diff options
Diffstat (limited to 'kernel/exit.c')
| -rw-r--r-- | kernel/exit.c | 713 |
1 files changed, 278 insertions, 435 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index 21aa7b3001f..e5c4668f179 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -20,6 +20,7 @@ #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> @@ -31,7 +32,6 @@ #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> -#include <linux/freezer.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> @@ -51,6 +51,8 @@ #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> @@ -69,9 +71,10 @@ static void __unhash_process(struct task_struct *p, bool group_dead) list_del_rcu(&p->tasks); list_del_init(&p->sibling); - __get_cpu_var(process_counts)--; + __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); + list_del_rcu(&p->thread_node); } /* @@ -83,9 +86,9 @@ static void __exit_signal(struct task_struct *tsk) 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, - rcu_read_lock_held() || lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); @@ -122,9 +125,10 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, tsk->utime); - sig->stime = cputime_add(sig->stime, tsk->stime); - sig->gtime = cputime_add(sig->gtime, tsk->gtime); + 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; @@ -169,7 +173,6 @@ void release_task(struct task_struct * p) struct task_struct *leader; int zap_leader; repeat: - tracehook_prepare_release_task(p); /* 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(); @@ -179,7 +182,7 @@ repeat: proc_flush_task(p); write_lock_irq(&tasklist_lock); - tracehook_finish_release_task(p); + ptrace_release_task(p); __exit_signal(p); /* @@ -190,22 +193,12 @@ repeat: zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { - BUG_ON(task_detached(leader)); - do_notify_parent(leader, leader->exit_signal); /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. - * - * do_notify_parent() will have marked it self-reaping in - * that case. - */ - zap_leader = task_detached(leader); - - /* - * This maintains the invariant that release_task() - * only runs on a task in EXIT_DEAD, just for sanity. */ + zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } @@ -277,18 +270,16 @@ int is_current_pgrp_orphaned(void) return retval; } -static int has_stopped_jobs(struct pid *pgrp) +static bool has_stopped_jobs(struct pid *pgrp) { - int retval = 0; struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { - if (!task_is_stopped(p)) - continue; - retval = 1; - break; + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); - return retval; + + return false; } /* @@ -322,268 +313,30 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) } } -/** - * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd - * - * If a kernel thread is launched as a result of a system call, or if - * it ever exits, it should generally reparent itself to kthreadd so it - * isn't in the way of other processes and is correctly cleaned up on exit. - * - * The various task state such as scheduling policy and priority may have - * been inherited from a user process, so we reset them to sane values here. - * - * NOTE that reparent_to_kthreadd() gives the caller full capabilities. - */ -static void reparent_to_kthreadd(void) -{ - write_lock_irq(&tasklist_lock); - - ptrace_unlink(current); - /* Reparent to init */ - current->real_parent = current->parent = kthreadd_task; - list_move_tail(¤t->sibling, ¤t->real_parent->children); - - /* Set the exit signal to SIGCHLD so we signal init on exit */ - current->exit_signal = SIGCHLD; - - if (task_nice(current) < 0) - set_user_nice(current, 0); - /* cpus_allowed? */ - /* rt_priority? */ - /* signals? */ - memcpy(current->signal->rlim, init_task.signal->rlim, - sizeof(current->signal->rlim)); - - atomic_inc(&init_cred.usage); - commit_creds(&init_cred); - write_unlock_irq(&tasklist_lock); -} - -void __set_special_pids(struct pid *pid) -{ - struct task_struct *curr = current->group_leader; - - if (task_session(curr) != pid) - change_pid(curr, PIDTYPE_SID, pid); - - if (task_pgrp(curr) != pid) - change_pid(curr, PIDTYPE_PGID, pid); -} - -static void set_special_pids(struct pid *pid) -{ - write_lock_irq(&tasklist_lock); - __set_special_pids(pid); - write_unlock_irq(&tasklist_lock); -} - -/* - * Let kernel threads use this to say that they allow a certain signal. - * Must not be used if kthread was cloned with CLONE_SIGHAND. - */ -int allow_signal(int sig) -{ - if (!valid_signal(sig) || sig < 1) - return -EINVAL; - - spin_lock_irq(¤t->sighand->siglock); - /* This is only needed for daemonize()'ed kthreads */ - sigdelset(¤t->blocked, sig); - /* - * Kernel