NORET_TYPE void do_exit(long code) { struct task_struct *tsk = current; if (in_interrupt()) panic("Aiee, killing interrupt handler!"); if (!tsk->pid) panic("Attempted to kill the idle task!"); if (tsk->pid == 1) panic("Attempted to kill init!"); tsk->flags |= PF_EXITING; del_timer_sync(&tsk->real_timer); fake_volatile: #ifdef CONFIG_BSD_PROCESS_ACCT acct_process(code); #endif 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(); } __exit_mm(tsk); lock_kernel(); sem_exit(); __exit_files(tsk); __exit_fs(tsk); exit_namespace(tsk); exit_sighand(tsk); exit_thread(); if (current->leader) disassociate_ctty(1); put_exec_domain(tsk->exec_domain); if (tsk->binfmt && tsk->binfmt->module) __MOD_DEC_USE_COUNT(tsk->binfmt->module); tsk->exit_code = code; exit_notify(); schedule(); BUG(); /* * In order to get rid of the "volatile function does return" message * I did this little loop that confuses gcc to think do_exit really * is volatile. In fact it's schedule() that is volatile in some * circumstances: when current->state = ZOMBIE, schedule() never * returns. * * In fact the natural way to do all this is to have the label and the * goto right after each other, but I put the fake_volatile label at * the start of the function just in case something /really/ bad * happens, and the schedule returns. This way we can try again. I'm * not paranoid: it's just that everybody is out to get me. */ goto fake_volatile; }
NORET_TYPE void do_exit(long code) { struct task_struct *tsk = current; if (in_interrupt()) panic("Aiee, killing interrupt handler!"); if (!tsk->pid) panic("Attempted to kill the idle task!"); if (tsk->pid == 1) panic("Attempted to kill init!"); /* * 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); tsk->flags |= PF_EXITING; del_timer_sync(&tsk->real_timer); fake_volatile: #ifdef CONFIG_BSD_PROCESS_ACCT acct_process(code); #endif __exit_mm(tsk); lock_kernel(); sem_exit(); __exit_files(tsk); __exit_fs(tsk); exit_namespace(tsk); exit_sighand(tsk); exit_thread(); if (current->leader) disassociate_ctty(1); put_exec_domain(tsk->exec_domain); if (tsk->binfmt && tsk->binfmt->module) __MOD_DEC_USE_COUNT(tsk->binfmt->module); tsk->exit_code = code; exit_notify(); schedule(); BUG(); /* * In order to get rid of the "volatile function does return" message * I did this little loop that confuses gcc to think do_exit really * is volatile. In fact it's schedule() that is volatile in some * circumstances: when current->state = ZOMBIE, schedule() never * returns. * * In fact the natural way to do all this is to have the label and the * goto right after each other, but I put the fake_volatile label at * the start of the function just in case something /really/ bad * happens, and the schedule returns. This way we can try again. I'm * not paranoid: it's just that everybody is out to get me. */ goto fake_volatile; }
/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int *parent_tidptr, int *child_tidptr) { int retval; struct task_struct *p = NULL; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); if ((clone_flags & CLONE_DETACHED) && !(clone_flags & CLONE_THREAD)) return ERR_PTR(-EINVAL); if (!(clone_flags & CLONE_DETACHED) && (clone_flags & CLONE_THREAD)) return ERR_PTR(-EINVAL); retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out; p->tux_info = NULL; retval = -EAGAIN; /* * Increment user->__count before the rlimit test so that it would * be correct if we take the bad_fork_free failure path. */ atomic_inc(&p->user->__count); if (atomic_read(&p->user->processes) >= p->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE)) goto bad_fork_free; } atomic_inc(&p->user->processes); /* * Counter increases are protected by * the kernel lock so nr_threads can't * increase under us (but it may decrease). */ if (nr_threads >= max_threads) goto bad_fork_cleanup_count; get_exec_domain(p->exec_domain); if (p->binfmt && p->binfmt->module) __MOD_INC_USE_COUNT(p->binfmt->module); p->did_exec = 0; p->swappable = 0; p->state = TASK_UNINTERRUPTIBLE; copy_flags(clone_flags, p); if (clone_flags & CLONE_IDLETASK) p->pid = 0; else { p->pid = alloc_pidmap(); if (p->pid == -1) goto bad_fork_cleanup; } retval = -EFAULT; if (clone_flags & CLONE_PARENT_SETTID) if (put_user(p->pid, parent_tidptr)) goto bad_fork_cleanup; INIT_LIST_HEAD(&p->run_list); INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); init_waitqueue_head(&p->wait_chldexit); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); spin_lock_init(&p->switch_lock); p->sigpending = 0; init_sigpending(&p->pending); p->it_real_value = p->it_virt_value = p->it_prof_value = 0; p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0; init_timer(&p->real_timer); p->real_timer.data = (unsigned long) p; p->leader = 0; /* session leadership doesn't inherit */ p->tty_old_pgrp = 0; memset(&p->utime, 