X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=0a76cce21ee083caf15dfb3ecaee6ce5d866f14a;hb=c12a26ee209e0f378cd0b31d3fd0186df09e14ce;hp=f74e4130deb80b526fbe6d70c0cd4ded29dfbcbd;hpb=6c3169a3dc041cbdbef506f19e3779940caa4b29;p=dpdk.git

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index f74e4130de..0a76cce21e 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1,7 +1,7 @@
 /*-
  *   BSD LICENSE
  *
- *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
  *   All rights reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
@@ -36,10 +36,6 @@
 #include <stdio.h>
 #include <errno.h>
 #include <unistd.h>
-#ifdef RTE_EXEC_ENV_LINUXAPP
-#include <dirent.h>
-#include <fcntl.h>
-#endif
 
 #include <rte_ethdev.h>
 #include <rte_memcpy.h>
@@ -51,6 +47,7 @@
 #include <rte_pci.h>
 #include <rte_ether.h>
 #include <rte_common.h>
+#include <rte_errno.h>
 
 #include <rte_memory.h>
 #include <rte_eal.h>
@@ -60,9 +57,9 @@
 #include "virtio_pci.h"
 #include "virtio_logs.h"
 #include "virtqueue.h"
+#include "virtio_rxtx.h"
 
-
-static int eth_virtio_dev_init(struct rte_eth_dev *eth_dev);
+static int eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev);
 static int  virtio_dev_configure(struct rte_eth_dev *dev);
 static int  virtio_dev_start(struct rte_eth_dev *dev);
 static void virtio_dev_stop(struct rte_eth_dev *dev);
@@ -78,10 +75,13 @@ static int virtio_dev_link_update(struct rte_eth_dev *dev,
 static void virtio_set_hwaddr(struct virtio_hw *hw);
 static void virtio_get_hwaddr(struct virtio_hw *hw);
 
-static void virtio_dev_rx_queue_release(__rte_unused void *rxq);
-static void virtio_dev_tx_queue_release(__rte_unused void *txq);
-
-static void virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats);
+static void 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);
+static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
+				       struct rte_eth_xstat_name *xstats_names,
+				       unsigned limit);
 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,
@@ -103,30 +103,75 @@ 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_LEGACY_DEVICEID_NET) },
+	{ RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_MODERN_DEVICEID_NET) },
+	{ .vendor_id = 0, /* sentinel */ },
+};
 
-#define RTE_PCI_DEV_ID_DECL_VIRTIO(vend, dev) {RTE_PCI_DEVICE(vend, dev)},
-#include "rte_pci_dev_ids.h"
+struct rte_virtio_xstats_name_off {
+	char name[RTE_ETH_XSTATS_NAME_SIZE];
+	unsigned offset;
+};
 
-{ .vendor_id = 0, /* sentinel */ },
+/* [rt]x_qX_ is prepended to the name string here */
+static const struct rte_virtio_xstats_name_off rte_virtio_rxq_stat_strings[] = {
+	{"good_packets",           offsetof(struct virtnet_rx, stats.packets)},
+	{"good_bytes",             offsetof(struct virtnet_rx, stats.bytes)},
+	{"errors",                 offsetof(struct virtnet_rx, stats.errors)},
+	{"multicast_packets",      offsetof(struct virtnet_rx, stats.multicast)},
+	{"broadcast_packets",      offsetof(struct virtnet_rx, stats.broadcast)},
+	{"undersize_packets",      offsetof(struct virtnet_rx, stats.size_bins[0])},
+	{"size_64_packets",        offsetof(struct virtnet_rx, stats.size_bins[1])},
+	{"size_65_127_packets",    offsetof(struct virtnet_rx, stats.size_bins[2])},
+	{"size_128_255_packets",   offsetof(struct virtnet_rx, stats.size_bins[3])},
+	{"size_256_511_packets",   offsetof(struct virtnet_rx, stats.size_bins[4])},
+	{"size_512_1023_packets",  offsetof(struct virtnet_rx, stats.size_bins[5])},
+	{"size_1024_1518_packets", offsetof(struct virtnet_rx, stats.size_bins[6])},
+	{"size_1519_max_packets",  offsetof(struct virtnet_rx, stats.size_bins[7])},
 };
 
+/* [rt]x_qX_ is prepended to the name string here */
+static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = {
+	{"good_packets",           offsetof(struct virtnet_tx, stats.packets)},
+	{"good_bytes",             offsetof(struct virtnet_tx, stats.bytes)},
+	{"errors",                 offsetof(struct virtnet_tx, stats.errors)},
+	{"multicast_packets",      offsetof(struct virtnet_tx, stats.multicast)},
+	{"broadcast_packets",      offsetof(struct virtnet_tx, stats.broadcast)},
+	{"undersize_packets",      offsetof(struct virtnet_tx, stats.size_bins[0])},
+	{"size_64_packets",        offsetof(struct virtnet_tx, stats.size_bins[1])},
+	{"size_65_127_packets",    offsetof(struct virtnet_tx, stats.size_bins[2])},
+	{"size_128_255_packets",   offsetof(struct virtnet_tx, stats.size_bins[3])},
+	{"size_256_511_packets",   offsetof(struct virtnet_tx, stats.size_bins[4])},
+	{"size_512_1023_packets",  offsetof(struct virtnet_tx, stats.size_bins[5])},
+	{"size_1024_1518_packets", offsetof(struct virtnet_tx, stats.size_bins[6])},
+	{"size_1519_max_packets",  offsetof(struct virtnet_tx, stats.size_bins[7])},
+};
+
+#define VIRTIO_NB_RXQ_XSTATS (sizeof(rte_virtio_rxq_stat_strings) / \
+			    sizeof(rte_virtio_rxq_stat_strings[0]))
+#define VIRTIO_NB_TXQ_XSTATS (sizeof(rte_virtio_txq_stat_strings) / \
+			    sizeof(rte_virtio_txq_stat_strings[0]))
+
+struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
+
 static int
-virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl,
+virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 		int *dlen, int pkt_num)
 {
-	uint16_t head = vq->vq_desc_head_idx, i;
+	uint32_t head, i;
 	int k, sum = 0;
 	virtio_net_ctrl_ack status = ~0;
 	struct virtio_pmd_ctrl result;
+	struct virtqueue *vq;
 
 	ctrl->status = status;
 
-	if (!vq->hw->cvq) {
-		PMD_INIT_LOG(ERR,
-			     "%s(): Control queue is not supported.",
-			     __func__);
+	if (!cvq || !cvq->vq) {
+		PMD_INIT_LOG(ERR, "Control queue is not supported.");
 		return -1;
 	}
+	vq = cvq->vq;
+	head = vq->vq_desc_head_idx;
 
 	PMD_INIT_LOG(DEBUG, "vq->vq_desc_head_idx = %d, status = %d, "
 		"vq->hw->cvq = %p vq = %p",
@@ -135,7 +180,7 @@ virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl,
 	if ((vq->vq_free_cnt < ((uint32_t)pkt_num + 2)) || (pkt_num < 1))
 		return -1;
 
-	memcpy(vq->virtio_net_hdr_mz->addr, ctrl,
+	memcpy(cvq->virtio_net_hdr_mz->addr, ctrl,
 		sizeof(struct virtio_pmd_ctrl));
 
