net/virtio: get all pending Rx packets in vectorized paths

The loop to read packets does not take all packets as the number of
available packets (nb_used) is decremented in the loop.
Take all available packets provides a performance improvement of 3%.

Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: stable@dpdk.org
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

diff --git a/drivers/net/virtio/virtio_rxtx_simple_neon.c b/drivers/net/virtio/virtio_rxtx_simple_neon.c
index 70e89fc..992e71f 100644 (file)
--- a/drivers/net/virtio/virtio_rxtx_simple_neon.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_neon.c
@@ -42,7 +42,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
        struct virtnet_rx *rxvq = rx_queue;
        struct virtqueue *vq = rxvq->vq;
        struct virtio_hw *hw = vq->hw;
-       uint16_t nb_used;
+       uint16_t nb_used, nb_total;
        uint16_t desc_idx;
        struct vring_used_elem *rused;
        struct rte_mbuf **sw_ring;
@@ -106,9 +106,10 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                        virtqueue_notify(vq);
        }
 
+       nb_total = nb_used;
        ref_rx_pkts = rx_pkts;
        for (nb_pkts_received = 0;
-               nb_pkts_received < nb_used;) {
+               nb_pkts_received < nb_total;) {
                uint64x2_t desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
                uint64x2_t mbp[RTE_VIRTIO_DESC_PER_LOOP / 2];
                uint64x2_t pkt_mb[RTE_VIRTIO_DESC_PER_LOOP];

diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
index cb1610e..f9ec4ae 100644 (file)
--- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
@@ -43,7 +43,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
        struct virtnet_rx *rxvq = rx_queue;
        struct virtqueue *vq = rxvq->vq;
        struct virtio_hw *hw = vq->hw;
-       uint16_t nb_used;
+       uint16_t nb_used, nb_total;
        uint16_t desc_idx;
        struct vring_used_elem *rused;
        struct rte_mbuf **sw_ring;
@@ -108,9 +108,10 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                        virtqueue_notify(vq);
        }
 
+       nb_total = nb_used;
        ref_rx_pkts = rx_pkts;
        for (nb_pkts_received = 0;
-               nb_pkts_received < nb_used;) {
+               nb_pkts_received < nb_total;) {
                __m128i desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
                __m128i mbp[RTE_VIRTIO_DESC_PER_LOOP / 2];
                __m128i pkt_mb[RTE_VIRTIO_DESC_PER_LOOP];