diff options
Diffstat (limited to 'kernel/exit.c')
| -rw-r--r-- | kernel/exit.c | 1624 |
1 files changed, 799 insertions, 825 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index 53872bf993f..e5c4668f179 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -12,13 +12,15 @@ #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> -#include <linux/mnt_namespace.h> +#include <linux/iocontext.h> #include <linux/key.h> #include <linux/security.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> @@ -30,7 +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> @@ -38,12 +39,20 @@ #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> -#include <linux/compat.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> +#include <linux/tracehook.h> +#include <linux/fs_struct.h> +#include <linux/init_task.h> +#include <linux/perf_event.h> +#include <trace/events/sched.h> +#include <linux/hw_breakpoint.h> +#include <linux/oom.h> +#include <linux/writeback.h> +#include <linux/shm.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -52,19 +61,20 @@ static void exit_mm(struct task_struct * tsk); -static void __unhash_process(struct task_struct *p) +static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); - if (thread_group_leader(p)) { + if (group_dead) { detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); - __get_cpu_var(process_counts)--; + list_del_init(&p->sibling); + __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); - remove_parent(p); + list_del_rcu(&p->thread_node); } /* @@ -73,24 +83,34 @@ static void __unhash_process(struct task_struct *p) static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; + bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; + struct tty_struct *uninitialized_var(tty); + cputime_t utime, stime; - BUG_ON(!sig); - BUG_ON(!atomic_read(&sig->count)); - - rcu_read_lock(); - sighand = rcu_dereference(tsk->sighand); + sighand = rcu_dereference_check(tsk->sighand, + lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); posix_cpu_timers_exit(tsk); - if (atomic_dec_and_test(&sig->count)) + if (group_dead) { posix_cpu_timers_exit_group(tsk); - else { + tty = sig->tty; + sig->tty = NULL; + } else { + /* + * This can only happen if the caller is de_thread(). + * FIXME: this is the temporary hack, we should teach + * posix-cpu-timers to handle this case correctly. + */ + if (unlikely(has_group_leader_pid(tsk))) + posix_cpu_timers_exit_group(tsk); + /* * If there is any task waiting for the group exit * then notify it: */ - if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) + if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) @@ -105,51 +125,64 @@ 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; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); + task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; - sig = NULL; /* Marker for below. */ } - __unhash_process(tsk); + sig->nr_threads--; + __unhash_process(tsk, group_dead); - tsk->signal = NULL; + /* + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ + flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); - rcu_read_unlock(); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk,TIF_SIGPENDING); - flush_sigqueue(&tsk->pending); - if (sig) { + if (group_dead) { flush_sigqueue(&sig->shared_pending); - taskstats_tgid_free(sig); - __cleanup_signal(sig); + tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { - put_task_struct(container_of(rhp, struct task_struct, rcu)); + struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); + + perf_event_delayed_put(tsk); + trace_sched_process_free(tsk); + put_task_struct(tsk); } + void release_task(struct task_struct * p) { struct task_struct *leader; int zap_leader; repeat: - atomic_dec(&p->user->processes); + /* don't need to get the RCU readlock here - the process is dead and + * can't be modifying its own credentials. But shut RCU-lockdep up */ + rcu_read_lock(); + atomic_dec(&__task_cred(p)->user->processes); + rcu_read_unlock(); + proc_flush_task(p); + write_lock_irq(&tasklist_lock); - ptrace_unlink(p); - BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); + ptrace_release_task(p); __exit_signal(p); /* @@ -160,17 +193,14 @@ repeat: zap_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 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 = (leader->exit_signal == -1); + zap_leader = do_notify_parent(leader, leader->exit_signal); + if (zap_leader) + leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); @@ -240,18 +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; } /* @@ -285,294 +313,93 @@ 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 */ - remove_parent(current); - current->real_parent = current->parent = kthreadd_task; - add_parent(current); - - /* Set the exit signal to SIGCHLD so we signal init on exit */ - current->exit_signal = SIGCHLD; - - if (task_nice(current) < 0) - set_user_nice(current, 0); - /* cpus_allowed? */ - /* rt_priority? */ - /* signals? */ - security_task_reparent_to_init(current); - memcpy(current->signal->rlim, init_task.signal->rlim, - sizeof(current->signal->rlim)); - atomic_inc(&(INIT_USER->__count)); - write_unlock_irq(&tasklist_lock); - switch_uid(INIT_USER); -} - -void __set_special_pids(struct