 	/*
@@ -145,14 +190,14 @@ virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl,
 	 * One RX packet for ACK.
 	 */
 	vq->vq_ring.desc[head].flags = VRING_DESC_F_NEXT;
-	vq->vq_ring.desc[head].addr = vq->virtio_net_hdr_mz->phys_addr;
+	vq->vq_ring.desc[head].addr = cvq->virtio_net_hdr_mem;
 	vq->vq_ring.desc[head].len = sizeof(struct virtio_net_ctrl_hdr);
 	vq->vq_free_cnt--;
 	i = vq->vq_ring.desc[head].next;
 
 	for (k = 0; k < pkt_num; k++) {
 		vq->vq_ring.desc[i].flags = VRING_DESC_F_NEXT;
-		vq->vq_ring.desc[i].addr = vq->virtio_net_hdr_mz->phys_addr
+		vq->vq_ring.desc[i].addr = cvq->virtio_net_hdr_mem
 			+ sizeof(struct virtio_net_ctrl_hdr)
 			+ sizeof(ctrl->status) + sizeof(uint8_t)*sum;
 		vq->vq_ring.desc[i].len = dlen[k];
@@ -162,7 +207,7 @@ virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl,
 	}
 
 	vq->vq_ring.desc[i].flags = VRING_DESC_F_WRITE;
-	vq->vq_ring.desc[i].addr = vq->virtio_net_hdr_mz->phys_addr
+	vq->vq_ring.desc[i].addr = cvq->virtio_net_hdr_mem
 			+ sizeof(struct virtio_net_ctrl_hdr);
 	vq->vq_ring.desc[i].len = sizeof(ctrl->status);
 	vq->vq_free_cnt--;
@@ -177,12 +222,12 @@ virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl,
 	virtqueue_notify(vq);
 
 	rte_rmb();
-	while (vq->vq_used_cons_idx == vq->vq_ring.used->idx) {
+	while (VIRTQUEUE_NUSED(vq) == 0) {
 		rte_rmb();
 		usleep(100);
 	}
 
-	while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) {
+	while (VIRTQUEUE_NUSED(vq)) {
 		uint32_t idx, desc_idx, used_idx;
 		struct vring_used_elem *uep;
 
@@ -207,7 +252,7 @@ virtio_send_command(struct virtqueue *vq, 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, vq->virtio_net_hdr_mz->addr,
+	memcpy(&result, cvq->virtio_net_hdr_mz->addr,
 			sizeof(struct virtio_pmd_ctrl));
 
 	return result.status;
@@ -228,7 +273,6 @@ virtio_set_multiple_queues(struct rte_eth_dev *dev, uint16_t nb_queues)
 	dlen[0] = sizeof(uint16_t);
 
 	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
-
 	if (ret) {
 		PMD_INIT_LOG(ERR, "Multiqueue configured but send command "
 			  "failed, this is too late now...");
@@ -238,169 +282,314 @@ virtio_set_multiple_queues(struct rte_eth_dev *dev, uint16_t nb_queues)
 	return 0;
 }
 
-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,
-			struct virtqueue **pvq)
+static void
+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)
+{
+	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;
+}
+
+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];
-	const struct rte_memzone *mz;
-	uint16_t vq_size;
-	int size;
+	char vq_hdr_name[VIRTQUEUE_MAX_NAME_SZ];
+	const struct rte_memzone *mz = NULL, *hdr_mz = NULL;
+	unsigned int vq_size, size;
 	struct virtio_hw *hw = dev->data->dev_private;
-	struct virtqueue  *vq = NULL;
+	struct virtnet_rx *rxvq = NULL;
+	struct virtnet_tx *txvq = NULL;
+	struct virtnet_ctl *cvq = NULL;
+	struct virtqueue *vq;
+	size_t sz_hdr_mz = 0;
+	void *sw_ring = NULL;
+	int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx);
+	int ret;
 
-	/* Write the virtqueue index to the Queue Select Field */
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_SEL, vtpci_queue_idx);
-	PMD_INIT_LOG(DEBUG, "selecting queue: %d", vtpci_queue_idx);
+	PMD_INIT_LOG(DEBUG, "setting up queue: %u", vtpci_queue_idx);
 
 	/*
 	 * Read the virtqueue size from the Queue Size field
 	 * Always power of 2 and if 0 virtqueue does not exist
 	 */
-	vq_size = VIRTIO_READ_REG_2(hw, VIRTIO_PCI_QUEUE_NUM);
-	PMD_INIT_LOG(DEBUG, "vq_size: %d nb_desc:%d", vq_size, nb_desc);
-	if (nb_desc == 0)
-		nb_desc = vq_size;
+	vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx);
+	PMD_INIT_LOG(DEBUG, "vq_size: %u", vq_size);
 	if (vq_size == 0) {
-		PMD_INIT_LOG(ERR, "%s: virtqueue does not exist", __func__);
+		PMD_INIT_LOG(ERR, "virtqueue does not exist");
 		return -EINVAL;
-	} else if (!rte_is_power_of_2(vq_size)) {
-		PMD_INIT_LOG(ERR, "%s: virtqueue size is not powerof 2", __func__);
+	}
+
+	if (!rte_is_power_of_2(vq_size)) {
+		PMD_INIT_LOG(ERR, "virtqueue size is not powerof 2");
 		return -EINVAL;
-	} else if (nb_desc != vq_size) {
-		PMD_INIT_LOG(ERR, "Warning: nb_desc(%d) is not equal to vq size (%d), fall to vq size",
-			nb_desc, vq_size);
-		nb_desc = vq_size;
 	}
 
-	if (queue_type == VTNET_RQ) {
-		snprintf(vq_name, sizeof(vq_name), "port%d_rvq%d",
-			dev->data->port_id, queue_idx);
-		vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) +
-			vq_size * sizeof(struct vq_desc_extra), RTE_CACHE_LINE_SIZE);
-	} else if (queue_type == VTNET_TQ) {
-		snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d",
-			dev->data->port_id, queue_idx);
-		vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) +
-			vq_size * sizeof(struct vq_desc_extra), RTE_CACHE_LINE_SIZE);
+	snprintf(vq_name, sizeof(vq_name), "port%d_vq%d",
+		 dev->data->port_id, vtpci_queue_idx);
+
+	size = RTE_ALIGN_CEIL(sizeof(*vq) +
+				vq_size * sizeof(struct vq_desc_extra),
+				RTE_CACHE_LINE_SIZE);
+	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) {
-		snprintf(vq_name, sizeof(vq_name), "port%d_cvq",
-			dev->data->port_id);
-		vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) +
-			vq_size * sizeof(struct vq_desc_extra),
-			RTE_CACHE_LINE_SIZE);
+		/* Allocate a page for control vq command, data and status */
+		sz_hdr_mz = PAGE_SIZE;
 	}
+
+	vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE,
+				SOCKET_ID_ANY);
 	if (vq == NULL) {
-		PMD_INIT_LOG(ERR, "%s: Can not allocate virtqueue", __func__);
-		return (-ENOMEM);
+		PMD_INIT_LOG(ERR, "can not allocate vq");
+		return -ENOMEM;
 	}
+	hw->vqs[vtpci_queue_idx] = vq;
 
 	vq->hw = hw;
-	vq->port_id = dev->data->port_id;
-	vq->queue_id = queue_idx;
 	vq->vq_queue_index = vtpci_queue_idx;
 	vq->vq_nentries = vq_size;
-	vq->vq_free_cnt = vq_size;
 
