X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=4f20e47cf9d41e0e755f94a6ec40cc028291ca1f;hb=3669a1af893088064778f14fba0c2ca88819e095;hp=d9986ab52e0ae1afc9717bd19995a8ae53839243;hpb=49d26d9e3f472f850d8fdfdbf85f6498e717e4f9;p=dpdk.git

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index d9986ab52e..4f20e47cf9 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1,34 +1,5 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
- *   All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
  */
 
 #include <stdint.h>
@@ -37,7 +8,8 @@
 #include <errno.h>
 #include <unistd.h>
 
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
+#include <rte_ethdev_pci.h>
 #include <rte_memcpy.h>
 #include <rte_string_fns.h>
 #include <rte_memzone.h>
@@ -45,13 +17,18 @@
 #include <rte_atomic.h>
 #include <rte_branch_prediction.h>
 #include <rte_pci.h>
+#include <rte_bus_pci.h>
 #include <rte_ether.h>
+#include <rte_ip.h>
+#include <rte_arp.h>
 #include <rte_common.h>
 #include <rte_errno.h>
+#include <rte_cpuflags.h>
 
 #include <rte_memory.h>
 #include <rte_eal.h>
 #include <rte_dev.h>
+#include <rte_cycles.h>
 
 #include "virtio_ethdev.h"
 #include "virtio_pci.h"
@@ -70,12 +47,13 @@ static void virtio_dev_allmulticast_disable(struct rte_eth_dev *dev);
 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,
-	__rte_unused int wait_to_complete);
+	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);
@@ -86,18 +64,27 @@ static void virtio_dev_stats_reset(struct rte_eth_dev *dev);
 static void virtio_dev_free_mbufs(struct rte_eth_dev *dev);
 static int virtio_vlan_filter_set(struct rte_eth_dev *dev,
 				uint16_t vlan_id, int on);
-static void virtio_mac_addr_add(struct rte_eth_dev *dev,
+static int virtio_mac_addr_add(struct rte_eth_dev *dev,
 				struct ether_addr *mac_addr,
-				uint32_t index, uint32_t vmdq __rte_unused);
+				uint32_t index, uint32_t vmdq);
 static void virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index);
 static void virtio_mac_addr_set(struct rte_eth_dev *dev,
 				struct ether_addr *mac_addr);
 
+static int virtio_intr_enable(struct rte_eth_dev *dev);
+static int virtio_intr_disable(struct rte_eth_dev *dev);
+
 static int virtio_dev_queue_stats_mapping_set(
-	__rte_unused struct rte_eth_dev *eth_dev,
-	__rte_unused uint16_t queue_id,
-	__rte_unused uint8_t stat_idx,
-	__rte_unused uint8_t is_rx);
+	struct rte_eth_dev *eth_dev,
+	uint16_t queue_id,
+	uint8_t stat_idx,
+	uint8_t is_rx);
+
+int virtio_logtype_init;
+int virtio_logtype_driver;
+
+static void virtio_notify_peers(struct rte_eth_dev *dev);
+static void virtio_ack_link_announce(struct rte_eth_dev *dev);
 
 /*
  * The set of PCI devices this driver supports
@@ -161,7 +148,7 @@ 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;
@@ -170,6 +157,8 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 		PMD_INIT_LOG(ERR, "Control queue is not supported.");
 		return -1;
 	}
+
+	rte_spinlock_lock(&cvq->lock);
 	vq = cvq->vq;
 	head = vq->vq_desc_head_idx;
 
@@ -177,8 +166,10 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 		"vq->hw->cvq = %p vq = %p",
 		vq->vq_desc_head_idx, status, vq->hw->cvq, vq);
 
-	if ((vq->vq_free_cnt < ((uint32_t)pkt_num + 2)) || (pkt_num < 1))
+	if (vq->vq_free_cnt < pkt_num + 2 || pkt_num < 1) {
+		rte_spinlock_unlock(&cvq->lock);
 		return -1;
+	}
 
 	memcpy(cvq->virtio_net_hdr_mz->addr, ctrl,
 		sizeof(struct virtio_pmd_ctrl));
@@ -252,10 +243,10 @@ 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;
+	rte_spinlock_unlock(&cvq->lock);
+	return result->status;
 }
 
 static int
@@ -288,17 +279,6 @@ virtio_dev_queue_release(void *queue __rte_unused)
 	/* do nothing */
 }
 