pid *pid) -{ - struct task_struct *curr = current->group_leader; - pid_t nr = pid_nr(pid); - - if (task_session(curr) != pid) { - detach_pid(curr, PIDTYPE_SID); - attach_pid(curr, PIDTYPE_SID, pid); - set_task_session(curr, nr); - } - if (task_pgrp(curr) != pid) { - detach_pid(curr, PIDTYPE_PGID); - attach_pid(curr, PIDTYPE_PGID, pid); - set_task_pgrp(curr, nr); - } -} - -static void set_special_pids(struct pid *pid) -{ - write_lock_irq(&tasklist_lock); - __set_special_pids(pid); - write_unlock_irq(&tasklist_lock); -} - -/* - * Let kernel threads use this to say that they - * allow a certain signal (since daemonize() will - * have disabled all of them by default). - */ -int allow_signal(int sig) -{ - if (!valid_signal(sig) || sig < 1) - return -EINVAL; - - spin_lock_irq(¤t->sighand->siglock); - sigdelset(¤t->blocked, sig); - if (!current->mm) { - /* Kernel threads handle their own signals. - Let the signal code know it'll be handled, so - that they don't get converted to SIGKILL or - just silently dropped */ - current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; - } - recalc_sigpending(); - spin_unlock_irq(¤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, ...) +void mm_update_next_owner(struct mm_struct *mm) { - va_list args; - struct fs_struct *fs; - sigset_t blocked; - - va_start(args, name); - vsnprintf(current->comm, sizeof(current->comm), name, args); - va_end(args); + struct task_struct *c, *g, *p = current; +retry: /* - * 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. + * If the exiting or execing task is not the owner, it's + * someone else's problem. */ - exit_mm(current); + if (mm->owner != p) + return; /* - * We don't want to have TIF_FREEZE set if the system-wide hibernation - * or suspend transition begins right now. + * The current owner is exiting/execing and there are no other + * candidates. Do not leave the mm pointing to a possibly + * freed task structure. */ - current->flags |= PF_NOFREEZE; - - if (current->nsproxy != &init_nsproxy) { - get_nsproxy(&init_nsproxy); - switch_task_namespaces(current, &init_nsproxy); + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; + return; } - set_special_pids(&init_struct_pid); - proc_clear_tty(current); - - /* Block and flush all signals */ - sigfillset(&blocked); - sigprocmask(SIG_BLOCK, &blocked, NULL); - flush_signals(current); - - /* Become as one with the init task */ - - exit_fs(current); /* current->fs->count--; */ - fs = init_task.fs; - current->fs = fs; - atomic_inc(&fs->count); - - exit_files(current); - current->files = init_task.files; - atomic_inc(¤t->files->count); - - reparent_to_kthreadd(); -} - -EXPORT_SYMBOL(daemonize); - -static void close_files(struct files_struct * files) -{ - int i, j; - struct fdtable *fdt; - - j = 0; + read_lock(&tasklist_lock); /* - * It is safe to dereference the fd table without RCU or - * ->file_lock because this is the last reference to the - * files structure. + * Search in the children */ - fdt = files_fdtable(files); - for (;;) { - unsigned long set; - i = j * __NFDBITS; - if (i >= fdt->max_fds) - break; - set = fdt->open_fds->fds_bits[j++]; - while (set) { - if (set & 1) { - struct file * file = xchg(&fdt->fd[i], NULL); - if (file) { - filp_close(file, files); - cond_resched(); - } - } - i++; - set >>= 1; - } + list_for_each_entry(c, &p->children, sibling) { + if (c->mm == mm) + goto assign_new_owner; } -} - -struct files_struct *get_files_struct(struct task_struct *task) -{ - struct files_struct *files; - - task_lock(task); - files = task->files; - if (files) - atomic_inc(&files->count); - task_unlock(task); - - return files; -} - -void put_files_struct(struct files_struct *files) -{ - struct fdtable *fdt; - if (atomic_dec_and_test(&files->count)) { - close_files(files); - /* - * Free the fd and fdset arrays if we expanded them. - * If the fdtable was embedded, pass files for freeing - * at the end of the RCU grace period. Otherwise, - * you can free files immediately. - */ - fdt = files_fdtable(files); - if (fdt != &files->fdtab) - kmem_cache_free(files_cachep, files); - free_fdtable(fdt); - } -} - -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 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); + /* + * Search in the siblings + */ + list_for_each_entry(c, &p->real_parent->children, sibling) { + if (c->mm == mm) + goto assign_new_owner; } -} -void exit_files(struct task_struct *tsk) -{ - __exit_files(tsk); -} - -static void __put_fs_struct(struct fs_struct *fs) -{ - /* No need to hold fs->lock if we are killing it */ - if (atomic_dec_and_test(&fs->count)) { - path_put(&fs->root); - path_put(&fs->pwd); - if (fs->altroot.dentry) - path_put(&fs->altroot); - kmem_cache_free(fs_cachep, fs); + /* + * Search through everything else, we should not get here often. + */ + for_each_process(g) { + if (g->flags & PF_KTHREAD) + continue; + for_each_thread(g, c) { + if (c->mm == mm) + goto assign_new_owner; + if (c->mm) + break; + } } -} - -void put_fs_struct(struct fs_struct *fs) -{ - __put_fs_struct(fs); -} - -static void __exit_fs(struct task_struct *tsk) -{ - struct fs_struct * fs = tsk->fs; + read_unlock(&tasklist_lock); + /* + * We found no owner yet mm_users > 1: this implies