threads handle their own signals. Let the signal code - * know it'll be handled, so that they don't get converted to - * SIGKILL or just silently dropped. - */ - current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - return 0; -} - -EXPORT_SYMBOL(allow_signal); - -int disallow_signal(int sig) -{ - if (!valid_signal(sig) || sig < 1) - return -EINVAL; - - spin_lock_irq(¤t->sighand->siglock); - current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - return 0; -} - -EXPORT_SYMBOL(disallow_signal); - +#ifdef CONFIG_MEMCG /* - * Put all the gunge required to become a kernel thread without - * attached user resources in one place where it belongs. + * A task is exiting. If it owned this mm, find a new owner for the mm. */ - -void daemonize(const char *name, ...) -{ - va_list args; - sigset_t blocked; - - va_start(args, name); - vsnprintf(current->comm, sizeof(current->comm), name, args); - va_end(args); - - /* - * If we were started as result of loading a module, close all of the - * user space pages. We don't need them, and if we didn't close them - * they would be locked into memory. - */ - exit_mm(current); - /* - * We don't want to have TIF_FREEZE set if the system-wide hibernation - * or suspend transition begins right now. - */ - current->flags |= (PF_NOFREEZE | PF_KTHREAD); - - if (current->nsproxy != &init_nsproxy) { - get_nsproxy(&init_nsproxy); - switch_task_namespaces(current, &init_nsproxy); - } - set_special_pids(&init_struct_pid); - proc_clear_tty(current); - - /* Block and flush all signals */ - sigfillset(&blocked); - sigprocmask(SIG_BLOCK, &blocked, NULL); - flush_signals(current); - - /* Become as one with the init task */ - - daemonize_fs_struct(); - exit_files(current); - current->files = init_task.files; - atomic_inc(¤t->files->count); - - reparent_to_kthreadd(); -} - -EXPORT_SYMBOL(daemonize); - -static void close_files(struct files_struct * files) +void mm_update_next_owner(struct mm_struct *mm) { - int i, j; - struct fdtable *fdt; - - j = 0; + struct task_struct *c, *g, *p = current; +retry: /* - * It is safe to dereference the fd table without RCU or - * ->file_lock because this is the last reference to the - * files structure. But use RCU to shut RCU-lockdep up. + * If the exiting or execing task is not the owner, it's + * someone else's problem. */ - rcu_read_lock(); - fdt = files_fdtable(files); - rcu_read_unlock(); - for (;;) { - unsigned long set; - i = j * __NFDBITS; - if (i >= fdt->max_fds) - break; - set = fdt->open_fds->fds_bits[j++]; - while (set) { - if (set & 1) { - struct file * file = xchg(&fdt->fd[i], NULL); - if (file) { - filp_close(file, files); - cond_resched(); - } - } - i++; - set >>= 1; - } - } -} - -struct files_struct *get_files_struct(struct task_struct *task) -{ - struct files_struct *files; - - task_lock(task); - files = task->files; - if (files) - atomic_inc(&files->count); - task_unlock(task); - - return files; -} - -void put_files_struct(struct files_struct *files) -{ - struct fdtable *fdt; - - if (atomic_dec_and_test(&files->count)) { - close_files(files); - /* - * Free the fd and fdset arrays if we expanded them. - * If the fdtable was embedded, pass files for freeing - * at the end of the RCU grace period. Otherwise, - * you can free files immediately. - */ - rcu_read_lock(); - fdt = files_fdtable(files); - if (fdt != &files->fdtab) - kmem_cache_free(files_cachep, files); - free_fdtable(fdt); - rcu_read_unlock(); - } -} - -void reset_files_struct(struct files_struct *files) -{ - struct task_struct *tsk = current; - struct files_struct *old; - - old = tsk->files; - task_lock(tsk); - tsk->files = files; - task_unlock(tsk); - put_files_struct(old); -} - -void exit_files(struct task_struct *tsk) -{ - struct files_struct * files = tsk->files; - - if (files) { - task_lock(tsk); - tsk->files = NULL; - task_unlock(tsk); - put_files_struct(files); - } -} - -#ifdef CONFIG_MM_OWNER -/* - * Task p is exiting and it owned mm, lets find a new owner for it - */ -static inline int -mm_need_new_owner(struct mm_struct *mm, struct task_struct *p) -{ + if (mm->owner != p) + return; /* - * If there are other users of the mm and the owner (us) is exiting - * we need to find a new owner to take on the responsibility. + * 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) - return 0; - if (mm->owner != p) - return 0; - return 1; -} - -void mm_update_next_owner(struct mm_struct *mm) -{ - struct task_struct *c, *g, *p = current; - -retry: - if (!mm_need_new_owner(mm, p)) + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; return; + } read_lock(&tasklist_lock); /* @@ -603,14 +356,18 @@ retry: } /* - * Search through everything else. We should not get - * here often + * Search through everything else, we should not get here often. */ - do_each_thread(g, c) { - if (c->mm == mm) - goto assign_new_owner; - } while_each_thread(g, c); - + 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 @@ -642,7 +399,7 @@ assign_new_owner: task_unlock(c); put_task_struct(c); } -#endif /* CONFIG_MM_OWNER */ +#endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we @@ -656,6 +413,7 @@ static void exit_mm(struct task_struct * tsk) 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 @@ -682,7 +440,7 @@ static void exit_mm(struct task_struct * tsk) set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; - schedule(); + freezable_schedule(); } __set_task_state(tsk, TASK_RUNNING); down_read(&mm->mmap_sem); @@ -694,21 +452,17 @@ static void exit_mm(struct task_struct * tsk) tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); - /* We don't want this task to be frozen prematurely */ - clear_freeze_flag(tsk); - if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&mm->oom_disable_count); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); } /* - * When we die, we re-parent all our children. - * Try to give them to another thread in our thread - * group, and if no such member exists, give it to - * the child reaper process (ie "init") in our pid - * space. + * 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) @@ -728,17 +482,37 @@ static struct task_struct *find_new_reaper(struct task_struct *father) if (unlikely(pid_ns->child_reaper == father)) { write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) - panic("Attempted to kill init!"); + 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; + /* - * We can not clear ->child_reaper or leave it alone. - * There may by stealth EXIT_DEAD tasks on ->children, - * forget_original_parent() must move them somewhere. + * 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 + * http://marc.info/?l=linux-kernel&m=131385460420380 */ - pid_ns->child_reaper = init_pid_ns.child_reaper; + for (reaper = father->real_parent; + reaper != &init_task; + reaper = reaper->real_parent) { + if (same_thread_group(reaper, pid_ns->child_reaper)) + break; + if (!reaper->signal->is_child_subreaper) + continue; + thread = reaper; + do { + if (!(thread->flags & PF_EXITING)) + return reaper; + } while_each_thread(reaper, thread); + } } return pid_ns->child_reaper; @@ -752,7 +526,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, { list_move_tail(&p->sibling, &p->real_parent->children); - if (task_detached(p)) + if (p->exit_state == EXIT_DEAD) return; /* * If this is a threaded reparent there is no need to @@ -761,14 +535,13 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, if (same_thread_group(p->real_parent, father)) return; - /* We don't want people slaying init. */ + /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ - if (!task_ptrace(p) && + if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { - do_notify_parent(p, p->exit_signal); - if (task_detached(p)) { + if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_move_tail(&p->sibling, dead); } @@ -795,7 +568,7 @@ static void forget_original_parent(struct task_struct *father) do { t->real_parent = reaper; if (t->parent == father) { - BUG_ON(task_ptrace(t)); + BUG_ON(t->ptrace); t->parent = t->real_parent; } if (t->pdeath_signal) @@ -820,8 +593,7 @@ static void forget_original_parent(struct task_struct *father) */ static void exit_notify(struct task_struct *tsk, int group_dead) { - int signal; - void *cookie; + bool autoreap; /* * This does two things: @@ -832,46 +604,33 @@ static void exit_notify(struct task_struct *tsk, int group_dead) * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ forget_original_parent(tsk); - exit_task_namespaces(tsk); write_lock_irq(&tasklist_lock); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); - /* Let father know we died - * - * Thread signals are configurable, but you aren't going to use - * that to send signals to arbitary processes. - * That stops right now. - * - * If the parent exec id doesn't match the exec id we saved - * when we started then we know the parent has changed security - * domain. - * - * If our self_exec id doesn't match our parent_exec_id then - * we have changed execution domain as these two values started - * the same after a fork. - */ - if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) && - (tsk->parent_exec_id != tsk->real_parent->self_exec_id || - tsk->self_exec_id != tsk->parent_exec_id)) - tsk->exit_signal = SIGCHLD; - - signal = tracehook_notify_death(tsk, &cookie, group_dead); - if (signal >= 0) - signal = do_notify_parent(tsk, signal); + if (unlikely(tsk->ptrace)) { + int sig = thread_group_leader(tsk) && + thread_group_empty(tsk) && + !ptrace_reparented(tsk) ? + tsk->exit_signal : SIGCHLD; + autoreap = do_notify_parent(tsk, sig); + } else if (thread_group_leader(tsk)) { + autoreap = thread_group_empty(tsk) && + do_notify_parent(tsk, tsk->exit_signal); + } else { + autoreap = true; + } - tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE; + tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exit_task); write_unlock_irq(&tasklist_lock); - tracehook_report_death(tsk, signal, cookie, group_dead); - /* If the process is dead, release it - nobody will wait for it */ - if (signal == DEATH_REAP) + if (autoreap) release_task(tsk); } @@ -889,9 +648,9 @@ static void check_stack_usage(void) spin_lock(&low_water_lock); if (free < lowest_to_date) { - printk(KERN_WARNING "%s used greatest stack depth: %lu bytes " - "left\n", - current->comm, free); + printk(KERN_WARNING "%s (%d) used greatest stack depth: " + "%lu bytes left\n", + current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); @@ -900,21 +659,30 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif -NORET_TYPE void do_exit(long code) +void do_exit(long code) { struct task_struct *tsk = current; int group_dead; profile_task_exit(tsk); - WARN_ON(atomic_read(&tsk->fs_excl)); + WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); - tracehook_report_exit(&code); + /* + * If do_exit is called because this processes oopsed, it's possible + * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before + * continuing. Amongst other possible reasons, this is to prevent + * mm_release()->clear_child_tid() from writing to a user-controlled + * kernel address. + */ + set_fs(USER_DS); + + ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); @@ -939,8 +707,6 @@ NORET_TYPE void do_exit(long code) schedule(); } - exit_irq_thread(); - exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against @@ -957,7 +723,7 @@ NORET_TYPE void do_exit(long code) acct_update_integrals(tsk); /* sync mm's RSS info before statistics gathering */ if (tsk->mm) - sync_mm_rss(tsk, tsk->mm); + sync_mm_rss(tsk->mm); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { hrtimer_cancel(&tsk->signal->real_timer); @@ -968,8 +734,7 @@ NORET_TYPE void do_exit(long code) acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); - if (unlikely(tsk->audit_context)) - audit_free(tsk); + audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); @@ -981,30 +746,34 @@ NORET_TYPE void do_exit(long code) trace_sched_process_exit(tsk); exit_sem(tsk); + exit_shm(tsk); exit_files(tsk); exit_fs(tsk); - check_stack_usage(); - exit_thread(); - cgroup_exit(tsk, 1); - if (group_dead) disassociate_ctty(1); + exit_task_namespaces(tsk); + exit_task_work(tsk); + exit_thread(); - module_put(task_thread_info(tsk)->exec_domain->module); + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + * + * because of cgroup mode, must be called before cgroup_exit() + */ + perf_event_exit_task(tsk); - proc_exit_connector(tsk); + cgroup_exit(tsk); + + module_put(task_thread_info(tsk)->exec_domain->module); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); - /* - * Flush inherited counters to the parent - before the parent - * gets woken up by child-exit notifications. - */ - perf_event_exit_task(tsk); exit_notify(tsk, group_dead); + proc_exit_connector(tsk); #ifdef CONFIG_NUMA task_lock(tsk); mpol_put(tsk->mempolicy); @@ -1018,7 +787,7 @@ NORET_TYPE void do_exit(long code) /* * Make sure we are holding no locks: */ - debug_check_no_locks_held(tsk); + debug_check_no_locks_held(); /* * We can do this unlocked here. The futex code uses this flag * just to verify whether the pi state cleanup has been done @@ -1030,14 +799,37 @@ NORET_TYPE void do_exit(long code) exit_io_context(tsk); if (tsk->splice_pipe) - __free_pipe_info(tsk->splice_pipe); + free_pipe_info(tsk->splice_pipe); + + if (tsk->task_frag.page) + put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); + check_stack_usage(); preempt_disable(); + if (tsk->nr_dirtied) + __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); + + /* + * The setting of TASK_RUNNING by try_to_wake_up() may be delayed + * when the following two conditions become true. + * - There is race condition of mmap_sem (It is acquired by + * exit_mm()), and + * - SMI occurs before setting TASK_RUNINNG. + * (or hypervisor of virtual machine switches to other guest) + * As a result, we may become TASK_RUNNING