New upstream version 17.11-rc3

Change-Id: I6a5baa40612fe0c20f30b5fa773a6cbbac63a685
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

16 files changed, 256 insertions, 96 deletions

diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
index b21b8781..f2b5d1c3 100644
--- a/drivers/net/virtio/Makefile
+++ b/drivers/net/virtio/Makefile
@@ -38,6 +38,12 @@ LIB = librte_pmd_virtio.a
 
 CFLAGS += -O3
 CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
+LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
+LDLIBS += -lrte_bus_pci
+ifeq ($(CONFIG_RTE_VIRTIO_USER),y)
+LDLIBS += -lrte_bus_vdev
+endif
 
 EXPORT_MAP := rte_pmd_virtio_version.map
 
diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index e320811e..d2576d5e 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -46,9 +46,11 @@
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
 #include <rte_pci.h>
+#include <rte_bus_pci.h>
 #include <rte_ether.h>
 #include <rte_common.h>
 #include <rte_errno.h>
+#include <rte_cpuflags.h>
 
 #include <rte_memory.h>
 #include <rte_eal.h>
@@ -72,11 +74,12 @@ static void virtio_dev_info_get(struct rte_eth_dev *dev,
 				struct rte_eth_dev_info *dev_info);
 static int virtio_dev_link_update(struct rte_eth_dev *dev,
 	int wait_to_complete);
+static int virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask);
 
 static void virtio_set_hwaddr(struct virtio_hw *hw);
 static void virtio_get_hwaddr(struct virtio_hw *hw);
 
-static void virtio_dev_stats_get(struct rte_eth_dev *dev,
+static int virtio_dev_stats_get(struct rte_eth_dev *dev,
 				 struct rte_eth_stats *stats);
 static int virtio_dev_xstats_get(struct rte_eth_dev *dev,
 				 struct rte_eth_xstat *xstats, unsigned n);
@@ -162,7 +165,7 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 	uint32_t head, i;
 	int k, sum = 0;
 	virtio_net_ctrl_ack status = ~0;
-	struct virtio_pmd_ctrl result;
+	struct virtio_pmd_ctrl *result;
 	struct virtqueue *vq;
 
 	ctrl->status = status;
@@ -253,10 +256,9 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 	PMD_INIT_LOG(DEBUG, "vq->vq_free_cnt=%d\nvq->vq_desc_head_idx=%d",
 			vq->vq_free_cnt, vq->vq_desc_head_idx);
 
-	memcpy(&result, cvq->virtio_net_hdr_mz->addr,
-			sizeof(struct virtio_pmd_ctrl));
+	result = cvq->virtio_net_hdr_mz->addr;
 
-	return result.status;
+	return result->status;
 }
 
 static int
@@ -426,10 +428,10 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 
 	memset(mz->addr, 0, mz->len);
 
-	vq->vq_ring_mem = mz->phys_addr;
+	vq->vq_ring_mem = mz->iova;
 	vq->vq_ring_virt_mem = mz->addr;
 	PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem:      0x%" PRIx64,
-		     (uint64_t)mz->phys_addr);
+		     (uint64_t)mz->iova);
 	PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%" PRIx64,
 		     (uint64_t)(uintptr_t)mz->addr);
 
@@ -474,13 +476,13 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 		txvq->port_id = dev->data->port_id;
 		txvq->mz = mz;
 		txvq->virtio_net_hdr_mz = hdr_mz;
-		txvq->virtio_net_hdr_mem = hdr_mz->phys_addr;
+		txvq->virtio_net_hdr_mem = hdr_mz->iova;
 	} else if (queue_type == VTNET_CQ) {
 		cvq = &vq->cq;
 		cvq->vq = vq;
 		cvq->mz = mz;
 		cvq->virtio_net_hdr_mz = hdr_mz;
-		cvq->virtio_net_hdr_mem = hdr_mz->phys_addr;
+		cvq->virtio_net_hdr_mem = hdr_mz->iova;
 		memset(cvq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE);
 