that we are + * most likely racing with swapoff (try_to_unuse()) or /proc or + * ptrace or page migration (get_task_mm()). Mark owner as NULL. + */ + mm->owner = NULL; + return; - if (fs) { - task_lock(tsk); - tsk->fs = NULL; - task_unlock(tsk); - __put_fs_struct(fs); +assign_new_owner: + BUG_ON(c == p); + get_task_struct(c); + /* + * The task_lock protects c->mm from changing. + * We always want mm->owner->mm == mm + */ + task_lock(c); + /* + * Delay read_unlock() till we have the task_lock() + * to ensure that c does not slip away underneath us + */ + read_unlock(&tasklist_lock); + if (c->mm != mm) { + task_unlock(c); + put_task_struct(c); + goto retry; } + mm->owner = c; + task_unlock(c); + put_task_struct(c); } - -void exit_fs(struct task_struct *tsk) -{ - __exit_fs(tsk); -} - -EXPORT_SYMBOL_GPL(exit_fs); +#endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we @@ -581,26 +408,41 @@ EXPORT_SYMBOL_GPL(exit_fs); static void exit_mm(struct task_struct * tsk) { struct mm_struct *mm = tsk->mm; + struct core_state *core_state; mm_release(tsk, mm); if (!mm) return; + sync_mm_rss(mm); /* * Serialize with any possible pending coredump. - * We must hold mmap_sem around checking core_waiters + * We must hold mmap_sem around checking core_state * and clearing tsk->mm. The core-inducing thread - * will increment core_waiters for each thread in the + * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ down_read(&mm->mmap_sem); - if (mm->core_waiters) { + core_state = mm->core_state; + if (core_state) { + struct core_thread self; up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); - if (!--mm->core_waiters) - complete(mm->core_startup_done); - up_write(&mm->mmap_sem); - wait_for_completion(&mm->core_done); + self.task = tsk; + self.next = xchg(&core_state->dumper.next, &self); + /* + * Implies mb(), the result of xchg() must be visible + * to core_state->dumper. + */ + if (atomic_dec_and_test(&core_state->nr_threads)) + complete(&core_state->startup); + + for (;;) { + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (!self.task) /* see coredump_finish() */ + break; + freezable_schedule(); + } + __set_task_state(tsk, TASK_RUNNING); down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); @@ -610,140 +452,139 @@ 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); task_unlock(tsk); + mm_update_next_owner(mm); mmput(mm); } -static void -reparent_thread(struct task_struct *p, struct task_struct *father, int traced) +/* + * When we die, we re-parent all our children, and try to: + * 1. give them to another thread in our thread group, if such a member exists + * 2. give it to the first ancestor process which prctl'd itself as a + * child_subreaper for its children (like a service manager) + * 3. give it to the init process (PID 1) in our pid namespace + */ +static struct task_struct *find_new_reaper(struct task_struct *father) + __releases(&tasklist_lock) + __acquires(&tasklist_lock) { - if (p->pdeath_signal) - /* We already hold the tasklist_lock here. */ - 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; - remove_parent(p); - p->parent = p->real_parent; - add_parent(p); + struct pid_namespace *pid_ns = task_active_pid_ns(father); + struct task_struct *thread; - if (task_is_traced(p)) { - /* - * If it was at a trace stop, turn it into - * a normal stop since it's no longer being - * traced. - */ - ptrace_untrace(p); + thread = father; + while_each_thread(father, thread) { + if (thread->flags & PF_EXITING) + continue; + if (unlikely(pid_ns->child_reaper == father)) + pid_ns->child_reaper = thread; + return thread; + } + + if (unlikely(pid_ns->child_reaper == father)) { + write_unlock_irq(&tasklist_lock); + if (unlikely(pid_ns == &init_pid_ns)) { + panic("Attempted to kill init! exitcode=0x%08x\n", + father->signal->group_exit_code ?: + father->exit_code); + } + + zap_pid_ns_processes(pid_ns); + write_lock_irq(&tasklist_lock); + } else if (father->signal->has_child_subreaper) { + struct task_struct *reaper; + + /* + * Find the first ancestor marked as child_subreaper. + * Note that the code below checks same_thread_group(reaper, + * pid_ns->child_reaper). This is what we need to DTRT in a + * PID namespace. However we still need the check above, see + * http://marc.info/?l=linux-kernel&m=131385460420380 + */ + 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); } } - /* If this is a threaded reparent there is no need to + return pid_ns->child_reaper; +} + +/* +* Any that need to be release_task'd are put on the @dead list. + */ +static void reparent_leader(struct task_struct *father, struct task_struct *p, + struct list_head *dead) +{ + list_move_tail(&p->sibling, &p->real_parent->children); + + if (p->exit_state == EXIT_DEAD) + return; + /* + * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ - if (p->real_parent->group_leader == father->group_leader) + if (same_thread_group(p->real_parent, father)) return; - /* We don't want people slaying init. */ - if (p->exit_signal != -1) - p->exit_signal = SIGCHLD; + /* We don't want people slaying init. */ + p->exit_signal = SIGCHLD; - /* If we'd notified the old parent about this child's death, - * also notify the new parent. - */ - if (!traced && p->exit_state == EXIT_ZOMBIE && - p->exit_signal != -1 && thread_group_empty(p)) - do_notify_parent(p, p->exit_signal); + /* If it has exited notify the new parent about this child's death. */ + if (!p->ptrace && + p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { + if (do_notify_parent(p, p->exit_signal)) { + p->exit_state = EXIT_DEAD; + list_move_tail(&p->sibling, dead); + } + } kill_orphaned_pgrp(p, father); } -/* - * When we die, we re-parent all our children. - * Try to give them to another thread in our thread - * group, and if no such member exists, give it to - * the child reaper process (ie "init") in our pid - * space. - */ static void forget_original_parent(struct task_struct *father) { - struct task_struct *p, *n, *reaper = father; - struct list_head ptrace_dead; - - INIT_LIST_HEAD(&ptrace_dead); + struct task_struct *p, *n, *reaper; + LIST_HEAD(dead_children); write_lock_irq(&tasklist_lock); - - do { - reaper = next_thread(reaper); - if (reaper == father) { - reaper = task_child_reaper(father); - break; - } - } while (reaper->flags & PF_EXITING); - /* - * There are only two places where our children can be: - * - * - in our child list - * - in our ptraced child list - * - * Search them and reparent children. + * Note that exit_ptrace() and find_new_reaper() might + * drop tasklist_lock and reacquire it. */ - list_for_each_entry_safe(p, n, &father->children, sibling) { - int ptrace; + exit_ptrace(father); + reaper = find_new_reaper(father); - 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 */ - p->real_parent = 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, &ptrace_dead); - } - - list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) { - p->real_parent = reaper; - reparent_thread(p, father, 1); + list_for_each_entry_safe(p, n, &father->children, sibling) { + struct task_struct *t = p; + do { + t->real_parent = reaper; + if (t->parent == father) { + BUG_ON(t->ptrace); + t->parent = t->real_parent; + } + if (t->pdeath_signal) + group_send_sig_info(t->pdeath_signal, + SEND_SIG_NOINFO, t); + } while_each_thread(p, t); + reparent_leader(father, p, &dead_children); } - write_unlock_irq(&tasklist_lock); + BUG_ON(!list_empty(&father->children)); - BUG_ON(!list_empty(&father->ptrace_children)); - list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_list) { - list_del_init(&p->ptrace_list); + list_for_each_entry_safe(p, n, &dead_children, sibling) { + list_del_init(&p->sibling); release_task(p); } - } /* @@ -752,7 +593,7 @@ static void forget_original_parent(struct task_struct *father) */ static void exit_notify(struct task_struct *tsk, int group_dead) { - int state; + bool autoreap; /* * This does two things: @@ -763,58 +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 && tsk->exit_signal != -1 && - (tsk->parent_exec_id != tsk->real_parent->self_exec_id || - tsk->self_exec_id != tsk->parent_exec_id) - && !capable(CAP_KILL)) - tsk->exit_signal = SIGCHLD; - - - /* 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 (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; } - state = EXIT_ZOMBIE; - if (tsk->exit_signal == -1 && likely(!tsk->ptrace)) - state = EXIT_DEAD; - tsk->exit_state = state; + tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; - if (thread_group_leader(tsk) && - tsk->signal->notify_count < 0 && - tsk->signal->group_exit_task) + /* 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); /* If the process is dead, release it - nobody will wait for it */ - if (state == EXIT_DEAD) + if (autoreap) release_task(tsk); } @@ -823,21 +639,18 @@ static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; - unsigned long *n = end_of_stack(current); unsigned long free; - while (*n == 0) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(current); + free = stack_not_used(current); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { - printk(KERN_WARNING "%s used greatest stack depth: %lu bytes " - "left\n", - current->comm, free); + 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); @@ -846,57 +659,32 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif -static inline void exit_child_reaper(struct task_struct *tsk) -{ - if (likely(tsk->group_leader != task_child_reaper(tsk))) - return; - - if (tsk->nsproxy->pid_ns == &init_pid_ns) - panic("Attempted to kill init!"); - - /* - * @tsk is the last thread in the 'cgroup-init' and is exiting. - * Terminate all remaining processes in the namespace and reap them - * before exiting @tsk. - * - * Note that @tsk (last thread of cgroup-init) may not necessarily - * be the child-reaper (i.e main thread of cgroup-init) of the - * namespace i.e the child_reaper may have already exited. - * - * Even after a child_reaper exits, we let it inherit orphaned children, - * because, pid_ns->child_reaper remains valid as long as there is - * at least one living sub-thread in the cgroup init. - - * This living sub-thread of the cgroup-init will be notified when - * a child inherited by the 'child-reaper' exits (do_notify_parent() - * uses __group_send_sig_info()). Further, when reaping child processes, - * do_wait() iterates over children of all living sub threads. - - * i.e even though 'child_reaper' thread is listed as the parent of