after becoming TASK_DEAD + * + * To avoid it, we have to wait for releasing tsk->pi_lock which + * is held by try_to_wake_up() + */ + smp_mb(); + raw_spin_unlock_wait(&tsk->pi_lock); + /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; + tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ schedule(); BUG(); /* Avoid "noreturn function does return". */ @@ -1047,7 +839,7 @@ NORET_TYPE void do_exit(long code) EXPORT_SYMBOL_GPL(do_exit); -NORET_TYPE void complete_and_exit(struct completion *comp, long code) +void complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); @@ -1066,7 +858,7 @@ SYSCALL_DEFINE1(exit, int, error_code) * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ -NORET_TYPE void +void do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; @@ -1187,7 +979,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); - uid_t uid = __task_cred(p)->uid; + uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct siginfo __user *infop; if (!likely(wo->wo_flags & WEXITED)) @@ -1209,22 +1001,18 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) return wait_noreap_copyout(wo, p, pid, uid, why, status); } + traced = ptrace_reparented(p); /* - * Try to move the task's state to DEAD - * only one thread is allowed to do this: + * Move the task's state to DEAD/TRACE, only one thread can do this. */ - state = xchg(&p->exit_state, EXIT_DEAD); - if (state != EXIT_ZOMBIE) { - BUG_ON(state != EXIT_DEAD); + state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD; + if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; - } - - traced = ptrace_reparented(p); /* * It can be ptraced but not reparented, check - * !task_detached() to filter out sub-threads. + * thread_group_leader() to filter out sub-threads. */ - if (likely(!traced) && likely(!task_detached(p))) { + if (likely(!traced) && thread_group_leader(p)) { struct signal_struct *psig; struct signal_struct *sig; unsigned long maxrss; @@ -1245,27 +1033,17 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * as other threads in the parent group can be right * here reaping other children at the same time. * - * We use thread_group_times() to get times for the thread + * We use thread_group_cputime_adjusted() to get times for the thread * group, which consolidates times for all threads in the * group including the group leader. */ - thread_group_times(p, &tgutime, &tgstime); + thread_group_cputime_adjusted(p, &tgutime, &tgstime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; - psig->cutime = - cputime_add(psig->cutime, - cputime_add(tgutime, - sig->cutime)); - psig->cstime = - cputime_add(psig->cstime, - cputime_add(tgstime, - sig->cstime)); - psig->cgtime = - cputime_add(psig->cgtime, - cputime_add(p->gtime, - cputime_add(sig->gtime, - sig->cgtime))); + psig->cutime += tgutime + sig->cutime; + psig->cstime += tgstime + sig->cstime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += @@ -1290,7 +1068,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) /* * Now we are sure this task is interesting, and no other - * thread can reap it because we set its state to EXIT_DEAD. + * thread can reap it because we its state == DEAD/TRACE. */ read_unlock(&tasklist_lock); @@ -1327,25 +1105,19 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) if (!retval) retval = pid; - if (traced) { + if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); - /* - * If this is not a detached task, notify the parent. - * If it's still not detached after that, don't release - * it now. - */ - if (!task_detached(p)) { - do_notify_parent(p, p->exit_signal); - if (!task_detached(p)) { - p->exit_state = EXIT_ZOMBIE; - p = NULL; - } - } + + /* If parent wants a zombie, don't release it now */ + state = EXIT_ZOMBIE; + if (do_notify_parent(p, p->exit_signal)) + state = EXIT_DEAD; + p->exit_state = state; write_unlock_irq(&tasklist_lock); } - if (p != NULL) + if (state == EXIT_DEAD) release_task(p); return retval; @@ -1354,7 +1126,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { - if (task_is_stopped_or_traced(p)) + if (task_is_stopped_or_traced(p) && + !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) @@ -1363,11 +1136,23 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace) return NULL; } -/* - * Handle sys_wait4 work for one task in state TASK_STOPPED. 