1 files changed, 290 insertions, 187 deletions

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 86cf8a38..079fd6c8 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -103,7 +103,8 @@ static int virtio_dev_queue_stats_mapping_set(
  * The set of PCI devices this driver supports
  */
 static const struct rte_pci_id pci_id_virtio_map[] = {
-	{ RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_DEVICEID_MIN) },
+	{ RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_LEGACY_DEVICEID_NET) },
+	{ RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_MODERN_DEVICEID_NET) },
 	{ .vendor_id = 0, /* sentinel */ },
 };
 
@@ -279,28 +280,65 @@ virtio_set_multiple_queues(struct rte_eth_dev *dev, uint16_t nb_queues)
 	return 0;
 }
 
-void
-virtio_dev_queue_release(struct virtqueue *vq)
+static void
+virtio_dev_queue_release(void *queue __rte_unused)
 {
-	struct virtio_hw *hw;
+	/* do nothing */
+}
 
-	if (vq) {
-		hw = vq->hw;
-		if (vq->configured)
-			hw->vtpci_ops->del_queue(hw, vq);
+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;
+}
 
-		rte_free(vq->sw_ring);
-		rte_free(vq);
-	}
+static uint16_t
+virtio_get_nr_vq(struct virtio_hw *hw)
+{
+	uint16_t nr_vq = hw->max_queue_pairs * 2;
+
+	if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ))
+		nr_vq += 1;
+
+	return nr_vq;
 }
 
-int virtio_dev_queue_setup(struct rte_eth_dev *dev,
-			int queue_type,
-			uint16_t queue_idx,
-			uint16_t vtpci_queue_idx,
-			uint16_t nb_desc,
-			unsigned int socket_id,
-			void **pvq)
+static void
+virtio_init_vring(struct virtqueue *vq)
+{
+	int size = vq->vq_nentries;
+	struct vring *vr = &vq->vq_ring;
+	uint8_t *ring_mem = vq->vq_ring_virt_mem;
+
+	PMD_INIT_FUNC_TRACE();
+
+	/*
+	 * Reinitialise since virtio port might have been stopped and restarted
+	 */
+	memset(ring_mem, 0, vq->vq_ring_size);
+	vring_init(vr, size, ring_mem, VIRTIO_PCI_VRING_ALIGN);
+	vq->vq_used_cons_idx = 0;
+	vq->vq_desc_head_idx = 0;
+	vq->vq_avail_idx = 0;
+	vq->vq_desc_tail_idx = (uint16_t)(vq->vq_nentries - 1);
+	vq->vq_free_cnt = vq->vq_nentries;
+	memset(vq->vq_descx, 0, sizeof(struct vq_desc_extra) * vq->vq_nentries);
+
+	vring_desc_init(vr->desc, size);
+
+	/*
+	 * Disable device(host) interrupting guest
+	 */
+	virtqueue_disable_intr(vq);
+}
+
+static int
+virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 {
 	char vq_name[VIRTQUEUE_MAX_NAME_SZ];
 	char vq_hdr_name[VIRTQUEUE_MAX_NAME_SZ];
@@ -311,9 +349,9 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 	struct virtnet_tx *txvq = NULL;
 	struct virtnet_ctl *cvq = NULL;
 	struct virtqueue *vq;
-	const char *queue_names[] = {"rvq", "txq", "cvq"};
-	size_t sz_vq, sz_q = 0, sz_hdr_mz = 0;
+	size_t sz_hdr_mz = 0;
 	void *sw_ring = NULL;
+	int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx);
 	int ret;
 
 	PMD_INIT_LOG(DEBUG, "setting up queue: %u", vtpci_queue_idx);
@@ -323,7 +361,7 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 	 * Always power of 2 and if 0 virtqueue does not exist
 	 */
 	vq_size = hw->vtpci_ops->get_queue_num(hw, vtpci_queue_idx);
-	PMD_INIT_LOG(DEBUG, "vq_size: %u nb_desc:%u", vq_size, nb_desc);
+	PMD_INIT_LOG(DEBUG, "vq_size: %u", vq_size);
 	if (vq_size == 0) {
 		PMD_INIT_LOG(ERR, "virtqueue does not exist");
 		return -EINVAL;
@@ -334,40 +372,35 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 		return -EINVAL;
 	}
 
