Re: [PATCH v1 10/13] xen/pvcalls: implement poll command

[Stefano Stabellini]

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:12, Stefano Stabellini wrote:
> > For active sockets, check the indexes and use the inflight_conn_req
> > waitqueue to wait.
> > 
> > For passive sockets, send PVCALLS_POLL to the backend. Use the
> > inflight_accept_req waitqueue if an accept is outstanding. Otherwise use
> > the inflight_req waitqueue: inflight_req is awaken when a new response
> > is received; on wakeup we check whether the POLL response is arrived by
> > looking at the PVCALLS_FLAG_POLL_RET flag. We set the flag from
> > pvcalls_front_event_handler, if the response was for a POLL command.
> > 
> > In pvcalls_front_event_handler, get the struct socket pointer from the
> > poll id (we previously converted struct socket* to uint64_t and used it
> > as id).
> > 
> > Signed-off-by: Stefano Stabellini <stefano@xxxxxxxxxxx>
> > CC: boris.ostrovsky@xxxxxxxxxx
> > CC: jgross@xxxxxxxx
> > ---
> >  drivers/xen/pvcalls-front.c | 123 ++++++++++++++++++++++++++++++++++++++++----
> >  drivers/xen/pvcalls-front.h |   3 ++
> >  2 files changed, 115 insertions(+), 11 deletions(-)
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index 3d1041a..b6cfb7d 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -128,17 +128,29 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
> >  		rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons);
> >  
> >  		req_id = rsp->req_id;
> > -		src = (uint8_t *)&bedata->rsp[req_id];
> > -		src += sizeof(rsp->req_id);
> > -		dst = (uint8_t *)rsp;
> > -		dst += sizeof(rsp->req_id);
> > -		memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id));
> > -		/*
> > -		 * First copy the rest of the data, then req_id. It is
> > -		 * paired with the barrier when accessing bedata->rsp.
> > -		 */
> > -		smp_wmb();
> > -		WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id);
> > +		if (rsp->cmd == PVCALLS_POLL) {
> > +			struct socket *sock = (struct socket *) rsp->u.poll.id;
> > +			struct sock_mapping *map =
> > +				(struct sock_mapping *)
> > +				READ_ONCE(sock->sk->sk_send_head);
> > +
> > +			set_bit(PVCALLS_FLAG_POLL_RET,
> > +				(void *)&map->passive.flags);
> 
> Add a barrier here to make sure PVCALLS_FLAG_POLL_INFLIGHT is cleared
> _after_ setting PVCALLS_FLAG_POLL_RET?

Yes, good point, I'll add an smp_wmb() here. A barrier is unnecessary at
the other end (the beginning of pvcalls_front_poll_passive) because of
the conditional instructions creating control dependencies. I'll add a
comment.


> > +			clear_bit(PVCALLS_FLAG_POLL_INFLIGHT,
> > +				  (void *)&map->passive.flags);
> > +		} else {
> > +			src = (uint8_t *)&bedata->rsp[req_id];
> > +			src += sizeof(rsp->req_id);
> > +			dst = (uint8_t *)rsp;
> > +			dst += sizeof(rsp->req_id);
> > +			memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id));
> > +			/*
> > +			 * First copy the rest of the data, then req_id. It is
> > +			 * paired with the barrier when accessing bedata->rsp.
> > +			 */
> > +			smp_wmb();
> > +			WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id);
> > +		}
> >  
> >  		bedata->ring.rsp_cons++;
> >  		wake_up(&bedata->inflight_req);
> > @@ -704,6 +716,95 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
> >  	return ret;
> >  }
> >  
> > +static unsigned int pvcalls_front_poll_passive(struct file *file,
> > +					       struct pvcalls_bedata *bedata,
> > +					       struct sock_mapping *map,
> > +					       poll_table *wait)
> > +{
> > +	int notify, req_id;
> > +	struct xen_pvcalls_request *req;
> > +
> > +	if (test_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
> > +		     (void *)&map->passive.flags)) {
> > +		poll_wait(file, &map->passive.inflight_accept_req, wait);
> > +		return 0;
> > +	}
> > +
> > +	if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET,
> > +			       (void *)&map->passive.flags))
> > +		return POLLIN;
> > +
> > +	if (test_and_set_bit(PVCALLS_FLAG_POLL_INFLIGHT,
> > +			     (void *)&map->passive.flags)) {
> > +		poll_wait(file, &bedata->inflight_req, wait);
> > +		return 0;
> > +	}
> > +
> > +	spin_lock(&bedata->pvcallss_lock);
> > +	req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
> > +	BUG_ON(req_id >= PVCALLS_NR_REQ_PER_RING);
> > +	if (RING_FULL(&bedata->ring) ||
> > +	    READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) {
> > +		spin_unlock(&bedata->pvcallss_lock);
> > +		return -EAGAIN;
> > +	}
> > +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> > +	req->req_id = req_id;
> > +	req->cmd = PVCALLS_POLL;
> > +	req->u.poll.id = (uint64_t) map->sock;
> > +
> > +	bedata->ring.req_prod_pvt++;
> > +	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
> > +	spin_unlock(&bedata->pvcallss_lock);
> > +	if (notify)
> > +		notify_remote_via_irq(bedata->irq);
> > +
> > +	poll_wait(file, &bedata->inflight_req, wait);
> > +	return 0;
> > +}
> > +
> > +static unsigned int pvcalls_front_poll_active(struct file *file,
> > +					      struct pvcalls_bedata *bedata,
> > +					      struct sock_mapping *map,
> > +					      poll_table *wait)
> > +{
> > +	unsigned int mask = 0;
> > +	int32_t in_error, out_error;
> > +	struct pvcalls_data_intf *intf = map->active.ring;
> > +
> > +	out_error = intf->out_error;
> > +	in_error = intf->in_error;
> > +
> > +	poll_wait(file, &map->active.inflight_conn_req, wait);
> > +	if (pvcalls_front_write_todo(map))
> > +		mask |= POLLOUT | POLLWRNORM;
> > +	if (pvcalls_front_read_todo(map))
> > +		mask |= POLLIN | POLLRDNORM;
> > +	if (in_error != 0 || out_error != 0)
> > +		mask |= POLLERR;
> > +
> > +	return mask;
> > +}
> > +
> > +unsigned int pvcalls_front_poll(struct file *file, struct socket *sock,
> > +			       poll_table *wait)
> > +{
> > +	struct pvcalls_bedata *bedata;
> > +	struct sock_mapping *map;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return POLLNVAL;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +
> > +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> > +	if (!map)
> > +		return POLLNVAL;
> > +	if (map->active_socket)
> > +		return pvcalls_front_poll_active(file, bedata, map, wait);
> > +	else
> > +		return pvcalls_front_poll_passive(file, bedata, map, wait);
> > +}
> > +
> >  static const struct xenbus_device_id pvcalls_front_ids[] = {
> >  	{ "pvcalls" },
> >  	{ "" }
> > diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> > index de24041..25e05b8 100644
> > --- a/drivers/xen/pvcalls-front.h
> > +++ b/drivers/xen/pvcalls-front.h
> > @@ -20,5 +20,8 @@ int pvcalls_front_recvmsg(struct socket *sock,
> >  			  struct msghdr *msg,
> >  			  size_t len,
> >  			  int flags);
> > +unsigned int pvcalls_front_poll(struct file *file,
> > +				struct socket *sock,
> > +				poll_table *wait);
> >  
> >  #endif
> > 
>