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. +/** + * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED + * @wo: wait options + * @ptrace: is the wait for ptrace + * @p: task to wait for + * + * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. + * + * CONTEXT: + * read_lock(&tasklist_lock), which is released if return value is + * non-zero. Also, grabs and releases @p->sighand->siglock. + * + * RETURNS: + * 0 if wait condition didn't exist and search for other wait conditions + * should continue. Non-zero return, -errno on failure and @p's pid on + * success, implies that tasklist_lock is released and wait condition + * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) @@ -1383,6 +1168,9 @@ static int wait_task_stopped(struct wait_opts *wo, if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; + if (!task_stopped_code(p, ptrace)) + return 0; + exit_code = 0; spin_lock_irq(&p->sighand->siglock); @@ -1397,7 +1185,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1470,7 +1258,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); @@ -1506,7 +1294,12 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { - int ret = eligible_child(wo, p); + int ret; + + if (unlikely(p->exit_state == EXIT_DEAD)) + return 0; + + ret = eligible_child(wo, p); if (!ret) return ret; @@ -1524,33 +1317,88 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, return 0; } - if (likely(!ptrace) && unlikely(task_ptrace(p))) { + if (unlikely(p->exit_state == EXIT_TRACE)) { /* - * This child is hidden by ptrace. - * We aren't allowed to see it now, but eventually we will. + * ptrace == 0 means we are the natural parent. In this case + * we should clear notask_error, debugger will notify us. */ - wo->notask_error = 0; + if (likely(!ptrace)) + wo->notask_error = 0; return 0; } - if (p->exit_state == EXIT_DEAD) - return 0; + if (likely(!ptrace) && unlikely(p->ptrace)) { + /* + * If it is traced by its real parent's group, just pretend + * the caller is ptrace_do_wait() and reap this child if it + * is zombie. + * + * This also hides group stop state from real parent; otherwise + * a single stop can be reported twice as group and ptrace stop. + * If a ptracer wants to distinguish these two events for its + * own children it should create a separate process which takes + * the role of real parent. + */ + if (!ptrace_reparented(p)) + ptrace = 1; + } + + /* slay zombie? */ + if (p->exit_state == EXIT_ZOMBIE) { + /* we don't reap group leaders with subthreads */ + if (!delay_group_leader(p)) { + /* + * A zombie ptracee is only visible to its ptracer. + * Notification and reaping will be cascaded to the + * real parent when the ptracer detaches. + */ + if (unlikely(ptrace) || likely(!p->ptrace)) + return wait_task_zombie(wo, p); + } + + /* + * Allow access to stopped/continued state via zombie by + * falling through. Clearing of notask_error is complex. + * + * When !@ptrace: + * + * If WEXITED is set, notask_error should naturally be + * cleared. If not, subset of WSTOPPED|WCONTINUED is set, + * so, if there are live subthreads, there are events to + * wait for. If all subthreads are dead, it's still safe + * to clear - this function will be called again in finite + * amount time once all the subthreads are released and + * will then return without clearing. + * + * When @ptrace: + * + * Stopped state is per-task and thus can't change once the + * target task dies. Only continued and exited can happen. + * Clear notask_error if WCONTINUED | WEXITED. + */ + if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) + wo->notask_error = 0; + } else { + /* + * @p is alive and it's gonna stop, continue or exit, so + * there always is something to wait for. + */ + wo->notask_error = 0; + } /* - * We don't reap group leaders with subthreads. + * Wait for stopped. Depending on @ptrace, different stopped state + * is used and the two don't interact with each other. */ - if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) - return wait_task_zombie(wo, p); + ret = wait_task_stopped(wo, ptrace, p); + if (ret) + return ret; /* - * It's stopped or running now, so it might - * later continue, exit, or stop again. + * Wait for continued. There's only one continued state and the + * ptracer can consume it which can confuse the real parent. Don't + * use WCONTINUED from ptracer. You don't need or want it. */ - wo->notask_error = 0; - - if (task_stopped_code(p, ptrace)) - return wait_task_stopped(wo, ptrace, p); - return wait_task_continued(wo, p); } @@ -1730,9 +1578,6 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, } put_pid(pid); - - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(5, ret, which, upid, infop, options, ru); return ret; } @@ -1770,8 +1615,6 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, ret = do_wait(&wo); put_pid(pid); - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(4, ret, upid, stat_addr, options, ru); return ret; } |