Re: [PATCH v1 04/13] xen/pvcalls: implement connect command

[Juergen Gross]

On 22/07/17 02:11, Stefano Stabellini wrote:
> Send PVCALLS_CONNECT to the backend. Allocate a new ring and evtchn for
> the active socket.
> 
> Introduce a data structure to keep track of sockets. Introduce a
> waitqueue to allow the frontend to wait on data coming from the backend
> on the active socket (recvmsg command).
> 
> Two mutexes (one of reads and one for writes) will be used to protect
> the active socket in and out rings from concurrent accesses.
> 
> 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.
> This way, we can easily get the struct sock_mapping from the struct
> socket.
> 
> Convert the 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@xxxxxxxxxxx>
> CC: boris.ostrovsky@xxxxxxxxxx
> CC: jgross@xxxxxxxx
> ---
>  drivers/xen/pvcalls-front.c | 153 ++++++++++++++++++++++++++++++++++++++++++++
>  drivers/xen/pvcalls-front.h |   2 +
>  2 files changed, 155 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index 7933c73..0d305e0 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -13,6 +13,8 @@
>   */
>  
>  #include <linux/module.h>
> +#include <linux/net.h>
> +#include <linux/socket.h>
>  
>  #include <xen/events.h>
>  #include <xen/grant_table.h>
> @@ -20,6 +22,8 @@
>  #include <xen/xenbus.h>
>  #include <xen/interface/io/pvcalls.h>
>  
> +#include <net/sock.h>
> +
>  #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)
> @@ -38,6 +42,24 @@ struct pvcalls_bedata {
>  };
>  struct xenbus_device *pvcalls_front_dev;
>  
> +struct sock_mapping {
> +	bool active_socket;
> +	struct list_head list;
> +	struct socket *sock;
> +	union {
> +		struct {
> +			int irq;
> +			grant_ref_t ref;
> +			struct pvcalls_data_intf *ring;
> +			struct pvcalls_data data;
> +			struct mutex in_mutex;
> +			struct mutex out_mutex;
> +
> +			wait_queue_head_t inflight_conn_req;
> +		} active;
> +	};
> +};
> +
>  static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>  {
>  	struct xenbus_device *dev = dev_id;
> @@ -80,6 +102,18 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>  	return IRQ_HANDLED;
>  }
>  
> +static irqreturn_t pvcalls_front_conn_handler(int irq, void *sock_map)
> +{
> +	struct sock_mapping *map = sock_map;
> +
> +	if (map == NULL)
> +		return IRQ_HANDLED;
> +
> +	wake_up_interruptible(&map->active.inflight_conn_req);
> +
> +	return IRQ_HANDLED;
> +}
> +
>  int pvcalls_front_socket(struct socket *sock)
>  {
>  	struct pvcalls_bedata *bedata;
> @@ -134,6 +168,125 @@ int pvcalls_front_socket(struct socket *sock)
>  	return ret;
>  }
>  
> +static struct sock_mapping *create_active(int *evtchn)
> +{
> +	struct sock_mapping *map = NULL;
> +	void *bytes;
> +	int ret, irq = -1, i;
> +
> +	map = kzalloc(sizeof(*map), GFP_KERNEL);
> +	if (map == NULL)
> +		return NULL;
> +
> +	init_waitqueue_head(&map->active.inflight_conn_req);
> +
> +	map->active.ring = (struct pvcalls_data_intf *)
> +		__get_free_page(GFP_KERNEL | __GFP_ZERO);
> +	if (map->active.ring == NULL)
> +		goto out_error;
> +	memset(map->active.ring, 0, XEN_PAGE_SIZE);
> +	map->active.ring->ring_order = RING_ORDER;
> +	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
> +					map->active.ring->ring_order);
> +	if (bytes == NULL)
> +		goto out_error;
> +	for (i = 0; i < (1 << map->active.ring->ring_order); i++)
> +		map->active.ring->ref[i] = gnttab_grant_foreign_access(
> +			pvcalls_front_dev->otherend_id,
> +			pfn_to_gfn(virt_to_pfn(bytes) + i), 0);
> +
> +	map->active.ref = gnttab_grant_foreign_access(
> +		pvcalls_front_dev->otherend_id,
> +		pfn_to_gfn(virt_to_pfn((void *)map->active.ring)), 0);
> +
> +	ret = xenbus_alloc_evtchn(pvcalls_front_dev, evtchn);
> +	if (ret)
> +		goto out_error;

You are leaking bytes here in case of error.

> +	map->active.data.in = bytes;
> +	map->active.data.out = bytes +
> +		XEN_FLEX_RING_SIZE(map->active.ring->ring_order);
> +	irq = bind_evtchn_to_irqhandler(*evtchn, pvcalls_front_conn_handler,
> +					0, "pvcalls-frontend", map);
> +	if (irq < 0)
> +		goto out_error;
> +
> +	map->active.irq = irq;
> +	map->active_socket = true;
> +	mutex_init(&map->active.in_mutex);
> +	mutex_init(&map->active.out_mutex);
> +
> +	return map;
> +
> +out_error:
> +	if (irq >= 0)
> +		unbind_from_irqhandler(irq, map);
> +	else if (*evtchn >= 0)
> +		xenbus_free_evtchn(pvcalls_front_dev, *evtchn);
> +	kfree(map->active.data.in);
> +	kfree(map->active.ring);
> +	kfree(map);
> +	return NULL;
> +}
> +
> +int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
> +				int addr_len, int flags)
> +{
> +	struct pvcalls_bedata *bedata;
> +	struct sock_mapping *map = NULL;
> +	struct xen_pvcalls_request *req;
> +	int notify, req_id, ret, evtchn;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENETUNREACH;
> +	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
> +		return -ENOTSUPP;
> +
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	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;
> +	}
> +
> +	map = create_active(&evtchn);
> +	if (!map)
> +	    return -ENOMEM;

spin_unlock()?


Juergen

> +
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	req->cmd = PVCALLS_CONNECT;
> +	req->u.connect.id = (uint64_t)sock;
> +	memcpy(req->u.connect.addr, addr, sizeof(*addr));
> +	req->u.connect.len = addr_len;
> +	req->u.connect.flags = flags;
> +	req->u.connect.ref = map->active.ref;
> +	req->u.connect.evtchn = evtchn;
> +	
> +	list_add_tail(&map->list, &bedata->socket_mappings);
> +	map->sock = sock;
> +	WRITE_ONCE(sock->sk->sk_send_head, (void *)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);
> +
> +	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 b7dabed..63b0417 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -4,5 +4,7 @@
>  #include <linux/net.h>
>  
>  int pvcalls_front_socket(struct socket *sock);
> +int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
> +			  int addr_len, int flags);
>  
>  #endif
>