Re: [PATCH v5 02/13] xen/pvcalls: implement frontend disconnect

From: Boris Ostrovsky
Date: Tue Oct 17 2017 - 11:59:36 EST


On 10/06/2017 08:30 PM, Stefano Stabellini wrote:
> Introduce a data structure named pvcalls_bedata. It contains pointers to
> the command ring, the event channel, a list of active sockets and a list
> of passive sockets. Lists accesses are protected by a spin_lock.
>
> Introduce a waitqueue to allow waiting for a response on commands sent
> to the backend.
>
> Introduce an array of struct xen_pvcalls_response to store commands
> responses.
>
> pvcalls_refcount is used to keep count of the outstanding pvcalls users.
> Only remove connections once the refcount is zero.
>
> 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@xxxxxxxxxxx>
> CC: boris.ostrovsky@xxxxxxxxxx
> CC: jgross@xxxxxxxx
> ---
> drivers/xen/pvcalls-front.c | 67 +++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 67 insertions(+)
>
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index a8d38c2..d8b7a04 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -20,6 +20,46 @@
> #include <xen/xenbus.h>
> #include <xen/interface/io/pvcalls.h>
>
> +#define PVCALLS_INVALID_ID UINT_MAX
> +#define PVCALLS_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
> +#define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
> +
> +struct pvcalls_bedata {
> + struct xen_pvcalls_front_ring ring;
> + grant_ref_t ref;
> + int irq;
> +
> + struct list_head socket_mappings;
> + struct list_head socketpass_mappings;
> + spinlock_t socket_lock;
> +
> + wait_queue_head_t inflight_req;
> + struct xen_pvcalls_response rsp[PVCALLS_NR_REQ_PER_RING];

Did you mean _REQ_ or _RSP_ in the macro name?

> +};
> +/* Only one front/back connection supported. */
> +static struct xenbus_device *pvcalls_front_dev;
> +static atomic_t pvcalls_refcount;
> +
> +/* first increment refcount, then proceed */
> +#define pvcalls_enter() { \
> + atomic_inc(&pvcalls_refcount); \
> +}
> +
> +/* first complete other operations, then decrement refcount */
> +#define pvcalls_exit() { \
> + atomic_dec(&pvcalls_refcount); \
> +}
> +
> +static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
> +{
> + return IRQ_HANDLED;
> +}
> +
> +static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
> + struct sock_mapping *map)
> +{
> +}
> +
> static const struct xenbus_device_id pvcalls_front_ids[] = {
> { "pvcalls" },
> { "" }
> @@ -27,6 +67,33 @@
>
> 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);
> + dev_set_drvdata(&dev->dev, NULL);
> + pvcalls_front_dev = NULL;
> + if (bedata->irq >= 0)
> + unbind_from_irqhandler(bedata->irq, dev);
> +
> + smp_mb();
> + while (atomic_read(&pvcalls_refcount) > 0)
> + cpu_relax();
> + list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
> + pvcalls_front_free_map(bedata, map);
> + kfree(map);
> + }
> + list_for_each_entry_safe(map, n, &bedata->socketpass_mappings, list) {
> + spin_lock(&bedata->socket_lock);
> + list_del_init(&map->list);
> + spin_unlock(&bedata->socket_lock);
> + kfree(map);

Why do you re-init the entry if you are freeing it? And do you really
need the locks around it? This looks similar to the case we've discussed
for other patches --- if we are concerned that someone may grab this
entry then something must be wrong.

(Sorry, this must have been here in earlier versions but I only now
noticed it.)

-boris

> + }
> + if (bedata->ref >= 0)
> + gnttab_end_foreign_access(bedata->ref, 0, 0);
> + kfree(bedata->ring.sring);
> + kfree(bedata);
> + xenbus_switch_state(dev, XenbusStateClosed);
> return 0;
> }
>