Re: [PATCH 3/4] aio: implement IOCB_CMD_POLL

[Al Viro]

On Mon, Jul 30, 2018 at 09:15:43AM +0200, Christoph Hellwig wrote:

> +static void aio_poll_complete_work(struct work_struct *work)
> +{
> +	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
> +	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
> +	struct poll_table_struct pt = { ._key = req->events };
> +	struct kioctx *ctx = iocb->ki_ctx;
> +	__poll_t mask;
> +
> +	if (READ_ONCE(req->cancelled)) {
....
> +	}
> +
> +	mask = vfs_poll(req->file, &pt) & req->events;
> +	if (!mask) {
> +		add_wait_queue(req->head, &req->wait);
> +		return;
> +	}
....
> +}

> +/* assumes we are called with irqs disabled */
> +static int aio_poll_cancel(struct kiocb *iocb)
> +{
> +	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
> +	struct poll_iocb *req = &aiocb->poll;
> +
> +	spin_lock(&req->head->lock);
> +	if (!list_empty(&req->wait.entry)) {
> +		WRITE_ONCE(req->cancelled, true);
> +		list_del_init(&req->wait.entry);
> +		schedule_work(&aiocb->poll.work);
> +	}
> +	spin_unlock(&req->head->lock);
> +
> +	return 0;
> +}

> +static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
> +		void *key)
> +{
> +	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
> +	__poll_t mask = key_to_poll(key);
> +
> +	/* for instances that support it check for an event match first: */
> +	if (mask && !(mask & req->events))
> +		return 0;
> +
> +	list_del_init(&req->wait.entry);
> +	schedule_work(&req->work);
> +	return 1;
> +}

> +static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
> +{
> +	struct kioctx *ctx = aiocb->ki_ctx;
> +	struct poll_iocb *req = &aiocb->poll;
> +	struct aio_poll_table apt;
> +	__poll_t mask;

> +	mask = vfs_poll(req->file, &apt.pt) & req->events;
> +	if (mask || apt.error) {

> +	} else {
> +		spin_lock_irq(&ctx->ctx_lock);
> +		if (!req->done) {
> +			list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
> +			aiocb->ki_cancel = aio_poll_cancel;
> +		}
> +		spin_unlock_irq(&ctx->ctx_lock);
> +	}

So what happens if
	* we call aio_poll(), add the sucker to queue and see that we need
to wait
	* add to ->active_refs just as the wakeup comes
	* wakeup removes from queue and hits schedule_work()
	* io_cancel() is called, triggering aio_poll_cancel(), which sees that
we are not from queue and buggers off.  We are gone from ->active_refs.
	* aio_poll_complete_work() is called, sees no ->cancelled
	* aio_poll_complete_work() calls vfs_poll(), sees nothing interesting
and puts us back on the queue.

Unless I'm misreading it, cancel will end up with iocb still around and now
impossible to cancel...  What am I missing?