Re: [PATCH v4 08/13] xen/pvcalls: implement accept command

[Boris Ostrovsky]

> +int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
> +{
> +	struct pvcalls_bedata *bedata;
> +	struct sock_mapping *map;
> +	struct sock_mapping *map2 = NULL;
> +	struct xen_pvcalls_request *req;
> +	int notify, req_id, ret, evtchn, nonblock;
> +
> +	pvcalls_enter;
> +	if (!pvcalls_front_dev) {
> +		pvcalls_exit;
> +		return -ENOTCONN;
> +	}
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = (struct sock_mapping *) sock->sk->sk_send_head;
> +	if (!map) {
> +		pvcalls_exit;
> +		return -ENOTSOCK;
> +	}
> +
> +	if (map->passive.status != PVCALLS_STATUS_LISTEN) {
> +		pvcalls_exit;
> +		return -EINVAL;
> +	}
> +
> +	nonblock = flags & SOCK_NONBLOCK;
> +	/*
> +	 * Backend only supports 1 inflight accept request, will return
> +	 * errors for the others
> +	 */
> +	if (test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
> +			     (void *)&map->passive.flags)) {
> +		req_id = READ_ONCE(map->passive.inflight_req_id);
> +		if (req_id != PVCALLS_INVALID_ID &&
> +		    READ_ONCE(bedata->rsp[req_id].req_id) == req_id) {
> +			map2 = map->passive.accept_map;
> +			goto received;
> +		}
> +		if (nonblock) {
> +			pvcalls_exit;
> +			return -EAGAIN;
> +		}
> +		if (wait_event_interruptible(map->passive.inflight_accept_req,
> +			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
> +					  (void *)&map->passive.flags))) {
> +			pvcalls_exit;
> +			return -EINTR;
> +		}
> +	}
> +
> +	spin_lock(&bedata->socket_lock);
> +	ret = get_request(bedata, &req_id);
> +	if (ret < 0) {
> +		spin_unlock(&bedata->socket_lock);
> +		pvcalls_exit;
> +		return ret;
> +	}
> +	map2 = kzalloc(sizeof(*map2), GFP_KERNEL);
> +	if (map2 == NULL) {
> +		spin_unlock(&bedata->socket_lock);
> +		pvcalls_exit;
> +		return -ENOMEM;
> +	}
> +	ret =  create_active(map2, &evtchn);
> +	if (ret < 0) {
> +		kfree(map2);
> +		spin_unlock(&bedata->socket_lock);
> +		pvcalls_exit;
> +		return -ENOMEM;
> +	}

Do you need to clear PVCALLS_FLAG_ACCEPT_INFLIGHT bit on errors (except 
for EAGAIN/EINTR)?

> +	list_add_tail(&map2->list, &bedata->socket_mappings);
> +
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	req->cmd = PVCALLS_ACCEPT;
> +	req->u.accept.id = (uint64_t) map;
> +	req->u.accept.ref = map2->active.ref;
> +	req->u.accept.id_new = (uint64_t) map2;
> +	req->u.accept.evtchn = evtchn;
> +	map->passive.accept_map = map2;
> +
> +	bedata->ring.req_prod_pvt++;
> +	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
> +	spin_unlock(&bedata->socket_lock);
> +	if (notify)
> +		notify_remote_via_irq(bedata->irq);
> +	/* We could check if we have received a response before returning. */
> +	if (nonblock) {
> +		WRITE_ONCE(map->passive.inflight_req_id, req_id);
> +		pvcalls_exit;
> +		return -EAGAIN;
> +	}
> +
> +	if (wait_event_interruptible(bedata->inflight_req,
> +		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
> +		pvcalls_exit;
> +		return -EINTR;
> +	}
> +
> +received:
> +	map2->sock = newsock;
> +	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
> +	if (!newsock->sk) {
> +		WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);
> +		WRITE_ONCE(map->passive.inflight_req_id, PVCALLS_INVALID_ID);
> +		pvcalls_front_free_map(bedata, map2);
> +		kfree(map2);
> +		pvcalls_exit;
> +		return -ENOMEM;
> +	}
> +	newsock->sk->sk_send_head = (void *)map2;
> +
> +	clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags);
> +	wake_up(&map->passive.inflight_accept_req);
> +
> +	ret = bedata->rsp[req_id].ret;
> +	/* read ret, then set this rsp slot to be reused */
> +	smp_mb();
> +	WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);
> +	WRITE_ONCE(map->passive.inflight_req_id, PVCALLS_INVALID_ID);

Should inflight_req_id be cleared at the same time as 
PVCALLS_FLAG_ACCEPT_INFLIGHT? They kind of belong together, don't they?

And I wonder whether you actually need the flag --- can you just key off 
map->passive.inflight_req_id not being PVCALLS_INVALID_ID?

(and again, I am not sure about all READ/WRITE_ONCE() macros here).


-boris