 		hw->cvq = cvq;
@@ -491,7 +493,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 	 * VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information.
 	 */
 	if (!hw->virtio_user_dev)
-		vq->offset = offsetof(struct rte_mbuf, buf_physaddr);
+		vq->offset = offsetof(struct rte_mbuf, buf_iova);
 	else {
 		vq->vq_ring_mem = (uintptr_t)mz->addr;
 		vq->offset = offsetof(struct rte_mbuf, buf_addr);
@@ -779,6 +781,7 @@ static const struct eth_dev_ops virtio_eth_dev_ops = {
 	.stats_reset             = virtio_dev_stats_reset,
 	.xstats_reset            = virtio_dev_stats_reset,
 	.link_update             = virtio_dev_link_update,
+	.vlan_offload_set        = virtio_dev_vlan_offload_set,
 	.rx_queue_setup          = virtio_dev_rx_queue_setup,
 	.rx_queue_intr_enable    = virtio_dev_rx_queue_intr_enable,
 	.rx_queue_intr_disable   = virtio_dev_rx_queue_intr_disable,
@@ -964,10 +967,12 @@ virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
 	return count;
 }
 
-static void
+static int
 virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
 	virtio_update_stats(dev, stats);
+
+	return 0;
 }
 
 static void
@@ -1235,14 +1240,36 @@ virtio_interrupt_handler(void *param)
 
 }
 
+/* set rx and tx handlers according to what is supported */
 static void
-rx_func_get(struct rte_eth_dev *eth_dev)
+set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 {
 	struct virtio_hw *hw = eth_dev->data->dev_private;
-	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF))
+
+	if (hw->use_simple_rx) {
+		PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u",
+			eth_dev->data->port_id);
+		eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
+	} else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+		PMD_INIT_LOG(INFO,
+			"virtio: using mergeable buffer Rx path on port %u",
+			eth_dev->data->port_id);
 		eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts;
-	else
+	} else {
+		PMD_INIT_LOG(INFO, "virtio: using standard Rx path on port %u",
+			eth_dev->data->port_id);
 		eth_dev->rx_pkt_burst = &virtio_recv_pkts;
+	}
+
+	if (hw->use_simple_tx) {
+		PMD_INIT_LOG(INFO, "virtio: using simple Tx path on port %u",
+			eth_dev->data->port_id);
+		eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple;
+	} else {
+		PMD_INIT_LOG(INFO, "virtio: using standard Tx path on port %u",
+			eth_dev->data->port_id);
+		eth_dev->tx_pkt_burst = virtio_xmit_pkts;
+	}
 }
 
 /* Only support 1:1 queue/interrupt mapping so far.
@@ -1360,15 +1387,12 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 		rte_eth_copy_pci_info(eth_dev, pci_dev);
 	}
 
-	eth_dev->data->dev_flags = RTE_ETH_DEV_DETACHABLE;
 	/* If host does not support both status and MSI-X then disable LSC */
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS) && hw->use_msix)
 		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
 	else
 		eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
 
-	rx_func_get(eth_dev);
-
 	/* Setting up rx_header size for the device */
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) ||
 	    vtpci_with_feature(hw, VIRTIO_F_VERSION_1))
@@ -1534,7 +1558,6 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	RTE_BUILD_BUG_ON(RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr_mrg_rxbuf));
 
 	eth_dev->dev_ops = &virtio_eth_dev_ops;
-	eth_dev->tx_pkt_burst = &virtio_xmit_pkts;
 
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
 		if (!hw->virtio_user_dev) {
@@ -1544,12 +1567,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 		}
 
 		virtio_set_vtpci_ops(hw);
-		if (hw->use_simple_rxtx) {
-			eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple;
-			eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
-		} else {
-			rx_func_get(eth_dev);
-		}
+		set_rxtx_funcs(eth_dev);
+
 		return 0;
 	}
 
@@ -1659,9 +1678,11 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 {
 	const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 	struct virtio_hw *hw = dev->data->dev_private;
+	uint64_t req_features;
 	int ret;
 
 	PMD_INIT_LOG(DEBUG, "configure");
+	req_features = VIRTIO_PMD_DEFAULT_GUEST_FEATURES;
 
 	if (dev->data->dev_conf.intr_conf.rxq) {
 		ret = virtio_init_device(dev, hw->req_guest_features);
@@ -1669,16 +1690,37 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return ret;
 	}
 