 	/*
 	 * Reserve a memzone for vring elements
 	 */
 	size = vring_size(vq_size, VIRTIO_PCI_VRING_ALIGN);
 	vq->vq_ring_size = RTE_ALIGN_CEIL(size, VIRTIO_PCI_VRING_ALIGN);
-	PMD_INIT_LOG(DEBUG, "vring_size: %d, rounded_vring_size: %d", size, vq->vq_ring_size);
+	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, 0, VIRTIO_PCI_VRING_ALIGN);
+					 SOCKET_ID_ANY,
+					 0, VIRTIO_PCI_VRING_ALIGN);
 	if (mz == NULL) {
-		rte_free(vq);
-		return -ENOMEM;
-	}
-
-	/*
-	 * Virtio PCI device VIRTIO_PCI_QUEUE_PF register is 32bit,
-	 * and only accepts 32 bit page frame number.
-	 * Check if the allocated physical memory exceeds 16TB.
-	 */
-	if ((mz->phys_addr + vq->vq_ring_size - 1) >> (VIRTIO_PCI_QUEUE_ADDR_SHIFT + 32)) {
-		PMD_INIT_LOG(ERR, "vring address shouldn't be above 16TB!");
-		rte_free(vq);
-		return -ENOMEM;
+		if (rte_errno == EEXIST)
+			mz = rte_memzone_lookup(vq_name);
+		if (mz == NULL) {
+			ret = -ENOMEM;
+			goto fail_q_alloc;
+		}
 	}
 
 	memset(mz->addr, 0, sizeof(mz->len));
-	vq->mz = mz;
+
 	vq->vq_ring_mem = mz->phys_addr;
 	vq->vq_ring_virt_mem = mz->addr;
-	PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem:      0x%"PRIx64, (uint64_t)mz->phys_addr);
-	PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%"PRIx64, (uint64_t)(uintptr_t)mz->addr);
-	vq->virtio_net_hdr_mz  = NULL;
-	vq->virtio_net_hdr_mem = 0;
+	PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem:      0x%" PRIx64,
+		     (uint64_t)mz->phys_addr);
+	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_vq%d_hdr",
+			 dev->data->port_id, vtpci_queue_idx);
+		hdr_mz = rte_memzone_reserve_aligned(vq_hdr_name, sz_hdr_mz,
+						     SOCKET_ID_ANY, 0,
+						     RTE_CACHE_LINE_SIZE);
+		if (hdr_mz == NULL) {
+			if (rte_errno == EEXIST)
+				hdr_mz = rte_memzone_lookup(vq_hdr_name);
+			if (hdr_mz == NULL) {
+				ret = -ENOMEM;
+				goto fail_q_alloc;
+			}
+		}
+	}
 
-	if (queue_type == VTNET_TQ) {
-		/*
-		 * For each xmit packet, allocate a virtio_net_hdr
-		 */
-		snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d_hdrzone",
-			dev->data->port_id, queue_idx);
-		vq->virtio_net_hdr_mz = rte_memzone_reserve_aligned(vq_name,
-			vq_size * hw->vtnet_hdr_size,
-			socket_id, 0, RTE_CACHE_LINE_SIZE);
-		if (vq->virtio_net_hdr_mz == NULL) {
-			rte_free(vq);
-			return -ENOMEM;
+	if (queue_type == VTNET_RQ) {
+		size_t sz_sw = (RTE_PMD_VIRTIO_RX_MAX_BURST + vq_size) *
+			       sizeof(vq->sw_ring[0]);
+
+		sw_ring = rte_zmalloc_socket("sw_ring", sz_sw,
+				RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+		if (!sw_ring) {
+			PMD_INIT_LOG(ERR, "can not allocate RX soft ring");
+			ret = -ENOMEM;
+			goto fail_q_alloc;
 		}
-		vq->virtio_net_hdr_mem =
-			vq->virtio_net_hdr_mz->phys_addr;
-		memset(vq->virtio_net_hdr_mz->addr, 0,
-			vq_size * hw->vtnet_hdr_size);
+
+		vq->sw_ring = sw_ring;
+		rxvq = &vq->rxq;
+		rxvq->vq = vq;
+		rxvq->port_id = dev->data->port_id;
+		rxvq->mz = mz;
+	} else if (queue_type == VTNET_TQ) {
+		txvq = &vq->txq;
+		txvq->vq = vq;
+		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;
 	} else if (queue_type == VTNET_CQ) {
-		/* Allocate a page for control vq command, data and status */
-		snprintf(vq_name, sizeof(vq_name), "port%d_cvq_hdrzone",
-			dev->data->port_id);
-		vq->virtio_net_hdr_mz = rte_memzone_reserve_aligned(vq_name,
-			PAGE_SIZE, socket_id, 0, RTE_CACHE_LINE_SIZE);
-		if (vq->virtio_net_hdr_mz == NULL) {
-			rte_free(vq);
-			return -ENOMEM;
-		}
-		vq->virtio_net_hdr_mem =
-			vq->virtio_net_hdr_mz->phys_addr;
-		memset(vq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE);
+		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);
+
+		hw->cvq = cvq;
 	}
 
-	/*
-	 * Set guest physical address of the virtqueue
-	 * in VIRTIO_PCI_QUEUE_PFN config register of device
+	/* For virtio_user case (that is when hw->dev is NULL), we use
+	 * virtual address. And we need properly set _offset_, please see
+	 * VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information.
 	 */
-	VIRTIO_WRITE_REG_4(hw, VIRTIO_PCI_QUEUE_PFN,
-			mz->phys_addr >> VIRTIO_PCI_QUEUE_ADDR_SHIFT);
-	*pvq = vq;
+	if (!hw->virtio_user_dev)
+		vq->offset = offsetof(struct rte_mbuf, buf_physaddr);
+	else {
+		vq->vq_ring_mem = (uintptr_t)mz->addr;
+		vq->offset = offsetof(struct rte_mbuf, buf_addr);
+		if (queue_type == VTNET_TQ)
+			txvq->virtio_net_hdr_mem = (uintptr_t)hdr_mz->addr;
+		else if (queue_type == VTNET_CQ)
+			cvq->virtio_net_hdr_mem = (uintptr_t)hdr_mz->addr;
+	}
+
+	if (queue_type == VTNET_TQ) {
+		struct virtio_tx_region *txr;
+		unsigned int i;
+
+		txr = hdr_mz->addr;
+		memset(txr, 0, vq_size * sizeof(*txr));
+		for (i = 0; i < vq_size; i++) {
+			struct vring_desc *start_dp = txr[i].tx_indir;
+
+			vring_desc_init(start_dp, RTE_DIM(txr[i].tx_indir));
+
+			/* first indirect descriptor is always the tx header */
+			start_dp->addr = txvq->virtio_net_hdr_mem
+				+ i * sizeof(*txr)
+				+ offsetof(struct virtio_tx_region, tx_hdr);
+
+			start_dp->len = hw->vtnet_hdr_size;
+			start_dp->flags = VRING_DESC_F_NEXT;
+		}
+	}
+
+	if (VTPCI_OPS(hw)->setup_queue(hw, vq) < 0) {
+		PMD_INIT_LOG(ERR, "setup_queue failed");
+		return -EINVAL;
+	}
+
 	return 0;
+
+fail_q_alloc:
+	rte_free(sw_ring);
+	rte_memzone_free(hdr_mz);
+	rte_memzone_free(mz);
+	rte_free(vq);
+
+	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)
 {
+	uint16_t nr_vq = virtio_get_nr_vq(hw);
 	struct virtqueue *vq;
-	uint16_t nb_desc = 0;
-	int ret;
+	int queue_type;
+	uint16_t i;
+
+	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);
+	}
+
+	rte_free(hw->vqs);
+}
+
+static int
+virtio_alloc_queues(struct rte_eth_dev *dev)
+{
 	struct virtio_hw *hw = dev->data->dev_private;
+	uint16_t nr_vq = virtio_get_nr_vq(hw);
+	uint16_t i;
+	int ret;
 
