tasklist_lock); } if (p != NULL) release_task(p); @@ -1026,9 +1199,9 @@ static int wait_task_zombie(task_t *p, unsigned int __user *stat_addr, struct ru * 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, - unsigned int __user *stat_addr, - struct rusage __user *ru) +static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code; @@ -1051,18 +1224,33 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, */ get_task_struct(p); read_unlock(&tasklist_lock); + + 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_TRACED)) + goto bail_ref; + return wait_noreap_copyout(p, pid, uid, + why, (exit_code << 8) | 0x7f, + infop, ru); + } + write_lock_irq(&tasklist_lock); /* * This uses xchg to be atomic with the thread resuming and setting * it. It must also be done with the write lock held to prevent a - * race with the TASK_ZOMBIE case. + * race with the EXIT_ZOMBIE case. */ exit_code = xchg(&p->exit_code, 0); - if (unlikely(p->state > TASK_STOPPED)) { + if (unlikely(p->exit_state)) { /* * The task resumed and then died. Let the next iteration - * catch it in TASK_ZOMBIE. Note that exit_code might + * catch it in EXIT_ZOMBIE. Note that exit_code might * already be zero here if it resumed and did _exit(0). * The task itself is dead and won't touch exit_code again; * other processors in this function are locked out. @@ -1076,9 +1264,17 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, * resumed, or it resumed and then died. */ write_unlock_irq(&tasklist_lock); +bail_ref: put_task_struct(p); - read_lock(&tasklist_lock); - return 0; + /* + * We are returning to the wait loop without having successfully + * removed the process and having released the lock. We cannot + * continue, since the "p" task pointer is potentially stale. + * + * Return -EAGAIN, and do_wait() will restart the loop from the + * beginning. Do _not_ re-acquire the lock. + */ + return -EAGAIN; } /* move to end of parent's list to avoid starvation */ @@ -1090,6 +1286,20 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; if (!retval && stat_addr) retval = put_user((exit_code << 8) | 0x7f, stat_addr); + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) + retval = put_user((short)((p->ptrace & PT_PTRACED) + ? CLD_TRAPPED : CLD_STOPPED), + &infop->si_code); + if (!retval && infop) + retval = put_user(exit_code, &infop->si_status); + if (!retval && infop) + retval = put_user(p->pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(p->uid, &infop->si_uid); if (!retval) retval = p->pid; put_task_struct(p); @@ -1098,17 +1308,88 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, return retval; } -asmlinkage long sys_wait4(pid_t pid,unsigned int __user *stat_addr, int options, struct rusage __user *ru) +/* + * Handle do_wait work for one task in a live, non-stopped state. + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_continued(task_t *p, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + int retval; + pid_t pid; + uid_t uid; + + if (unlikely(!p->signal)) + return 0; + + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) + return 0; + + spin_lock_irq(&p->sighand->siglock); + /* Re-check with the lock held. */ + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { + spin_unlock_irq(&p->sighand->siglock); + return 0; + } + if (!noreap) + p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + spin_unlock_irq(&p->sighand->siglock); + + pid = p->pid; + uid = p->uid; + get_task_struct(p); + read_unlock(&tasklist_lock); + + if (!infop) { + retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + put_task_struct(p); + if (!retval && stat_addr) + retval = put_user(0xffff, stat_addr); + if (!retval) + retval = p->pid; + } else { + retval = wait_noreap_copyout(p, pid, uid, + CLD_CONTINUED, SIGCONT, + infop, ru); + BUG_ON(retval == 0); + } + + return retval; +} + + +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) { DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; int flag, retval; - if (options & ~(WNOHANG|WUNTRACED|__WNOTHREAD|__WCLONE|__WALL)) - return -EINVAL; - - add_wait_queue(¤t->wait_chldexit,&wait); + add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: + /* + * We will set this flag if we see any child that might later + * match our criteria, even if we are not able to reap it yet. + */ flag = 