vhost: replace SMP with thread fence for control path

[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 10dec5e..fec08b2 100644 (file)
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -171,7 +171,8 @@ vhost_flush_enqueue_shadow_packed(struct virtio_net *dev,
                        used_idx -= vq->size;
        }
 
-       rte_smp_wmb();
+       /* The ordering for storing desc flags needs to be enforced. */
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        for (i = 0; i < vq->shadow_used_idx; i++) {
                uint16_t flags;
@@ -222,8 +223,9 @@ 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),
@@ -253,7 +255,7 @@ vhost_flush_enqueue_batch_packed(struct virtio_net *dev,
                vq->desc_packed[vq->last_used_idx + i].len = lens[i];
        }
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
                vq->desc_packed[vq->last_used_idx + i].flags = flags;
@@ -312,7 +314,7 @@ vhost_shadow_dequeue_batch_packed(struct virtio_net *dev,
                vq->desc_packed[vq->last_used_idx + i].len = 0;
        }
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
        vhost_for_each_try_unroll(i, begin, PACKED_BATCH_SIZE)
                vq->desc_packed[vq->last_used_idx + i].flags = flags;
 
@@ -1281,8 +1283,6 @@ 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 +1343,6 @@ 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 +1496,10 @@ 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)]);
 
@@ -1567,7 +1563,7 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
                        src_it = it_pool;
                        dst_it = it_pool + 1;
                        segs_await = 0;
-                       vq->async_pkts_inflight_n += n_pkts;
+                       vq->async_pkts_inflight_n += pkt_burst_idx;
 
                        if (unlikely(n_pkts < (int)pkt_burst_idx)) {
                                /*
@@ -1587,7 +1583,7 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
        if (pkt_burst_idx) {
                n_pkts = vq->async_ops.transfer_data(dev->vid,
                                queue_id, tdes, 0, pkt_burst_idx);
-               vq->async_pkts_inflight_n += n_pkts;
+               vq->async_pkts_inflight_n += pkt_burst_idx;
 
                if (unlikely(n_pkts < (int)pkt_burst_idx))
                        pkt_err = pkt_burst_idx - n_pkts;
@@ -1667,7 +1663,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
                        queue_id, 0, count - vq->async_last_pkts_n);
        n_pkts_cpl += vq->async_last_pkts_n;
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        while (likely((n_pkts_put < count) && n_inflight)) {
                uint16_t info_idx = (start_idx + n_pkts_put) & (vq_size - 1);
@@ -2251,7 +2247,7 @@ vhost_reserve_avail_batch_packed(struct virtio_net *dev,
                        return -1;
        }
 
-       rte_smp_rmb();
+       rte_atomic_thread_fence(__ATOMIC_ACQUIRE);
 
        vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
                lens[i] = descs[avail_idx + i].len;