On 10/20, Andy Lutomirski wrote: > > > --- a/kernel/sched/core.c > > +++ b/kernel/sched/core.c > > @@ -3380,8 +3380,22 @@ static void __sched notrace __schedule(bool preempt) > > * If a worker went to sleep, notify and ask > > workqueue > > * whether it wants to wake up a task to maintain > > * concurrency. > > + * > > + * Also the following stack is possible: > > + * oops_end() > > + * do_exit() > > + * schedule() > > + * > > + * If panic_on_oops is not set and oops happens on > > + * a workqueue execution path, thread will be > > killed. > > + * That is definitly sad, but not to make the > > situation > > + * even worse we have to ignore dead tasks in order > > not > > + * to step on zeroed out members (e.g. > > t->vfork_done is > > + * already NULL on that path, since we were called > > by > > + * do_exit()))
And we have more problems like this. Say, if blk_flush_plug_list() crashes it will likely crash again and again recursively. > > */ > > - if (prev->flags & PF_WQ_WORKER) { > > + if (prev->flags & PF_WQ_WORKER && > > + prev->state != TASK_DEAD) { I don't think we should change __schedule()... Can't we simply clear PF_WQ_WORKER in complete_vfork_done() ? Or add the PF_EXITING checks into wq_worker_sleeping() and wq_worker_waking_up(). Or perhaps something like the change below. Oleg. --- x/kernel/workqueue.c +++ x/kernel/workqueue.c @@ -2157,6 +2157,14 @@ static void process_scheduled_works(stru } } +static void oops_handler(struct callback_head *oops_work) +{ + if (!(current->flags & PF_WQ_WORKER)) + return; + + clear PF_WQ_WORKER, probably do more cleanups +} + /** * worker_thread - the worker thread function * @__worker: self @@ -2171,11 +2179,14 @@ static void process_scheduled_works(stru */ static int worker_thread(void *__worker) { + struct callback_head oops_work; struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ worker->task->flags |= PF_WQ_WORKER; + init_task_work(&oops_work, oops_handler); + task_work_add(current, &oops_work, false); woke_up: spin_lock_irq(&pool->lock);