0, sizeof(p->utime)); memset(&p->stime, 0, sizeof(p->stime)); memset(&p->cutime, 0, sizeof(p->cutime)); memset(&p->cstime, 0, sizeof(p->cstime)); memset(&p->group_utime, 0, sizeof(p->group_utime)); memset(&p->group_stime, 0, sizeof(p->group_stime)); memset(&p->group_cutime, 0, sizeof(p->group_cutime)); memset(&p->group_cstime, 0, sizeof(p->group_cstime)); #ifdef CONFIG_SMP memset(&p->per_cpu_utime, 0, sizeof(p->per_cpu_utime)); memset(&p->per_cpu_stime, 0, sizeof(p->per_cpu_stime)); #endif memset(&p->timing_state, 0, sizeof(p->timing_state)); p->timing_state.type = PROCESS_TIMING_USER; p->last_sigxcpu = 0; p->array = NULL; p->lock_depth = -1; /* -1 = no lock */ p->start_time = jiffies; retval = -ENOMEM; /* copy all the process information */ if (copy_files(clone_flags, p)) goto bad_fork_cleanup; if (copy_fs(clone_flags, p)) goto bad_fork_cleanup_files; if (copy_sighand(clone_flags, p)) goto bad_fork_cleanup_fs; if (copy_signal(clone_flags, p)) goto bad_fork_cleanup_sighand; if (copy_mm(clone_flags, p)) goto bad_fork_cleanup_signal; if (copy_namespace(clone_flags, p)) goto bad_fork_cleanup_mm; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_namespace; p->semundo = NULL; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; /* Our parent execution domain becomes current domain These must match for thread signalling to apply */ p->parent_exec_id = p->self_exec_id; /* ok, now we should be set up.. */ p->swappable = 1; if (clone_flags & CLONE_DETACHED) p->exit_signal = -1; else p->exit_signal = clone_flags & CSIGNAL; p->pdeath_signal = 0; /* * Share the timeslice between parent and child, thus the * total amount of pending timeslices in the system doesnt change, * resulting in more scheduling fairness. */ local_irq_disable(); p->time_slice = (current->time_slice + 1) >> 1; p->first_time_slice = 1; /* * The remainder of the first timeslice might be recovered by * the parent if the child exits early enough. */ current->time_slice >>= 1; p->last_run = jiffies; if (!current->time_slice) { /* * This case is rare, it happens when the parent has only * a single jiffy left from its timeslice. Taking the * runqueue lock is not a problem. */ current->time_slice = 1; scheduler_tick(0 /* don't update the time stats */); } local_irq_enable(); if ((int)current->time_slice <= 0) BUG(); if ((int)p->time_slice <= 0) BUG(); /* * Ok, add it to the run-queues and make it * visible to the rest of the system. * * Let it rip! */ p->tgid = p->pid; p->group_leader = p; INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* * Check for pending SIGKILL! The new thread should not be allowed * to slip out of an OOM kill. (or normal SIGKILL.) */ if (sigismember(¤t->pending.signal, SIGKILL)) { write_unlock_irq(&tasklist_lock); retval = -EINTR; goto bad_fork_cleanup_namespace; } /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) p->real_parent = current->real_parent; else p->real_parent = current; p->parent = p->real_parent; if (clone_flags & CLONE_THREAD) { spin_lock(¤t->sighand->siglock); /* * Important: if an exit-all has been started then * do not create this new thread - the whole thread * group is supposed to exit anyway. */ if (current->signal->group_exit) { spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -EINTR; goto bad_fork_cleanup_namespace; } p->tgid = current->tgid; p->group_leader = current->group_leader; if (current->signal->group_stop_count > 0) { /* * There is an all-stop in progress for the group. * We ourselves will stop as soon as we check signals. * Make the new thread part of that group stop too. */ current->signal->group_stop_count++; p->sigpending = 1; } spin_unlock(¤t->sighand->siglock); } SET_LINKS(p); if (p->ptrace & PT_PTRACED) __ptrace_link(p, current->parent); attach_pid(p, PIDTYPE_PID, p->pid); if (thread_group_leader(p)) { attach_pid(p, PIDTYPE_TGID, p->tgid); attach_pid(p, PIDTYPE_PGID, p->pgrp); attach_pid(p, PIDTYPE_SID, p->session); } else { link_pid(p, p->pids + PIDTYPE_TGID, &p->group_leader->pids[PIDTYPE_TGID].pid); } /* clear controlling tty of new task if parent's was just cleared */ if (!current->tty && p->tty) p->tty = NULL; nr_threads++; write_unlock_irq(&tasklist_lock); retval = 0; fork_out: if (retval) return ERR_PTR(retval); return p; bad_fork_cleanup_namespace: exit_namespace(p); bad_fork_cleanup_mm: exit_mm(p); if (p->active_mm) mmdrop(p->active_mm); bad_fork_cleanup_signal: exit_signal(p); bad_fork_cleanup_sighand: exit_sighand(p); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup: if (p->pid > 0) free_pidmap(p->pid); put_exec_domain(p->exec_domain); if (p->binfmt && p->binfmt->module) __MOD_DEC_USE_COUNT(p->binfmt->module); bad_fork_cleanup_count: atomic_dec(&p->user->processes); bad_fork_free: p->state = TASK_ZOMBIE; /* debug */ atomic_dec(&p->usage); put_task_struct(p); goto fork_out; }