-static int
-virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx)
-{
-	if (vtpci_queue_idx == hw->max_queue_pairs * 2)
-		return VTNET_CQ;
-	else if (vtpci_queue_idx % 2 == 0)
-		return VTNET_RQ;
-	else
-		return VTNET_TQ;
-}
-
 static uint16_t
 virtio_get_nr_vq(struct virtio_hw *hw)
 {
@@ -423,12 +403,12 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 		}
 	}
 
-	memset(mz->addr, 0, sizeof(mz->len));
+	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);
 
@@ -473,13 +453,13 @@ 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;
@@ -490,7 +470,7 @@ 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);
@@ -545,6 +525,9 @@ virtio_free_queues(struct virtio_hw *hw)
 	int queue_type;
 	uint16_t i;
 
+	if (hw->vqs == NULL)
+		return;
+
 	for (i = 0; i < nr_vq; i++) {
 		vq = hw->vqs[i];
 		if (!vq)
@@ -563,9 +546,11 @@ virtio_free_queues(struct virtio_hw *hw)
 		}
 
 		rte_free(vq);
+		hw->vqs[i] = NULL;
 	}
 
 	rte_free(hw->vqs);
+	hw->vqs = NULL;
 }
 
 static int
@@ -610,7 +595,7 @@ virtio_dev_close(struct rte_eth_dev *dev)
 		virtio_queues_unbind_intr(dev);
 
 	if (intr_conf->lsc || intr_conf->rxq) {
-		rte_intr_disable(dev->intr_handle);
+		virtio_intr_disable(dev);
 		rte_intr_efd_disable(dev->intr_handle);
 		rte_free(dev->intr_handle->intr_vec);
 		dev->intr_handle->intr_vec = NULL;
@@ -773,6 +758,7 @@ 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,
@@ -881,7 +867,7 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
 		/* Note: limit checked in rte_eth_xstats_names() */
 
 		for (i = 0; i < dev->data->nb_rx_queues; i++) {
-			struct virtqueue *rxvq = dev->data->rx_queues[i];
+			struct virtnet_rx *rxvq = dev->data->rx_queues[i];
 			if (rxvq == NULL)
 				continue;
 			for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
@@ -894,7 +880,7 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
 		}
 
 		for (i = 0; i < dev->data->nb_tx_queues; i++) {
-			struct virtqueue *txvq = dev->data->tx_queues[i];
+			struct virtnet_tx *txvq = dev->data->tx_queues[i];
 			if (txvq == NULL)
 				continue;
 			for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
@@ -958,10 +944,12 @@ 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
@@ -1019,7 +1007,7 @@ virtio_get_hwaddr(struct virtio_hw *hw)
 	}
 }
 
-static void
+static int
 virtio_mac_table_set(struct virtio_hw *hw,
 		     const struct virtio_net_ctrl_mac *uc,
 		     const struct virtio_net_ctrl_mac *mc)
@@ -1029,7 +1017,7 @@ virtio_mac_table_set(struct virtio_hw *hw,
 
 	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
 		PMD_DRV_LOG(INFO, "host does not support mac table");
-		return;
+		return -1;
 	}
 
 	ctrl.hdr.class = VIRTIO_NET_CTRL_MAC;
@@ -1044,9 +1032,10 @@ virtio_mac_table_set(struct virtio_hw *hw,
 	err = virtio_send_command(hw->cvq, &ctrl, len, 2);
 	if (err != 0)
 		PMD_DRV_LOG(NOTICE, "mac table set failed: %d", err);
+	return err;
 }
 
-static void
+static int
 virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
 		    uint32_t index, uint32_t vmdq __rte_unused)
 {
@@ -1057,7 +1046,7 @@ virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
 
 	if (index >= VIRTIO_MAX_MAC_ADDRS) {
 		PMD_DRV_LOG(ERR, "mac address index %u out of range", index);
-		return;
+		return -EINVAL;
 	}
 
 	uc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(uc->entries));
@@ -1074,7 +1063,7 @@ virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
 		memcpy(&tbl->macs[tbl->entries++], addr, ETHER_ADDR_LEN);
 	}
 
