Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1694071 > unrolled thread

[PATCH v1 00/13] introduce the Xen PV Calls frontend

Back to article view | Back to linux.kernel

Contents

  [PATCH v1 00/13] introduce the Xen PV Calls frontend Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
    [PATCH v1 12/13] xen/pvcalls: implement frontend disconnect Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
      Re: [PATCH v1 12/13] xen/pvcalls: implement frontend disconnect Juergen Gross <jgross@suse.com> - 2017-07-24 22:20 +0200
    [PATCH v1 11/13] xen/pvcalls: implement release command Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
      Re: [PATCH v1 11/13] xen/pvcalls: implement release command Juergen Gross <jgross@suse.com> - 2017-07-24 22:20 +0200
        Re: [PATCH v1 11/13] xen/pvcalls: implement release command Stefano Stabellini <sstabellini@kernel.org> - 2017-07-25 23:10 +0200
    [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus frontend Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
      [PATCH v1 09/13] xen/pvcalls: implement recvmsg Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
        Re: [PATCH v1 09/13] xen/pvcalls: implement recvmsg Juergen Gross <jgross@suse.com> - 2017-07-24 22:00 +0200
          Re: [PATCH v1 09/13] xen/pvcalls: implement recvmsg Stefano Stabellini <sstabellini@kernel.org> - 2017-07-25 00:40 +0200
      [PATCH v1 07/13] xen/pvcalls: implement accept command Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
        Re: [PATCH v1 07/13] xen/pvcalls: implement accept command Juergen Gross <jgross@suse.com> - 2017-07-24 21:50 +0200
          Re: [PATCH v1 07/13] xen/pvcalls: implement accept command Stefano Stabellini <sstabellini@kernel.org> - 2017-07-25 01:00 +0200
      [PATCH v1 08/13] xen/pvcalls: implement sendmsg Stefano Stabellini <sstabellini@kernel.org> - 2017-07-22 02:20 +0200
        Re: [PATCH v1 08/13] xen/pvcalls: implement sendmsg Juergen Gross <jgross@suse.com> - 2017-07-24 22:00 +0200
          Re: [PATCH v1 08/13] xen/pvcalls: implement sendmsg Stefano Stabellini <sstabellini@kernel.org> - 2017-07-25 00:40 +0200
      Re: [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus  frontend Juergen Gross <jgross@suse.com> - 2017-07-24 21:10 +0200
        Re: [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus  frontend Stefano Stabellini <sstabellini@kernel.org> - 2017-07-25 00:40 +0200

#1694071 — [PATCH v1 00/13] introduce the Xen PV Calls frontend

Hi all,

this series introduces the frontend for the newly introduced PV Calls
procotol.

PV Calls is a paravirtualized protocol that allows the implementation of
a set of POSIX functions in a different domain. The PV Calls frontend
sends POSIX function calls to the backend, which implements them and
returns a value to the frontend and acts on the function call.

For more information about PV Calls, please read:

https://xenbits.xen.org/docs/unstable/misc/pvcalls.html

This patch series only implements the frontend driver. It doesn't
attempt to redirect POSIX calls to it. The functions exported in
pvcalls-front.h are meant to be used for that. A separate patch series
will be sent to use them and hook them into the system.


Stefano Stabellini (13):
      xen/pvcalls: introduce the pvcalls xenbus frontend
      xen/pvcalls: connect to the backend
      xen/pvcalls: implement socket command and handle events
      xen/pvcalls: implement connect command
      xen/pvcalls: implement bind command
      xen/pvcalls: implement listen command
      xen/pvcalls: implement accept command
      xen/pvcalls: implement sendmsg
      xen/pvcalls: implement recvmsg
      xen/pvcalls: implement poll command
      xen/pvcalls: implement release command
      xen/pvcalls: implement frontend disconnect
      xen: introduce a Kconfig option to enable the pvcalls frontend

 drivers/xen/Kconfig         |    9 +
 drivers/xen/Makefile        |    1 +
 drivers/xen/pvcalls-front.c | 1097 +++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/pvcalls-front.h |   28 ++
 4 files changed, 1135 insertions(+)
 create mode 100644 drivers/xen/pvcalls-front.c
 create mode 100644 drivers/xen/pvcalls-front.h

[toc] | [next] | [standalone]

#1694072 — [PATCH v1 12/13] xen/pvcalls: implement frontend disconnect

Implement pvcalls frontend removal function. Go through the list of
active and passive sockets and free them all, one at a time.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index bd3dfac..fcc15fb 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -898,6 +898,34 @@ int pvcalls_front_release(struct socket *sock)
 
 static int pvcalls_front_remove(struct xenbus_device *dev)
 {
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map = NULL, *n;
+
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
+		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);
+	}
+	list_for_each_entry_safe(map, n, &bedata->socketpass_mappings, list) {
+		spin_lock(&bedata->pvcallss_lock);
+		list_del_init(&map->list);
+		spin_unlock(&bedata->pvcallss_lock);
+		kfree(map);
+	}
+	if (bedata->irq > 0)
+		unbind_from_irqhandler(bedata->irq, dev);
+	if (bedata->ref >= 0)
+		gnttab_end_foreign_access(bedata->ref, 0, 0);
+	kfree(bedata->ring.sring);
+	kfree(bedata);
+	dev_set_drvdata(&dev->dev, NULL);
+	xenbus_switch_state(dev, XenbusStateClosed);
+	pvcalls_front_dev = NULL;
 	return 0;
 }
 
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1695067 — Re: [PATCH v1 12/13] xen/pvcalls: implement frontend disconnect

On 22/07/17 02:12, Stefano Stabellini wrote:
> Implement pvcalls frontend removal function. Go through the list of
> active and passive sockets and free them all, one at a time.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com

Reviewed-by: Juergen Gross <jgross@suse.com>


Juergen

[toc] | [prev] | [next] | [standalone]

#1694073 — [PATCH v1 11/13] xen/pvcalls: implement release command

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@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 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? */
+	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;
+	}
+	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
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1695068 — Re: [PATCH v1 11/13] xen/pvcalls: implement release command

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@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  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?

> +	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?


Juergen

> +	}
> +	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
> 

[toc] | [prev] | [next] | [standalone]

#1696483 — Re: [PATCH v1 11/13] xen/pvcalls: implement release command

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@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  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

[toc] | [prev] | [next] | [standalone]

#1694074 — [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus frontend

Introduce a xenbus frontend for the pvcalls protocol, as defined by
https://xenbits.xen.org/docs/unstable/misc/pvcalls.html.

