X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=kernel%2Fexit.c;h=fedcdeaf3e60cb32bb0b16a993a3e7fc1d0b3d26;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=c84802f4fd1bc811c9149e7033bbfd16c960a4c0;hpb=cee37fe97739d85991964371c1f3a745c00dd236;p=linux-2.6.git diff --git a/kernel/exit.c b/kernel/exit.c index c84802f4f..fedcdeaf3 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -28,8 +29,17 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include /* for audit_free() */ #include +#include #include +#include #include #include @@ -46,21 +56,86 @@ static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p) { nr_threads--; - /* tasklist_lock is held, is this sufficient? */ - if (p->vx_info) { - atomic_dec(&p->vx_info->cvirt.nr_threads); - vx_nproc_dec(p); - } detach_pid(p, PIDTYPE_PID); - detach_pid(p, PIDTYPE_TGID); if (thread_group_leader(p)) { detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); - if (p->pid) - __get_cpu_var(process_counts)--; + + list_del_rcu(&p->tasks); + __get_cpu_var(process_counts)--; } + list_del_rcu(&p->thread_group); + remove_parent(p); +} - REMOVE_LINKS(p); +/* + * This function expects the tasklist_lock write-locked. + */ +static void __exit_signal(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct sighand_struct *sighand; + + BUG_ON(!sig); + BUG_ON(!atomic_read(&sig->count)); + + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + spin_lock(&sighand->siglock); + + posix_cpu_timers_exit(tsk); + if (atomic_dec_and_test(&sig->count)) + posix_cpu_timers_exit_group(tsk); + else { + /* + * If there is any task waiting for the group exit + * then notify it: + */ + if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) { + wake_up_process(sig->group_exit_task); + sig->group_exit_task = NULL; + } + if (tsk == sig->curr_target) + sig->curr_target = next_thread(tsk); + /* + * Accumulate here the counters for all threads but the + * group leader as they die, so they can be added into + * the process-wide totals when those are taken. + * The group leader stays around as a zombie as long + * as there are other threads. When it gets reaped, + * the exit.c code will add its counts into these totals. + * We won't ever get here for the group leader, since it + * will have been the last reference on the signal_struct. + */ + sig->utime = cputime_add(sig->utime, tsk->utime); + sig->stime = cputime_add(sig->stime, tsk->stime); + sig->min_flt += tsk->min_flt; + sig->maj_flt += tsk->maj_flt; + sig->nvcsw += tsk->nvcsw; + sig->nivcsw += tsk->nivcsw; + sig->sched_time += tsk->sched_time; + sig = NULL; /* Marker for below. */ + } + + __unhash_process(tsk); + + tsk->signal = NULL; + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + + __cleanup_sighand(sighand); + clear_tsk_thread_flag(tsk,TIF_SIGPENDING); + flush_sigqueue(&tsk->pending); + if (sig) { + flush_sigqueue(&sig->shared_pending); + __cleanup_signal(sig); + } +} + +static void delayed_put_task_struct(struct rcu_head *rhp) +{ + put_task_struct(container_of(rhp, struct task_struct, rcu)); } void release_task(struct task_struct * p) @@ -69,17 +144,14 @@ void release_task(struct task_struct * p) task_t *leader; struct dentry *proc_dentry; -repeat: +repeat: atomic_dec(&p->user->processes); spin_lock(&p->proc_lock); proc_dentry = proc_pid_unhash(p); write_lock_irq(&tasklist_lock); - if (unlikely(p->ptrace)) - __ptrace_unlink(p); + ptrace_unlink(p); BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); __exit_signal(p); - __exit_sighand(p); - __unhash_process(p); /* * If we are the last non-leader member of the thread @@ -107,32 +179,13 @@ repeat: spin_unlock(&p->proc_lock); proc_pid_flush(proc_dentry); release_thread(p); - if (p->vx_info) - release_vx_info(p->vx_info, p); - if (p->nx_info) - release_nx_info(p->nx_info, p); - put_task_struct(p); + call_rcu(&p->rcu, delayed_put_task_struct); p = leader; if (unlikely(zap_leader)) goto repeat; } -/* we are using it only for SMP init */ - -void unhash_process(struct task_struct *p) -{ - struct dentry *proc_dentry; - - spin_lock(&p->proc_lock); - proc_dentry = proc_pid_unhash(p); - write_lock_irq(&tasklist_lock); - __unhash_process(p); - write_unlock_irq(&tasklist_lock); - spin_unlock(&p->proc_lock); - proc_pid_flush(proc_dentry); -} - /* * This checks not only the pgrp, but falls back on the pid if no * satisfactory pgrp is found. I dunno - gdb doesn't work correctly @@ -197,7 +250,7 @@ int is_orphaned_pgrp(int pgrp) return retval; } -static inline int has_stopped_jobs(int pgrp) +static int has_stopped_jobs(int pgrp) { int retval = 0; struct task_struct *p; @@ -234,22 +287,24 @@ static inline int has_stopped_jobs(int pgrp) * * NOTE that reparent_to_init() gives the caller full capabilities. */ -static inline void reparent_to_init(void) +static void reparent_to_init(void) { write_lock_irq(&tasklist_lock); ptrace_unlink(current); /* Reparent to init */ - REMOVE_LINKS(current); - /* FIXME handle vchild_reaper/initpid */ + remove_parent(current); + /* FIXME: handle vchild_reaper/initpid */ current->parent = child_reaper; current->real_parent = child_reaper; - SET_LINKS(current); + add_parent(current); /* Set the exit signal to SIGCHLD so we signal init on exit */ current->exit_signal = SIGCHLD; - if ((current->policy == SCHED_NORMAL) && (task_nice(current) < 0)) + if ((current->policy == SCHED_NORMAL || + current->policy == SCHED_BATCH) + && (task_nice(current) < 0)) set_user_nice(current, 0); /* cpus_allowed? */ /* rt_priority? */ @@ -264,7 +319,7 @@ static inline void reparent_to_init(void) void __set_special_pids(pid_t session, pid_t pgrp) { - struct task_struct *curr = current; + struct task_struct *curr = current->group_leader; if (curr->signal->session != session) { detach_pid(curr, PIDTYPE_SID); @@ -348,9 +403,9 @@ void daemonize(const char *name, ...) exit_mm(current); set_special_pids(1, 1); - down(&tty_sem); + mutex_lock(&tty_mutex); current->signal->tty = NULL; - up(&tty_sem); + mutex_unlock(&tty_mutex); /* Block and flush all signals */ sigfillset(&blocked); @@ -363,6 +418,9 @@ void daemonize(const char *name, ...) fs = init_task.fs; current->fs = fs; atomic_inc(&fs->count); + exit_namespace(current); + current->namespace = init_task.namespace; + get_namespace(current->namespace); exit_files(current); current->files = init_task.files; atomic_inc(¤t->files->count); @@ -372,20 +430,28 @@ void daemonize(const char *name, ...) EXPORT_SYMBOL(daemonize); -static inline void close_files(struct files_struct * files) +static void close_files(struct files_struct * files) { int i, j; + struct fdtable *fdt; j = 0; + + /* + * It is safe to dereference the fd table without RCU or + * ->file_lock because this is the last reference to the + * files structure. + */ + fdt = files_fdtable(files); for (;;) { unsigned long set; i = j * __NFDBITS; - if (i >= files->max_fdset || i >= files->max_fds) + if (i >= fdt->max_fdset || i >= fdt->max_fds) break; - set = files->open_fds->fds_bits[j++]; + set = fdt->open_fds->fds_bits[j++]; while (set) { if (set & 1) { - struct file * file = xchg(&files->fd[i], NULL); + struct file * file = xchg(&fdt->fd[i], NULL); if (file) filp_close(file, files); vx_openfd_dec(i); @@ -411,18 +477,22 @@ struct files_struct *get_files_struct(struct task_struct *task) void fastcall put_files_struct(struct files_struct *files) { + struct fdtable *fdt; + if (atomic_dec_and_test(&files->count)) { close_files(files); /* * Free the fd and fdset arrays if we expanded them. + * If the fdtable was embedded, pass files for freeing + * at the end of the RCU grace period. Otherwise, + * you can free files immediately. */ - if (files->fd != &files->fd_array[0]) - free_fd_array(files->fd, files->max_fds); - if (files->max_fdset > __FD_SETSIZE) { - free_fdset(files->open_fds, files->max_fdset); - free_fdset(files->close_on_exec, files->max_fdset); - } - kmem_cache_free(files_cachep, files); + fdt = files_fdtable(files); + if (fdt == &files->fdtab) + fdt->free_files = files; + else + kmem_cache_free(files_cachep, files); + free_fdtable(fdt); } } @@ -525,17 +595,22 @@ static void exit_mm(struct task_struct * tsk) mmput(mm); } -static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_reaper) +static inline void choose_new_parent(task_t *p, task_t *reaper) { + /* check for reaper context */ + vxwprintk((p->xid != reaper->xid) && (reaper != child_reaper), + "rogue reaper: %p[%d,#%u] <> %p[%d,#%u]", + p, p->pid, p->xid, reaper, reaper->pid, reaper->xid); + /* * Make sure we're not reparenting to ourselves and that * the parent is not a zombie. */ - BUG_ON(p == reaper || reaper->exit_state >= EXIT_ZOMBIE); + BUG_ON(p == reaper || reaper->exit_state); p->real_parent = reaper; } -static inline void reparent_thread(task_t *p, task_t *father, int traced) +static void reparent_thread(task_t *p, task_t *father, int traced) { /* We don't want people slaying init. */ if (p->exit_signal != -1) @@ -543,7 +618,7 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) if (p->pdeath_signal) /* We already hold the tasklist_lock here. */ - group_send_sig_info(p->pdeath_signal, (void *) 0, p); + group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); /* Move the child from its dying parent to the new one. */ if (unlikely(traced)) { @@ -556,9 +631,9 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * anyway, so let go of it. */ p->ptrace = 0; - list_del_init(&p->sibling); + remove_parent(p); p->parent = p->real_parent; - list_add_tail(&p->sibling, &p->parent->children); + add_parent(p); /* If we'd notified the old parent about this child's death, * also notify the new parent. @@ -587,8 +662,8 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) int pgrp = process_group(p); if (will_become_orphaned_pgrp(pgrp, NULL) && has_stopped_jobs(pgrp)) { - __kill_pg_info(SIGHUP, (void *)1, pgrp); - __kill_pg_info(SIGCONT, (void *)1, pgrp); + __kill_pg_info(SIGHUP, SEND_SIG_PRIV, pgrp); + __kill_pg_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } } @@ -599,17 +674,16 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * group, and if no such member exists, give it to * the global child reaper process (ie "init") */ -static inline void forget_original_parent(struct task_struct * father, +static void forget_original_parent(struct task_struct * father, struct list_head *to_release) { struct task_struct *p, *reaper = father; struct list_head *_p, *_n; - /* FIXME handle vchild_reaper/initpid */ do { reaper = next_thread(reaper); if (reaper == father) { - reaper = child_reaper; + reaper = vx_child_reaper(father); break; } } while (reaper->exit_state); @@ -633,7 +707,7 @@ static inline void forget_original_parent(struct task_struct * father, if (father == p->real_parent) { /* reparent with a reaper, real father it's us */ - choose_new_parent(p, reaper, child_reaper); + choose_new_parent(p, vx_child_reaper(p)); reparent_thread(p, father, 0); } else { /* reparent ptraced task to its real parent */ @@ -654,7 +728,8 @@ static inline void forget_original_parent(struct task_struct * father, } list_for_each_safe(_p, _n, &father->ptrace_children) { p = list_entry(_p,struct task_struct,ptrace_list); - choose_new_parent(p, reaper, child_reaper); + /* check for reaper context */ + choose_new_parent(p, reaper); reparent_thread(p, father, 1); } } @@ -724,8 +799,8 @@ static void exit_notify(struct task_struct *tsk) (t->signal->session == tsk->signal->session) && will_become_orphaned_pgrp(process_group(tsk), tsk) && has_stopped_jobs(process_group(tsk))) { - __kill_pg_info(SIGHUP, (void *)1, process_group(tsk)); - __kill_pg_info(SIGCONT, (void *)1, process_group(tsk)); + __kill_pg_info(SIGHUP, SEND_SIG_PRIV, process_group(tsk)); + __kill_pg_info(SIGCONT, SEND_SIG_PRIV, process_group(tsk)); } /* Let father know we died @@ -780,10 +855,6 @@ static void exit_notify(struct task_struct *tsk) /* If the process is dead, release it - nobody will wait for it */ if (state == EXIT_DEAD) release_task(tsk); - - /* PF_DEAD causes final put_task_struct after we schedule. */ - preempt_disable(); - tsk->flags |= PF_DEAD; } fastcall NORET_TYPE void do_exit(long code) @@ -793,29 +864,34 @@ fastcall NORET_TYPE void do_exit(long code) profile_task_exit(tsk); + WARN_ON(atomic_read(&tsk->fs_excl)); + if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); - if (unlikely(tsk->pid == 1)) + if (unlikely(tsk == child_reaper)) panic("Attempted to kill init!"); - if (tsk->io_context) - exit_io_context(); if (unlikely(current->ptrace & PT_TRACE_EXIT)) { current->ptrace_message = code; ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); } - tsk->flags |= PF_EXITING; - /* - * Make sure we don't try to process any timer firings - * while we are already exiting. + * We're taking recursive faults here in do_exit. Safest is to just + * leave this task alone and wait for reboot. */ - tsk->it_virt_expires = cputime_zero; - tsk->it_prof_expires = cputime_zero; - tsk->it_sched_expires = 0; + if (unlikely(tsk->flags & PF_EXITING)) { + printk(KERN_ALERT + "Fixing recursive fault but reboot is needed!\n"); + if (tsk->io_context) + exit_io_context(); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + } + + tsk->flags |= PF_EXITING; if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", @@ -823,16 +899,39 @@ fastcall NORET_TYPE void do_exit(long code) preempt_count()); acct_update_integrals(tsk); - update_mem_hiwater(tsk); + if (tsk->mm) { + update_hiwater_rss(tsk->mm); + update_hiwater_vm(tsk->mm); + } group_dead = atomic_dec_and_test(&tsk->signal->live); - if (group_dead) + if (group_dead) { + hrtimer_cancel(&tsk->signal->real_timer); + exit_itimers(tsk->signal); acct_process(code); + if (current->tux_info) { +#ifdef CONFIG_TUX_DEBUG + printk("Possibly unexpected TUX-thread exit(%ld) at %p?\n", + code, __builtin_return_address(0)); +#endif + current->tux_exit(); + } + } + if (unlikely(tsk->robust_list)) + exit_robust_list(tsk); +#if defined(CONFIG_FUTEX) && defined(CONFIG_COMPAT) + if (unlikely(tsk->compat_robust_list)) + compat_exit_robust_list(tsk); +#endif + if (unlikely(tsk->audit_context)) + audit_free(tsk); exit_mm(tsk); exit_sem(tsk); __exit_files(tsk); __exit_fs(tsk); exit_namespace(tsk); + exit_vx_info(tsk, code); + exit_nx_info(tsk); exit_thread(); cpuset_exit(tsk); exit_keys(tsk); @@ -840,18 +939,33 @@ fastcall NORET_TYPE void do_exit(long code) if (group_dead && tsk->signal->leader) disassociate_ctty(1); - module_put(tsk->thread_info->exec_domain->module); + module_put(task_thread_info(tsk)->exec_domain->module); if (tsk->binfmt) module_put(tsk->binfmt->module); tsk->exit_code = code; + proc_exit_connector(tsk); exit_notify(tsk); #ifdef CONFIG_NUMA mpol_free(tsk->mempolicy); tsk->mempolicy = NULL; #endif + /* + * If DEBUG_MUTEXES is on, make sure we are holding no locks: + */ + mutex_debug_check_no_locks_held(tsk); + + if (tsk->io_context) + exit_io_context(); + + if (tsk->splice_pipe) + __free_pipe_info(tsk->splice_pipe); + + /* PF_DEAD causes final put_task_struct after we schedule. */ + preempt_disable(); + BUG_ON(tsk->flags & PF_DEAD); + tsk->flags |= PF_DEAD; - BUG_ON(!