-	snprintf(vq_name, sizeof(vq_name), "port%d_%s%d",
-		 dev->data->port_id, queue_names[queue_type], queue_idx);
+	snprintf(vq_name, sizeof(vq_name), "port%d_vq%d",
+		 dev->data->port_id, vtpci_queue_idx);
 
-	sz_vq = RTE_ALIGN_CEIL(sizeof(*vq) +
+	size = RTE_ALIGN_CEIL(sizeof(*vq) +
 				vq_size * sizeof(struct vq_desc_extra),
 				RTE_CACHE_LINE_SIZE);
-	if (queue_type == VTNET_RQ) {
-		sz_q = sz_vq + sizeof(*rxvq);
-	} else if (queue_type == VTNET_TQ) {
-		sz_q = sz_vq + sizeof(*txvq);
+	if (queue_type == VTNET_TQ) {
 		/*
 		 * For each xmit packet, allocate a virtio_net_hdr
 		 * and indirect ring elements
 		 */
 		sz_hdr_mz = vq_size * sizeof(struct virtio_tx_region);
 	} else if (queue_type == VTNET_CQ) {
-		sz_q = sz_vq + sizeof(*cvq);
 		/* Allocate a page for control vq command, data and status */
 		sz_hdr_mz = PAGE_SIZE;
 	}
 
-	vq = rte_zmalloc_socket(vq_name, sz_q, RTE_CACHE_LINE_SIZE, socket_id);
+	vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE,
+				SOCKET_ID_ANY);
 	if (vq == NULL) {
 		PMD_INIT_LOG(ERR, "can not allocate vq");
 		return -ENOMEM;
 	}
+	hw->vqs[vtpci_queue_idx] = vq;
+
 	vq->hw = hw;
 	vq->vq_queue_index = vtpci_queue_idx;
 	vq->vq_nentries = vq_size;
 
-	if (nb_desc == 0 || nb_desc > vq_size)
-		nb_desc = vq_size;
-	vq->vq_free_cnt = nb_desc;
-
 	/*
 	 * Reserve a memzone for vring elements
 	 */
@@ -376,7 +409,8 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 	PMD_INIT_LOG(DEBUG, "vring_size: %d, rounded_vring_size: %d",
 		     size, vq->vq_ring_size);
 
-	mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size, socket_id,
+	mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size,
+					 SOCKET_ID_ANY,
 					 0, VIRTIO_PCI_VRING_ALIGN);
 	if (mz == NULL) {
 		if (rte_errno == EEXIST)
@@ -396,12 +430,13 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 	PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%" PRIx64,
 		     (uint64_t)(uintptr_t)mz->addr);
 
+	virtio_init_vring(vq);
+
 	if (sz_hdr_mz) {
-		snprintf(vq_hdr_name, sizeof(vq_hdr_name), "port%d_%s%d_hdr",
-			 dev->data->port_id, queue_names[queue_type],
-			 queue_idx);
+		snprintf(vq_hdr_name, sizeof(vq_hdr_name), "port%d_vq%d_hdr",
+			 dev->data->port_id, vtpci_queue_idx);
 		hdr_mz = rte_memzone_reserve_aligned(vq_hdr_name, sz_hdr_mz,
-						     socket_id, 0,
+						     SOCKET_ID_ANY, 0,
 						     RTE_CACHE_LINE_SIZE);
 		if (hdr_mz == NULL) {
 			if (rte_errno == EEXIST)
@@ -418,7 +453,7 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 			       sizeof(vq->sw_ring[0]);
 
 		sw_ring = rte_zmalloc_socket("sw_ring", sz_sw,
-					     RTE_CACHE_LINE_SIZE, socket_id);
+				RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
 		if (!sw_ring) {
 			PMD_INIT_LOG(ERR, "can not allocate RX soft ring");
 			ret = -ENOMEM;
@@ -426,30 +461,26 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 		}
 