This patch only adds the stubs, the code will be added by the following
patches.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 68 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100644 drivers/xen/pvcalls-front.c

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
new file mode 100644
index 0000000..173e204
--- /dev/null
+++ b/drivers/xen/pvcalls-front.c
@@ -0,0 +1,68 @@
+/*
+ * (c) 2017 Stefano Stabellini <stefano@aporeto.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pvcalls.h>
+
+static const struct xenbus_device_id pvcalls_front_ids[] = {
+	{ "pvcalls" },
+	{ "" }
+};
+
+static int pvcalls_front_remove(struct xenbus_device *dev)
+{
+	return 0;
+}
+
+static int pvcalls_front_probe(struct xenbus_device *dev,
+			  const struct xenbus_device_id *id)
+{
+	return 0;
+}
+
+static int pvcalls_front_resume(struct xenbus_device *dev)
+{
+	dev_warn(&dev->dev, "suspsend/resume unsupported\n");
+	return 0;
+}
+
+static void pvcalls_front_changed(struct xenbus_device *dev,
+			    enum xenbus_state backend_state)
+{
+}
+
+static struct xenbus_driver pvcalls_front_driver = {
+	.ids = pvcalls_front_ids,
+	.probe = pvcalls_front_probe,
+	.remove = pvcalls_front_remove,
+	.resume = pvcalls_front_resume,
+	.otherend_changed = pvcalls_front_changed,
+};
+
+static int __init pvcalls_frontend_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	pr_info("Initialising Xen pvcalls frontend driver\n");
+
+	return xenbus_register_frontend(&pvcalls_front_driver);
+}
+
+module_init(pvcalls_frontend_init);
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1694075 — [PATCH v1 09/13] xen/pvcalls: implement recvmsg

Implement recvmsg by copying data from the "in" ring. If not enough data
is available and the recvmsg call is blocking, then wait on the
inflight_conn_req waitqueue. Take the active socket in_mutex so that
only one function can access the ring at any given time.

If not enough data is available on the ring, rather than returning
immediately or sleep-waiting, spin for up to 5000 cycles. This small
optimization turns out to improve performance and latency significantly.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 106 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/pvcalls-front.h |   4 ++
 2 files changed, 110 insertions(+)

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index bf29f40..3d1041a 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -94,6 +94,20 @@ static int pvcalls_front_write_todo(struct sock_mapping *map)
 	return size - pvcalls_queued(prod, cons, size);
 }
 
+static int pvcalls_front_read_todo(struct sock_mapping *map)
+{
+	struct pvcalls_data_intf *intf = map->active.ring;
+	RING_IDX cons, prod;
+	int32_t error;
+
+	cons = intf->in_cons;
+	prod = intf->in_prod;
+	error = intf->in_error;
+	return (error != 0 ||
+		pvcalls_queued(prod, cons,
+			       XEN_FLEX_RING_SIZE(intf->ring_order))) != 0;
+}
+
 static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 {
 	struct xenbus_device *dev = dev_id;
@@ -413,6 +427,98 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
 	return tot_sent;
 }
 
+static int __read_ring(struct pvcalls_data_intf *intf,
+		       struct pvcalls_data *data,
+		       struct iov_iter *msg_iter,
+		       size_t len, int flags)
+{
+	RING_IDX cons, prod, size, masked_prod, masked_cons;
+	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
+	int32_t error;
+
+	cons = intf->in_cons;
+	prod = intf->in_prod;
+	error = intf->in_error;
+	/* get pointers before reading from the ring */
+	virt_rmb();
+	if (error < 0)
+		return error;
+
+	size = pvcalls_queued(prod, cons, array_size);
+	masked_prod = pvcalls_mask(prod, array_size);
+	masked_cons = pvcalls_mask(cons, array_size);
+
+	if (size == 0)
+		return 0;
+
+	if (len > size)
+		len = size;
+
+	if (masked_prod > masked_cons) {
+		copy_to_iter(data->in + masked_cons, len, msg_iter);
+	} else {
+		if (len > (array_size - masked_cons)) {
+			copy_to_iter(data->in + masked_cons,
+				     array_size - masked_cons, msg_iter);
+			copy_to_iter(data->in,
+				     len - (array_size - masked_cons),
+				     msg_iter);
+		} else {
+			copy_to_iter(data->in + masked_cons, len, msg_iter);
+		}
+	}
+	/* read data from the ring before increasing the index */
+	virt_mb();
+	if (!(flags & MSG_PEEK))
+		intf->in_cons += len;
+
+	return len;
+}
+
+int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		     int flags)
+{
+	struct pvcalls_bedata *bedata;
+	int ret = -EAGAIN;
+	struct sock_mapping *map;
+	int count = 0;
+
+	if (!pvcalls_front_dev)
+		return -ENOTCONN;
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
+	if (!map)
+		return -ENOTSOCK;
+
+	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&map->active.in_mutex);
+	if (len > XEN_FLEX_RING_SIZE(map->active.ring->ring_order))
+		len = XEN_FLEX_RING_SIZE(map->active.ring->ring_order);
+
+	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
+		if (count < PVCALLS_FRON_MAX_SPIN)
+			count++;
+		else
+			wait_event_interruptible(map->active.inflight_conn_req,
+						 pvcalls_front_read_todo(map));
+	}
+	ret = __read_ring(map->active.ring, &map->active.data,
+			  &msg->msg_iter, len, flags);
+
+	if (ret > 0)
+		notify_remote_via_irq(map->active.irq);
+	if (ret == 0)
+		ret = -EAGAIN;
+	if (ret == -ENOTCONN)
+		ret = 0;
+
+	mutex_unlock(&map->active.in_mutex);
+	return ret;
+}
+
 int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
 	struct pvcalls_bedata *bedata;
diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
index d937c24..de24041 100644
--- a/drivers/xen/pvcalls-front.h
+++ b/drivers/xen/pvcalls-front.h
@@ -16,5 +16,9 @@ int pvcalls_front_accept(struct socket *sock,
 int pvcalls_front_sendmsg(struct socket *sock,
 			  struct msghdr *msg,
 			  size_t len);
+int pvcalls_front_recvmsg(struct socket *sock,
+			  struct msghdr *msg,
+			  size_t len,
+			  int flags);
 
 #endif
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1695048 — Re: [PATCH v1 09/13] xen/pvcalls: implement recvmsg

On 22/07/17 02:11, Stefano Stabellini wrote:
> Implement recvmsg by copying data from the "in" ring. If not enough data
> is available and the recvmsg call is blocking, then wait on the
> inflight_conn_req waitqueue. Take the active socket in_mutex so that
> only one function can access the ring at any given time.
> 
> If not enough data is available on the ring, rather than returning
> immediately or sleep-waiting, spin for up to 5000 cycles. This small
> optimization turns out to improve performance and latency significantly.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-front.c | 106 ++++++++++++++++++++++++++++++++++++++++++++
>  drivers/xen/pvcalls-front.h |   4 ++
>  2 files changed, 110 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index bf29f40..3d1041a 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -94,6 +94,20 @@ static int pvcalls_front_write_todo(struct sock_mapping *map)
>  	return size - pvcalls_queued(prod, cons, size);
>  }
>  
> +static int pvcalls_front_read_todo(struct sock_mapping *map)

Return type bool?


