Re: [PATCH v1 11/13] xen/pvcalls: implement release command

[Stefano Stabellini]

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:12, Stefano Stabellini wrote:
> > Send PVCALLS_RELEASE to the backend and wait for a reply. Take both
> > in_mutex and out_mutex to avoid concurrent accesses. Then, free the
> > socket.
> > 
> > Signed-off-by: Stefano Stabellini <stefano@xxxxxxxxxxx>
> > CC: boris.ostrovsky@xxxxxxxxxx
> > CC: jgross@xxxxxxxx
> > ---
> >  drivers/xen/pvcalls-front.c | 86 +++++++++++++++++++++++++++++++++++++++++++++
> >  drivers/xen/pvcalls-front.h |  1 +
> >  2 files changed, 87 insertions(+)
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index b6cfb7d..bd3dfac 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -174,6 +174,24 @@ static irqreturn_t pvcalls_front_conn_handler(int irq, void *sock_map)
> >  	return IRQ_HANDLED;
> >  }
> >  
> > +static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
> > +				   struct sock_mapping *map)
> > +{
> > +	int i;
> > +
> > +	spin_lock(&bedata->pvcallss_lock);
> > +	if (!list_empty(&map->list))
> > +		list_del_init(&map->list);
> > +	spin_unlock(&bedata->pvcallss_lock);
> > +
> > +	/* what if the thread waiting still need access? */
> 
> Is this handled? If not, why is it no problem?

Yes, sorry. This is a left-over from earlier versions of the code.

This scenario is handled because threads waiting will have already been
awaken by the wake_up_interruptible call in pvcalls_front_release, and
also the code is protected by both the in_mutex and out_mutex. I hadn't
introduced in_mutex and out_mutex yet when I wrote this comment, it no
longer applies.



> > +	for (i = 0; i < (1 << map->active.ring->ring_order); i++)
> > +		gnttab_end_foreign_access(map->active.ring->ref[i], 0, 0);
> > +	gnttab_end_foreign_access(map->active.ref, 0, 0);
> > +	free_page((unsigned long)map->active.ring);
> > +	unbind_from_irqhandler(map->active.irq, map);
> > +}
> > +
> >  int pvcalls_front_socket(struct socket *sock)
> >  {
> >  	struct pvcalls_bedata *bedata;
> > @@ -805,6 +823,74 @@ unsigned int pvcalls_front_poll(struct file *file, struct socket *sock,
> >  		return pvcalls_front_poll_passive(file, bedata, map, wait);
> >  }
> >  
> > +int pvcalls_front_release(struct socket *sock)
> > +{
> > +	struct pvcalls_bedata *bedata;
> > +	struct sock_mapping *map;
> > +	int req_id, notify;
> > +	struct xen_pvcalls_request *req;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return -EIO;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +	if (!bedata)
> > +		return -EIO;
> > +
> > +	if (sock->sk == NULL)
> > +		return 0;
> > +
> > +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> > +	if (map == NULL)
> > +		return 0;
> > +	WRITE_ONCE(sock->sk->sk_send_head, NULL);
> > +
> > +	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;
> 
> Isn't it a problem you already cleared sock->sk->sk_send_head?

Yes, you are right. It would effectively leak the socket. I'll move the
clearing of sk_send_head after this check.



> > +	}
> > +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> > +	req->req_id = req_id;
> > +	req->cmd = PVCALLS_RELEASE;
> > +	req->u.release.id = (uint64_t)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);
> > +
> > +	wait_event(bedata->inflight_req,
> > +		READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
> > +
> > +	if (map->active_socket) {
> > +		/* 
> > +		 * Set in_error and wake up inflight_conn_req to force
> > +		 * recvmsg waiters to exit.
> > +		 */
> > +		map->active.ring->in_error = -EBADF;
> > +		wake_up_interruptible(&map->active.inflight_conn_req);
> > +
> > +		mutex_lock(&map->active.in_mutex);
> > +		mutex_lock(&map->active.out_mutex);
> > +		pvcalls_front_free_map(bedata, map);
> > +		mutex_unlock(&map->active.out_mutex);
> > +		mutex_unlock(&map->active.in_mutex);
> > +		kfree(map);
> > +	} else {
> > +		spin_lock(&bedata->pvcallss_lock);
> > +		list_del_init(&map->list);
> > +		kfree(map);
> > +		spin_unlock(&bedata->pvcallss_lock);
> > +	}
> > +	WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);
> > +
> > +	return 0;
> > +}
> > +
> >  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 25e05b8..3332978 100644
> > --- a/drivers/xen/pvcalls-front.h
> > +++ b/drivers/xen/pvcalls-front.h
> > @@ -23,5 +23,6 @@ int pvcalls_front_recvmsg(struct socket *sock,
> >  unsigned int pvcalls_front_poll(struct file *file,
> >  				struct socket *sock,
> >  				poll_table *wait);
> > +int pvcalls_front_release(struct socket *sock);
> >  
> >  #endif