Re: [Qemu-devel] [PATCH RFC 1/6] virtio-bus: common ioeventfd infrastructure

["Michael S. Tsirkin" <mst@redhat.com>]

On Thu, Mar 17, 2016 at 11:01:28AM +0100, Cornelia Huck wrote:
> Introduce a set of ioeventfd callbacks on the virtio-bus level
> that can be implemented by the individual transports. At the
> virtio-bus level, do common handling for host notifiers (which
> is actually most of it).
> 
> Two things of note:
> - We always iterate over all possible virtio queues, even though
> ccw (currently) has a lower limit. It does not really matter in
> this place.
> - We allow for the virtio-bus caller to pass an "assign" argument
> down when stopping ioeventfd, which the old interface did not allow.
> 
> Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>

So it sounds like this is supposed to fix races
in current code, pls document how.


> ---
>  hw/virtio/virtio-bus.c         | 108 +++++++++++++++++++++++++++++++++++++++++
>  include/hw/virtio/virtio-bus.h |  14 ++++++
>  2 files changed, 122 insertions(+)
> 
> diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c
> index 574f0e2..501300f 100644
> --- a/hw/virtio/virtio-bus.c
> +++ b/hw/virtio/virtio-bus.c
> @@ -146,6 +146,114 @@ void virtio_bus_set_vdev_config(VirtioBusState *bus, uint8_t *config)
>      }
>  }
>  
> +static int set_host_notifier_internal(DeviceState *proxy, VirtioBusState *bus,
> +                                      int n, bool assign, bool set_handler)
> +{
> +    VirtIODevice *vdev = virtio_bus_get_device(bus);
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
> +    VirtQueue *vq = virtio_get_queue(vdev, n);
> +    EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
> +    int r = 0;
> +
> +    if (assign) {
> +        r = event_notifier_init(notifier, 1);
> +        if (r < 0) {
> +            error_report("%s: unable to init event notifier: %d", __func__, r);
> +            return r;
> +        }
> +        virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
> +        r = k->ioeventfd_assign(proxy, notifier, n, assign);
> +        if (r < 0) {
> +            error_report("%s: unable to assign ioeventfd: %d", __func__, r);
> +            virtio_queue_set_host_notifier_fd_handler(vq, false, false);
> +            event_notifier_cleanup(notifier);
> +            return r;
> +        }
> +    } else {
> +        virtio_queue_set_host_notifier_fd_handler(vq, false, false);
> +        k->ioeventfd_assign(proxy, notifier, n, assign);
> +        event_notifier_cleanup(notifier);
> +    }
> +    return r;
> +}
> +
> +void virtio_bus_start_ioeventfd(VirtioBusState *bus)
> +{
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
> +    DeviceState *proxy = DEVICE(BUS(bus)->parent);
> +    VirtIODevice *vdev;
> +    int n, r;
> +
> +    if (!k->ioeventfd_started || k->ioeventfd_started(proxy)) {
> +        return;
> +    }
> +    if (!k->ioeventfd_disabled(proxy)) {
> +        return;
> +    }
> +    vdev = virtio_bus_get_device(bus);
> +    for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
> +        if (!virtio_queue_get_num(vdev, n)) {
> +            continue;
> +        }
> +        r = set_host_notifier_internal(proxy, bus, n, true, true);
> +        if (r < 0) {
> +            goto assign_error;
> +        }
> +    }
> +    k->ioeventfd_set_started(proxy, true, false);
> +    return;
> +
> +assign_error:
> +    while (--n >= 0) {
> +        if (!virtio_queue_get_num(vdev, n)) {
> +            continue;
> +        }
> +
> +        r = set_host_notifier_internal(proxy, bus, n, false, false);
> +        assert(r >= 0);
> +    }
> +    k->ioeventfd_set_started(proxy, false, true);
> +    error_report("%s: failed. Fallback to userspace (slower).", __func__);
> +}
> +
> +void virtio_bus_stop_ioeventfd(VirtioBusState *bus, bool assign)
> +{
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
> +    DeviceState *proxy = DEVICE(BUS(bus)->parent);
> +    VirtIODevice *vdev;
> +    int n, r;
> +
> +    if (!k->ioeventfd_started || !k->ioeventfd_started(proxy)) {
> +        return;
> +    }
> +    vdev = virtio_bus_get_device(bus);
> +    for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
> +        if (!virtio_queue_get_num(vdev, n)) {
> +            continue;
> +        }
> +        r = set_host_notifier_internal(proxy, bus, n, assign, false);
> +        assert(r >= 0);
> +    }
> +    k->ioeventfd_set_started(proxy, false, false);
> +}
> +
> +int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)


Could you add documentation for what does "assign" mean here?
It was there as an internal API, but now it's external
so needs better docs.

> +{
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
> +    DeviceState *proxy = DEVICE(BUS(bus)->parent);
> +
> +    if (!k->ioeventfd_started) {
> +        return -ENOSYS;
> +    }
> +    /* Stop using the generic ioeventfd, we are doing eventfd handling
> +     * ourselves below */
> +    k->ioeventfd_set_disabled(proxy, assign);
> +    if (assign) {
> +        virtio_bus_stop_ioeventfd(bus, assign);
> +    }

Need comment to explain why don't we start on !assign.

> +    return set_host_notifier_internal(proxy, bus, n, assign, false);
> +}
> +
>  static char *virtio_bus_get_dev_path(DeviceState *dev)
>  {
>      BusState *bus = qdev_get_parent_bus(dev);
> diff --git a/include/hw/virtio/virtio-bus.h b/include/hw/virtio/virtio-bus.h
> index 3f2c136..0281cbf 100644
> --- a/include/hw/virtio/virtio-bus.h
> +++ b/include/hw/virtio/virtio-bus.h
> @@ -71,6 +71,16 @@ typedef struct VirtioBusClass {
>      void (*device_unplugged)(DeviceState *d);
>      int (*query_nvectors)(DeviceState *d);
>      /*
> +     * ioeventfd handling: if the transport implements ioeventfd_started,
> +     * it must implement the other ioeventfd callbacks as well
> +     */
> +    bool (*ioeventfd_started)(DeviceState *d);
> +    void (*ioeventfd_set_started)(DeviceState *d, bool started, bool err);
> +    bool (*ioeventfd_disabled)(DeviceState *d);
> +    void (*ioeventfd_set_disabled)(DeviceState *d, bool disabled);
> +    int (*ioeventfd_assign)(DeviceState *d, EventNotifier *notifier,
> +                            int n, bool assign);
> +    /*
>       * Does the transport have variable vring alignment?
>       * (ie can it ever call virtio_queue_set_align()?)
>       * Note that changing this will break migration for this transport.
> @@ -111,4 +121,8 @@ static inline VirtIODevice *virtio_bus_get_device(VirtioBusState *bus)
>      return (VirtIODevice *)qdev;
>  }
>  
> +void virtio_bus_start_ioeventfd(VirtioBusState *bus);
> +void virtio_bus_stop_ioeventfd(VirtioBusState *bus, bool assign);
> +int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign);
> +
>  #endif /* VIRTIO_BUS_H */
> -- 
> 2.6.5