Juergen

> +{
> +	struct pvcalls_data_intf *intf = map->active.ring;
> +	RING_IDX cons, prod;
> +	int32_t error;
> +
> +	cons = intf->in_cons;
> +	prod = intf->in_prod;
> +	error = intf->in_error;
> +	return (error != 0 ||
> +		pvcalls_queued(prod, cons,
> +			       XEN_FLEX_RING_SIZE(intf->ring_order))) != 0;
> +}
> +
>  static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>  {
>  	struct xenbus_device *dev = dev_id;
> @@ -413,6 +427,98 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
>  	return tot_sent;
>  }
>  
> +static int __read_ring(struct pvcalls_data_intf *intf,
> +		       struct pvcalls_data *data,
> +		       struct iov_iter *msg_iter,
> +		       size_t len, int flags)
> +{
> +	RING_IDX cons, prod, size, masked_prod, masked_cons;
> +	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
> +	int32_t error;
> +
> +	cons = intf->in_cons;
> +	prod = intf->in_prod;
> +	error = intf->in_error;
> +	/* get pointers before reading from the ring */
> +	virt_rmb();
> +	if (error < 0)
> +		return error;
> +
> +	size = pvcalls_queued(prod, cons, array_size);
> +	masked_prod = pvcalls_mask(prod, array_size);
> +	masked_cons = pvcalls_mask(cons, array_size);
> +
> +	if (size == 0)
> +		return 0;
> +
> +	if (len > size)
> +		len = size;
> +
> +	if (masked_prod > masked_cons) {
> +		copy_to_iter(data->in + masked_cons, len, msg_iter);
> +	} else {
> +		if (len > (array_size - masked_cons)) {
> +			copy_to_iter(data->in + masked_cons,
> +				     array_size - masked_cons, msg_iter);
> +			copy_to_iter(data->in,
> +				     len - (array_size - masked_cons),
> +				     msg_iter);
> +		} else {
> +			copy_to_iter(data->in + masked_cons, len, msg_iter);
> +		}
> +	}
> +	/* read data from the ring before increasing the index */
> +	virt_mb();
> +	if (!(flags & MSG_PEEK))
> +		intf->in_cons += len;
> +
> +	return len;
> +}
> +
> +int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
> +		     int flags)
> +{
> +	struct pvcalls_bedata *bedata;
> +	int ret = -EAGAIN;
> +	struct sock_mapping *map;
> +	int count = 0;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENOTCONN;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> +	if (!map)
> +		return -ENOTSOCK;
> +
> +	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
> +		return -EOPNOTSUPP;
> +
> +	mutex_lock(&map->active.in_mutex);
> +	if (len > XEN_FLEX_RING_SIZE(map->active.ring->ring_order))
> +		len = XEN_FLEX_RING_SIZE(map->active.ring->ring_order);
> +
> +	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
> +		if (count < PVCALLS_FRON_MAX_SPIN)
> +			count++;
> +		else
> +			wait_event_interruptible(map->active.inflight_conn_req,
> +						 pvcalls_front_read_todo(map));
> +	}
> +	ret = __read_ring(map->active.ring, &map->active.data,
> +			  &msg->msg_iter, len, flags);
> +
> +	if (ret > 0)
> +		notify_remote_via_irq(map->active.irq);
> +	if (ret == 0)
> +		ret = -EAGAIN;
> +	if (ret == -ENOTCONN)
> +		ret = 0;
> +
> +	mutex_unlock(&map->active.in_mutex);
> +	return ret;
> +}
> +
>  int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
>  {
>  	struct pvcalls_bedata *bedata;
> diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> index d937c24..de24041 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -16,5 +16,9 @@ int pvcalls_front_accept(struct socket *sock,
>  int pvcalls_front_sendmsg(struct socket *sock,
>  			  struct msghdr *msg,
>  			  size_t len);
> +int pvcalls_front_recvmsg(struct socket *sock,
> +			  struct msghdr *msg,
> +			  size_t len,
> +			  int flags);
>  
>  #endif
> 

[toc] | [prev] | [next] | [standalone]

#1695214 — Re: [PATCH v1 09/13] xen/pvcalls: implement recvmsg

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:11, Stefano Stabellini wrote:
> > Implement recvmsg by copying data from the "in" ring. If not enough data
> > is available and the recvmsg call is blocking, then wait on the
> > inflight_conn_req waitqueue. Take the active socket in_mutex so that
> > only one function can access the ring at any given time.
> > 
> > If not enough data is available on the ring, rather than returning
> > immediately or sleep-waiting, spin for up to 5000 cycles. This small
> > optimization turns out to improve performance and latency significantly.
> > 
> > Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  drivers/xen/pvcalls-front.c | 106 ++++++++++++++++++++++++++++++++++++++++++++
> >  drivers/xen/pvcalls-front.h |   4 ++
> >  2 files changed, 110 insertions(+)
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index bf29f40..3d1041a 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -94,6 +94,20 @@ static int pvcalls_front_write_todo(struct sock_mapping *map)
> >  	return size - pvcalls_queued(prod, cons, size);
> >  }
> >  
> > +static int pvcalls_front_read_todo(struct sock_mapping *map)
> 
> Return type bool?