-	virtio_mac_table_set(hw, uc, mc);
+	return virtio_mac_table_set(hw, uc, mc);
 }
 
 static void
@@ -1147,6 +1136,34 @@ virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on)
 	return virtio_send_command(hw->cvq, &ctrl, &len, 1);
 }
 
+static int
+virtio_intr_enable(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	if (rte_intr_enable(dev->intr_handle) < 0)
+		return -1;
+
+	if (!hw->virtio_user_dev)
+		hw->use_msix = vtpci_msix_detect(RTE_ETH_DEV_TO_PCI(dev));
+
+	return 0;
+}
+
+static int
+virtio_intr_disable(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	if (rte_intr_disable(dev->intr_handle) < 0)
+		return -1;
+
+	if (!hw->virtio_user_dev)
+		hw->use_msix = vtpci_msix_detect(RTE_ETH_DEV_TO_PCI(dev));
+
+	return 0;
+}
+
 static int
 virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 {
@@ -1201,13 +1218,100 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 	return 0;
 }
 
+int
+virtio_dev_pause(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	rte_spinlock_lock(&hw->state_lock);
+
+	if (hw->started == 0) {
+		/* Device is just stopped. */
+		rte_spinlock_unlock(&hw->state_lock);
+		return -1;
+	}
+	hw->started = 0;
+	/*
+	 * Prevent the worker threads from touching queues to avoid contention,
+	 * 1 ms should be enough for the ongoing Tx function to finish.
+	 */
+	rte_delay_ms(1);
+	return 0;
+}
+
+/*
+ * Recover hw state to let the worker threads continue.
+ */
+void
+virtio_dev_resume(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+
+	hw->started = 1;
+	rte_spinlock_unlock(&hw->state_lock);
+}
+
 /*
- * Process Virtio Config changed interrupt and call the callback
- * if link state changed.
+ * Should be called only after device is paused.
  */
+int
+virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts,
+		int nb_pkts)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtnet_tx *txvq = dev->data->tx_queues[0];
+	int ret;
+
+	hw->inject_pkts = tx_pkts;
+	ret = dev->tx_pkt_burst(txvq, tx_pkts, nb_pkts);
+	hw->inject_pkts = NULL;
+
+	return ret;
+}
+
 static void
-virtio_interrupt_handler(struct rte_intr_handle *handle,
-			 void *param)
+virtio_notify_peers(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtnet_rx *rxvq = dev->data->rx_queues[0];
+	struct rte_mbuf *rarp_mbuf;
+
+	rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool,
+			(struct ether_addr *)hw->mac_addr);
+	if (rarp_mbuf == NULL) {
+		PMD_DRV_LOG(ERR, "failed to make RARP packet.");
+		return;
+	}
+
+	/* If virtio port just stopped, no need to send RARP */
+	if (virtio_dev_pause(dev) < 0) {
+		rte_pktmbuf_free(rarp_mbuf);
+		return;
+	}
+
+	virtio_inject_pkts(dev, &rarp_mbuf, 1);
+	virtio_dev_resume(dev);
+}
+
+static void
+virtio_ack_link_announce(struct rte_eth_dev *dev)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	struct virtio_pmd_ctrl ctrl;
+
+	ctrl.hdr.class = VIRTIO_NET_CTRL_ANNOUNCE;
+	ctrl.hdr.cmd = VIRTIO_NET_CTRL_ANNOUNCE_ACK;
+
+	virtio_send_command(hw->cvq, &ctrl, NULL, 0);
+}
+
+/*
+ * Process virtio config changed interrupt. Call the callback
+ * if link state changed, generate gratuitous RARP packet if
+ * the status indicates an ANNOUNCE.
+ */
+void
+virtio_interrupt_handler(void *param)
 {
 	struct rte_eth_dev *dev = param;
 	struct virtio_hw *hw = dev->data->dev_private;
@@ -1217,25 +1321,52 @@ virtio_interrupt_handler(struct rte_intr_handle *handle,
 	isr = vtpci_isr(hw);
 	PMD_DRV_LOG(INFO, "interrupt status = %#x", isr);
 
