X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=04aecb75983b4b004dfc8eb0fb500ab6cbd253ae;hb=e876497c4f6baef09fbee14b702025b67f4fed1c;hp=2ba66d2916c25027c6355d84cefa2c4d6f6ba363;hpb=705dced4a72a1053368c84c4b68f04f028a78b30;p=dpdk.git

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 2ba66d2916..04aecb7598 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -35,6 +35,7 @@
 #include "virtio_logs.h"
 #include "virtqueue.h"
 #include "virtio_rxtx.h"
+#include "virtio_user/virtio_user_dev.h"
 
 static int eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev);
 static int  virtio_dev_configure(struct rte_eth_dev *dev);
@@ -65,13 +66,12 @@ 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 int virtio_mac_addr_add(struct rte_eth_dev *dev,
-				struct ether_addr *mac_addr,
+				struct rte_ether_addr *mac_addr,
 				uint32_t index, uint32_t vmdq);
 static void virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index);
 static int virtio_mac_addr_set(struct rte_eth_dev *dev,
-				struct ether_addr *mac_addr);
+				struct rte_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(
@@ -141,38 +141,112 @@ static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = {
 
 struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
 
-static int
-virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
-		int *dlen, int pkt_num)
+static struct virtio_pmd_ctrl *
+virtio_send_command_packed(struct virtnet_ctl *cvq,
+			   struct virtio_pmd_ctrl *ctrl,
+			   int *dlen, int pkt_num)
 {
-	uint32_t head, i;
-	int k, sum = 0;
-	virtio_net_ctrl_ack status = ~0;
+	struct virtqueue *vq = cvq->vq;
+	int head;
+	struct vring_packed_desc *desc = vq->vq_packed.ring.desc;
 	struct virtio_pmd_ctrl *result;
-	struct virtqueue *vq;
+	uint16_t flags;
+	int sum = 0;
+	int nb_descs = 0;
+	int k;
 
-	ctrl->status = status;
+	/*
+	 * Format is enforced in qemu code:
+	 * One TX packet for header;
+	 * At least one TX packet per argument;
+	 * One RX packet for ACK.
+	 */
+	head = vq->vq_avail_idx;
+	flags = vq->vq_packed.cached_flags;
+	desc[head].addr = cvq->virtio_net_hdr_mem;
+	desc[head].len = sizeof(struct virtio_net_ctrl_hdr);
+	vq->vq_free_cnt--;
+	nb_descs++;
+	if (++vq->vq_avail_idx >= vq->vq_nentries) {
+		vq->vq_avail_idx -= vq->vq_nentries;
+		vq->vq_packed.cached_flags ^= VRING_PACKED_DESC_F_AVAIL_USED;
+	}
 
-	if (!cvq || !cvq->vq) {
-		PMD_INIT_LOG(ERR, "Control queue is not supported.");
-		return -1;
+	for (k = 0; k < pkt_num; k++) {
+		desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem
+			+ sizeof(struct virtio_net_ctrl_hdr)
+			+ sizeof(ctrl->status) + sizeof(uint8_t) * sum;
+		desc[vq->vq_avail_idx].len = dlen[k];
+		desc[vq->vq_avail_idx].flags = VRING_DESC_F_NEXT |
+			vq->vq_packed.cached_flags;
+		sum += dlen[k];
+		vq->vq_free_cnt--;
+		nb_descs++;
+		if (++vq->vq_avail_idx >= vq->vq_nentries) {
+			vq->vq_avail_idx -= vq->vq_nentries;
+			vq->vq_packed.cached_flags ^=
+				VRING_PACKED_DESC_F_AVAIL_USED;
+		}
 	}
 
-	rte_spinlock_lock(&cvq->lock);
-	vq = cvq->vq;
-	head = vq->vq_desc_head_idx;
+	desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem
+		+ sizeof(struct virtio_net_ctrl_hdr);
+	desc[vq->vq_avail_idx].len = sizeof(ctrl->status);
+	desc[vq->vq_avail_idx].flags = VRING_DESC_F_WRITE |
+		vq->vq_packed.cached_flags;
+	vq->vq_free_cnt--;
+	nb_descs++;
+	if (++vq->vq_avail_idx >= vq->vq_nentries) {
+		vq->vq_avail_idx -= vq->vq_nentries;
+		vq->vq_packed.cached_flags ^= VRING_PACKED_DESC_F_AVAIL_USED;
+	}
 
-	PMD_INIT_LOG(DEBUG, "vq->vq_desc_head_idx = %d, status = %d, "
-		"vq->hw->cvq = %p vq = %p",
-		vq->vq_desc_head_idx, status, vq->hw->cvq, vq);
+	virtio_wmb(vq->hw->weak_barriers);
+	desc[head].flags = VRING_DESC_F_NEXT | flags;
 