Yes, good idea


> > +{
> > +	struct pvcalls_data_intf *intf = map->active.ring;
> > +	RING_IDX cons, prod;
> > +	int32_t error;
> > +
> > +	cons = intf->in_cons;
> > +	prod = intf->in_prod;
> > +	error = intf->in_error;
> > +	return (error != 0 ||
> > +		pvcalls_queued(prod, cons,
> > +			       XEN_FLEX_RING_SIZE(intf->ring_order))) != 0;
> > +}
> > +
> >  static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
> >  {
> >  	struct xenbus_device *dev = dev_id;
> > @@ -413,6 +427,98 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
> >  	return tot_sent;
> >  }
> >  
> > +static int __read_ring(struct pvcalls_data_intf *intf,
> > +		       struct pvcalls_data *data,
> > +		       struct iov_iter *msg_iter,
> > +		       size_t len, int flags)
> > +{
> > +	RING_IDX cons, prod, size, masked_prod, masked_cons;
> > +	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
> > +	int32_t error;
> > +
> > +	cons = intf->in_cons;
> > +	prod = intf->in_prod;
> > +	error = intf->in_error;
> > +	/* get pointers before reading from the ring */
> > +	virt_rmb();
> > +	if (error < 0)
> > +		return error;
> > +
> > +	size = pvcalls_queued(prod, cons, array_size);
> > +	masked_prod = pvcalls_mask(prod, array_size);
> > +	masked_cons = pvcalls_mask(cons, array_size);
> > +
> > +	if (size == 0)
> > +		return 0;
> > +
> > +	if (len > size)
> > +		len = size;
> > +
> > +	if (masked_prod > masked_cons) {
> > +		copy_to_iter(data->in + masked_cons, len, msg_iter);
> > +	} else {
> > +		if (len > (array_size - masked_cons)) {
> > +			copy_to_iter(data->in + masked_cons,
> > +				     array_size - masked_cons, msg_iter);
> > +			copy_to_iter(data->in,
> > +				     len - (array_size - masked_cons),
> > +				     msg_iter);
> > +		} else {
> > +			copy_to_iter(data->in + masked_cons, len, msg_iter);
> > +		}
> > +	}
> > +	/* read data from the ring before increasing the index */
> > +	virt_mb();
> > +	if (!(flags & MSG_PEEK))
> > +		intf->in_cons += len;
> > +
> > +	return len;
> > +}
> > +
> > +int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
> > +		     int flags)
> > +{
> > +	struct pvcalls_bedata *bedata;
> > +	int ret = -EAGAIN;
> > +	struct sock_mapping *map;
> > +	int count = 0;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return -ENOTCONN;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +
> > +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> > +	if (!map)
> > +		return -ENOTSOCK;
> > +
> > +	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
> > +		return -EOPNOTSUPP;
> > +
> > +	mutex_lock(&map->active.in_mutex);
> > +	if (len > XEN_FLEX_RING_SIZE(map->active.ring->ring_order))
> > +		len = XEN_FLEX_RING_SIZE(map->active.ring->ring_order);
> > +
> > +	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
> > +		if (count < PVCALLS_FRON_MAX_SPIN)
> > +			count++;
> > +		else
> > +			wait_event_interruptible(map->active.inflight_conn_req,
> > +						 pvcalls_front_read_todo(map));
> > +	}
> > +	ret = __read_ring(map->active.ring, &map->active.data,
> > +			  &msg->msg_iter, len, flags);
> > +
> > +	if (ret > 0)
> > +		notify_remote_via_irq(map->active.irq);
> > +	if (ret == 0)
> > +		ret = -EAGAIN;
> > +	if (ret == -ENOTCONN)
> > +		ret = 0;
> > +
> > +	mutex_unlock(&map->active.in_mutex);
> > +	return ret;
> > +}
> > +
> >  int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
> >  {
> >  	struct pvcalls_bedata *bedata;
> > diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> > index d937c24..de24041 100644
> > --- a/drivers/xen/pvcalls-front.h
> > +++ b/drivers/xen/pvcalls-front.h
> > @@ -16,5 +16,9 @@ int pvcalls_front_accept(struct socket *sock,
> >  int pvcalls_front_sendmsg(struct socket *sock,
> >  			  struct msghdr *msg,
> >  			  size_t len);
> > +int pvcalls_front_recvmsg(struct socket *sock,
> > +			  struct msghdr *msg,
> > +			  size_t len,
> > +			  int flags);
> >  
> >  #endif
> > 
> 

[toc] | [prev] | [next] | [standalone]

#1694076 — [PATCH v1 07/13] xen/pvcalls: implement accept command

Send PVCALLS_ACCEPT to the backend. Allocate a new active socket. Make
sure that only one accept command is executed at any given time by
setting PVCALLS_FLAG_ACCEPT_INFLIGHT and waiting on the
inflight_accept_req waitqueue.

sock->sk->sk_send_head is not used for ip sockets: reuse the field to
store a pointer to the struct sock_mapping corresponding to the socket.

Convert the new struct socket pointer into an uint64_t and use it as id
for the new socket to pass to the backend.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 79 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/pvcalls-front.h |  3 ++
 2 files changed, 82 insertions(+)

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index 80fd5fb..f3a04a2 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -410,6 +410,85 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	return ret;
 }
 
+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;
+
+	if (!pvcalls_front_dev)
+		return -ENOTCONN;
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
+	if (!map)
+		return -ENOTSOCK;
+
+	if (map->passive.status != PVCALLS_STATUS_LISTEN)
+		return -EINVAL;
+
+	/*
+	 * 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)) {
+		if (wait_event_interruptible(map->passive.inflight_accept_req,
+			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+					  (void *)&map->passive.flags))
+			!= 0)
+			return -EINTR;
+	}
+
+
+	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
+	if (newsock->sk == NULL)
+		return -ENOMEM;
+
+	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;
+	}
+
+	map2 = create_active(&evtchn);
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_ACCEPT;
+	req->u.accept.id = (uint64_t) sock;
+	req->u.accept.ref = map2->active.ref;
+	req->u.accept.id_new = (uint64_t) newsock;
+	req->u.accept.evtchn = evtchn;
+
+	list_add_tail(&map2->list, &bedata->socket_mappings);
+	WRITE_ONCE(newsock->sk->sk_send_head, (void *)map2);
+	map2->sock = newsock;
+
+	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);
+
+	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);
+	return ret;
+}
+
 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 aa8fe10..ab4f1da 100644
--- a/drivers/xen/pvcalls-front.h
+++ b/drivers/xen/pvcalls-front.h
@@ -10,5 +10,8 @@ int pvcalls_front_bind(struct socket *sock,
 		       struct sockaddr *addr,
 		       int addr_len);
 int pvcalls_front_listen(struct socket *sock, int backlog);
+int pvcalls_front_accept(struct socket *sock,
+			 struct socket *newsock,
+			 int flags);
 
 #endif
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1695046 — Re: [PATCH v1 07/13] xen/pvcalls: implement accept command

On 22/07/17 02:11, Stefano Stabellini wrote:
> Send PVCALLS_ACCEPT to the backend. Allocate a new active socket. Make
> sure that only one accept command is executed at any given time by
> setting PVCALLS_FLAG_ACCEPT_INFLIGHT and waiting on the
> inflight_accept_req waitqueue.
> 
> sock->sk->sk_send_head is not used for ip sockets: reuse the field to
> store a pointer to the struct sock_mapping corresponding to the socket.
> 
> Convert the new struct socket pointer into an uint64_t and use it as id
> for the new socket to pass to the backend.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-front.c | 79 +++++++++++++++++++++++++++++++++++++++++++++
>  drivers/xen/pvcalls-front.h |  3 ++
>  2 files changed, 82 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index 80fd5fb..f3a04a2 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -410,6 +410,85 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
>  	return ret;
>  }
>  
> +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;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENOTCONN;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> +	if (!map)
> +		return -ENOTSOCK;
> +
> +	if (map->passive.status != PVCALLS_STATUS_LISTEN)
> +		return -EINVAL;
> +
> +	/*
> +	 * 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)) {
> +		if (wait_event_interruptible(map->passive.inflight_accept_req,
> +			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
> +					  (void *)&map->passive.flags))
> +			!= 0)
> +			return -EINTR;
> +	}
> +
> +
> +	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
> +	if (newsock->sk == NULL)
> +		return -ENOMEM;
> +
> +	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);

BUG_ON()?