 		vq->sw_ring = sw_ring;
-		rxvq = (struct virtnet_rx *)RTE_PTR_ADD(vq, sz_vq);
+		rxvq = &vq->rxq;
 		rxvq->vq = vq;
 		rxvq->port_id = dev->data->port_id;
-		rxvq->queue_id = queue_idx;
 		rxvq->mz = mz;
-		*pvq = rxvq;
 	} else if (queue_type == VTNET_TQ) {
-		txvq = (struct virtnet_tx *)RTE_PTR_ADD(vq, sz_vq);
+		txvq = &vq->txq;
 		txvq->vq = vq;
 		txvq->port_id = dev->data->port_id;
-		txvq->queue_id = queue_idx;
 		txvq->mz = mz;
 		txvq->virtio_net_hdr_mz = hdr_mz;
 		txvq->virtio_net_hdr_mem = hdr_mz->phys_addr;
-
-		*pvq = txvq;
 	} else if (queue_type == VTNET_CQ) {
-		cvq = (struct virtnet_ctl *)RTE_PTR_ADD(vq, sz_vq);
+		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;
 		memset(cvq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE);
-		*pvq = cvq;
+
+		hw->cvq = cvq;
 	}
 
 	/* For virtio_user case (that is when dev->pci_dev is NULL), we use
@@ -490,11 +521,9 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev,
 
 	if (hw->vtpci_ops->setup_queue(hw, vq) < 0) {
 		PMD_INIT_LOG(ERR, "setup_queue failed");
-		virtio_dev_queue_release(vq);
 		return -EINVAL;
 	}
 
-	vq->configured = 1;
 	return 0;
 
 fail_q_alloc:
@@ -506,40 +535,60 @@ fail_q_alloc:
 	return ret;
 }
 
-static int
-virtio_dev_cq_queue_setup(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx,
-		uint32_t socket_id)
+static void
+virtio_free_queues(struct virtio_hw *hw)
 {
-	struct virtnet_ctl *cvq;
-	int ret;
-	struct virtio_hw *hw = dev->data->dev_private;
+	uint16_t nr_vq = virtio_get_nr_vq(hw);
+	struct virtqueue *vq;
+	int queue_type;
+	uint16_t i;
 
-	PMD_INIT_FUNC_TRACE();
-	ret = virtio_dev_queue_setup(dev, VTNET_CQ, VTNET_SQ_CQ_QUEUE_IDX,
-			vtpci_queue_idx, 0, socket_id, (void **)&cvq);
-	if (ret < 0) {
-		PMD_INIT_LOG(ERR, "control vq initialization failed");
-		return ret;
+	for (i = 0; i < nr_vq; i++) {
+		vq = hw->vqs[i];
+		if (!vq)
+			continue;
+
+		queue_type = virtio_get_queue_type(hw, i);
+		if (queue_type == VTNET_RQ) {
+			rte_free(vq->sw_ring);
+			rte_memzone_free(vq->rxq.mz);
+		} else if (queue_type == VTNET_TQ) {
+			rte_memzone_free(vq->txq.mz);
+			rte_memzone_free(vq->txq.virtio_net_hdr_mz);
+		} else {
+			rte_memzone_free(vq->cq.mz);
+			rte_memzone_free(vq->cq.virtio_net_hdr_mz);
+		}
+
+		rte_free(vq);
 	}
 
-	hw->cvq = cvq;
-	return 0;
+	rte_free(hw->vqs);
 }
 
-static void
-virtio_free_queues(struct rte_eth_dev *dev)
+static int
+virtio_alloc_queues(struct rte_eth_dev *dev)
 {
-	unsigned int i;
-
-	for (i = 0; i < dev->data->nb_rx_queues; i++)
-		virtio_dev_rx_queue_release(dev->data->rx_queues[i]);
+	struct virtio_hw *hw = dev->data->dev_private;
+	uint16_t nr_vq = virtio_get_nr_vq(hw);
+	uint16_t i;
+	int ret;
 
-	dev->data->nb_rx_queues = 0;
+	hw->vqs = rte_zmalloc(NULL, sizeof(struct virtqueue *) * nr_vq, 0);
+	if (!hw->vqs) {
+		PMD_INIT_LOG(ERR, "failed to allocate vqs");
+		return -ENOMEM;
+	}
 
-	for (i = 0; i < dev->data->nb_tx_queues; i++)
-		virtio_dev_tx_queue_release(dev->data->tx_queues[i]);
+	for (i = 0; i < nr_vq; i++) {
+		ret = virtio_init_queue(dev, i);
+		if (ret < 0) {
+			virtio_free_queues(hw);
+			return ret;
+		}
+	}
 