-	PMD_INIT_FUNC_TRACE();
-	ret = virtio_dev_queue_setup(dev, VTNET_CQ, VTNET_SQ_CQ_QUEUE_IDX,
-			vtpci_queue_idx, nb_desc, socket_id, &vq);
+	hw->vqs = rte_zmalloc(NULL, sizeof(struct virtqueue *) * nr_vq, 0);
+	if (!hw->vqs) {
+		PMD_INIT_LOG(ERR, "failed to allocate vqs");
+		return -ENOMEM;
+	}
 
-	if (ret < 0) {
-		PMD_INIT_LOG(ERR, "control vq initialization failed");
-		return ret;
+	for (i = 0; i < nr_vq; i++) {
+		ret = virtio_init_queue(dev, i);
+		if (ret < 0) {
+			virtio_free_queues(hw);
+			return ret;
+		}
 	}
 
-	hw->cvq = vq;
 	return 0;
 }
 
@@ -408,16 +597,15 @@ static void
 virtio_dev_close(struct rte_eth_dev *dev)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
-	struct rte_pci_device *pci_dev = dev->pci_dev;
 
 	PMD_INIT_LOG(DEBUG, "virtio_dev_close");
 
 	/* reset the NIC */
-	if (pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC)
+	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(hw);
 }
 
 static void
@@ -428,13 +616,17 @@ virtio_dev_promiscuous_enable(struct rte_eth_dev *dev)
 	int dlen[1];
 	int ret;
 
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
+		PMD_INIT_LOG(INFO, "host does not support rx control\n");
+		return;
+	}
+
 	ctrl.hdr.class = VIRTIO_NET_CTRL_RX;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_RX_PROMISC;
 	ctrl.data[0] = 1;
 	dlen[0] = 1;
 
 	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
-
 	if (ret)
 		PMD_INIT_LOG(ERR, "Failed to enable promisc");
 }
@@ -447,13 +639,17 @@ virtio_dev_promiscuous_disable(struct rte_eth_dev *dev)
 	int dlen[1];
 	int ret;
 
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
+		PMD_INIT_LOG(INFO, "host does not support rx control\n");
+		return;
+	}
+
 	ctrl.hdr.class = VIRTIO_NET_CTRL_RX;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_RX_PROMISC;
 	ctrl.data[0] = 0;
 	dlen[0] = 1;
 
 	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
-
 	if (ret)
 		PMD_INIT_LOG(ERR, "Failed to disable promisc");
 }
@@ -466,13 +662,17 @@ virtio_dev_allmulticast_enable(struct rte_eth_dev *dev)
 	int dlen[1];
 	int ret;
 
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
+		PMD_INIT_LOG(INFO, "host does not support rx control\n");
+		return;
+	}
+
 	ctrl.hdr.class = VIRTIO_NET_CTRL_RX;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_RX_ALLMULTI;
 	ctrl.data[0] = 1;
 	dlen[0] = 1;
 
 	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
-
 	if (ret)
 		PMD_INIT_LOG(ERR, "Failed to enable allmulticast");
 }
@@ -485,17 +685,38 @@ virtio_dev_allmulticast_disable(struct rte_eth_dev *dev)
 	int dlen[1];
 	int ret;
 
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
+		PMD_INIT_LOG(INFO, "host does not support rx control\n");
+		return;
+	}
+
 	ctrl.hdr.class = VIRTIO_NET_CTRL_RX;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_RX_ALLMULTI;
 	ctrl.data[0] = 0;
 	dlen[0] = 1;
 
 	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
-
 	if (ret)
 		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
  */
@@ -508,17 +729,18 @@ 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,
+	.xstats_get_names        = virtio_dev_xstats_get_names,
 	.stats_reset             = virtio_dev_stats_reset,
+	.xstats_reset            = virtio_dev_stats_reset,
 	.link_update             = virtio_dev_link_update,
 	.rx_queue_setup          = virtio_dev_rx_queue_setup,
-	/* meaningfull only to multiple queue */
-	.rx_queue_release        = virtio_dev_rx_queue_release,
+	.rx_queue_release        = virtio_dev_queue_release,
 	.tx_queue_setup          = virtio_dev_tx_queue_setup,
-	/* meaningfull only to multiple queue */
-	.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,
@@ -568,69 +790,173 @@ virtio_dev_atomic_write_link_status(struct rte_eth_dev *dev,
 }
 
 static void
-virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
+virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
 	unsigned i;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
-		const struct virtqueue *txvq = dev->data->tx_queues[i];
+		const struct virtnet_tx *txvq = dev->data->tx_queues[i];
 		if (txvq == NULL)
 			continue;
 
-		stats->opackets += txvq->packets;
-		stats->obytes += txvq->bytes;
-		stats->oerrors += txvq->errors;
+		stats->opackets += txvq->stats.packets;
+		stats->obytes += txvq->stats.bytes;
+		stats->oerrors += txvq->stats.errors;
 
 		if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
-			stats->q_opackets[i] = txvq->packets;
-			stats->q_obytes[i] = txvq->bytes;
+			stats->q_opackets[i] = txvq->stats.packets;
+			stats->q_obytes[i] = txvq->stats.bytes;
 		}
 	}
 
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
-		const struct virtqueue *rxvq = dev->data->rx_queues[i];
+		const struct virtnet_rx *rxvq = dev->data->rx_queues[i];
 		if (rxvq == NULL)
 			continue;
 