-	/* Virtio does L4 checksum but not L3! */
-	if (rxmode->hw_ip_checksum) {
-		PMD_DRV_LOG(NOTICE,
-			    "virtio does not support IP checksum");
+	/* The name hw_ip_checksum is a bit confusing since it can be
+	 * set by the application to request L3 and/or L4 checksums. In
+	 * case of virtio, only L4 checksum is supported.
+	 */
+	if (rxmode->hw_ip_checksum)
+		req_features |= (1ULL << VIRTIO_NET_F_GUEST_CSUM);
+
+	if (rxmode->enable_lro)
+		req_features |=
+			(1ULL << VIRTIO_NET_F_GUEST_TSO4) |
+			(1ULL << VIRTIO_NET_F_GUEST_TSO6);
+
+	/* if request features changed, reinit the device */
+	if (req_features != hw->req_guest_features) {
+		ret = virtio_init_device(dev, req_features);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (rxmode->hw_ip_checksum &&
+		!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) {
+		PMD_DRV_LOG(ERR,
+			"rx checksum not available on this host");
 		return -ENOTSUP;
 	}
 
-	if (rxmode->enable_lro) {
-		PMD_DRV_LOG(NOTICE,
-			    "virtio does not support Large Receive Offload");
+	if (rxmode->enable_lro &&
+		(!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
+			!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4))) {
+		PMD_DRV_LOG(ERR,
+			"Large Receive Offload not available on this host");
 		return -ENOTSUP;
 	}
 
@@ -1690,7 +1732,7 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 
 	if (rxmode->hw_vlan_filter
 	    && !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
-		PMD_DRV_LOG(NOTICE,
+		PMD_DRV_LOG(ERR,
 			    "vlan filtering not available on this host");
 		return -ENOTSUP;
 	}
@@ -1703,6 +1745,23 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
+	hw->use_simple_rx = 1;
+	hw->use_simple_tx = 1;
+
+#if defined RTE_ARCH_ARM64 || defined CONFIG_RTE_ARCH_ARM
+	if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) {
+		hw->use_simple_rx = 0;
+		hw->use_simple_tx = 0;
+	}
+#endif
+	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+		hw->use_simple_rx = 0;
+		hw->use_simple_tx = 0;
+	}
+
+	if (rxmode->hw_ip_checksum)
+		hw->use_simple_rx = 0;
+
 	return 0;
 }
 
@@ -1714,6 +1773,19 @@ virtio_dev_start(struct rte_eth_dev *dev)
 	struct virtnet_rx *rxvq;
 	struct virtnet_tx *txvq __rte_unused;
 	struct virtio_hw *hw = dev->data->dev_private;
+	int ret;
+
+	/* Finish the initialization of the queues */
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		ret = virtio_dev_rx_queue_setup_finish(dev, i);
+		if (ret < 0)
+			return ret;
+	}
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		ret = virtio_dev_tx_queue_setup_finish(dev, i);
+		if (ret < 0)
+			return ret;
+	}
 
 	/* check if lsc interrupt feature is enabled */
 	if (dev->data->dev_conf.intr_conf.lsc) {
@@ -1751,9 +1823,16 @@ virtio_dev_start(struct rte_eth_dev *dev)
 
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		rxvq = dev->data->rx_queues[i];
+		/* Flush the old packets */
+		virtqueue_flush(rxvq->vq);
 		virtqueue_notify(rxvq->vq);
 	}
 
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		txvq = dev->data->tx_queues[i];
+		virtqueue_notify(txvq->vq);
+	}
+
 	PMD_INIT_LOG(DEBUG, "Notified backend at initialization");
 
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
@@ -1766,6 +1845,7 @@ virtio_dev_start(struct rte_eth_dev *dev)
 		VIRTQUEUE_DUMP(txvq->vq);
 	}
 
+	set_rxtx_funcs(dev);
 	hw->started = 1;
 
 	/* Initialize Link state */
@@ -1875,6 +1955,29 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 	return (old.link_status == link.link_status) ? -1 : 0;
 }
 