-	dev->data->nb_tx_queues = 0;
+	return 0;
 }
 
 static void
@@ -553,9 +602,8 @@ virtio_dev_close(struct rte_eth_dev *dev)
 	if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
 		vtpci_irq_config(hw, VIRTIO_MSI_NO_VECTOR);
 	vtpci_reset(hw);
-	hw->started = 0;
 	virtio_dev_free_mbufs(dev);
-	virtio_free_queues(dev);
+	virtio_free_queues(hw);
 }
 
 static void
@@ -650,6 +698,23 @@ virtio_dev_allmulticast_disable(struct rte_eth_dev *dev)
 		PMD_INIT_LOG(ERR, "Failed to disable allmulticast");
 }
 
+#define VLAN_TAG_LEN           4    /* 802.3ac tag (not DMA'd) */
+static int
+virtio_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
+{
+	struct virtio_hw *hw = dev->data->dev_private;
+	uint32_t ether_hdr_len = ETHER_HDR_LEN + VLAN_TAG_LEN +
+				 hw->vtnet_hdr_size;
+	uint32_t frame_size = mtu + ether_hdr_len;
+
+	if (mtu < ETHER_MIN_MTU || frame_size > VIRTIO_MAX_RX_PKTLEN) {
+		PMD_INIT_LOG(ERR, "MTU should be between %d and %d\n",
+			ETHER_MIN_MTU, VIRTIO_MAX_RX_PKTLEN - ether_hdr_len);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /*
  * dev_ops for virtio, bare necessities for basic operation
  */
@@ -662,7 +727,7 @@ static const struct eth_dev_ops virtio_eth_dev_ops = {
 	.promiscuous_disable     = virtio_dev_promiscuous_disable,
 	.allmulticast_enable     = virtio_dev_allmulticast_enable,
 	.allmulticast_disable    = virtio_dev_allmulticast_disable,
-
+	.mtu_set                 = virtio_mtu_set,
 	.dev_infos_get           = virtio_dev_info_get,
 	.stats_get               = virtio_dev_stats_get,
 	.xstats_get              = virtio_dev_xstats_get,
@@ -671,9 +736,9 @@ static const struct eth_dev_ops virtio_eth_dev_ops = {
 	.xstats_reset            = virtio_dev_stats_reset,
 	.link_update             = virtio_dev_link_update,
 	.rx_queue_setup          = virtio_dev_rx_queue_setup,
-	.rx_queue_release        = virtio_dev_rx_queue_release,
+	.rx_queue_release        = virtio_dev_queue_release,
 	.tx_queue_setup          = virtio_dev_tx_queue_setup,
-	.tx_queue_release        = virtio_dev_tx_queue_release,
+	.tx_queue_release        = virtio_dev_queue_release,
 	/* collect stats per queue */
 	.queue_stats_mapping_set = virtio_dev_queue_stats_mapping_set,
 	.vlan_filter_set         = virtio_vlan_filter_set,
@@ -1040,14 +1105,13 @@ virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on)
 }
 
 static int
-virtio_negotiate_features(struct virtio_hw *hw)
+virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 {
 	uint64_t host_features;
 
 	/* Prepare guest_features: feature that driver wants to support */
-	hw->guest_features = VIRTIO_PMD_GUEST_FEATURES;
 	PMD_INIT_LOG(DEBUG, "guest_features before negotiate = %" PRIx64,
-		hw->guest_features);
+		req_features);
 
 	/* Read device(host) feature bits */
 	host_features = hw->vtpci_ops->get_features(hw);
@@ -1058,6 +1122,7 @@ virtio_negotiate_features(struct virtio_hw *hw)
 	 * Negotiate features: Subset of device feature bits are written back
 	 * guest feature bits.
 	 */
+	hw->guest_features = req_features;
 	hw->guest_features = vtpci_negotiate_features(hw, host_features);
 	PMD_INIT_LOG(DEBUG, "features after negotiate = %" PRIx64,
 		hw->guest_features);
@@ -1076,6 +1141,8 @@ virtio_negotiate_features(struct virtio_hw *hw)
 		}
 	}
 
