Re: [PATCH v2 05/13] xen/pvcalls: implement bind command

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

On 7/25/2017 5:22 PM, Stefano Stabellini wrote:
> Send PVCALLS_BIND to the backend. Introduce a new structure, part of
> struct sock_mapping, to store information specific to passive sockets.
>
> Introduce a status field to keep track of the status of the passive
> socket.
>
> Introduce a waitqueue for the "accept" command (see the accept command
> implementation): it is used to allow only one outstanding accept
> command at any given time and to implement polling on the passive
> socket. Introduce a flags field to keep track of in-flight accept and
> poll commands.
>
> 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 struct socket pointer into an uint64_t and use it as id for
> the 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 | 73 +++++++++++++++++++++++++++++++++++++++++++++
>   drivers/xen/pvcalls-front.h |  3 ++
>   2 files changed, 76 insertions(+)
>
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index d0f5f42..af2ce20 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -59,6 +59,23 @@ struct sock_mapping {
>   
>   			wait_queue_head_t inflight_conn_req;
>   		} active;
> +		struct {
> +		/* Socket status */
> +#define PVCALLS_STATUS_UNINITALIZED  0
> +#define PVCALLS_STATUS_BIND          1
> +#define PVCALLS_STATUS_LISTEN        2
> +			uint8_t status;
> +		/*
> +		 * Internal state-machine flags.
> +		 * Only one accept operation can be inflight for a socket.
> +		 * Only one poll operation can be inflight for a given socket.
> +		 */
> +#define PVCALLS_FLAG_ACCEPT_INFLIGHT 0
> +#define PVCALLS_FLAG_POLL_INFLIGHT   1
> +#define PVCALLS_FLAG_POLL_RET        2
> +			uint8_t flags;
> +			wait_queue_head_t inflight_accept_req;
> +		} passive;
>   	};
>   };
>   
> @@ -292,6 +309,62 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
>   	return ret;
>   }
>   
> +int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
> +{
> +	struct pvcalls_bedata *bedata;
> +	struct sock_mapping *map = NULL;
> +	struct xen_pvcalls_request *req;
> +	int notify, req_id, ret;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENOTCONN;
> +	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
> +		return -ENOTSUPP;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = kzalloc(sizeof(*map), GFP_KERNEL);
> +	if (map == NULL)
> +		return -ENOMEM;
> +
> +	spin_lock(&bedata->pvcallss_lock);
> +	req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
> +	if (RING_FULL(&bedata->ring) ||
> +	    READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) {
> +		kfree(map);
> +		spin_unlock(&bedata->pvcallss_lock);
> +		return -EAGAIN;
> +	}
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	map->sock = sock;
> +	req->cmd = PVCALLS_BIND;
> +	req->u.bind.id = (uint64_t) sock;
> +	memcpy(req->u.bind.addr, addr, sizeof(*addr));
> +	req->u.bind.len = addr_len;
> +
> +	init_waitqueue_head(&map->passive.inflight_accept_req);
> +
> +	list_add_tail(&map->list, &bedata->socketpass_mappings);
> +	WRITE_ONCE(sock->sk->sk_send_head, (void *)map);
> +	map->active_socket = false;
> +
> +	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);

This all looks very similar to previous patches. Can it be factored out?

Also, you've used wait_event_interruptible in socket() implementation. 
Why not here (and connect())?

-boris

> +
> +	map->passive.status = PVCALLS_STATUS_BIND;
> +	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 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 63b0417..8b0a274 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -6,5 +6,8 @@
>   int pvcalls_front_socket(struct socket *sock);
>   int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
>   			  int addr_len, int flags);
> +int pvcalls_front_bind(struct socket *sock,
> +		       struct sockaddr *addr,
> +		       int addr_len);
>   
>   #endif