-		stats->ipackets += rxvq->packets;
-		stats->ibytes += rxvq->bytes;
-		stats->ierrors += rxvq->errors;
+		stats->ipackets += rxvq->stats.packets;
+		stats->ibytes += rxvq->stats.bytes;
+		stats->ierrors += rxvq->stats.errors;
 
 		if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) {
-			stats->q_ipackets[i] = rxvq->packets;
-			stats->q_ibytes[i] = rxvq->bytes;
+			stats->q_ipackets[i] = rxvq->stats.packets;
+			stats->q_ibytes[i] = rxvq->stats.bytes;
 		}
 	}
 
 	stats->rx_nombuf = dev->data->rx_mbuf_alloc_failed;
 }
 
+static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
+				       struct rte_eth_xstat_name *xstats_names,
+				       __rte_unused unsigned limit)
+{
+	unsigned i;
+	unsigned count = 0;
+	unsigned t;
+
+	unsigned nstats = dev->data->nb_tx_queues * VIRTIO_NB_TXQ_XSTATS +
+		dev->data->nb_rx_queues * VIRTIO_NB_RXQ_XSTATS;
+
+	if (xstats_names != NULL) {
+		/* 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];
+			if (rxvq == NULL)
+				continue;
+			for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
+				snprintf(xstats_names[count].name,
+					sizeof(xstats_names[count].name),
+					"rx_q%u_%s", i,
+					rte_virtio_rxq_stat_strings[t].name);
+				count++;
+			}
+		}
+
+		for (i = 0; i < dev->data->nb_tx_queues; i++) {
+			struct virtqueue *txvq = dev->data->tx_queues[i];
+			if (txvq == NULL)
+				continue;
+			for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
+				snprintf(xstats_names[count].name,
+					sizeof(xstats_names[count].name),
+					"tx_q%u_%s", i,
+					rte_virtio_txq_stat_strings[t].name);
+				count++;
+			}
+		}
+		return count;
+	}
+	return nstats;
+}
+
+static int
+virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
+		      unsigned n)
+{
+	unsigned i;
+	unsigned count = 0;
+
+	unsigned nstats = dev->data->nb_tx_queues * VIRTIO_NB_TXQ_XSTATS +
+		dev->data->nb_rx_queues * VIRTIO_NB_RXQ_XSTATS;
+
+	if (n < nstats)
+		return nstats;
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		struct virtnet_rx *rxvq = dev->data->rx_queues[i];
+
+		if (rxvq == NULL)
+			continue;
+
+		unsigned t;
+
+		for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
+			xstats[count].value = *(uint64_t *)(((char *)rxvq) +
+				rte_virtio_rxq_stat_strings[t].offset);
+			xstats[count].id = count;
+			count++;
+		}
+	}
+
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		struct virtnet_tx *txvq = dev->data->tx_queues[i];
+
+		if (txvq == NULL)
+			continue;
+
+		unsigned t;
+
+		for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
+			xstats[count].value = *(uint64_t *)(((char *)txvq) +
+				rte_virtio_txq_stat_strings[t].offset);
+			xstats[count].id = count;
+			count++;
+		}
+	}
+
+	return count;
+}
+
+static void
+virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
+{
+	virtio_update_stats(dev, stats);
+}
+
 static void
 virtio_dev_stats_reset(struct rte_eth_dev *dev)
 {
 	unsigned int i;
 
 	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;
 
-		txvq->packets = 0;
-		txvq->bytes = 0;
-		txvq->errors = 0;
+		txvq->stats.packets = 0;
+		txvq->stats.bytes = 0;
+		txvq->stats.errors = 0;
+		txvq->stats.multicast = 0;
+		txvq->stats.broadcast = 0;
+		memset(txvq->stats.size_bins, 0,
+		       sizeof(txvq->stats.size_bins[0]) * 8);
 	}
 
 	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;
 
-		rxvq->packets = 0;
-		rxvq->bytes = 0;
-		rxvq->errors = 0;
+		rxvq->stats.packets = 0;
+		rxvq->stats.bytes = 0;
+		rxvq->stats.errors = 0;
+		rxvq->stats.multicast = 0;
+		rxvq->stats.broadcast = 0;
+		memset(rxvq->stats.size_bins, 0,
+		       sizeof(rxvq->stats.size_bins[0]) * 8);
 	}
-
-	dev->data->rx_mbuf_alloc_failed = 0;
 }
 
 static void
@@ -654,7 +980,7 @@ virtio_get_hwaddr(struct virtio_hw *hw)
 	}
 }
 
-static int
+static void
 virtio_mac_table_set(struct virtio_hw *hw,
 		     const struct virtio_net_ctrl_mac *uc,
 		     const struct virtio_net_ctrl_mac *mc)
@@ -662,6 +988,11 @@ virtio_mac_table_set(struct virtio_hw *hw,
 	struct virtio_pmd_ctrl ctrl;
 	int err, len[2];
 
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+		PMD_DRV_LOG(INFO, "host does not support mac table");
+		return;
+	}
+
 	ctrl.hdr.class = VIRTIO_NET_CTRL_MAC;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_TABLE_SET;
 
@@ -674,8 +1005,6 @@ 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
@@ -779,303 +1108,54 @@ 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 void
-virtio_negotiate_features(struct virtio_hw *hw)
+static int
+virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 {
-	uint32_t host_features, mask;
-
-	/* checksum offload not implemented */
-	mask = VIRTIO_NET_F_CSUM | VIRTIO_NET_F_GUEST_CSUM;
-
-	/* TSO and LRO are only available when their corresponding
-	 * checksum offload feature is also negotiated.
-	 */
-	mask |= VIRTIO_NET_F_HOST_TSO4 | VIRTIO_NET_F_HOST_TSO6 | VIRTIO_NET_F_HOST_ECN;
-	mask |= VIRTIO_NET_F_GUEST_TSO4 | VIRTIO_NET_F_GUEST_TSO6 | VIRTIO_NET_F_GUEST_ECN;
-	mask |= VTNET_LRO_FEATURES;
-
-	/* not negotiating INDIRECT descriptor table support */
-	mask |= VIRTIO_RING_F_INDIRECT_DESC;
+	uint64_t host_features;
 
 	/* Prepare guest_features: feature that driver wants to support */
-	hw->guest_features = VTNET_FEATURES & ~mask;
-	PMD_INIT_LOG(DEBUG, "guest_features before negotiate = %x",
-		hw->guest_features);
+	PMD_INIT_LOG(DEBUG, "guest_features before negotiate = %" PRIx64,
+		req_features);
 
 	/* Read device(host) feature bits */
-	host_features = VIRTIO_READ_REG_4(hw, VIRTIO_PCI_HOST_FEATURES);
-	PMD_INIT_LOG(DEBUG, "host_features before negotiate = %x",
+	host_features = VTPCI_OPS(hw)->get_features(hw);
+	PMD_INIT_LOG(DEBUG, "host_features before negotiate = %" PRIx64,
 		host_features);
 
 	/*
 	 * 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 = %x",
+	PMD_INIT_LOG(DEBUG, "features after negotiate = %" PRIx64,
 		hw->guest_features);
-}
-
-#ifdef RTE_EXEC_ENV_LINUXAPP
-static int
-parse_sysfs_value(const char *filename, unsigned long *val)
-{
-	FILE *f;
-	char buf[BUFSIZ];
-	char *end = NULL;
-
-	f = fopen(filename, "r");
-	if (f == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): cannot open sysfs value %s",
-			     __func__, filename);
-		return -1;
-	}
-
-	if (fgets(buf, sizeof(buf), f) == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): cannot read sysfs value %s",
-			     __func__, filename);
-		fclose(f);
-		return -1;
-	}
-	*val = strtoul(buf, &end, 0);
-	if ((buf[0] == '\0') || (end == NULL) || (*end != '\n')) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse sysfs value %s",
-			     __func__, filename);
-		fclose(f);
-		return -1;
-	}
-	fclose(f);
-	return 0;
-}
 