+static int
+virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask)
+{
+	const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	if (mask & ETH_VLAN_FILTER_MASK) {
+		if (rxmode->hw_vlan_filter &&
+				!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
+
+			PMD_DRV_LOG(NOTICE,
+				"vlan filtering not available on this host");
+
+			return -ENOTSUP;
+		}
+	}
+
+	if (mask & ETH_VLAN_STRIP_MASK)
+		hw->vlan_strip = rxmode->hw_vlan_strip;
+
+	return 0;
+}
+
 static void
 virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 {
@@ -1904,6 +2007,8 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 	}
 	tso_mask = (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
 		(1ULL << VIRTIO_NET_F_GUEST_TSO6);
+	if ((host_features & tso_mask) == tso_mask)
+		dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO;
 
 	dev_info->tx_offload_capa = 0;
 	if (hw->guest_features & (1ULL << VIRTIO_NET_F_CSUM)) {
diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
index c3413c6d..2039bc54 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -92,10 +92,16 @@ int  virtio_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t rx_queue_id,
 		const struct rte_eth_rxconf *rx_conf,
 		struct rte_mempool *mb_pool);
 
+int virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev,
+				uint16_t rx_queue_id);
+
 int  virtio_dev_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id,
 		uint16_t nb_tx_desc, unsigned int socket_id,
 		const struct rte_eth_txconf *tx_conf);
 
+int virtio_dev_tx_queue_setup_finish(struct rte_eth_dev *dev,
+				uint16_t tx_queue_id);
+
 uint16_t virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		uint16_t nb_pkts);
 
diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c
index e6da6802..55b717c0 100644
--- a/drivers/net/virtio/virtio_pci.c
+++ b/drivers/net/virtio/virtio_pci.c
@@ -553,7 +553,7 @@ get_cfg_addr(struct rte_pci_device *dev, struct virtio_pci_cap *cap)
 	uint32_t offset = cap->offset;
 	uint8_t *base;
 
-	if (bar > 5) {
+	if (bar >= PCI_MAX_RESOURCE) {
 		PMD_INIT_LOG(ERR, "invalid bar: %u", bar);
 		return NULL;
 	}
diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h
index 18caebdd..36d452c0 100644
--- a/drivers/net/virtio/virtio_pci.h
+++ b/drivers/net/virtio/virtio_pci.h
@@ -37,6 +37,7 @@
 #include <stdint.h>
 
 #include <rte_pci.h>
+#include <rte_bus_pci.h>
 #include <rte_ethdev.h>
 
 struct virtqueue;
@@ -259,8 +260,9 @@ struct virtio_hw {
 	uint8_t	    vlan_strip;
 	uint8_t	    use_msix;
 	uint8_t     modern;
-	uint8_t     use_simple_rxtx;
-	uint8_t     port_id;
+	uint8_t     use_simple_rx;
+	uint8_t     use_simple_tx;
+	uint16_t    port_id;
 	uint8_t     mac_addr[ETHER_ADDR_LEN];
 	uint32_t    notify_off_multiplier;
 	uint8_t     *isr;
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index e30377c5..390c137c 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -39,7 +39,6 @@
 
 #include <rte_cycles.h>
 #include <rte_memory.h>
-#include <rte_memzone.h>
 #include <rte_branch_prediction.h>
 #include <rte_mempool.h>
 #include <rte_malloc.h>
@@ -50,7 +49,6 @@
 #include <rte_string_fns.h>
 #include <rte_errno.h>
 #include <rte_byteorder.h>
-#include <rte_cpuflags.h>
 #include <rte_net.h>
 #include <rte_ip.h>
 #include <rte_udp.h>
@@ -81,7 +79,7 @@ virtio_dev_rx_queue_done(void *rxq, uint16_t offset)
 	return VIRTQUEUE_NUSED(vq) >= offset;
 }
 
-static void
+void
 vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx)
 {
 	struct vring_desc *dp, *dp_tail;
@@ -300,6 +298,10 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 		/* prepend cannot fail, checked by caller */
 		hdr = (struct virtio_net_hdr *)
 			rte_pktmbuf_prepend(cookie, head_size);
+		/* rte_pktmbuf_prepend() counts the hdr size to the pkt length,
+		 * which is wrong. Below subtract restores correct pkt size.
+		 */
+		cookie->pkt_len -= head_size;
 		/* if offload disabled, it is not zeroed below, do it now */
 		if (offload == 0) {
 			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
@@ -421,9 +423,6 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	struct virtio_hw *hw = dev->data->dev_private;
 	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
 	struct virtnet_rx *rxvq;
-	int error, nbufs;
-	struct rte_mbuf *m;
-	uint16_t desc_idx;
 