+	hw->req_guest_features = req_features;
+
 	return 0;
 }
 
@@ -1101,7 +1168,7 @@ virtio_interrupt_handler(__rte_unused struct rte_intr_handle *handle,
 	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);
+						      RTE_ETH_EVENT_INTR_LSC, NULL);
 	}
 
 }
@@ -1116,47 +1183,16 @@ rx_func_get(struct rte_eth_dev *eth_dev)
 		eth_dev->rx_pkt_burst = &virtio_recv_pkts;
 }
 
-/*
- * This function is based on probe() function in virtio_pci.c
- * It returns 0 on success.
- */
-int
-eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
+/* reset device and renegotiate features if needed */
+static int
+virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 {
 	struct virtio_hw *hw = eth_dev->data->dev_private;
 	struct virtio_net_config *config;
 	struct virtio_net_config local_config;
-	struct rte_pci_device *pci_dev;
-	uint32_t dev_flags = RTE_ETH_DEV_DETACHABLE;
+	struct rte_pci_device *pci_dev = eth_dev->pci_dev;
 	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) {
-		rx_func_get(eth_dev);
-		return 0;
-	}
-
-	/* Allocate memory for storing MAC addresses */
-	eth_dev->data->mac_addrs = rte_zmalloc("virtio", VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN, 0);
-	if (eth_dev->data->mac_addrs == NULL) {
-		PMD_INIT_LOG(ERR,
-			"Failed to allocate %d bytes needed to store MAC addresses",
-			VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN);
-		return -ENOMEM;
-	}
-
-	pci_dev = eth_dev->pci_dev;
-
-	if (pci_dev) {
-		ret = vtpci_init(pci_dev, hw, &dev_flags);
-		if (ret)
-			return ret;
-	}
-
 	/* Reset the device although not necessary at startup */
 	vtpci_reset(hw);
 
@@ -1165,15 +1201,16 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 
 	/* Tell the host we've known how to drive the device. */
 	vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER);
-	if (virtio_negotiate_features(hw) < 0)
+	if (virtio_negotiate_features(hw, req_features) < 0)
 		return -1;
 
 	/* If host does not support status then disable LSC */
 	if (!vtpci_with_feature(hw, VIRTIO_NET_F_STATUS))
-		dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
+		eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
+	else
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
 
 	rte_eth_copy_pci_info(eth_dev, pci_dev);
-	eth_dev->data->dev_flags = dev_flags;
 
 	rx_func_get(eth_dev);
 
@@ -1221,16 +1258,7 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 			config->max_virtqueue_pairs = 1;
 		}
 
-		hw->max_rx_queues =
-			(VIRTIO_MAX_RX_QUEUES < config->max_virtqueue_pairs) ?
-			VIRTIO_MAX_RX_QUEUES : config->max_virtqueue_pairs;
-		hw->max_tx_queues =
-			(VIRTIO_MAX_TX_QUEUES < config->max_virtqueue_pairs) ?
-			VIRTIO_MAX_TX_QUEUES : config->max_virtqueue_pairs;
-
-		virtio_dev_cq_queue_setup(eth_dev,
-					config->max_virtqueue_pairs * 2,
-					SOCKET_ID_ANY);
+		hw->max_queue_pairs = config->max_virtqueue_pairs;
 
 		PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=%d",
 				config->max_virtqueue_pairs);
@@ -1241,23 +1269,73 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 				config->mac[2], config->mac[3],
 				config->mac[4], config->mac[5]);
 	} else {
-		hw->max_rx_queues = 1;
-		hw->max_tx_queues = 1;
+		PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=1");
+		hw->max_queue_pairs = 1;
 	}
 
-	PMD_INIT_LOG(DEBUG, "hw->max_rx_queues=%d   hw->max_tx_queues=%d",
-			hw->max_rx_queues, hw->max_tx_queues);
+	ret = virtio_alloc_queues(eth_dev);
+	if (ret < 0)
+		return ret;
+	vtpci_reinit_complete(hw);
+
 	if (pci_dev)
 		PMD_INIT_LOG(DEBUG, "port %d vendorID=0x%x deviceID=0x%x",
 			eth_dev->data->port_id, pci_dev->id.vendor_id,
 			pci_dev->id.device_id);
 