-static int get_uio_dev(struct rte_pci_addr *loc, char *buf, unsigned int buflen,
-			unsigned int *uio_num)
-{
-	struct dirent *e;
-	DIR *dir;
-	char dirname[PATH_MAX];
-
-	/* depending on kernel version, uio can be located in uio/uioX
-	 * or uio:uioX */
-	snprintf(dirname, sizeof(dirname),
-		     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/uio",
-		     loc->domain, loc->bus, loc->devid, loc->function);
-	dir = opendir(dirname);
-	if (dir == NULL) {
-		/* retry with the parent directory */
-		snprintf(dirname, sizeof(dirname),
-			     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT,
-			     loc->domain, loc->bus, loc->devid, loc->function);
-		dir = opendir(dirname);
-
-		if (dir == NULL) {
-			PMD_INIT_LOG(ERR, "Cannot opendir %s", dirname);
+	if (hw->modern) {
+		if (!vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) {
+			PMD_INIT_LOG(ERR,
+				"VIRTIO_F_VERSION_1 features is not enabled.");
 			return -1;
 		}
-	}
-
-	/* take the first file starting with "uio" */
-	while ((e = readdir(dir)) != NULL) {
-		/* format could be uio%d ...*/
-		int shortprefix_len = sizeof("uio") - 1;
-		/* ... or uio:uio%d */
-		int longprefix_len = sizeof("uio:uio") - 1;
-		char *endptr;
-
-		if (strncmp(e->d_name, "uio", 3) != 0)
-			continue;
-
-		/* first try uio%d */
-		errno = 0;
-		*uio_num = strtoull(e->d_name + shortprefix_len, &endptr, 10);
-		if (errno == 0 && endptr != (e->d_name + shortprefix_len)) {
-			snprintf(buf, buflen, "%s/uio%u", dirname, *uio_num);
-			break;
-		}
-
-		/* then try uio:uio%d */
-		errno = 0;
-		*uio_num = strtoull(e->d_name + longprefix_len, &endptr, 10);
-		if (errno == 0 && endptr != (e->d_name + longprefix_len)) {
-			snprintf(buf, buflen, "%s/uio:uio%u", dirname,
-				     *uio_num);
-			break;
-		}
-	}
-	closedir(dir);
-
-	/* No uio resource found */
-	if (e == NULL) {
-		PMD_INIT_LOG(ERR, "Could not find uio resource");
-		return -1;
-	}
-
-	return 0;
-}
-
-static int
-virtio_has_msix(const struct rte_pci_addr *loc)
-{
-	DIR *d;
-	char dirname[PATH_MAX];
-
-	snprintf(dirname, sizeof(dirname),
-		     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/msi_irqs",
-		     loc->domain, loc->bus, loc->devid, loc->function);
-
-	d = opendir(dirname);
-	if (d)
-		closedir(d);
-
-	return (d != NULL);
-}
-
-/* Extract I/O port numbers from sysfs */
-static int virtio_resource_init_by_uio(struct rte_pci_device *pci_dev)
-{
-	char dirname[PATH_MAX];
-	char filename[PATH_MAX];
-	unsigned long start, size;
-	unsigned int uio_num;
-
-	if (get_uio_dev(&pci_dev->addr, dirname, sizeof(dirname), &uio_num) < 0)
-		return -1;
-
-	/* get portio size */
-	snprintf(filename, sizeof(filename),
-		     "%s/portio/port0/size", dirname);
-	if (parse_sysfs_value(filename, &size) < 0) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse size",
-			     __func__);
-		return -1;
-	}
-
-	/* get portio start */
-	snprintf(filename, sizeof(filename),
-		 "%s/portio/port0/start", dirname);
-	if (parse_sysfs_value(filename, &start) < 0) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse portio start",
-			     __func__);
-		return -1;
-	}
-	pci_dev->mem_resource[0].addr = (void *)(uintptr_t)start;
-	pci_dev->mem_resource[0].len =  (uint64_t)size;
-	PMD_INIT_LOG(DEBUG,
-		     "PCI Port IO found start=0x%lx with size=0x%lx",
-		     start, size);
-
-	/* save fd */
-	memset(dirname, 0, sizeof(dirname));
-	snprintf(dirname, sizeof(dirname), "/dev/uio%u", uio_num);
-	pci_dev->intr_handle.fd = open(dirname, O_RDWR);
-	if (pci_dev->intr_handle.fd < 0) {
-		PMD_INIT_LOG(ERR, "Cannot open %s: %s\n",
-			dirname, strerror(errno));
-		return -1;
-	}
-
-	pci_dev->intr_handle.type = RTE_INTR_HANDLE_UIO;
-	pci_dev->driver->drv_flags |= RTE_PCI_DRV_INTR_LSC;
-
-	return 0;
-}
-
-/* Extract port I/O numbers from proc/ioports */
-static int virtio_resource_init_by_ioports(struct rte_pci_device *pci_dev)
-{
-	uint16_t start, end;
-	int size;
-	FILE *fp;
-	char *line = NULL;
-	char pci_id[16];
-	int found = 0;
-	size_t linesz;
-
-	snprintf(pci_id, sizeof(pci_id), PCI_PRI_FMT,
-		 pci_dev->addr.domain,
-		 pci_dev->addr.bus,
-		 pci_dev->addr.devid,
-		 pci_dev->addr.function);
-
-	fp = fopen("/proc/ioports", "r");
-	if (fp == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): can't open ioports", __func__);
-		return -1;
-	}
-
-	while (getdelim(&line, &linesz, '\n', fp) > 0) {
-		char *ptr = line;
-		char *left;
-		int n;
-
-		n = strcspn(ptr, ":");
-		ptr[n] = 0;
-		left = &ptr[n+1];
-
-		while (*left && isspace(*left))
-			left++;
-
-		if (!strncmp(left, pci_id, strlen(pci_id))) {
-			found = 1;
-
-			while (*ptr && isspace(*ptr))
-				ptr++;
-
-			sscanf(ptr, "%04hx-%04hx", &start, &end);
-			size = end - start + 1;
-
-			break;
+		vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_FEATURES_OK);
+		if (!(vtpci_get_status(hw) & VIRTIO_CONFIG_STATUS_FEATURES_OK)) {
+			PMD_INIT_LOG(ERR,
+				"failed to set FEATURES_OK status!");
+			return -1;
 		}
 	}
 
-	free(line);
-	fclose(fp);
-
-	if (!found)
-		return -1;
-
-	pci_dev->mem_resource[0].addr = (void *)(uintptr_t)(uint32_t)start;
-	pci_dev->mem_resource[0].len =  (uint64_t)size;
-	PMD_INIT_LOG(DEBUG,
-		"PCI Port IO found start=0x%x with size=0x%x",
-		start, size);
-
-	/* can't support lsc interrupt without uio */
-	pci_dev->driver->drv_flags &= ~RTE_PCI_DRV_INTR_LSC;
-
-	return 0;
-}
-
-/* Extract I/O port numbers from sysfs */
-static int virtio_resource_init(struct rte_pci_device *pci_dev)
-{
-	if (virtio_resource_init_by_uio(pci_dev) == 0)
-		return 0;
-	else
-		return virtio_resource_init_by_ioports(pci_dev);
-}
-
-#else
-static int
-virtio_has_msix(const struct rte_pci_addr *loc __rte_unused)
-{
-	/* nic_uio does not enable interrupts, return 0 (false). */
-	return 0;
-}
+	hw->req_guest_features = req_features;
 