 	PMD_INIT_FUNC_TRACE();
 
@@ -440,12 +439,26 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	}
 	dev->data->rx_queues[queue_idx] = rxvq;
 
+	return 0;
+}
+
+int
+virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx)
+{
+	uint16_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_RQ_QUEUE_IDX;
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
+	struct virtnet_rx *rxvq = &vq->rxq;
+	struct rte_mbuf *m;
+	uint16_t desc_idx;
+	int error, nbufs;
+
+	PMD_INIT_FUNC_TRACE();
 
 	/* Allocate blank mbufs for the each rx descriptor */
 	nbufs = 0;
-	error = ENOSPC;
 
-	if (hw->use_simple_rxtx) {
+	if (hw->use_simple_rx) {
 		for (desc_idx = 0; desc_idx < vq->vq_nentries;
 		     desc_idx++) {
 			vq->vq_ring.avail->ring[desc_idx] = desc_idx;
@@ -467,7 +480,7 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			break;
 
 		/* Enqueue allocated buffers */
-		if (hw->use_simple_rxtx)
+		if (hw->use_simple_rx)
 			error = virtqueue_enqueue_recv_refill_simple(vq, m);
 		else
 			error = virtqueue_enqueue_recv_refill(vq, m);
@@ -490,31 +503,6 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	return 0;
 }
 
-static void
-virtio_update_rxtx_handler(struct rte_eth_dev *dev,
-			   const struct rte_eth_txconf *tx_conf)
-{
-	uint8_t use_simple_rxtx = 0;
-	struct virtio_hw *hw = dev->data->dev_private;
-
-#if defined RTE_ARCH_X86
-	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE3))
-		use_simple_rxtx = 1;
-#elif defined RTE_ARCH_ARM64 || defined CONFIG_RTE_ARCH_ARM
-	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
-		use_simple_rxtx = 1;
-#endif
-	/* Use simple rx/tx func if single segment and no offloads */
-	if (use_simple_rxtx &&
-	    (tx_conf->txq_flags & VIRTIO_SIMPLE_FLAGS) == VIRTIO_SIMPLE_FLAGS &&
-	    !vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
-		PMD_INIT_LOG(INFO, "Using simple rx/tx path");
-		dev->tx_pkt_burst = virtio_xmit_pkts_simple;
-		dev->rx_pkt_burst = virtio_recv_pkts_vec;
-		hw->use_simple_rxtx = use_simple_rxtx;
-	}
-}
-
 /*
  * struct rte_eth_dev *dev: Used to update dev
  * uint16_t nb_desc: Defaults to values read from config space
@@ -534,11 +522,12 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
 	struct virtnet_tx *txvq;
 	uint16_t tx_free_thresh;
-	uint16_t desc_idx;
 
 	PMD_INIT_FUNC_TRACE();
 
-	virtio_update_rxtx_handler(dev, tx_conf);
+	/* cannot use simple rxtx funcs with multisegs or offloads */
+	if ((tx_conf->txq_flags & VIRTIO_SIMPLE_FLAGS) != VIRTIO_SIMPLE_FLAGS)
+		hw->use_simple_tx = 0;
 
 	if (nb_desc == 0 || nb_desc > vq->vq_nentries)
 		nb_desc = vq->vq_nentries;
@@ -563,9 +552,24 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
 
 	vq->vq_free_thresh = tx_free_thresh;
 
-	if (hw->use_simple_rxtx) {
-		uint16_t mid_idx  = vq->vq_nentries >> 1;
+	dev->data->tx_queues[queue_idx] = txvq;
+	return 0;
+}
 
+int
+virtio_dev_tx_queue_setup_finish(struct rte_eth_dev *dev,
+				uint16_t queue_idx)
+{
+	uint8_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_TQ_QUEUE_IDX;
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
+	uint16_t mid_idx = vq->vq_nentries >> 1;
+	struct virtnet_tx *txvq = &vq->txq;
+	uint16_t desc_idx;
+
+	PMD_INIT_FUNC_TRACE();
+
+	if (hw->use_simple_tx) {
 		for (desc_idx = 0; desc_idx < mid_idx; desc_idx++) {
 			vq->vq_ring.avail->ring[desc_idx] =
 				desc_idx + mid_idx;
@@ -587,7 +591,6 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
 