+	return 0;
+}
+
+/*
+ * This function is based on probe() function in virtio_pci.c
+ * It returns 0 on success.
+ */
+int
+eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
+{
+	struct virtio_hw *hw = eth_dev->data->dev_private;
+	struct rte_pci_device *pci_dev;
+	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) {
+		rx_func_get(eth_dev);
+		return 0;
+	}
+
+	/* Allocate memory for storing MAC addresses */
+	eth_dev->data->mac_addrs = rte_zmalloc("virtio", VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN, 0);
+	if (eth_dev->data->mac_addrs == NULL) {
+		PMD_INIT_LOG(ERR,
+			"Failed to allocate %d bytes needed to store MAC addresses",
+			VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN);
+		return -ENOMEM;
+	}
+
+	pci_dev = eth_dev->pci_dev;
+
+	if (pci_dev) {
+		ret = vtpci_init(pci_dev, hw, &dev_flags);
+		if (ret)
+			return ret;
+	}
+
+	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;
+
 	/* Setup interrupt callback  */
 	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
 		rte_intr_callback_register(&pci_dev->intr_handle,
-				   virtio_interrupt_handler, eth_dev);
-
-	virtio_dev_cq_start(eth_dev);
+			virtio_interrupt_handler, eth_dev);
 
 	return 0;
 }
@@ -1266,26 +1344,20 @@ static int
 eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 {
 	struct rte_pci_device *pci_dev;
-	struct virtio_hw *hw = eth_dev->data->dev_private;
 
 	PMD_INIT_FUNC_TRACE();
 
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY)
 		return -EPERM;
 
-	if (hw->started == 1) {
-		virtio_dev_stop(eth_dev);
-		virtio_dev_close(eth_dev);
-	}
+	virtio_dev_stop(eth_dev);
+	virtio_dev_close(eth_dev);
 	pci_dev = eth_dev->pci_dev;
 
 	eth_dev->dev_ops = NULL;
 	eth_dev->tx_pkt_burst = NULL;
 	eth_dev->rx_pkt_burst = NULL;
 
-	if (hw->cvq)
-		virtio_dev_queue_release(hw->cvq->vq);
-
 	rte_free(eth_dev->data->mac_addrs);
 	eth_dev->data->mac_addrs = NULL;
 
@@ -1303,32 +1375,29 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 
 static struct eth_driver rte_virtio_pmd = {
 	.pci_drv = {
-		.name = "rte_virtio_pmd",
+		.driver = {
+			.name = "net_virtio",
+		},
 		.id_table = pci_id_virtio_map,
 		.drv_flags = RTE_PCI_DRV_DETACHABLE,
+		.probe = rte_eth_dev_pci_probe,
+		.remove = rte_eth_dev_pci_remove,
 	},
 	.eth_dev_init = eth_virtio_dev_init,
 	.eth_dev_uninit = eth_virtio_dev_uninit,
 	.dev_private_size = sizeof(struct virtio_hw),
 };
 
-/*
- * Driver initialization routine.
- * Invoked once at EAL init time.
- * Register itself as the [Poll Mode] Driver of PCI virtio devices.
- * Returns 0 on success.
- */
-static int
-rte_virtio_pmd_init(const char *name __rte_unused,
-		    const char *param __rte_unused)
+RTE_INIT(rte_virtio_pmd_init);
+static void
+rte_virtio_pmd_init(void)
 {
 	if (rte_eal_iopl_init() != 0) {
 		PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
-		return -1;
+		return;
 	}
 
-	rte_eth_driver_register(&rte_virtio_pmd);
-	return 0;
+	rte_eal_pci_register(&rte_virtio_pmd.pci_drv);
 }
 
 /*
@@ -1340,14 +1409,44 @@ 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 (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) {
-		PMD_DRV_LOG(ERR, "HW IP checksum not supported");
-		return -EINVAL;
+	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");
+		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");
+		return -ENOTSUP;
 	}
 
+	/* start control queue */
+	if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ))
+		virtio_dev_cq_start(dev);
+
 	hw->vlan_strip = rxmode->hw_vlan_strip;
 
 	if (rxmode->hw_vlan_filter
@@ -1371,9 +1470,9 @@ static int
 virtio_dev_start(struct rte_eth_dev *dev)
 {
 	uint16_t nb_queues, i;
-	struct virtio_hw *hw = dev->data->dev_private;
 	struct virtnet_rx *rxvq;
 	struct virtnet_tx *txvq __rte_unused;
+	struct virtio_hw *hw = dev->data->dev_private;
 