the - * orphaned children, any living sub-thread in the cgroup-init can - * perform the role of the child_reaper. - */ - zap_pid_ns_processes(tsk->nsproxy->pid_ns); -} - -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!"); - if (unlikely(current->ptrace & PT_TRACE_EXIT)) { - current->ptrace_message = code; - ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); - } + /* + * 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); /* * We're taking recursive faults here in do_exit. Safest is to just @@ -915,8 +703,6 @@ NORET_TYPE void do_exit(long code) * task into the wait for ever nirwana as well. */ tsk->flags |= PF_EXITPIDONE; - if (tsk->io_context) - exit_io_context(); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } @@ -927,7 +713,7 @@ NORET_TYPE void do_exit(long code) * an exiting task cleaning up the robust pi futexes. */ smp_mb(); - spin_unlock_wait(&tsk->pi_lock); + raw_spin_unlock_wait(&tsk->pi_lock); if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", @@ -935,29 +721,20 @@ NORET_TYPE void do_exit(long code) preempt_count()); acct_update_integrals(tsk); - if (tsk->mm) { - update_hiwater_rss(tsk->mm); - update_hiwater_vm(tsk->mm); - } + /* sync mm's RSS info before statistics gathering */ + if (tsk->mm) + sync_mm_rss(tsk->mm); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { - exit_child_reaper(tsk); hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); + if (tsk->mm) + setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); -#ifdef CONFIG_FUTEX - if (unlikely(tsk->robust_list)) - exit_robust_list(tsk); -#ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) - compat_exit_robust_list(tsk); -#endif -#endif 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); @@ -966,41 +743,51 @@ NORET_TYPE void do_exit(long code) if (group_dead) acct_process(); + trace_sched_process_exit(tsk); + exit_sem(tsk); - __exit_files(tsk); - __exit_fs(tsk); - check_stack_usage(); + exit_shm(tsk); + exit_files(tsk); + exit_fs(tsk); + if (group_dead) + disassociate_ctty(1); + exit_task_namespaces(tsk); + exit_task_work(tsk); exit_thread(); - cgroup_exit(tsk, 1); - exit_keys(tsk); - if (group_dead && tsk->signal->leader) - disassociate_ctty(1); + /* + * 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); + + cgroup_exit(tsk); module_put(task_thread_info(tsk)->exec_domain->module); - if (tsk->binfmt) - module_put(tsk->binfmt->module); - proc_exit_connector(tsk); + /* + * FIXME: do that only when needed, using sched_exit tracepoint + */ + flush_ptrace_hw_breakpoint(tsk); + exit_notify(tsk, group_dead); + proc_exit_connector(tsk); #ifdef CONFIG_NUMA - mpol_free(tsk->mempolicy); + task_lock(tsk); + mpol_put(tsk->mempolicy); tsk->mempolicy = NULL; + task_unlock(tsk); #endif #ifdef CONFIG_FUTEX - /* - * 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); #endif /* * 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 @@ -1009,15 +796,40 @@ NORET_TYPE void do_exit(long code) tsk->flags |= PF_EXITPIDONE; if (tsk->io_context) - exit_io_context(); + 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". */ @@ -1027,7 +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); @@ -1037,7 +849,7 @@ NORET_TYPE void complete_and_exit(struct completion *comp, long code) EXPORT_SYMBOL(complete_and_exit); -asmlinkage long sys_exit(int error_code) +SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } @@ -1046,15 +858,16 @@ asmlinkage long sys_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; + BUG_ON(exit_code & 0x80); /* core dumps don't get here */ - if (current->signal->flags & SIGNAL_GROUP_EXIT) - exit_code = current->signal->group_exit_code; + if (signal_group_exit(sig)) + exit_code = sig->group_exit_code; else if (!thread_group_empty(current)) { - struct signal_struct *const sig = current->signal; struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (signal_group_exit(sig)) @@ -1077,78 +890,79 @@ do_group_exit(int exit_code) * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ -asmlinkage void sys_exit_group(int error_code) +SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); + /* NOTREACHED */ + return 0; } -static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) +struct wait_opts { + enum pid_type wo_type; + int wo_flags; + struct pid *wo_pid; + + struct siginfo __user *wo_info; + int __user *wo_stat; + struct rusage __user *wo_rusage; + + wait_queue_t child_wait; + int notask_error; +}; + +static inline +struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { - struct pid *pid = NULL; - if (type == PIDTYPE_PID) - pid = task->pids[type].pid; - else if (type < PIDTYPE_MAX) - pid = task->group_leader->pids[type].pid; - return pid; + if (type != PIDTYPE_PID) + task = task->group_leader; + return task->pids[type].pid; } -static int eligible_child(enum pid_type type, struct pid *pid, int options, - struct task_struct *p) +static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { - int err; - - if (type < PIDTYPE_MAX) { - if (task_pid_type(p, type) != pid) - return 0; - } + return wo->wo_type == PIDTYPE_MAX || + task_pid_type(p, wo->wo_type) == wo->wo_pid; +} - /* - * Do not consider detached threads that are - * not ptraced: - */ - if (p->exit_signal == -1 && !p->ptrace) +static int eligible_child(struct wait_opts *wo, struct task_struct *p) +{ + if (!eligible_pid(wo, p)) return 0; - /* Wait for all children (clone and not) if __WALL is set; * otherwise, wait for clone children *only* if __WCLONE is * set; otherwise, wait for non-clone children *only*. (Note: * A "clone" child here is one that reports to its parent * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0)) - && !