vhost: avoid memory barriers when no descriptors dequeued

In both split and packed dequeue paths, flush_shadow_used_ring
and vhost_ring_call variants gets called even if not packets
have been dequeued, and so no descriptors updates happened.

It has an impact on CPU pipeline, as memory barriers are used
in these functions.

This patch don't call these functions if no descriptors have
been dequeued. The performance gain with split ring when
dequeue zero-copy is disabled should be null, but should be
noticeable with packed ring or dequeue zero-copy enabled.

Fixes: ae999ce49dcb ("vhost: add Tx support for packed ring")
Fixes: 915cf9404225 ("vhost: use shadow used ring in dequeue path")
Cc: stable@dpdk.org
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Jens Freimann <jfreimann@redhat.com>
Tested-by: Jens Freimann <jfreimann@redhat.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>

diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 1c31c05..8ad30c9 100644 (file)
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1360,8 +1360,10 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
                        }
                }
 
-               flush_shadow_used_ring_split(dev, vq);
-               vhost_vring_call_split(dev, vq);
+               if (likely(vq->shadow_used_idx)) {
+                       flush_shadow_used_ring_split(dev, vq);
+                       vhost_vring_call_split(dev, vq);
+               }
        }
 
        rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
@@ -1440,8 +1442,10 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
                do_data_copy_dequeue(vq);
                if (unlikely(i < count))
                        vq->shadow_used_idx = i;
-               flush_shadow_used_ring_split(dev, vq);
-               vhost_vring_call_split(dev, vq);
+               if (likely(vq->shadow_used_idx)) {
+                       flush_shadow_used_ring_split(dev, vq);
+                       vhost_vring_call_split(dev, vq);
+               }
        }
 
        return i;
@@ -1476,8 +1480,10 @@ virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
                        }
                }
 
-               flush_shadow_used_ring_packed(dev, vq);
-               vhost_vring_call_packed(dev, vq);
+               if (likely(vq->shadow_used_idx)) {
+                       flush_shadow_used_ring_packed(dev, vq);
+                       vhost_vring_call_packed(dev, vq);
+               }
        }
 
        VHOST_LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
@@ -1555,8 +1561,10 @@ virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
                do_data_copy_dequeue(vq);
                if (unlikely(i < count))
                        vq->shadow_used_idx = i;
-               flush_shadow_used_ring_packed(dev, vq);
-               vhost_vring_call_packed(dev, vq);
+               if (likely(vq->shadow_used_idx)) {
+                       flush_shadow_used_ring_packed(dev, vq);
+                       vhost_vring_call_packed(dev, vq);
+               }
        }
 
        return i;