Subject: Re: [PATCH v3 08/18] xen/pvcalls: implement connect command
To: Stefano Stabellini <sstabellini@kernel.org>, xen-devel@lists.xen.org
Cc: linux-kernel@vger.kernel.org, boris.ostrovsky@oracle.com,
        Stefano Stabellini <stefano@aporeto.com>
References: <alpine.DEB.2.10.1706021225440.18759@sstabellini-ThinkPad-X260>
 <1496431915-20774-1-git-send-email-sstabellini@kernel.org>
 <1496431915-20774-8-git-send-email-sstabellini@kernel.org>
From: Juergen Gross <jgross@suse.com>
Message-ID: <3c2a8a1e-e50e-8d69-69ec-1a8bde626876@suse.com>
Date: Tue, 13 Jun 2017 08:17:10 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.1.1
MIME-Version: 1.0
In-Reply-To: <1496431915-20774-8-git-send-email-sstabellini@kernel.org>
Content-Type: text/plain; charset=utf-8
Content-Language: de-DE
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 6352
Lines: 234

On 02/06/17 21:31, Stefano Stabellini wrote:
> Allocate a socket. Keep track of socket <-> ring mappings with a new data
> structure, called sock_mapping. Implement the connect command by calling
> inet_stream_connect, and mapping the new indexes page and data ring.
> Allocate a workqueue and a work_struct, called ioworker, to perform
> reads and writes to the socket.
> 
> When an active socket is closed (sk_state_change), set in_error to
> -ENOTCONN and notify the other end, as specified by the protocol.
> 
> sk_data_ready and pvcalls_back_ioworker will be implemented later.
> 
> Signed-off-by: Stefano Stabellini <stefano@aporeto.com>
> CC: boris.ostrovsky@oracle.com
> CC: jgross@suse.com
> ---
>  drivers/xen/pvcalls-back.c | 170 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 170 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c
> index 1f2bb26..3eb84ef 100644
> --- a/drivers/xen/pvcalls-back.c
> +++ b/drivers/xen/pvcalls-back.c
> @@ -56,6 +56,40 @@ struct pvcalls_fedata {
>  	struct work_struct register_work;
>  };
>  
> +struct pvcalls_ioworker {
> +	struct work_struct register_work;
> +	struct workqueue_struct *wq;
> +	unsigned int cpu;
> +};
> +
> +struct sock_mapping {
> +	struct list_head list;
> +	struct pvcalls_fedata *priv;
> +	struct socket *sock;
> +	uint64_t id;
> +	grant_ref_t ref;
> +	struct pvcalls_data_intf *ring;
> +	void *bytes;
> +	struct pvcalls_data data;
> +	uint32_t ring_order;
> +	int irq;
> +	atomic_t read;
> +	atomic_t write;
> +	atomic_t io;
> +	atomic_t release;
> +	void (*saved_data_ready)(struct sock *sk);
> +	struct pvcalls_ioworker ioworker;
> +};
> +
> +static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map);
> +static int pvcalls_back_release_active(struct xenbus_device *dev,
> +				       struct pvcalls_fedata *priv,
> +				       struct sock_mapping *map);
> +
> +static void pvcalls_back_ioworker(struct work_struct *work)
> +{
> +}
> +
>  static int pvcalls_back_socket(struct xenbus_device *dev,
>  		struct xen_pvcalls_request *req)
>  {
> @@ -84,9 +118,140 @@ static int pvcalls_back_socket(struct xenbus_device *dev,
>  	return ret;
>  }
>  
> +static void pvcalls_sk_state_change(struct sock *sock)
> +{
> +	struct sock_mapping *map = sock->sk_user_data;
> +	struct pvcalls_data_intf *intf;
> +
> +	if (map == NULL)
> +		return;
> +
> +	intf = map->ring;
> +	intf->in_error = -ENOTCONN;
> +	notify_remote_via_irq(map->irq);
> +}
> +
> +static void pvcalls_sk_data_ready(struct sock *sock)
> +{
> +}
> +
> +static struct sock_mapping *pvcalls_new_active_socket(
> +		struct pvcalls_fedata *priv,
> +		uint64_t id,
> +		grant_ref_t ref,
> +		uint32_t evtchn,
> +		struct socket *sock)
> +{
> +	int ret;
> +	struct sock_mapping *map = NULL;

Pointless initializer.

