On Fri, Jan 11, 2013 at 7:37 AM, Rusty Russell <rusty@xxxxxxxxxxxxxxx> wrote: >virtio_host: host-side implementation of virtio rings (untested!) > >Getting use of virtio rings correct is tricky, and a recent patch saw >an implementation of in-kernel rings (as separate from userspace). How do you see the in-kernel API for this? I would like to see something similar to my previous patches, where we extend the virtqueue API. E.g. something like this: struct virtqueue *vring_new_virtqueueh(unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, void *pages, void (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name); int virtqueueh_get_iov(struct virtqueue *vqh, struct vringh_iov *riov, struct vringh_iov *wiov, gfp_t gfp); int virtqueueh_add_iov(struct virtqueue *vqh, struct vringh_iov *riov, struct vringh_iov *wiov); I guess implementation of the host-virtqueue should stay in drivers/virtio? Regards, Sjur _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