(options & __WALL)) + if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) + && !(wo->wo_flags & __WALL)) return 0; - err = security_task_wait(p); - if (likely(!err)) - return 1; - - if (type != PIDTYPE_PID) - return 0; - /* This child was explicitly requested, abort */ - read_unlock(&tasklist_lock); - return err; + return 1; } -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) +static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, + pid_t pid, uid_t uid, int why, int status) { - int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + struct siginfo __user *infop; + int retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 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); + infop = wo->wo_info; + if (infop) { + 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; @@ -1160,18 +974,20 @@ static int wait_noreap_copyout(struct task_struct *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(struct task_struct *p, int noreap, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +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 = from_kuid_munged(current_user_ns(), task_uid(p)); + struct siginfo __user *infop; - if (unlikely(noreap)) { - uid_t uid = p->uid; + if (!likely(wo->wo_flags & WEXITED)) + return 0; + + if (unlikely(wo->wo_flags & WNOWAIT)) { int exit_code = p->exit_code; - int why, status; + int why; get_task_struct(p); read_unlock(&tasklist_lock); @@ -1182,26 +998,25 @@ static int wait_task_zombie(struct task_struct *p, int noreap, why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; status = exit_code & 0x7f; } - return wait_noreap_copyout(p, pid, uid, why, - status, infop, ru); + 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 means p->ptrace, but not vice versa */ - traced = (p->real_parent != p->parent); - - if (likely(!traced)) { + /* + * It can be ptraced but not reparented, check + * thread_group_leader() to filter out sub-threads. + */ + if (likely(!traced) && thread_group_leader(p)) { struct signal_struct *psig; struct signal_struct *sig; + unsigned long maxrss; + cputime_t tgutime, tgstime; /* * The resource counters for the group leader are in its @@ -1214,28 +1029,21 @@ static int wait_task_zombie(struct task_struct *p, int noreap, * 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, + * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * 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. */ - spin_lock_irq(&p->parent->sighand->siglock); - psig = p->parent->signal; + 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(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->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 += @@ -1250,20 +1058,28 @@ static int wait_task_zombie(struct task_struct *p, int noreap, psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; - spin_unlock_irq(&p->parent->sighand->siglock); + maxrss = max(sig->maxrss, sig->cmaxrss); + if (psig->cmaxrss < maxrss) + psig->cmaxrss = maxrss; + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); + spin_unlock_irq(&p->real_parent->sighand->siglock); } /* * 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); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; 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 && wo->wo_stat) + retval = put_user(status, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1285,69 +1101,91 @@ static int wait_task_zombie(struct task_struct *p, int noreap, if (!retval && infop) retval = put_user(pid, &infop->si_pid); if (!retval && infop) - retval = put_user(p->uid, &infop->si_uid); + retval = put_user(uid, &infop->si_uid); 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 (p->exit_signal != -1) { - do_notify_parent(p, p->exit_signal); - if (p->exit_signal != -1) { - 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; } -/* - * 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. +static int *task_stopped_code(struct task_struct *p, bool ptrace) +{ + if (ptrace) { + if (task_is_stopped_or_traced(p) && + !(p->jobctl & JOBCTL_LISTENING)) + return &p->exit_code; + } else { + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return &p->signal->group_exit_code; + } + return NULL; +} + +/** + * 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 task_struct *p, - int noreap, struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_stopped(struct wait_opts *wo, + int ptrace, struct task_struct *p) { - int retval, exit_code, why; + struct siginfo __user *infop; + int retval, exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; + /* + * Traditionally we see ptrace'd stopped tasks regardless of options. + */ + 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); - if (unlikely(!task_is_stopped_or_traced(p))) + p_code = task_stopped_code(p, ptrace); + if (unlikely(!p_code)) goto unlock_sig; - if (!