vhost: relax full barriers for desc flags

[dpdk.git] / lib / librte_vhost / virtio_net.c

diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 6c51286..b779034 100644 (file)
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -222,8 +222,9 @@ vhost_flush_dequeue_shadow_packed(struct virtio_net *dev,
        struct vring_used_elem_packed *used_elem = &vq->shadow_used_packed[0];
 
        vq->desc_packed[vq->shadow_last_used_idx].id = used_elem->id;
-       rte_smp_wmb();
-       vq->desc_packed[vq->shadow_last_used_idx].flags = used_elem->flags;
+       /* desc flags is the synchronization point for virtio packed vring */
+       __atomic_store_n(&vq->desc_packed[vq->shadow_last_used_idx].flags,
+                        used_elem->flags, __ATOMIC_RELEASE);
 
        vhost_log_cache_used_vring(dev, vq, vq->shadow_last_used_idx *
                                   sizeof(struct vring_packed_desc),
@@ -1281,8 +1282,6 @@ virtio_dev_rx_batch_packed(struct virtio_net *dev,
                        return -1;
        }
 
-       rte_smp_rmb();
-
        vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
                lens[i] = descs[avail_idx + i].len;
 
@@ -1343,7 +1342,6 @@ virtio_dev_rx_single_packed(struct virtio_net *dev,
        struct buf_vector buf_vec[BUF_VECTOR_MAX];
        uint16_t nr_descs = 0;
 
-       rte_smp_rmb();
        if (unlikely(vhost_enqueue_single_packed(dev, vq, pkt, buf_vec,
                                                 &nr_descs) < 0)) {
                VHOST_LOG_DATA(DEBUG,
@@ -1497,13 +1495,10 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
        struct async_inflight_info *pkts_info = vq->async_pkts_info;
        int n_pkts = 0;
 
-       avail_head = __atomic_load_n(&vq->avail->idx, __ATOMIC_ACQUIRE);
-
        /*
-        * The ordering between avail index and
-        * desc reads needs to be enforced.
+        * The ordering between avail index and desc reads need to be enforced.
         */
-       rte_smp_rmb();
+       avail_head = __atomic_load_n(&vq->avail->idx, __ATOMIC_ACQUIRE);
 
        rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);