-	if (rte_intr_enable(handle) < 0)
+	if (virtio_intr_enable(dev) < 0)
 		PMD_DRV_LOG(ERR, "interrupt enable failed");
 
 	if (isr & VIRTIO_PCI_ISR_CONFIG) {
 		if (virtio_dev_link_update(dev, 0) == 0)
 			_rte_eth_dev_callback_process(dev,
-						      RTE_ETH_EVENT_INTR_LSC, NULL);
+						      RTE_ETH_EVENT_INTR_LSC,
+						      NULL);
 	}
 
+	if (isr & VIRTIO_NET_S_ANNOUNCE) {
+		virtio_notify_peers(dev);
+		virtio_ack_link_announce(dev);
+	}
 }
 
+/* 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.
@@ -1314,7 +1445,7 @@ virtio_configure_intr(struct rte_eth_dev *dev)
 	 * to change the config size from 20 to 24, or VIRTIO_MSI_QUEUE_VECTOR
 	 * (22) will be ignored.
 	 */
-	if (rte_intr_enable(dev->intr_handle) < 0) {
+	if (virtio_intr_enable(dev) < 0) {
 		PMD_DRV_LOG(ERR, "interrupt enable failed");
 		return -1;
 	}
@@ -1340,6 +1471,11 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	/* Reset the device although not necessary at startup */
 	vtpci_reset(hw);
 
+	if (hw->vqs) {
+		virtio_dev_free_mbufs(eth_dev);
+		virtio_free_queues(hw);
+	}
+
 	/* Tell the host we've noticed this device. */
 	vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_ACK);
 
@@ -1348,19 +1484,18 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	if (virtio_negotiate_features(hw, req_features) < 0)
 		return -1;
 
-	if (eth_dev->device) {
-		pci_dev = RTE_DEV_TO_PCI(eth_dev->device);
+	if (!hw->virtio_user_dev) {
+		pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
 		rte_eth_copy_pci_info(eth_dev, pci_dev);
 	}
 
 	/* 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)
+	if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS) &&
+	    hw->use_msix != VIRTIO_MSIX_NONE)
 		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))
@@ -1444,6 +1579,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	} else {
 		PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=1");
 		hw->max_queue_pairs = 1;
+		hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN -
+			VLAN_TAG_LEN - hw->vtnet_hdr_size;
 	}
 
 	ret = virtio_alloc_queues(eth_dev);
@@ -1478,7 +1615,7 @@ virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw)
 	if (hw->modern) {
 		/*
 		 * We don't have to re-parse the PCI config space, since
-		 * rte_eal_pci_map_device() makes sure the mapped address
+		 * rte_pci_map_device() makes sure the mapped address
 		 * in secondary process would equal to the one mapped in
 		 * the primary process: error will be returned if that
 		 * requirement is not met.
@@ -1487,12 +1624,12 @@ virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw)
 		 * (such as dev_cfg, common_cfg, etc.) parsed from the
 		 * primary process, which is stored in shared memory.
 		 */
-		if (rte_eal_pci_map_device(pci_dev)) {
+		if (rte_pci_map_device(pci_dev)) {
 			PMD_INIT_LOG(DEBUG, "failed to map pci device!");
 			return -1;
 		}
 	} else {
-		if (rte_eal_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0)
+		if (rte_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0)
 			return -1;
 	}
 
@@ -1521,29 +1658,22 @@ int
 eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 {
 	struct virtio_hw *hw = eth_dev->data->dev_private;
-	uint32_t dev_flags = RTE_ETH_DEV_DETACHABLE;
 	int ret;
 
 	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) {
-			ret = virtio_remap_pci(RTE_DEV_TO_PCI(eth_dev->device),
-					       hw);
+			ret = virtio_remap_pci(RTE_ETH_DEV_TO_PCI(eth_dev), hw);
 			if (ret)
 				return ret;
 		}
 