> +	if (RING_FULL(&bedata->ring) ||
> +	    READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) {
> +		spin_unlock(&bedata->pvcallss_lock);
> +		return -EAGAIN;

Leaking newsock->sk?


Juergen

> +	}
> +
> +	map2 = create_active(&evtchn);
> +
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	req->cmd = PVCALLS_ACCEPT;
> +	req->u.accept.id = (uint64_t) sock;
> +	req->u.accept.ref = map2->active.ref;
> +	req->u.accept.id_new = (uint64_t) newsock;
> +	req->u.accept.evtchn = evtchn;
> +
> +	list_add_tail(&map2->list, &bedata->socket_mappings);
> +	WRITE_ONCE(newsock->sk->sk_send_head, (void *)map2);
> +	map2->sock = newsock;
> +
> +	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);
> +
> +	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);
> +	return ret;
> +}
> +
>  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 aa8fe10..ab4f1da 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -10,5 +10,8 @@ int pvcalls_front_bind(struct socket *sock,
>  		       struct sockaddr *addr,
>  		       int addr_len);
>  int pvcalls_front_listen(struct socket *sock, int backlog);
> +int pvcalls_front_accept(struct socket *sock,
> +			 struct socket *newsock,
> +			 int flags);
>  
>  #endif
> 

[toc] | [prev] | [next] | [standalone]

#1695225 — Re: [PATCH v1 07/13] xen/pvcalls: implement accept command

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:11, Stefano Stabellini wrote:
> > Send PVCALLS_ACCEPT to the backend. Allocate a new active socket. Make
> > sure that only one accept command is executed at any given time by
> > setting PVCALLS_FLAG_ACCEPT_INFLIGHT and waiting on the
> > inflight_accept_req waitqueue.
> > 
> > sock->sk->sk_send_head is not used for ip sockets: reuse the field to
> > store a pointer to the struct sock_mapping corresponding to the socket.
> > 
> > Convert the new struct socket pointer into an uint64_t and use it as id
> > for the new socket to pass to the backend.
> > 
> > Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  drivers/xen/pvcalls-front.c | 79 +++++++++++++++++++++++++++++++++++++++++++++
> >  drivers/xen/pvcalls-front.h |  3 ++
> >  2 files changed, 82 insertions(+)
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index 80fd5fb..f3a04a2 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -410,6 +410,85 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
> >  	return ret;
> >  }
> >  
> > +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;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return -ENOTCONN;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +
> > +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> > +	if (!map)
> > +		return -ENOTSOCK;
> > +
> > +	if (map->passive.status != PVCALLS_STATUS_LISTEN)
> > +		return -EINVAL;
> > +
> > +	/*
> > +	 * 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)) {
> > +		if (wait_event_interruptible(map->passive.inflight_accept_req,
> > +			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
> > +					  (void *)&map->passive.flags))
> > +			!= 0)
> > +			return -EINTR;
> > +	}
> > +
> > +
> > +	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
> > +	if (newsock->sk == NULL)
> > +		return -ENOMEM;
> > +
> > +	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);
> 
> BUG_ON()?
> 
> > +	if (RING_FULL(&bedata->ring) ||
> > +	    READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) {
> > +		spin_unlock(&bedata->pvcallss_lock);
> > +		return -EAGAIN;
> 
> Leaking newsock->sk?

I'll fix


> > +	}
> > +
> > +	map2 = create_active(&evtchn);
> > +
> > +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> > +	req->req_id = req_id;
> > +	req->cmd = PVCALLS_ACCEPT;
> > +	req->u.accept.id = (uint64_t) sock;
> > +	req->u.accept.ref = map2->active.ref;
> > +	req->u.accept.id_new = (uint64_t) newsock;
> > +	req->u.accept.evtchn = evtchn;
> > +
> > +	list_add_tail(&map2->list, &bedata->socket_mappings);
> > +	WRITE_ONCE(newsock->sk->sk_send_head, (void *)map2);
> > +	map2->sock = newsock;
> > +
> > +	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);
> > +
> > +	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);
> > +	return ret;
> > +}
> > +
> >  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 aa8fe10..ab4f1da 100644
> > --- a/drivers/xen/pvcalls-front.h
> > +++ b/drivers/xen/pvcalls-front.h
> > @@ -10,5 +10,8 @@ int pvcalls_front_bind(struct socket *sock,
> >  		       struct sockaddr *addr,
> >  		       int addr_len);
> >  int pvcalls_front_listen(struct socket *sock, int backlog);
> > +int pvcalls_front_accept(struct socket *sock,
> > +			 struct socket *newsock,
> > +			 int flags);
> >  
> >  #endif
> > 
> 

[toc] | [prev] | [next] | [standalone]

#1694077 — [PATCH v1 08/13] xen/pvcalls: implement sendmsg

Send data to an active socket by copying data to the "out" ring. Take
the active socket out_mutex so that only one function can access the
ring at any given time.

If not enough room is available on the ring, rather than returning
immediately or sleep-waiting, spin for up to 5000 cycles. This small
optimization turns out to improve performance significantly.

Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
CC: boris.ostrovsky@oracle.com
CC: jgross@suse.com
---
 drivers/xen/pvcalls-front.c | 109 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/pvcalls-front.h |   3 ++
 2 files changed, 112 insertions(+)

diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index f3a04a2..bf29f40 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -27,6 +27,7 @@
 #define PVCALLS_INVALID_ID (UINT_MAX)
 #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
 #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
+#define PVCALLS_FRON_MAX_SPIN 5000
 
 struct pvcalls_bedata {
 	struct xen_pvcalls_front_ring ring;
@@ -77,6 +78,22 @@ struct sock_mapping {
 	};
 };
 
+static int pvcalls_front_write_todo(struct sock_mapping *map)
+{
+	struct pvcalls_data_intf *intf = map->active.ring;
+	RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(intf->ring_order);
+	int32_t error;
+
+	cons = intf->out_cons;
+	prod = intf->out_prod;
+	error = intf->out_error;
+	if (error == -ENOTCONN)
+		return 0;
+	if (error != 0)
+		return error;
+	return size - pvcalls_queued(prod, cons, size);
+}
+
 static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 {
 	struct xenbus_device *dev = dev_id;
@@ -304,6 +321,98 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	return ret;
 }
 
