net/virtio: fix vectorized Rx queue rearm

[ upstream commit d990884 ]

When Rx queue worked in vectorized mode and rxd <= 512, under traffic of
high PPS rate, testpmd often start and receive packets of rxd without
further growth.

Testpmd started with rxq flush which tried to rx MAX_PKT_BURST(512)
packets and drop. When Rx burst size >= Rx queue size, all descriptors
in used queue consumed without rearm, device can't receive more packets.
The next Rx burst returned at once since no used descriptors found,
rearm logic was skipped, rx vq kept in starving state.

To avoid rx vq starving, this patch always check the available queue,
rearm if needed even no used descriptor reported by device.

Fixes: fc3d662 ("virtio: add vector Rx")
Fixes: 2d7c371 ("net/virtio: add NEON based Rx handler")
Fixes: 52b5a70 ("net/virtio: add Altivec Rx")

Signed-off-by: Xueming Li <xuemingl@nvidia.com>
Reviewed-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

drivers/net/virtio/virtio_rxtx_simple_altivec.c

@@ -85,6 +85,12 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	if (unlikely(nb_pkts < RTE_VIRTIO_DESC_PER_LOOP))
 		return 0;
 
+	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
+		virtio_rxq_rearm_vec(rxvq);
+		if (unlikely(virtqueue_kick_prepare(vq)))
+			virtqueue_notify(vq);
+	}
+
 	nb_used = virtqueue_nused(vq);
 
 	rte_compiler_barrier();
@@ -102,12 +108,6 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 
 	rte_prefetch0(rused);
 
-	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
-		virtio_rxq_rearm_vec(rxvq);
-		if (unlikely(virtqueue_kick_prepare(vq)))
-			virtqueue_notify(vq);
-	}
-
 	nb_total = nb_used;
 	ref_rx_pkts = rx_pkts;
 	for (nb_pkts_received = 0;

drivers/net/virtio/virtio_rxtx_simple_neon.c

@@ -84,6 +84,12 @@ virtio_recv_pkts_vec(void *rx_queue,
 	if (unlikely(nb_pkts < RTE_VIRTIO_DESC_PER_LOOP))
 		return 0;
 
+	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
+		virtio_rxq_rearm_vec(rxvq);
+		if (unlikely(virtqueue_kick_prepare(vq)))
+			virtqueue_notify(vq);
+	}
+
 	/* virtqueue_nused has a load-acquire or rte_io_rmb inside */
 	nb_used = virtqueue_nused(vq);
 
@@ -100,12 +106,6 @@ virtio_recv_pkts_vec(void *rx_queue,
 
 	rte_prefetch_non_temporal(rused);
 
-	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
-		virtio_rxq_rearm_vec(rxvq);
-		if (unlikely(virtqueue_kick_prepare(vq)))
-			virtqueue_notify(vq);
-	}
-
 	nb_total = nb_used;
 	ref_rx_pkts = rx_pkts;
 	for (nb_pkts_received = 0;

drivers/net/virtio/virtio_rxtx_simple_sse.c

@@ -85,6 +85,12 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	if (unlikely(nb_pkts < RTE_VIRTIO_DESC_PER_LOOP))
 		return 0;
 
+	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
+		virtio_rxq_rearm_vec(rxvq);
+		if (unlikely(virtqueue_kick_prepare(vq)))
+			virtqueue_notify(vq);
+	}
+
 	nb_used = virtqueue_nused(vq);
 
 	if (unlikely(nb_used == 0))
@@ -100,12 +106,6 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 
 	rte_prefetch0(rused);
 
-	if (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) {
-		virtio_rxq_rearm_vec(rxvq);
-		if (unlikely(virtqueue_kick_prepare(vq)))
-			virtqueue_notify(vq);
-	}
-
 	nb_total = nb_used;
 	ref_rx_pkts = rx_pkts;
 	for (nb_pkts_received = 0;