 		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;
 	}
 
@@ -1561,18 +1691,15 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	 * virtio_user_eth_dev_alloc() before eth_virtio_dev_init() is called.
 	 */
 	if (!hw->virtio_user_dev) {
-		ret = vtpci_init(RTE_DEV_TO_PCI(eth_dev->device), hw,
-				 &dev_flags);
+		ret = vtpci_init(RTE_ETH_DEV_TO_PCI(eth_dev), hw);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
-	eth_dev->data->dev_flags = dev_flags;
-
 	/* reset device and negotiate default features */
 	ret = virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	/* Setup interrupt callback  */
 	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
@@ -1580,6 +1707,10 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 			virtio_interrupt_handler, eth_dev);
 
 	return 0;
+
+out:
+	rte_free(eth_dev->data->mac_addrs);
+	return ret;
 }
 
 static int
@@ -1606,26 +1737,33 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 						virtio_interrupt_handler,
 						eth_dev);
 	if (eth_dev->device)
-		rte_eal_pci_unmap_device(RTE_DEV_TO_PCI(eth_dev->device));
+		rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev));
 
 	PMD_INIT_LOG(DEBUG, "dev_uninit completed");
 
 	return 0;
 }
 
-static struct eth_driver rte_virtio_pmd = {
-	.pci_drv = {
-		.driver = {
-			.name = "net_virtio",
-		},
-		.id_table = pci_id_virtio_map,
-		.drv_flags = 0,
-		.probe = rte_eth_dev_pci_probe,
-		.remove = rte_eth_dev_pci_remove,
+static int eth_virtio_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
+	struct rte_pci_device *pci_dev)
+{
+	return rte_eth_dev_pci_generic_probe(pci_dev, sizeof(struct virtio_hw),
+		eth_virtio_dev_init);
+}
+
+static int eth_virtio_pci_remove(struct rte_pci_device *pci_dev)
+{
+	return rte_eth_dev_pci_generic_remove(pci_dev, eth_virtio_dev_uninit);
+}
+
+static struct rte_pci_driver rte_virtio_pmd = {
+	.driver = {
+		.name = "net_virtio",
 	},
-	.eth_dev_init = eth_virtio_dev_init,
-	.eth_dev_uninit = eth_virtio_dev_uninit,
-	.dev_private_size = sizeof(struct virtio_hw),
+	.id_table = pci_id_virtio_map,
+	.drv_flags = 0,
+	.probe = eth_virtio_pci_probe,
+	.remove = eth_virtio_pci_remove,
 };
 
 RTE_INIT(rte_virtio_pmd_init);
@@ -1637,7 +1775,7 @@ rte_virtio_pmd_init(void)
 		return;
 	}
 
-	rte_eal_pci_register(&rte_virtio_pmd.pci_drv);
+	rte_pci_register(&rte_virtio_pmd);
 }
 
 /*
@@ -1654,8 +1792,20 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 
 	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);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* 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) |
@@ -1670,16 +1820,16 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 
 	if (rxmode->hw_ip_checksum &&
 		!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) {
-		PMD_DRV_LOG(NOTICE,
-			"rx ip checksum not available on this host");
+		PMD_DRV_LOG(ERR,
+			"rx checksum not available on this host");
 		return -ENOTSUP;
 	}
 
 	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(NOTICE,
-			"lro not available on this host");
+		 !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6))) {
+		PMD_DRV_LOG(ERR,
+			"Large Receive Offload not available on this host");
 		return -ENOTSUP;
 	}
 
@@ -1691,7 +1841,7 @@ 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;
 	}
@@ -1704,6 +1854,25 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return -EBUSY;
 		}
 
+	rte_spinlock_init(&hw->state_lock);
+
+	hw->use_simple_rx = 1;
+	hw->use_simple_tx = 1;
+
+#if defined RTE_ARCH_ARM64 || defined 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;
 }
 
@@ -1715,6 +1884,19 @@ 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) {
@@ -1730,17 +1912,14 @@ virtio_dev_start(struct rte_eth_dev *dev)
 	 */
 	if (dev->data->dev_conf.intr_conf.lsc ||
 	    dev->data->dev_conf.intr_conf.rxq) {
-		rte_intr_disable(dev->intr_handle);
+		virtio_intr_disable(dev);
 
-		if (rte_intr_enable(dev->intr_handle) < 0) {
+		if (virtio_intr_enable(dev) < 0) {
 			PMD_DRV_LOG(ERR, "interrupt enable failed");
 			return -EIO;
 		}
 	}
 