 	VIRTQUEUE_DUMP(vq);
 
-	dev->data->tx_queues[queue_idx] = txvq;
 	return 0;
 }
 
@@ -670,7 +673,7 @@ virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr)
 			 * In case of SCTP, this will be wrong since it's a CRC
 			 * but there's nothing we can do.
 			 */
-			uint16_t csum, off;
+			uint16_t csum = 0, off;
 
 			rte_raw_cksum_mbuf(m, hdr->csum_start,
 				rte_pktmbuf_pkt_len(m) - hdr->csum_start,
diff --git a/drivers/net/virtio/virtio_rxtx.h b/drivers/net/virtio/virtio_rxtx.h
index 28f82d6a..54f1e849 100644
--- a/drivers/net/virtio/virtio_rxtx.h
+++ b/drivers/net/virtio/virtio_rxtx.h
@@ -54,7 +54,7 @@ struct virtnet_rx {
 	struct rte_mempool *mpool; /**< mempool for mbuf allocation */
 
 	uint16_t queue_id;   /**< DPDK queue index. */
-	uint8_t port_id;     /**< Device port identifier. */
+	uint16_t port_id;     /**< Device port identifier. */
 
 	/* Statistics */
 	struct virtnet_stats stats;
@@ -66,10 +66,10 @@ struct virtnet_tx {
 	struct virtqueue *vq;
 	/**< memzone to populate hdr. */
 	const struct rte_memzone *virtio_net_hdr_mz;
-	phys_addr_t virtio_net_hdr_mem;  /**< hdr for each xmit packet */
+	rte_iova_t virtio_net_hdr_mem;   /**< hdr for each xmit packet */
 
 	uint16_t    queue_id;            /**< DPDK queue index. */
-	uint8_t     port_id;             /**< Device port identifier. */
+	uint16_t    port_id;             /**< Device port identifier. */
 
 	/* Statistics */
 	struct virtnet_stats stats;
@@ -81,9 +81,9 @@ struct virtnet_ctl {
 	struct virtqueue *vq;
 	/**< memzone to populate hdr. */
 	const struct rte_memzone *virtio_net_hdr_mz;
-	phys_addr_t virtio_net_hdr_mem; /**< hdr for each xmit packet */
-	uint8_t port_id;                /**< Device port identifier. */
-	const struct rte_memzone *mz;   /**< mem zone to populate RX ring. */
+	rte_iova_t virtio_net_hdr_mem;  /**< hdr for each xmit packet */
+	uint16_t port_id;               /**< Device port identifier. */
+	const struct rte_memzone *mz;   /**< mem zone to populate CTL ring. */
 };
 
 int virtio_rxq_vec_setup(struct virtnet_rx *rxvq);
diff --git a/drivers/net/virtio/virtio_rxtx_simple.c b/drivers/net/virtio/virtio_rxtx_simple.c
index 542cf805..b5bc1c49 100644
--- a/drivers/net/virtio/virtio_rxtx_simple.c
+++ b/drivers/net/virtio/virtio_rxtx_simple.c
@@ -39,7 +39,6 @@
 
 #include <rte_cycles.h>
 #include <rte_memory.h>
-#include <rte_memzone.h>
 #include <rte_branch_prediction.h>
 #include <rte_mempool.h>
 #include <rte_malloc.h>
@@ -65,6 +64,8 @@ virtqueue_enqueue_recv_refill_simple(struct virtqueue *vq,
 	struct vring_desc *start_dp;
 	uint16_t desc_idx;
 