+static int __write_ring(struct pvcalls_data_intf *intf,
+			struct pvcalls_data *data,
+			struct iov_iter *msg_iter,
+			size_t len)
+{
+	RING_IDX cons, prod, size, masked_prod, masked_cons;
+	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
+	int32_t error;
+
+	cons = intf->out_cons;
+	prod = intf->out_prod;
+	error = intf->out_error;
+	/* read indexes before continuing */
+	virt_mb();
+
+	if (error < 0)
+		return error;
+
+	size = pvcalls_queued(prod, cons, array_size);
+	if (size >= array_size)
+		return 0;
+	if (len > array_size - size)
+		len = array_size - size;
+
+	masked_prod = pvcalls_mask(prod, array_size);
+	masked_cons = pvcalls_mask(cons, array_size);
+
+	if (masked_prod < masked_cons) {
+		copy_from_iter(data->out + masked_prod, len, msg_iter);
+	} else {
+		if (len > array_size - masked_prod) {
+			copy_from_iter(data->out + masked_prod,
+				       array_size - masked_prod, msg_iter);
+			copy_from_iter(data->out,
+				       len - (array_size - masked_prod),
+				       msg_iter);
+		} else {
+			copy_from_iter(data->out + masked_prod, len, msg_iter);
+		}
+	}
+	/* write to ring before updating pointer */
+	virt_wmb();
+	intf->out_prod += len;
+
+	return len;
+}
+
+int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
+			  size_t len)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	int sent = 0, tot_sent = 0;
+	int count = 0, flags;
+
+	if (!pvcalls_front_dev)
+		return -ENOTCONN;
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
+	if (!map)
+		return -ENOTSOCK;
+
+	flags = msg->msg_flags;
+	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&map->active.out_mutex);
+	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
+		mutex_unlock(&map->active.out_mutex);
+		return -EAGAIN;
+	}
+
+again:
+	count++;
+	sent = __write_ring(map->active.ring,
+			    &map->active.data, &msg->msg_iter,
+			    len);
+	if (sent > 0) {
+		len -= sent;
+		tot_sent += sent;
+		notify_remote_via_irq(map->active.irq);
+	}
+	if (sent >= 0 && len > 0 && count < PVCALLS_FRON_MAX_SPIN)
+		goto again;
+	if (sent < 0)
+		tot_sent = sent;
+
+	mutex_unlock(&map->active.out_mutex);
+	return tot_sent;
+}
+
 int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
 	struct pvcalls_bedata *bedata;
diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
index ab4f1da..d937c24 100644
--- a/drivers/xen/pvcalls-front.h
+++ b/drivers/xen/pvcalls-front.h
@@ -13,5 +13,8 @@ int pvcalls_front_bind(struct socket *sock,
 int pvcalls_front_accept(struct socket *sock,
 			 struct socket *newsock,
 			 int flags);
+int pvcalls_front_sendmsg(struct socket *sock,
+			  struct msghdr *msg,
+			  size_t len);
 
 #endif
-- 
1.9.1

[toc] | [prev] | [next] | [standalone]

#1695047 — Re: [PATCH v1 08/13] xen/pvcalls: implement sendmsg

On 22/07/17 02:11, Stefano Stabellini wrote:
> Send data to an active socket by copying data to the "out" ring. Take
> the active socket out_mutex so that only one function can access the
> ring at any given time.
> 
> If not enough room is available on the ring, rather than returning
> immediately or sleep-waiting, spin for up to 5000 cycles. This small
> optimization turns out to improve performance significantly.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-front.c | 109 ++++++++++++++++++++++++++++++++++++++++++++
>  drivers/xen/pvcalls-front.h |   3 ++
>  2 files changed, 112 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index f3a04a2..bf29f40 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -27,6 +27,7 @@
>  #define PVCALLS_INVALID_ID (UINT_MAX)
>  #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
>  #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
> +#define PVCALLS_FRON_MAX_SPIN 5000

Any reason not to name it PVCALLS_FRONT_MAX_SPIN? I first thought you
meant FROM instead.


Juergen

>  
>  struct pvcalls_bedata {
>  	struct xen_pvcalls_front_ring ring;
> @@ -77,6 +78,22 @@ struct sock_mapping {
>  	};
>  };
>  
> +static int pvcalls_front_write_todo(struct sock_mapping *map)
> +{
> +	struct pvcalls_data_intf *intf = map->active.ring;
> +	RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(intf->ring_order);
> +	int32_t error;
> +
> +	cons = intf->out_cons;
> +	prod = intf->out_prod;
> +	error = intf->out_error;
> +	if (error == -ENOTCONN)
> +		return 0;
> +	if (error != 0)
> +		return error;
> +	return size - pvcalls_queued(prod, cons, size);
> +}
> +
>  static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>  {
>  	struct xenbus_device *dev = dev_id;
> @@ -304,6 +321,98 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
>  	return ret;
>  }
>  
> +static int __write_ring(struct pvcalls_data_intf *intf,
> +			struct pvcalls_data *data,
> +			struct iov_iter *msg_iter,
> +			size_t len)
> +{
> +	RING_IDX cons, prod, size, masked_prod, masked_cons;
> +	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
> +	int32_t error;
> +
> +	cons = intf->out_cons;
> +	prod = intf->out_prod;
> +	error = intf->out_error;
> +	/* read indexes before continuing */
> +	virt_mb();
> +
> +	if (error < 0)
> +		return error;
> +
> +	size = pvcalls_queued(prod, cons, array_size);
> +	if (size >= array_size)
> +		return 0;
> +	if (len > array_size - size)
> +		len = array_size - size;
> +
> +	masked_prod = pvcalls_mask(prod, array_size);
> +	masked_cons = pvcalls_mask(cons, array_size);
> +
> +	if (masked_prod < masked_cons) {
> +		copy_from_iter(data->out + masked_prod, len, msg_iter);
> +	} else {
> +		if (len > array_size - masked_prod) {
> +			copy_from_iter(data->out + masked_prod,
> +				       array_size - masked_prod, msg_iter);
> +			copy_from_iter(data->out,
> +				       len - (array_size - masked_prod),
> +				       msg_iter);
> +		} else {
> +			copy_from_iter(data->out + masked_prod, len, msg_iter);
> +		}
> +	}
> +	/* write to ring before updating pointer */
> +	virt_wmb();
> +	intf->out_prod += len;
> +
> +	return len;
> +}
> +
> +int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
> +			  size_t len)
> +{
> +	struct pvcalls_bedata *bedata;
> +	struct sock_mapping *map;
> +	int sent = 0, tot_sent = 0;
> +	int count = 0, flags;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENOTCONN;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> +	if (!map)
> +		return -ENOTSOCK;
> +
> +	flags = msg->msg_flags;
> +	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
> +		return -EOPNOTSUPP;
> +
> +	mutex_lock(&map->active.out_mutex);
> +	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
> +		mutex_unlock(&map->active.out_mutex);
> +		return -EAGAIN;
> +	}
> +
> +again:
> +	count++;
> +	sent = __write_ring(map->active.ring,
> +			    &map->active.data, &msg->msg_iter,
> +			    len);
> +	if (sent > 0) {
> +		len -= sent;
> +		tot_sent += sent;
> +		notify_remote_via_irq(map->active.irq);
> +	}
> +	if (sent >= 0 && len > 0 && count < PVCALLS_FRON_MAX_SPIN)
> +		goto again;
> +	if (sent < 0)
> +		tot_sent = sent;
> +
> +	mutex_unlock(&map->active.out_mutex);
> +	return tot_sent;
> +}
> +
>  int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
>  {
>  	struct pvcalls_bedata *bedata;
> diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> index ab4f1da..d937c24 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -13,5 +13,8 @@ int pvcalls_front_bind(struct socket *sock,
>  int pvcalls_front_accept(struct socket *sock,
>  			 struct socket *newsock,
>  			 int flags);
> +int pvcalls_front_sendmsg(struct socket *sock,
> +			  struct msghdr *msg,
> +			  size_t len);
>  
>  #endif
> 