-	/* Initialize Link state */
-	virtio_dev_link_update(dev, 0);
-
 	/*Notify the backend
 	 *Otherwise the tap backend might already stop its queue due to fullness.
 	 *vhost backend will have no chance to be waked up
@@ -1755,9 +1934,16 @@ 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_rxvq_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++) {
@@ -1770,6 +1956,12 @@ virtio_dev_start(struct rte_eth_dev *dev)
 		VIRTQUEUE_DUMP(txvq->vq);
 	}
 
+	set_rxtx_funcs(dev);
+	hw->started = 1;
+
+	/* Initialize Link state */
+	virtio_dev_link_update(dev, 0);
+
 	return 0;
 }
 
@@ -1781,6 +1973,9 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		struct virtnet_rx *rxvq = dev->data->rx_queues[i];
 
+		if (rxvq == NULL || rxvq->vq == NULL)
+			continue;
+
 		PMD_INIT_LOG(DEBUG,
 			     "Before freeing rxq[%d] used and unused buf", i);
 		VIRTQUEUE_DUMP(rxvq->vq);
@@ -1800,6 +1995,9 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
 		struct virtnet_tx *txvq = dev->data->tx_queues[i];
 
+		if (txvq == NULL || txvq->vq == NULL)
+			continue;
+
 		PMD_INIT_LOG(DEBUG,
 			     "Before freeing txq[%d] used and unused bufs",
 			     i);
@@ -1824,16 +2022,20 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
 static void
 virtio_dev_stop(struct rte_eth_dev *dev)
 {
+	struct virtio_hw *hw = dev->data->dev_private;
 	struct rte_eth_link link;
 	struct rte_intr_conf *intr_conf = &dev->data->dev_conf.intr_conf;
 
 	PMD_INIT_LOG(DEBUG, "stop");
 
+	rte_spinlock_lock(&hw->state_lock);
 	if (intr_conf->lsc || intr_conf->rxq)
-		rte_intr_disable(dev->intr_handle);
+		virtio_intr_disable(dev);
 
+	hw->started = 0;
 	memset(&link, 0, sizeof(link));
 	virtio_dev_atomic_write_link_status(dev, &link);
+	rte_spinlock_unlock(&hw->state_lock);
 }
 
 static int
@@ -1846,9 +2048,11 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 	virtio_dev_atomic_read_link_status(dev, &link);
 	old = link;
 	link.link_duplex = ETH_LINK_FULL_DUPLEX;
-	link.link_speed  = SPEED_10G;
+	link.link_speed  = ETH_SPEED_NUM_10G;
 
-	if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
+	if (hw->started == 0) {
+		link.link_status = ETH_LINK_DOWN;
+	} else if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
 		PMD_INIT_LOG(DEBUG, "Get link status from hw");
 		vtpci_read_dev_config(hw,
 				offsetof(struct virtio_net_config, status),
@@ -1870,6 +2074,29 @@ 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)
 {
@@ -1878,7 +2105,7 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 
 	dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */
 
-	dev_info->pci_dev = dev->device ? RTE_DEV_TO_PCI(dev->device) : NULL;
+	dev_info->pci_dev = dev->device ? RTE_ETH_DEV_TO_PCI(dev) : NULL;
 	dev_info->max_rx_queues =
 		RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES);
 	dev_info->max_tx_queues =
@@ -1927,4 +2154,16 @@ __rte_unused uint8_t is_rx)
 
 RTE_PMD_EXPORT_NAME(net_virtio, __COUNTER__);
 RTE_PMD_REGISTER_PCI_TABLE(net_virtio, pci_id_virtio_map);
-RTE_PMD_REGISTER_KMOD_DEP(net_virtio, "* igb_uio | uio_pci_generic | vfio");
+RTE_PMD_REGISTER_KMOD_DEP(net_virtio, "* igb_uio | uio_pci_generic | vfio-pci");
+
+RTE_INIT(virtio_init_log);
+static void
+virtio_init_log(void)
+{
+	virtio_logtype_init = rte_log_register("pmd.virtio.init");
+	if (virtio_logtype_init >= 0)
+		rte_log_set_level(virtio_logtype_init, RTE_LOG_NOTICE);
+	virtio_logtype_driver = rte_log_register("pmd.virtio.driver");
+	if (virtio_logtype_driver >= 0)
+		rte_log_set_level(virtio_logtype_driver, RTE_LOG_NOTICE);
+}