0; current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); @@ -1124,33 +1405,81 @@ repeat: ret = eligible_child(pid, options, p); if (!ret) continue; - flag = 1; switch (p->state) { + case TASK_TRACED: + /* + * When we hit the race with PTRACE_ATTACH, + * we will not report this child. But the + * race means it has not yet been moved to + * our ptrace_children list, so we need to + * set the flag here to avoid a spurious ECHILD + * when the race happens with the only child. + */ + flag = 1; + if (!my_ptrace_child(p)) + continue; + /*FALLTHROUGH*/ case TASK_STOPPED: + /* + * It's stopped now, so it might later + * continue, exit, or stop again. + */ + flag = 1; if (!(options & WUNTRACED) && - !(p->ptrace & PT_PTRACED)) + !my_ptrace_child(p)) continue; retval = wait_task_stopped(p, ret == 2, + (options & WNOWAIT), + infop, stat_addr, ru); + if (retval == -EAGAIN) + goto repeat; if (retval != 0) /* He released the lock. */ - goto end_wait4; + goto end; break; - case TASK_ZOMBIE: + default: + // case EXIT_DEAD: + if (p->exit_state == EXIT_DEAD) + continue; + // case EXIT_ZOMBIE: + if (p->exit_state == EXIT_ZOMBIE) { + /* + * Eligible but we cannot release + * it yet: + */ + if (ret == 2) + goto check_continued; + if (!likely(options & WEXITED)) + continue; + retval = wait_task_zombie( + p, (options & WNOWAIT), + infop, stat_addr, ru); + /* He released the lock. */ + if (retval != 0) + goto end; + break; + } +check_continued: /* - * Eligible but we cannot release it yet: + * It's running now, so it might later + * exit, stop, or stop and then continue. */ - if (ret == 2) + flag = 1; + if (!unlikely(options & WCONTINUED)) continue; - retval = wait_task_zombie(p, stat_addr, ru); + retval = wait_task_continued( + p, (options & WNOWAIT), + infop, stat_addr, ru); if (retval != 0) /* He released the lock. */ - goto end_wait4; + goto end; break; } } if (!flag) { - list_for_each (_p,&tsk->ptrace_children) { - p = list_entry(_p,struct task_struct,ptrace_list); + 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; @@ -1163,31 +1492,105 @@ repeat: if (tsk->signal != current->signal) BUG(); } while (tsk != current); + read_unlock(&tasklist_lock); if (flag) { retval = 0; if (options & WNOHANG) - goto end_wait4; + goto end; retval = -ERESTARTSYS; if (signal_pending(current)) - goto end_wait4; + goto end; schedule(); goto repeat; } retval = -ECHILD; -end_wait4: +end: current->state = TASK_RUNNING; - remove_wait_queue(¤t->wait_chldexit,&wait); + remove_wait_queue(¤t->signal->wait_chldexit,&wait); + if (infop) { + if (retval > 0) + retval = 0; + else { + /* + * For a WNOHANG return, clear out all the fields + * we would set so the user can easily tell the + * difference. + */ + if (!retval) + retval = put_user(0, &infop->si_signo); + if (!retval) + retval = put_user(0, &infop->si_errno); + if (!retval) + retval = put_user(0, &infop->si_code); + if (!retval) + retval = put_user(0, &infop->si_pid); + if (!retval) + retval = put_user(0, &infop->si_uid); + if (!retval) + retval = put_user(0, &infop->si_status); + } + } return retval; } +asmlinkage long sys_waitid(int which, pid_t pid, + struct siginfo __user *infop, int options, + struct rusage __user *ru) +{ + long ret; + + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + return -EINVAL; + if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) + return -EINVAL; + + switch (which) { + case P_ALL: + pid = -1; + break; + case P_PID: + if (pid <= 0) + return -EINVAL; + break; + case P_PGID: + if (pid <= 0) + return -EINVAL; + pid = -pid; + break; + default: + return -EINVAL; + } + + ret = do_wait(pid, options, infop, NULL, ru); + + /* avoid REGPARM breakage on x86: */ + prevent_tail_call(ret); + return ret; +} + +asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, + int options, struct rusage __user *ru) +{ + long ret; + + if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) + return -EINVAL; + ret = do_wait(pid, options | WEXITED, NULL, stat_addr, ru); + + /* avoid REGPARM breakage on x86: */ + prevent_tail_call(ret); + return ret; +} + #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ -asmlinkage long sys_waitpid(pid_t pid, unsigned __user *stat_addr, int options) +asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options) { return sys_wait4(pid, stat_addr, options, NULL); }