[toc] | [prev] | [next] | [standalone]

#1695218 — Re: [PATCH v1 08/13] xen/pvcalls: implement sendmsg

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:11, Stefano Stabellini wrote:
> > Send data to an active socket by copying data to the "out" ring. Take
> > the active socket out_mutex so that only one function can access the
> > ring at any given time.
> > 
> > If not enough room is available on the ring, rather than returning
> > immediately or sleep-waiting, spin for up to 5000 cycles. This small
> > optimization turns out to improve performance significantly.
> > 
> > Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  drivers/xen/pvcalls-front.c | 109 ++++++++++++++++++++++++++++++++++++++++++++
> >  drivers/xen/pvcalls-front.h |   3 ++
> >  2 files changed, 112 insertions(+)
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > index f3a04a2..bf29f40 100644
> > --- a/drivers/xen/pvcalls-front.c
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -27,6 +27,7 @@
> >  #define PVCALLS_INVALID_ID (UINT_MAX)
> >  #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
> >  #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
> > +#define PVCALLS_FRON_MAX_SPIN 5000
> 
> Any reason not to name it PVCALLS_FRONT_MAX_SPIN? I first thought you
> meant FROM instead.

Clearly a typo :-)  I'll fix it.


> 
> >  
> >  struct pvcalls_bedata {
> >  	struct xen_pvcalls_front_ring ring;
> > @@ -77,6 +78,22 @@ struct sock_mapping {
> >  	};
> >  };
> >  
> > +static int pvcalls_front_write_todo(struct sock_mapping *map)
> > +{
> > +	struct pvcalls_data_intf *intf = map->active.ring;
> > +	RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(intf->ring_order);
> > +	int32_t error;
> > +
> > +	cons = intf->out_cons;
> > +	prod = intf->out_prod;
> > +	error = intf->out_error;
> > +	if (error == -ENOTCONN)
> > +		return 0;
> > +	if (error != 0)
> > +		return error;
> > +	return size - pvcalls_queued(prod, cons, size);
> > +}
> > +
> >  static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
> >  {
> >  	struct xenbus_device *dev = dev_id;
> > @@ -304,6 +321,98 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
> >  	return ret;
> >  }
> >  
> > +static int __write_ring(struct pvcalls_data_intf *intf,
> > +			struct pvcalls_data *data,
> > +			struct iov_iter *msg_iter,
> > +			size_t len)
> > +{
> > +	RING_IDX cons, prod, size, masked_prod, masked_cons;
> > +	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
> > +	int32_t error;
> > +
> > +	cons = intf->out_cons;
> > +	prod = intf->out_prod;
> > +	error = intf->out_error;
> > +	/* read indexes before continuing */
> > +	virt_mb();
> > +
> > +	if (error < 0)
> > +		return error;
> > +
> > +	size = pvcalls_queued(prod, cons, array_size);
> > +	if (size >= array_size)
> > +		return 0;
> > +	if (len > array_size - size)
> > +		len = array_size - size;
> > +
> > +	masked_prod = pvcalls_mask(prod, array_size);
> > +	masked_cons = pvcalls_mask(cons, array_size);
> > +
> > +	if (masked_prod < masked_cons) {
> > +		copy_from_iter(data->out + masked_prod, len, msg_iter);
> > +	} else {
> > +		if (len > array_size - masked_prod) {
> > +			copy_from_iter(data->out + masked_prod,
> > +				       array_size - masked_prod, msg_iter);
> > +			copy_from_iter(data->out,
> > +				       len - (array_size - masked_prod),
> > +				       msg_iter);
> > +		} else {
> > +			copy_from_iter(data->out + masked_prod, len, msg_iter);
> > +		}
> > +	}
> > +	/* write to ring before updating pointer */
> > +	virt_wmb();
> > +	intf->out_prod += len;
> > +
> > +	return len;
> > +}
> > +
> > +int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
> > +			  size_t len)
> > +{
> > +	struct pvcalls_bedata *bedata;
> > +	struct sock_mapping *map;
> > +	int sent = 0, tot_sent = 0;
> > +	int count = 0, flags;
> > +
> > +	if (!pvcalls_front_dev)
> > +		return -ENOTCONN;
> > +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> > +
> > +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> > +	if (!map)
> > +		return -ENOTSOCK;
> > +
> > +	flags = msg->msg_flags;
> > +	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
> > +		return -EOPNOTSUPP;
> > +
> > +	mutex_lock(&map->active.out_mutex);
> > +	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
> > +		mutex_unlock(&map->active.out_mutex);
> > +		return -EAGAIN;
> > +	}
> > +
> > +again:
> > +	count++;
> > +	sent = __write_ring(map->active.ring,
> > +			    &map->active.data, &msg->msg_iter,
> > +			    len);
> > +	if (sent > 0) {
> > +		len -= sent;
> > +		tot_sent += sent;
> > +		notify_remote_via_irq(map->active.irq);
> > +	}
> > +	if (sent >= 0 && len > 0 && count < PVCALLS_FRON_MAX_SPIN)
> > +		goto again;
> > +	if (sent < 0)
> > +		tot_sent = sent;
> > +
> > +	mutex_unlock(&map->active.out_mutex);
> > +	return tot_sent;
> > +}
> > +
> >  int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
> >  {
> >  	struct pvcalls_bedata *bedata;
> > diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> > index ab4f1da..d937c24 100644
> > --- a/drivers/xen/pvcalls-front.h
> > +++ b/drivers/xen/pvcalls-front.h
> > @@ -13,5 +13,8 @@ int pvcalls_front_bind(struct socket *sock,
> >  int pvcalls_front_accept(struct socket *sock,
> >  			 struct socket *newsock,
> >  			 int flags);
> > +int pvcalls_front_sendmsg(struct socket *sock,
> > +			  struct msghdr *msg,
> > +			  size_t len);
> >  
> >  #endif
> > 
> 

