search for: virtio_queue_set_last_avail_idx

..._vring_state state = { - .index = idx - dev->vq_index + .index = vhost_vq_index, }; int r; assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); @@ -759,6 +793,20 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, } virtio_queue_set_last_avail_idx(vdev, idx, state.num); virtio_queue_invalidate_signalled_used(vdev, idx); + + /* In the cross-endian case, we need to reset the vring endianness to + * native as legacy devices expect so by default. + */ + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) && + virt...

Hi, This series allows QEMU to use vhost with legacy virtio devices when host and target don't have the same endianness. Only network devices are covered for the moment. I had already posted a series some monthes ago but it never got reviewed. Moreover, the underlying kernel support was entirely re-written and is still waiting to be applied by Michael. I hence post as RFC. The corresponding

Hi, This series allows QEMU to use vhost with legacy virtio devices when host and target don't have the same endianness. Only network devices are covered for the moment. I had already posted a series some monthes ago but it never got reviewed. Moreover, the underlying kernel support was entirely re-written and is still waiting to be applied by Michael. I hence post as RFC. The corresponding