diff mbox

[v3,12/13] xen/pvcalls: implement release command

Message ID 1501541855-7354-12-git-send-email-sstabellini@kernel.org (mailing list archive)
State New, archived
Headers show

Commit Message

Stefano Stabellini July 31, 2017, 10:57 p.m. UTC
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.

For passive sockets, check whether we have already pre-allocated an
active socket for the purpose of being accepted. If so, free that as
well.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 88 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/pvcalls-front.h |  1 +
 2 files changed, 89 insertions(+)

Comments

Boris Ostrovsky Aug. 15, 2017, 8:44 p.m. UTC | #1
On 07/31/2017 06:57 PM, 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.
>
> For passive sockets, check whether we have already pre-allocated an
> active socket for the purpose of being accepted. If so, free that as
> well.
>
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-front.c | 88 +++++++++++++++++++++++++++++++++++++++++++++
>  drivers/xen/pvcalls-front.h |  1 +
>  2 files changed, 89 insertions(+)
>
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index 1c975d6..775a6d2 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -192,6 +192,23 @@ 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);
> +
> +	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);

Would it better to first unbind the handler? Any chance an interrupt
might come in?

> +}
> +
>  int pvcalls_front_socket(struct socket *sock)
>  {
>  	struct pvcalls_bedata *bedata;
> @@ -853,6 +870,77 @@ 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, ret;
> +	struct xen_pvcalls_request *req;
> +
> +	if (!pvcalls_front_dev)
> +		return -EIO;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	if (sock->sk == NULL)
> +		return 0;

This can go above bedata access.

(You are going to address locking here so I won't review the rest)

-boris

> +
> +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> +	if (map == NULL)
> +		return 0;
> +
> +	spin_lock(&bedata->pvcallss_lock);
> +	ret = get_request(bedata, &req_id);
> +	if (ret < 0) {
> +		spin_unlock(&bedata->pvcallss_lock);
> +		return ret;
> +	}
> +	WRITE_ONCE(sock->sk->sk_send_head, NULL);
> +
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	req->cmd = PVCALLS_RELEASE;
> +	req->u.release.id = (uint64_t)map;
> +
> +	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);
> +		if (READ_ONCE(map->passive.inflight_req_id) !=
> +		    PVCALLS_INVALID_ID) {
> +			pvcalls_front_free_map(bedata,
> +					       map->passive.accept_map);
> +			kfree(map->passive.accept_map);
> +		}
> +		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
Stefano Stabellini Sept. 8, 2017, 11:09 p.m. UTC | #2
On Tue, 15 Aug 2017, Boris Ostrovsky wrote:
> On 07/31/2017 06:57 PM, 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.
> >
> > For passive sockets, check whether we have already pre-allocated an
> > active socket for the purpose of being accepted. If so, free that as
> > well.
> >
> > Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  drivers/xen/pvcalls-front.c | 88 +++++++++++++++++++++++++++++++++++++++++++++
> >  drivers/xen/pvcalls-front.h |  1 +
> >  2 files changed, 89 insertions(+)
> >
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index 1c975d6..775a6d2 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -192,6 +192,23 @@ 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);
> > +
> > +	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);
> 
> Would it better to first unbind the handler? Any chance an interrupt
> might come in?

Fair enough, I'll do that.


> > +}
> > +
> >  int pvcalls_front_socket(struct socket *sock)
> >  {
> >  	struct pvcalls_bedata *bedata;
> > @@ -853,6 +870,77 @@ 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, ret;
> > +	struct xen_pvcalls_request *req;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return -EIO;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +
> > +	if (sock->sk == NULL)
> > +		return 0;
> 
> This can go above bedata access.

Yes, good idea.


> (You are going to address locking here so I won't review the rest)

Yes, I will. Thanks for the review! And sorry for taking so long to
come back to you.
diff mbox

Patch

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index 1c975d6..775a6d2 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -192,6 +192,23 @@  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);
+
+	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;
@@ -853,6 +870,77 @@  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, ret;
+	struct xen_pvcalls_request *req;
+
+	if (!pvcalls_front_dev)
+		return -EIO;
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	if (sock->sk == NULL)
+		return 0;
+
+	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
+	if (map == NULL)
+		return 0;
+
+	spin_lock(&bedata->pvcallss_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->pvcallss_lock);
+		return ret;
+	}
+	WRITE_ONCE(sock->sk->sk_send_head, NULL);
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_RELEASE;
+	req->u.release.id = (uint64_t)map;
+
+	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);
+		if (READ_ONCE(map->passive.inflight_req_id) !=
+		    PVCALLS_INVALID_ID) {
+			pvcalls_front_free_map(bedata,
+					       map->passive.accept_map);
+			kfree(map->passive.accept_map);
+		}
+		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