The code used to limit the maximum size of tx queue for others backends than vhost_user since the introduction of configurable tx queue size in 9b02e1618cf2 ("virtio-net: enable configurable tx queue size").
As vhost_user, vhost_vdpa devices should deal with memory region crosses already, so let's use the full tx size. Signed-off-by: Eugenio Pérez <epere...@redhat.com> --- hw/net/virtio-net.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 49cd13314a..b1769bfee0 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -629,17 +629,20 @@ static int virtio_net_max_tx_queue_size(VirtIONet *n) NetClientState *peer = n->nic_conf.peers.ncs[0]; /* - * Backends other than vhost-user don't support max queue size. + * Backends other than vhost-user or vhost-vdpa don't support max queue + * size. */ if (!peer) { return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE; } - if (peer->info->type != NET_CLIENT_DRIVER_VHOST_USER) { + switch(peer->info->type) { + case NET_CLIENT_DRIVER_VHOST_USER: + case NET_CLIENT_DRIVER_VHOST_VDPA: + return VIRTQUEUE_MAX_SIZE; + default: return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE; - } - - return VIRTQUEUE_MAX_SIZE; + }; } static int peer_attach(VirtIONet *n, int index) -- 2.27.0