(p->ptrace & PT_PTRACED) && p->signal->group_stop_count > 0) - /* - * A group stop is in progress and this is the group leader. - * We won't report until all threads have stopped. - */ - goto unlock_sig; - - exit_code = p->exit_code; + exit_code = *p_code; if (!exit_code) goto unlock_sig; - if (!noreap) - p->exit_code = 0; + if (!unlikely(wo->wo_flags & WNOWAIT)) + *p_code = 0; - uid = p->uid; + uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1362,17 +1200,18 @@ unlock_sig: */ get_task_struct(p); pid = task_pid_vnr(p); - why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; + why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); - if (unlikely(noreap)) - return wait_noreap_copyout(p, pid, uid, - why, exit_code, - infop, ru); + if (unlikely(wo->wo_flags & WNOWAIT)) + return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; - if (!retval && stat_addr) - retval = put_user((exit_code << 8) | 0x7f, stat_addr); + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (!retval && wo->wo_stat) + retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1399,14 +1238,15 @@ unlock_sig: * 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(struct task_struct *p, int noreap, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { int retval; pid_t pid; uid_t uid; + if (!unlikely(wo->wo_flags & WCONTINUED)) + return 0; + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; @@ -1416,165 +1256,267 @@ static int wait_task_continued(struct task_struct *p, int noreap, spin_unlock_irq(&p->sighand->siglock); return 0; } - if (!noreap) + if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); - uid = p->uid; get_task_struct(p); read_unlock(&tasklist_lock); - if (!infop) { - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + if (!wo->wo_info) { + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); - if (!retval && stat_addr) - retval = put_user(0xffff, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(0xffff, wo->wo_stat); if (!retval) retval = pid; } else { - retval = wait_noreap_copyout(p, pid, uid, - CLD_CONTINUED, SIGCONT, - infop, ru); + retval = wait_noreap_copyout(wo, p, pid, uid, + CLD_CONTINUED, SIGCONT); BUG_ON(retval == 0); } return retval; } -static long do_wait(enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +/* + * Consider @p for a wait by @parent. + * + * -ECHILD should be in ->notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; + * then ->notask_error is 0 if @p is an eligible child, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int wait_consider_task(struct wait_opts *wo, int ptrace, + struct task_struct *p) +{ + int ret; + + if (unlikely(p->exit_state == EXIT_DEAD)) + return 0; + + ret = eligible_child(wo, p); + if (!ret) + return ret; + + ret = security_task_wait(p); + if (unlikely(ret < 0)) { + /* + * If we have not yet seen any eligible child, + * then let this error code replace -ECHILD. + * A permission error will give the user a clue + * to look for security policy problems, rather + * than for mysterious wait bugs. + */ + if (wo->notask_error) + wo->notask_error = ret; + return 0; + } + + if (unlikely(p->exit_state == EXIT_TRACE)) { + /* + * ptrace == 0 means we are the natural parent. In this case + * we should clear notask_error, debugger will notify us. + */ + if (likely(!ptrace)) + wo->notask_error = 0; + 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; + } + + /* + * Wait for stopped. Depending on @ptrace, different stopped state + * is used and the two don't interact with each other. + */ + ret = wait_task_stopped(wo, ptrace, p); + if (ret) + return ret; + + /* + * 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. + */ + return wait_task_continued(wo, p); +} + +/* + * Do the work of do_wait() for one thread in the group, @tsk. + * + * -ECHILD should be in ->notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; then + * ->notask_error is 0 if there were any eligible children, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) +{ + struct task_struct *p; + + list_for_each_entry(p, &tsk->children, sibling) { + int ret = wait_consider_task(wo, 0, p); + if (ret) + return ret; + } + + return 0; +} + +static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) +{ + struct task_struct *p; + + list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { + int ret = wait_consider_task(wo, 1, p); + if (ret) + return ret; + } + + return 0; +} + +static int child_wait_callback(wait_queue_t *wait, unsigned mode, + int sync, void *key) +{ + struct wait_opts *wo = container_of(wait, struct wait_opts, + child_wait); + struct task_struct *p = key; + + if (!eligible_pid(wo, p)) + return 0; + + if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) + return 0; + + return default_wake_function(wait, mode, sync, key); +} + +void __wake_up_parent(struct task_struct *p, struct task_struct *parent) +{ + __wake_up_sync_key(&parent->signal->wait_chldexit, + TASK_INTERRUPTIBLE, 1, p); +} + +static long do_wait(struct wait_opts *wo) { - DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; - int flag, retval; + int retval; - add_wait_queue(¤t->signal->wait_chldexit,&wait); -repeat: - /* If there is nothing that can match our critier just get out */ - retval = -ECHILD; - if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type]))) - goto end; + trace_sched_process_wait(wo->wo_pid); + init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); + wo->child_wait.private = current; + add_wait_queue(¤t->signal->wait_chldexit, &wo->child_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. + * If there is nothing that can match our critiera just get out. + * We will clear ->notask_error to zero if we see any child that + * might later match our criteria, even if we are not able to reap + * it yet. */ - flag = retval = 0; - current->state = TASK_INTERRUPTIBLE; + wo->notask_error = -ECHILD; + if ((wo->wo_type < PIDTYPE_MAX) && + (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) + goto notask; + + set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); tsk = current; do { - struct task_struct *p; + retval = do_wait_thread(wo, tsk); + if (retval) + goto end; - list_for_each_entry(p, &tsk->children, sibling) { - int ret = eligible_child(type, pid, options, p); - if (!ret) - continue; + retval = ptrace_do_wait(wo, tsk); + if (retval) + goto end; - if (unlikely(ret < 0)) { - retval = ret; - } else if (task_is_stopped_or_traced(p)) { - /* - * It's stopped now, so it might later - * continue, exit, or stop again. - */ - flag = 1; - if (!(p->ptrace & PT_PTRACED) && - !(options & WUNTRACED)) - continue; - - retval = wait_task_stopped(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } else if (p->exit_state == EXIT_ZOMBIE && - !delay_group_leader(p)) { - /* - * We don't reap group leaders with subthreads. - */ - if (!likely(options & WEXITED)) - continue; - retval = wait_task_zombie(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } else if (p->exit_state != EXIT_DEAD) { - /* - * It's running now, so it might later - * exit, stop, or stop and then continue. - */ - flag = 1; - if (!unlikely(options & WCONTINUED)) - continue; - retval = wait_task_continued(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } - if (retval != 0) /* tasklist_lock released */ - goto end; - } - if (!flag) { - list_for_each_entry(p, &tsk->ptrace_children, - ptrace_list) { - flag = eligible_child(type, pid, options, p); - if (!flag) - continue; - if (likely(flag > 0)) - break; - retval = flag; - goto end; - } - } - if (options & __WNOTHREAD) + if (wo->wo_flags & __WNOTHREAD) break; - tsk = next_thread(tsk); - BUG_ON(tsk->signal != current->signal); - } while (tsk != current); + } while_each_thread(current, tsk); read_unlock(&tasklist_lock); - if (flag) { - if (options & WNOHANG) - goto end; +notask: + retval = wo->notask_error; + if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; - if (signal_pending(current)) - goto end; - schedule(); - goto repeat; - } - retval = -ECHILD; -end: - current->state = TASK_RUNNING; - 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); + if (!signal_pending(current)) { + schedule(); + goto repeat; } } +end: + __set_current_state(TASK_RUNNING); + remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } -asmlinkage long sys_waitid(int which, pid_t upid, - struct siginfo __user *infop, int options, - struct rusage __user *ru) +SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, + infop, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1604,17 +1546,45 @@ asmlinkage long sys_waitid(int which, pid_t upid, if (type < PIDTYPE_MAX) pid = find_get_pid(upid); - ret = do_wait(type, pid, options, infop, NULL, ru); - put_pid(pid); - /* avoid REGPARM breakage on x86: */ - prevent_tail_call(ret); + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options; + wo.wo_info = infop; + wo.wo_stat = NULL; + wo.wo_rusage = ru; + ret = do_wait(&wo); + + if (ret > 0) { + ret = 0; + } else if (infop) { + /* + * For a WNOHANG return, clear out all the fields + * we would set so the user can easily tell the + * difference. + */ + if (!ret) + ret = put_user(0, &infop->si_signo); + if (!ret) + ret = put_user(0, &infop->si_errno); + if (!ret) + ret = put_user(0, &infop->si_code); + if (!ret) + ret = put_user(0, &infop->si_pid); + if (!ret) + ret = put_user(0, &infop->si_uid); + if (!ret) + ret = put_user(0, &infop->si_status); + } + + put_pid(pid); return ret; } -asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr, - int options, struct rusage __user *ru) +SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, + int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1630,17 +1600,21 @@ asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr, pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; - pid = get_pid(task_pgrp(current)); + pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } - ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru); + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options | WEXITED; + wo.wo_info = NULL; + wo.wo_stat = stat_addr; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); - /* avoid REGPARM breakage on x86: */ - prevent_tail_call(ret); return ret; } @@ -1650,7 +1624,7 @@ asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr, * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ -asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options) +SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return sys_wait4(pid, stat_addr, options, NULL); } |