> +	void *page;
> +
> +	map = kzalloc(sizeof(*map), GFP_KERNEL);
> +	if (map == NULL)
> +		return NULL;
> +
> +	map->priv = priv;
> +	map->sock = sock;
> +	map->id = id;
> +	map->ref = ref;
> +
> +	ret = xenbus_map_ring_valloc(priv->dev, &ref, 1, &page);
> +	if (ret < 0)
> +		goto out;
> +	map->ring = page;
> +	map->ring_order = map->ring->ring_order;
> +	/* first read the order, then map the data ring */
> +	virt_rmb();
> +	if (map->ring_order > MAX_RING_ORDER)

Issue a message?

> +		goto out;
> +	ret = xenbus_map_ring_valloc(priv->dev, map->ring->ref,
> +				     (1 << map->ring_order), &page);
> +	if (ret < 0)
> +		goto out;
> +	map->bytes = page;
> +
> +	ret = bind_interdomain_evtchn_to_irqhandler(priv->dev->otherend_id,
> +						    evtchn,
> +						    pvcalls_back_conn_event,
> +						    0,
> +						    "pvcalls-backend",
> +						    map);
> +	if (ret < 0)
> +		goto out;
> +	map->irq = ret;
> +
> +	map->data.in = map->bytes;
> +	map->data.out = map->bytes + XEN_FLEX_RING_SIZE(map->ring_order);
> +	
> +	map->ioworker.wq = alloc_workqueue("pvcalls_io", WQ_UNBOUND, 1);
> +	if (!map->ioworker.wq)
> +		goto out;
> +	map->ioworker.cpu = get_random_int() % num_online_cpus();

So you expect all cpus [0..num_online_cpus()[ to be online. I don't
think this is always true.

> +	atomic_set(&map->io, 1);
> +	INIT_WORK(&map->ioworker.register_work,	pvcalls_back_ioworker);
> +
> +	down(&priv->socket_lock);
> +	list_add_tail(&map->list, &priv->socket_mappings);
> +	up(&priv->socket_lock);
> +
> +	write_lock_bh(&map->sock->sk->sk_callback_lock);
> +	map->saved_data_ready = map->sock->sk->sk_data_ready;
> +	map->sock->sk->sk_user_data = map;
> +	map->sock->sk->sk_data_ready = pvcalls_sk_data_ready;
> +	map->sock->sk->sk_state_change = pvcalls_sk_state_change;
> +	write_unlock_bh(&map->sock->sk->sk_callback_lock);
> +
> +	return map;
> +out:
> +	pvcalls_back_release_active(priv->dev, priv, map);
> +	return NULL;
> +}
> +
>  static int pvcalls_back_connect(struct xenbus_device *dev,
>  				struct xen_pvcalls_request *req)
>  {
> +	struct pvcalls_fedata *priv;
> +	int ret;
> +	struct socket *sock;
> +	struct sock_mapping *map = NULL;
> +	struct xen_pvcalls_response *rsp;
> +
> +	priv = dev_get_drvdata(&dev->dev);
> +
> +	ret = sock_create(AF_INET, SOCK_STREAM, 0, &sock);
> +	if (ret < 0)
> +		goto out;
> +	ret = inet_stream_connect(sock, (struct sockaddr *)&req->u.connect.addr,
> +				  req->u.connect.len, req->u.connect.flags);
> +	if (ret < 0) {
> +		sock_release(map->sock);
> +		goto out;
> +	}
> +	
> +	map = pvcalls_new_active_socket(priv,
> +					req->u.connect.id,
> +					req->u.connect.ref,
> +					req->u.connect.evtchn,
> +					sock);
> +	if (!map) {
> +		sock_release(map->sock);
> +		goto out;

ret will be 0 here. So there was a failure and you report success.


Juergen

> +	}
> +
> +out:
> +	rsp = RING_GET_RESPONSE(&priv->ring, priv->ring.rsp_prod_pvt++);
> +	rsp->req_id = req->req_id;
> +	rsp->cmd = req->cmd;
> +	rsp->u.connect.id = req->u.connect.id;
> +	rsp->ret = ret;
> +
> +	return ret;
> +}
> +
> +static int pvcalls_back_release_active(struct xenbus_device *dev,
> +				       struct pvcalls_fedata *priv,
> +				       struct sock_mapping *map)
> +{
>  	return 0;
>  }
>  
> @@ -206,6 +371,11 @@ static irqreturn_t pvcalls_back_event(int irq, void *dev_id)
>  	return IRQ_HANDLED;
>  }
>  
> +static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map)
> +{
> +	return IRQ_HANDLED;
> +}
> +
>  static int backend_connect(struct xenbus_device *dev)
>  {
>  	int err, evtchn;
>