 	/* check if lsc interrupt feature is enabled */
 	if (dev->data->dev_conf.intr_conf.lsc) {
@@ -1391,29 +1490,19 @@ virtio_dev_start(struct rte_eth_dev *dev)
 	/* Initialize Link state */
 	virtio_dev_link_update(dev, 0);
 
-	/* On restart after stop do not touch queues */
-	if (hw->started)
-		return 0;
-
-	/* Do final configuration before rx/tx engine starts */
-	virtio_dev_rxtx_start(dev);
-	vtpci_reinit_complete(hw);
-
-	hw->started = 1;
-
 	/*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
 	 */
-	nb_queues = dev->data->nb_rx_queues;
-	if (nb_queues > 1) {
+	nb_queues = RTE_MAX(dev->data->nb_rx_queues, dev->data->nb_tx_queues);
+	if (hw->max_queue_pairs > 1) {
 		if (virtio_set_multiple_queues(dev, nb_queues) != 0)
 			return -EINVAL;
 	}
 
 	PMD_INIT_LOG(DEBUG, "nb_queues=%d", nb_queues);
 
-	for (i = 0; i < nb_queues; i++) {
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		rxvq = dev->data->rx_queues[i];
 		virtqueue_notify(rxvq->vq);
 	}
@@ -1532,20 +1621,39 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 static void
 virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 {
+	uint64_t tso_mask;
 	struct virtio_hw *hw = dev->data->dev_private;
 
 	if (dev->pci_dev)
-		dev_info->driver_name = dev->driver->pci_drv.name;
+		dev_info->driver_name = dev->driver->pci_drv.driver.name;
 	else
 		dev_info->driver_name = "virtio_user PMD";
-	dev_info->max_rx_queues = (uint16_t)hw->max_rx_queues;
-	dev_info->max_tx_queues = (uint16_t)hw->max_tx_queues;
+	dev_info->max_rx_queues =
+		RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES);
+	dev_info->max_tx_queues =
+		RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_TX_QUEUES);
 	dev_info->min_rx_bufsize = VIRTIO_MIN_RX_BUFSIZE;
 	dev_info->max_rx_pktlen = VIRTIO_MAX_RX_PKTLEN;
 	dev_info->max_mac_addrs = VIRTIO_MAX_MAC_ADDRS;
 	dev_info->default_txconf = (struct rte_eth_txconf) {
 		.txq_flags = ETH_TXQ_FLAGS_NOOFFLOADS
 	};
+	dev_info->rx_offload_capa =
+		DEV_RX_OFFLOAD_TCP_CKSUM |
+		DEV_RX_OFFLOAD_UDP_CKSUM |
+		DEV_RX_OFFLOAD_TCP_LRO;
+	dev_info->tx_offload_capa = 0;
+
+	if (hw->guest_features & (1ULL << VIRTIO_NET_F_CSUM)) {
+		dev_info->tx_offload_capa |=
+			DEV_TX_OFFLOAD_UDP_CKSUM |
+			DEV_TX_OFFLOAD_TCP_CKSUM;
+	}
+
+	tso_mask = (1ULL << VIRTIO_NET_F_HOST_TSO4) |
+		(1ULL << VIRTIO_NET_F_HOST_TSO6);
+	if ((hw->guest_features & tso_mask) == tso_mask)
+		dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO;
 }
 
 /*
@@ -1559,10 +1667,5 @@ __rte_unused uint8_t is_rx)
 	return 0;
 }
 
-static struct rte_driver rte_virtio_driver = {
-	.type = PMD_PDEV,
-	.init = rte_virtio_pmd_init,
-};
-
-PMD_REGISTER_DRIVER(rte_virtio_driver, virtio_net);
-DRIVER_REGISTER_PCI_TABLE(virtio_net, pci_id_virtio_map);
+RTE_PMD_EXPORT_NAME(net_virtio, __COUNTER__);
+RTE_PMD_REGISTER_PCI_TABLE(net_virtio, pci_id_virtio_map);