+	cookie->port = vq->rxq.port_id;
+
 	desc_idx = vq->vq_avail_idx & (vq->vq_nentries - 1);
 	dxp = &vq->vq_descx[desc_idx];
 	dxp->cookie = (void *)cookie;
diff --git a/drivers/net/virtio/virtio_rxtx_simple_neon.c b/drivers/net/virtio/virtio_rxtx_simple_neon.c
index 6b40c7f7..b8b93551 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_neon.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_neon.c
@@ -43,7 +43,6 @@
 #include <rte_ethdev.h>
 #include <rte_errno.h>
 #include <rte_memory.h>
-#include <rte_memzone.h>
 #include <rte_mempool.h>
 #include <rte_malloc.h>
 #include <rte_mbuf.h>
diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
index 7cf0f8b8..94f65143 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
@@ -46,7 +46,6 @@
 #include <rte_ethdev.h>
 #include <rte_errno.h>
 #include <rte_memory.h>
-#include <rte_memzone.h>
 #include <rte_mempool.h>
 #include <rte_malloc.h>
 #include <rte_mbuf.h>
diff --git a/drivers/net/virtio/virtio_user/vhost_kernel_tap.c b/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
index f585de8c..689a5cff 100644
--- a/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
+++ b/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
@@ -95,9 +95,9 @@ vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq)
 		ifr.ifr_flags |= IFF_MULTI_QUEUE;
 
 	if (*p_ifname)
-		strncpy(ifr.ifr_name, *p_ifname, IFNAMSIZ);
+		strncpy(ifr.ifr_name, *p_ifname, IFNAMSIZ - 1);
 	else
-		strncpy(ifr.ifr_name, "tap%d", IFNAMSIZ);
+		strncpy(ifr.ifr_name, "tap%d", IFNAMSIZ - 1);
 	if (ioctl(tapfd, TUNSETIFF, (void *)&ifr) == -1) {
 		PMD_DRV_LOG(ERR, "TUNSETIFF failed: %s", strerror(errno));
 		goto error;
diff --git a/drivers/net/virtio/virtio_user/vhost_user.c b/drivers/net/virtio/virtio_user/vhost_user.c
index 4ad7b21b..97bd8326 100644
--- a/drivers/net/virtio/virtio_user/vhost_user.c
+++ b/drivers/net/virtio/virtio_user/vhost_user.c
@@ -130,6 +130,10 @@ vhost_user_read(int fd, struct vhost_user_msg *msg)
 	}
 
 	sz_payload = msg->size;
+
+	if ((size_t)sz_payload > sizeof(msg->payload))
+		goto fail;
+
 	if (sz_payload) {
 		ret = recv(fd, (void *)((char *)msg + sz_hdr), sz_payload, 0);
 		if (ret < sz_payload) {
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
index 79412714..906d7a2b 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -270,6 +270,8 @@ virtio_user_fill_intr_handle(struct virtio_user_dev *dev)
 	eth_dev->intr_handle->nb_efd = dev->max_queue_pairs;
 	eth_dev->intr_handle->max_intr = dev->max_queue_pairs + 1;
 	eth_dev->intr_handle->type = RTE_INTR_HANDLE_VDEV;
+	/* For virtio vdev, no need to read counter for clean */
+	eth_dev->intr_handle->efd_counter_size = 0;
 	if (dev->vhostfd >= 0)
 		eth_dev->intr_handle->fd = dev->vhostfd;
 
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index c9614443..7be57ce6 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -40,7 +40,7 @@
 #include <rte_malloc.h>
 #include <rte_kvargs.h>
 #include <rte_ethdev_vdev.h>
-#include <rte_vdev.h>
+#include <rte_bus_vdev.h>
 #include <rte_alarm.h>
 
 #include "virtio_ethdev.h"
@@ -86,7 +86,11 @@ virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
 			int flags;
 
 			flags = fcntl(dev->vhostfd, F_GETFL);
-			fcntl(dev->vhostfd, F_SETFL, flags | O_NONBLOCK);
+			if (fcntl(dev->vhostfd, F_SETFL,
+					flags | O_NONBLOCK) == -1) {
+				PMD_DRV_LOG(ERR, "error setting O_NONBLOCK flag");
+				return;
+			}
 			r = recv(dev->vhostfd, buf, 128, MSG_PEEK);
 			if (r == 0 || (r < 0 && errno != EAGAIN)) {
 				dev->status &= (~VIRTIO_NET_S_LINK_UP);
@@ -369,9 +373,9 @@ virtio_user_eth_dev_alloc(struct rte_vdev_device *vdev)
 	 */
 	hw->use_msix = 1;
 	hw->modern   = 0;
-	hw->use_simple_rxtx = 0;
+	hw->use_simple_rx = 0;
+	hw->use_simple_tx = 0;
 	hw->virtio_user_dev = dev;
-	data->dev_flags = RTE_ETH_DEV_DETACHABLE;
 	return eth_dev;
 }
 