-static int virtio_resource_init(struct rte_pci_device *pci_dev __rte_unused)
-{
-	/* no setup required */
 	return 0;
 }
-#endif
 
 /*
  * Process Virtio Config changed interrupt and call the callback
  * if link state changed.
  */
 static void
-virtio_interrupt_handler(__rte_unused struct rte_intr_handle *handle,
+virtio_interrupt_handler(struct rte_intr_handle *handle,
 			 void *param)
 {
 	struct rte_eth_dev *dev = param;
@@ -1086,13 +1166,13 @@ virtio_interrupt_handler(__rte_unused struct rte_intr_handle *handle,
 	isr = vtpci_isr(hw);
 	PMD_DRV_LOG(INFO, "interrupt status = %#x", isr);
 
-	if (rte_intr_enable(&dev->pci_dev->intr_handle) < 0)
+	if (rte_intr_enable(handle) < 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);
+						      RTE_ETH_EVENT_INTR_LSC, NULL);
 	}
 
 }
@@ -1107,44 +1187,15 @@ 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.
- */
+/* reset device and renegotiate features if needed */
 static int
-eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
+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;
-	uint32_t offset_conf = sizeof(config->mac);
-	struct rte_pci_device *pci_dev;
-
-	RTE_BUILD_BUG_ON(RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr));
-
-	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", 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",
-			ETHER_ADDR_LEN);
-		return -ENOMEM;
-	}
-
-	pci_dev = eth_dev->pci_dev;
-	if (virtio_resource_init(pci_dev) < 0)
-		return -1;
-
-	hw->use_msix = virtio_has_msix(&pci_dev->addr);
-	hw->io_base = (uint32_t)(uintptr_t)pci_dev->mem_resource[0].addr;
+	struct rte_pci_device *pci_dev = NULL;
+	int ret;
 
 	/* Reset the device although not necessary at startup */
 	vtpci_reset(hw);
@@ -1154,12 +1205,26 @@ 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);
-	virtio_negotiate_features(hw);
+	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))
+		eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
+	else
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
+
+	if (eth_dev->device) {
+		pci_dev = RTE_DEV_TO_PCI(eth_dev->device);
+		rte_eth_copy_pci_info(eth_dev, pci_dev);
+		eth_dev->data->dev_flags = RTE_ETH_DEV_DETACHABLE;
+	}
 
 	rx_func_get(eth_dev);
 
 	/* Setting up rx_header size for the device */
-	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF))
+	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) ||
+	    vtpci_with_feature(hw, VIRTIO_F_VERSION_1))
 		hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	else
 		hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr);
@@ -1176,8 +1241,14 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) {
 		config = &local_config;
 
+		vtpci_read_dev_config(hw,
+			offsetof(struct virtio_net_config, mac),
+			&config->mac, sizeof(config->mac));
+
 		if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
-			offset_conf += sizeof(config->status);
+			vtpci_read_dev_config(hw,
+				offsetof(struct virtio_net_config, status),
+				&config->status, sizeof(config->status));
 		} else {
 			PMD_INIT_LOG(DEBUG,
 				     "VIRTIO_NET_F_STATUS is not supported");
@@ -1185,25 +1256,17 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 		}
 
 		if (vtpci_with_feature(hw, VIRTIO_NET_F_MQ)) {
-			offset_conf += sizeof(config->max_virtqueue_pairs);
+			vtpci_read_dev_config(hw,
+				offsetof(struct virtio_net_config, max_virtqueue_pairs),
+				&config->max_virtqueue_pairs,
+				sizeof(config->max_virtqueue_pairs));
 		} else {
 			PMD_INIT_LOG(DEBUG,
 				     "VIRTIO_NET_F_MQ is not supported");
 			config->max_virtqueue_pairs = 1;
 		}
 
-		vtpci_read_dev_config(hw, 0, (uint8_t *)config, offset_conf);
-
-		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);
@@ -1214,68 +1277,191 @@ 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;
 	}
 
-	eth_dev->data->nb_rx_queues = hw->max_rx_queues;
-	eth_dev->data->nb_tx_queues = hw->max_tx_queues;
+	ret = virtio_alloc_queues(eth_dev);
+	if (ret < 0)
+		return ret;
+	vtpci_reinit_complete(hw);
 
-	PMD_INIT_LOG(DEBUG, "hw->max_rx_queues=%d   hw->max_tx_queues=%d",
-			hw->max_rx_queues, hw->max_tx_queues);
-	PMD_INIT_LOG(DEBUG, "port %d vendorID=0x%x deviceID=0x%x",
+	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);
 
-	/* Setup interrupt callback  */
-	if (pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC)
-		rte_intr_callback_register(&pci_dev->intr_handle,
-				   virtio_interrupt_handler, eth_dev);
-
-	virtio_dev_cq_start(eth_dev);
-
 	return 0;
 }
 
-static struct eth_driver rte_virtio_pmd = {
-	{
-		.name = "rte_virtio_pmd",
-		.id_table = pci_id_virtio_map,
-	},
-	.eth_dev_init = eth_virtio_dev_init,
-	.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.
+ * Remap the PCI device again (IO port map for legacy device and
+ * memory map for modern device), so that the secondary process
+ * could have the PCI initiated correctly.
  */
 static int
-rte_virtio_pmd_init(const char *name __rte_unused,
-		    const char *param __rte_unused)
+virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw)
 {
-	if (rte_eal_iopl_init() != 0) {
-		PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
-		return -1;
+	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
+		 * in secondary process would equal to the one mapped in
+		 * the primary process: error will be returned if that
+		 * requirement is not met.
+		 *
+		 * That said, we could simply reuse all cap pointers
+		 * (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)) {
+			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)
+			return -1;
 	}
 
-	rte_eth_driver_register(&rte_virtio_pmd);
 	return 0;
 }
 
+static void
+virtio_set_vtpci_ops(struct virtio_hw *hw)
+{
+	if (hw->virtio_user_dev)
+		VTPCI_OPS(hw) = &virtio_user_ops;
+	else if (hw->modern)
+		VTPCI_OPS(hw) = &modern_ops;
+	else
+		VTPCI_OPS(hw) = &legacy_ops;
+}
+
 /*
- * Only 1 queue is supported, no queue release related operation
+ * This function is based on probe() function in virtio_pci.c
+ * It returns 0 on success.
  */
-static void
-virtio_dev_rx_queue_release(__rte_unused void *rxq)
+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);
+			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);
+		}
+		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;
+	}
+
+	/* For virtio_user case the hw->virtio_user_dev is populated by
+	 * 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);
+		if (ret)
+			return ret;
+	}
+
+	hw->port_id = eth_dev->data->port_id;
+	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(eth_dev->intr_handle,
+			virtio_interrupt_handler, eth_dev);
+
+	return 0;
+}
+
+static int
+eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 {
+	PMD_INIT_FUNC_TRACE();
+
+	if (rte_eal_process_type() == RTE_PROC_SECONDARY)
+		return -EPERM;
+
+	virtio_dev_stop(eth_dev);
+	virtio_dev_close(eth_dev);
+
+	eth_dev->dev_ops = NULL;
+	eth_dev->tx_pkt_burst = NULL;
+	eth_dev->rx_pkt_burst = NULL;
+
+	rte_free(eth_dev->data->mac_addrs);
+	eth_dev->data->mac_addrs = NULL;
+
+	/* reset interrupt callback  */
+	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
+		rte_intr_callback_unregister(eth_dev->intr_handle,
+						virtio_interrupt_handler,
+						eth_dev);
+	if (eth_dev->device)
+		rte_eal_pci_unmap_device(RTE_DEV_TO_PCI(eth_dev->device));
+
+	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,
+	},
+	.eth_dev_init = eth_virtio_dev_init,
+	.eth_dev_uninit = eth_virtio_dev_uninit,
+	.dev_private_size = sizeof(struct virtio_hw),
+};
+
+RTE_INIT(rte_virtio_pmd_init);
 static void
-virtio_dev_tx_queue_release(__rte_unused void *txq)
+rte_virtio_pmd_init(void)
 {
+	if (rte_eal_iopl_init() != 0) {
+		PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
+		return;
+	}
+
+	rte_eal_pci_register(&rte_virtio_pmd.pci_drv);
 }
 