(current->flags & PF_DEAD)); schedule(); BUG(); /* Avoid "noreturn function does return". */ @@ -875,13 +989,6 @@ asmlinkage long sys_exit(int error_code) do_exit((error_code&0xff)<<8); } -task_t fastcall *next_thread(const task_t *p) -{ - return pid_task(p->pids[PIDTYPE_TGID].pid_list.next, PIDTYPE_TGID); -} - -EXPORT_SYMBOL(next_thread); - /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). @@ -896,18 +1003,15 @@ do_group_exit(int exit_code) else if (!thread_group_empty(current)) { struct signal_struct *const sig = current->signal; struct sighand_struct *const sighand = current->sighand; - read_lock(&tasklist_lock); spin_lock_irq(&sighand->siglock); if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { - sig->flags = SIGNAL_GROUP_EXIT; sig->group_exit_code = exit_code; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); - read_unlock(&tasklist_lock); } do_exit(exit_code); @@ -1044,6 +1148,9 @@ static int wait_task_zombie(task_t *p, int noreap, } if (likely(p->real_parent == p->parent) && likely(p->signal)) { + struct signal_struct *psig; + struct signal_struct *sig; + /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group @@ -1060,24 +1167,26 @@ static int wait_task_zombie(task_t *p, int noreap, * here reaping other children at the same time. */ spin_lock_irq(&p->parent->sighand->siglock); - p->parent->signal->cutime = - cputime_add(p->parent->signal->cutime, + psig = p->parent->signal; + sig = p->signal; + psig->cutime = + cputime_add(psig->cutime, cputime_add(p->utime, - cputime_add(p->signal->utime, - p->signal->cutime))); - p->parent->signal->cstime = - cputime_add(p->parent->signal->cstime, + cputime_add(sig->utime, + sig->cutime))); + psig->cstime = + cputime_add(psig->cstime, cputime_add(p->stime, - cputime_add(p->signal->stime, - p->signal->cstime))); - p->parent->signal->cmin_flt += - p->min_flt + p->signal->min_flt + p->signal->cmin_flt; - p->parent->signal->cmaj_flt += - p->maj_flt + p->signal->maj_flt + p->signal->cmaj_flt; - p->parent->signal->cnvcsw += - p->nvcsw + p->signal->nvcsw + p->signal->cnvcsw; - p->parent->signal->cnivcsw += - p->nivcsw + p->signal->nivcsw + p->signal->cnivcsw; + cputime_add(sig->stime, + sig->cstime))); + psig->cmin_flt += + p->min_flt + sig->min_flt + sig->cmin_flt; + psig->cmaj_flt += + p->maj_flt + sig->maj_flt + sig->cmaj_flt; + psig->cnvcsw += + p->nvcsw + sig->nvcsw + sig->cnvcsw; + psig->cnivcsw += + p->nivcsw + sig->nivcsw + sig->cnivcsw; spin_unlock_irq(&p->parent->sighand->siglock); } @@ -1185,7 +1294,7 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap, exit_code = p->exit_code; if (unlikely(!exit_code) || - unlikely(p->state > TASK_STOPPED)) + unlikely(p->state & TASK_TRACED)) goto bail_ref; return wait_noreap_copyout(p, pid, uid, why, (exit_code << 8) | 0x7f, @@ -1232,7 +1341,7 @@ bail_ref: /* move to end of parent's list to avoid starvation */ remove_parent(p); - add_parent(p, p->parent); + add_parent(p); write_unlock_irq(&tasklist_lock); @@ -1361,6 +1470,15 @@ repeat: switch (p->state) { case TASK_TRACED: + /* + * When we hit the race with PTRACE_ATTACH, + * we will not report this child. But the + * race means it has not yet been moved to + * our ptrace_children list, so we need to + * set the flag here to avoid a spurious ECHILD + * when the race happens with the only child. + */ + flag = 1; if (!my_ptrace_child(p)) continue; /*FALLTHROUGH*/