diff --git a/drivers/net/virtio/virtqueue.c b/drivers/net/virtio/virtqueue.c
index 9ad77b8a..c3a536f8 100644
--- a/drivers/net/virtio/virtqueue.c
+++ b/drivers/net/virtio/virtqueue.c
@@ -59,3 +59,28 @@ virtqueue_detatch_unused(struct virtqueue *vq)
 		}
 	return NULL;
 }
+
+/* Flush the elements in the used ring. */
+void
+virtqueue_flush(struct virtqueue *vq)
+{
+	struct vring_used_elem *uep;
+	struct vq_desc_extra *dxp;
+	uint16_t used_idx, desc_idx;
+	uint16_t nb_used, i;
+
+	nb_used = VIRTQUEUE_NUSED(vq);
+
+	for (i = 0; i < nb_used; i++) {
+		used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1);
+		uep = &vq->vq_ring.used->ring[used_idx];
+		desc_idx = (uint16_t)uep->id;
+		dxp = &vq->vq_descx[desc_idx];
+		if (dxp->cookie != NULL) {
+			rte_pktmbuf_free(dxp->cookie);
+			dxp->cookie = NULL;
+		}
+		vq->vq_used_cons_idx++;
+		vq_ring_free_chain(vq, desc_idx);
+	}
+}
diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h
index 2e120861..2305d91a 100644
--- a/drivers/net/virtio/virtqueue.h
+++ b/drivers/net/virtio/virtqueue.h
@@ -38,7 +38,6 @@
 
 #include <rte_atomic.h>
 #include <rte_memory.h>
-#include <rte_memzone.h>
 #include <rte_mempool.h>
 
 #include "virtio_pci.h"
@@ -80,7 +79,7 @@ struct rte_mbuf;
 #define VIRTIO_MBUF_ADDR(mb, vq) \
 	((uint64_t)(*(uintptr_t *)((uintptr_t)(mb) + (vq)->offset)))
 #else
-#define VIRTIO_MBUF_ADDR(mb, vq) ((mb)->buf_physaddr)
+#define VIRTIO_MBUF_ADDR(mb, vq) ((mb)->buf_iova)
 #endif
 
 /**
@@ -143,8 +142,8 @@ struct virtio_net_ctrl_mac {
 } __attribute__((__packed__));
 
 #define VIRTIO_NET_CTRL_MAC    1
- #define VIRTIO_NET_CTRL_MAC_TABLE_SET        0
- #define VIRTIO_NET_CTRL_MAC_ADDR_SET         1
+#define VIRTIO_NET_CTRL_MAC_TABLE_SET        0
+#define VIRTIO_NET_CTRL_MAC_ADDR_SET         1
 
 /**
  * Control VLAN filtering
@@ -204,8 +203,8 @@ struct virtqueue {
 		struct virtnet_ctl cq;
 	};
 
-	phys_addr_t vq_ring_mem; /**< physical address of vring,
-				  * or virtual address for virtio_user. */
+	rte_iova_t vq_ring_mem; /**< physical address of vring,
+	                         * or virtual address for virtio_user. */
 
 	/**
 	 * Head of the free chain in the descriptor table. If
@@ -304,6 +303,9 @@ void virtqueue_dump(struct virtqueue *vq);
  */
 struct rte_mbuf *virtqueue_detatch_unused(struct virtqueue *vq);
 
+/* Flush the elements in the used ring. */
+void virtqueue_flush(struct virtqueue *vq);
+
 static inline int
 virtqueue_full(const struct virtqueue *vq)
 {
@@ -312,6 +314,8 @@ virtqueue_full(const struct virtqueue *vq)
 
 #define VIRTQUEUE_NUSED(vq) ((uint16_t)((vq)->vq_ring.used->idx - (vq)->vq_used_cons_idx))
 
+void vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx);
+
 static inline void
 vq_update_avail_idx(struct virtqueue *vq)
 {