 /*
@@ -1287,15 +1473,44 @@ 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;
-	struct rte_pci_device *pci_dev = dev->pci_dev;
+	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
@@ -1305,7 +1520,7 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 		return -ENOTSUP;
 	}
 
-	if (pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC)
+	if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
 		if (vtpci_irq_config(hw, 0) == VIRTIO_MSI_NO_VECTOR) {
 			PMD_DRV_LOG(ERR, "failed to set config vector");
 			return -EBUSY;
@@ -1319,18 +1534,18 @@ static int
 virtio_dev_start(struct rte_eth_dev *dev)
 {
 	uint16_t nb_queues, i;
+	struct virtnet_rx *rxvq;
+	struct virtnet_tx *txvq __rte_unused;
 	struct virtio_hw *hw = dev->data->dev_private;
-	struct rte_pci_device *pci_dev = dev->pci_dev;
 
 	/* check if lsc interrupt feature is enabled */
-	if ((dev->data->dev_conf.intr_conf.lsc) &&
-		(pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC)) {
-		if (!vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
+	if (dev->data->dev_conf.intr_conf.lsc) {
+		if (!(dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)) {
 			PMD_DRV_LOG(ERR, "link status not supported by host");
 			return -ENOTSUP;
 		}
 
-		if (rte_intr_enable(&dev->pci_dev->intr_handle) < 0) {
+		if (rte_intr_enable(dev->intr_handle) < 0) {
 			PMD_DRV_LOG(ERR, "interrupt enable failed");
 			return -EIO;
 		}
@@ -1339,38 +1554,34 @@ 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++)
-		virtqueue_notify(dev->data->rx_queues[i]);
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		rxvq = dev->data->rx_queues[i];
+		virtqueue_notify(rxvq->vq);
+	}
 
 	PMD_INIT_LOG(DEBUG, "Notified backend at initialization");
 
-	for (i = 0; i < dev->data->nb_rx_queues; i++)
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]);
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		rxvq = dev->data->rx_queues[i];
+		VIRTQUEUE_DUMP(rxvq->vq);
+	}
 
-	for (i = 0; i < dev->data->nb_tx_queues; i++)
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[i]);
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		txvq = dev->data->tx_queues[i];
+		VIRTQUEUE_DUMP(txvq->vq);
+	}
 
 	return 0;
 }
@@ -1381,12 +1592,14 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
 	int i, mbuf_num = 0;
 
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		struct virtnet_rx *rxvq = dev->data->rx_queues[i];
+
 		PMD_INIT_LOG(DEBUG,
 			     "Before freeing rxq[%d] used and unused buf", i);
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]);
+		VIRTQUEUE_DUMP(rxvq->vq);
 
-		while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused(
-					dev->data->rx_queues[i])) != NULL) {
+		PMD_INIT_LOG(DEBUG, "rx_queues[%d]=%p", i, rxvq);
+		while ((buf = virtqueue_detatch_unused(rxvq->vq)) != NULL) {
 			rte_pktmbuf_free(buf);
 			mbuf_num++;
 		}
@@ -1394,27 +1607,27 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
 		PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num);
 		PMD_INIT_LOG(DEBUG,
 			     "After freeing rxq[%d] used and unused buf", i);
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]);
+		VIRTQUEUE_DUMP(rxvq->vq);
 	}
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		struct virtnet_tx *txvq = dev->data->tx_queues[i];
+
 		PMD_INIT_LOG(DEBUG,
 			     "Before freeing txq[%d] used and unused bufs",
 			     i);
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[i]);
+		VIRTQUEUE_DUMP(txvq->vq);
 
 		mbuf_num = 0;
-		while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused(
-					dev->data->tx_queues[i])) != NULL) {
+		while ((buf = virtqueue_detatch_unused(txvq->vq)) != NULL) {
 			rte_pktmbuf_free(buf);
-
 			mbuf_num++;
 		}
 
 		PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num);
 		PMD_INIT_LOG(DEBUG,
 			     "After freeing txq[%d] used and unused buf", i);
-		VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[i]);
+		VIRTQUEUE_DUMP(txvq->vq);
 	}
 }
 
@@ -1429,7 +1642,7 @@ virtio_dev_stop(struct rte_eth_dev *dev)
 	PMD_INIT_LOG(DEBUG, "stop");
 
 	if (dev->data->dev_conf.intr_conf.lsc)
-		rte_intr_disable(&dev->pci_dev->intr_handle);
+		rte_intr_disable(dev->intr_handle);
 
 	memset(&link, 0, sizeof(link));
 	virtio_dev_atomic_write_link_status(dev, &link);
@@ -1444,7 +1657,7 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 	memset(&link, 0, sizeof(link));
 	virtio_dev_atomic_read_link_status(dev, &link);
 	old = link;
-	link.link_duplex = FULL_DUPLEX;
+	link.link_duplex = ETH_LINK_FULL_DUPLEX;
 	link.link_speed  = SPEED_10G;
 
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
@@ -1453,16 +1666,16 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 				offsetof(struct virtio_net_config, status),
 				&status, sizeof(status));
 		if ((status & VIRTIO_NET_S_LINK_UP) == 0) {
-			link.link_status = 0;
+			link.link_status = ETH_LINK_DOWN;
 			PMD_INIT_LOG(DEBUG, "Port %d is down",
 				     dev->data->port_id);
 		} else {
-			link.link_status = 1;
+			link.link_status = ETH_LINK_UP;
 			PMD_INIT_LOG(DEBUG, "Port %d is up",
 				     dev->data->port_id);
 		}
 	} else {
-		link.link_status = 1;   /* Link up */
+		link.link_status = ETH_LINK_UP;
 	}
 	virtio_dev_atomic_write_link_status(dev, &link);
 
@@ -1472,17 +1685,36 @@ 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;
 
-	dev_info->driver_name = dev->driver->pci_drv.name;
-	dev_info->max_rx_queues = (uint16_t)hw->max_rx_queues;
-	dev_info->max_tx_queues = (uint16_t)hw->max_tx_queues;
+	dev_info->pci_dev = dev->device ? RTE_DEV_TO_PCI(dev->device) : NULL;
+	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;
 }
 
 /*
@@ -1496,9 +1728,6 @@ __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);
+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");