[toc] | [prev] | [next] | [standalone]

#1695009 — Re: [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus frontend

On 22/07/17 02:11, Stefano Stabellini wrote:
> Introduce a xenbus frontend for the pvcalls protocol, as defined by
> https://xenbits.xen.org/docs/unstable/misc/pvcalls.html.
> 
> This patch only adds the stubs, the code will be added by the following
> patches.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-front.c | 68 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 68 insertions(+)
>  create mode 100644 drivers/xen/pvcalls-front.c
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> new file mode 100644
> index 0000000..173e204
> --- /dev/null
> +++ b/drivers/xen/pvcalls-front.c
> @@ -0,0 +1,68 @@
> +/*
> + * (c) 2017 Stefano Stabellini <stefano@aporeto.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + */
> +
> +#include <linux/module.h>
> +
> +#include <xen/events.h>
> +#include <xen/grant_table.h>
> +#include <xen/xen.h>
> +#include <xen/xenbus.h>
> +#include <xen/interface/io/pvcalls.h>
> +
> +static const struct xenbus_device_id pvcalls_front_ids[] = {
> +	{ "pvcalls" },
> +	{ "" }
> +};
> +
> +static int pvcalls_front_remove(struct xenbus_device *dev)
> +{
> +	return 0;
> +}
> +
> +static int pvcalls_front_probe(struct xenbus_device *dev,
> +			  const struct xenbus_device_id *id)
> +{
> +	return 0;
> +}
> +
> +static int pvcalls_front_resume(struct xenbus_device *dev)
> +{
> +	dev_warn(&dev->dev, "suspsend/resume unsupported\n");
> +	return 0;
> +}

Why are you adding a resume function doing nothing but issuing a
message? Just omit it.


Juergen

> +
> +static void pvcalls_front_changed(struct xenbus_device *dev,
> +			    enum xenbus_state backend_state)
> +{
> +}
> +
> +static struct xenbus_driver pvcalls_front_driver = {
> +	.ids = pvcalls_front_ids,
> +	.probe = pvcalls_front_probe,
> +	.remove = pvcalls_front_remove,
> +	.resume = pvcalls_front_resume,
> +	.otherend_changed = pvcalls_front_changed,
> +};
> +
> +static int __init pvcalls_frontend_init(void)
> +{
> +	if (!xen_domain())
> +		return -ENODEV;
> +
> +	pr_info("Initialising Xen pvcalls frontend driver\n");
> +
> +	return xenbus_register_frontend(&pvcalls_front_driver);
> +}
> +
> +module_init(pvcalls_frontend_init);
> 

[toc] | [prev] | [next] | [standalone]

#1695216 — Re: [PATCH v1 01/13] xen/pvcalls: introduce the pvcalls xenbus frontend

On Mon, 24 Jul 2017, Juergen Gross wrote:
> On 22/07/17 02:11, Stefano Stabellini wrote:
> > Introduce a xenbus frontend for the pvcalls protocol, as defined by
> > https://xenbits.xen.org/docs/unstable/misc/pvcalls.html.
> > 
> > This patch only adds the stubs, the code will be added by the following
> > patches.
> > 
> > Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> > CC: boris.ostrovsky@oracle.com
> > CC: jgross@suse.com
> > ---
> >  drivers/xen/pvcalls-front.c | 68 +++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 68 insertions(+)
> >  create mode 100644 drivers/xen/pvcalls-front.c
> > 
> > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> > new file mode 100644
> > index 0000000..173e204
> > --- /dev/null
> > +++ b/drivers/xen/pvcalls-front.c
> > @@ -0,0 +1,68 @@
> > +/*
> > + * (c) 2017 Stefano Stabellini <stefano@aporeto.com>
> > + *
> > + * This program is free software; you can redistribute it and/or modify
> > + * it under the terms of the GNU General Public License as published by
> > + * the Free Software Foundation; either version 2 of the License, or
> > + * (at your option) any later version.
> > + *
> > + * This program is distributed in the hope that it will be useful,
> > + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> > + * GNU General Public License for more details.
> > + */
> > +
> > +#include <linux/module.h>
> > +
> > +#include <xen/events.h>
> > +#include <xen/grant_table.h>
> > +#include <xen/xen.h>
> > +#include <xen/xenbus.h>
> > +#include <xen/interface/io/pvcalls.h>
> > +
> > +static const struct xenbus_device_id pvcalls_front_ids[] = {
> > +	{ "pvcalls" },
> > +	{ "" }
> > +};
> > +
> > +static int pvcalls_front_remove(struct xenbus_device *dev)
> > +{
> > +	return 0;
> > +}
> > +
> > +static int pvcalls_front_probe(struct xenbus_device *dev,
> > +			  const struct xenbus_device_id *id)
> > +{
> > +	return 0;
> > +}
> > +
> > +static int pvcalls_front_resume(struct xenbus_device *dev)
> > +{
> > +	dev_warn(&dev->dev, "suspsend/resume unsupported\n");
> > +	return 0;
> > +}
> 
> Why are you adding a resume function doing nothing but issuing a
> message? Just omit it.

I'll do, thanks!


> > +
> > +static void pvcalls_front_changed(struct xenbus_device *dev,
> > +			    enum xenbus_state backend_state)
> > +{
> > +}
> > +
> > +static struct xenbus_driver pvcalls_front_driver = {
> > +	.ids = pvcalls_front_ids,
> > +	.probe = pvcalls_front_probe,
> > +	.remove = pvcalls_front_remove,
> > +	.resume = pvcalls_front_resume,
> > +	.otherend_changed = pvcalls_front_changed,
> > +};
> > +
> > +static int __init pvcalls_frontend_init(void)
> > +{
> > +	if (!xen_domain())
> > +		return -ENODEV;
> > +
> > +	pr_info("Initialising Xen pvcalls frontend driver\n");
> > +
> > +	return xenbus_register_frontend(&pvcalls_front_driver);
> > +}
> > +
> > +module_init(pvcalls_frontend_init);
> > 
> 

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web