-	if (vq->vq_free_cnt < pkt_num + 2 || pkt_num < 1) {
-		rte_spinlock_unlock(&cvq->lock);
-		return -1;
+	virtio_wmb(vq->hw->weak_barriers);
+	virtqueue_notify(vq);
+
+	/* wait for used descriptors in virtqueue */
+	while (!desc_is_used(&desc[head], vq))
+		usleep(100);
+
+	virtio_rmb(vq->hw->weak_barriers);
+
+	/* now get used descriptors */
+	vq->vq_free_cnt += nb_descs;
+	vq->vq_used_cons_idx += nb_descs;
+	if (vq->vq_used_cons_idx >= vq->vq_nentries) {
+		vq->vq_used_cons_idx -= vq->vq_nentries;
+		vq->vq_packed.used_wrap_counter ^= 1;
 	}
 
-	memcpy(cvq->virtio_net_hdr_mz->addr, ctrl,
-		sizeof(struct virtio_pmd_ctrl));
+	PMD_INIT_LOG(DEBUG, "vq->vq_free_cnt=%d\n"
+			"vq->vq_avail_idx=%d\n"
+			"vq->vq_used_cons_idx=%d\n"
+			"vq->vq_packed.cached_flags=0x%x\n"
+			"vq->vq_packed.used_wrap_counter=%d\n",
+			vq->vq_free_cnt,
+			vq->vq_avail_idx,
+			vq->vq_used_cons_idx,
+			vq->vq_packed.cached_flags,
+			vq->vq_packed.used_wrap_counter);
+
+	result = cvq->virtio_net_hdr_mz->addr;
+	return result;
+}
+
+static struct virtio_pmd_ctrl *
+virtio_send_command_split(struct virtnet_ctl *cvq,
+			  struct virtio_pmd_ctrl *ctrl,
+			  int *dlen, int pkt_num)
+{
+	struct virtio_pmd_ctrl *result;
+	struct virtqueue *vq = cvq->vq;
+	uint32_t head, i;
+	int k, sum = 0;
+
+	head = vq->vq_desc_head_idx;
 
 	/*
 	 * Format is enforced in qemu code:
@@ -180,30 +254,30 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 	 * At least one TX packet per argument;
 	 * One RX packet for ACK.
 	 */
-	vq->vq_ring.desc[head].flags = VRING_DESC_F_NEXT;
-	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_split.ring.desc[head].flags = VRING_DESC_F_NEXT;
+	vq->vq_split.ring.desc[head].addr = cvq->virtio_net_hdr_mem;
+	vq->vq_split.ring.desc[head].len = sizeof(struct virtio_net_ctrl_hdr);
 	vq->vq_free_cnt--;
-	i = vq->vq_ring.desc[head].next;
+	i = vq->vq_split.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 = cvq->virtio_net_hdr_mem
+		vq->vq_split.ring.desc[i].flags = VRING_DESC_F_NEXT;
+		vq->vq_split.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];
+		vq->vq_split.ring.desc[i].len = dlen[k];
 		sum += dlen[k];
 		vq->vq_free_cnt--;
-		i = vq->vq_ring.desc[i].next;
+		i = vq->vq_split.ring.desc[i].next;
 	}
 
-	vq->vq_ring.desc[i].flags = VRING_DESC_F_WRITE;
-	vq->vq_ring.desc[i].addr = cvq->virtio_net_hdr_mem
+	vq->vq_split.ring.desc[i].flags = VRING_DESC_F_WRITE;
+	vq->vq_split.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_split.ring.desc[i].len = sizeof(ctrl->status);
 	vq->vq_free_cnt--;
 
-	vq->vq_desc_head_idx = vq->vq_ring.desc[i].next;
+	vq->vq_desc_head_idx = vq->vq_split.ring.desc[i].next;
 
 	vq_update_avail_ring(vq, head);
 	vq_update_avail_idx(vq);
@@ -224,16 +298,17 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 
 		used_idx = (uint32_t)(vq->vq_used_cons_idx
 				& (vq->vq_nentries - 1));
-		uep = &vq->vq_ring.used->ring[used_idx];
+		uep = &vq->vq_split.ring.used->ring[used_idx];
 		idx = (uint32_t) uep->id;
 		desc_idx = idx;
 
-		while (vq->vq_ring.desc[desc_idx].flags & VRING_DESC_F_NEXT) {
-			desc_idx = vq->vq_ring.desc[desc_idx].next;
+		while (vq->vq_split.ring.desc[desc_idx].flags &
+				VRING_DESC_F_NEXT) {
+			desc_idx = vq->vq_split.ring.desc[desc_idx].next;
 			vq->vq_free_cnt++;
 		}
 
-		vq->vq_ring.desc[desc_idx].next = vq->vq_desc_head_idx;
+		vq->vq_split.ring.desc[desc_idx].next = vq->vq_desc_head_idx;
 		vq->vq_desc_head_idx = idx;
 
 		vq->vq_used_cons_idx++;
@@ -244,6 +319,43 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 			vq->vq_free_cnt, vq->vq_desc_head_idx);
 
 	result = cvq->virtio_net_hdr_mz->addr;
+	return result;
+}
+
+static int
+virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
+		    int *dlen, int pkt_num)
+{
+	virtio_net_ctrl_ack status = ~0;
+	struct virtio_pmd_ctrl *result;
+	struct virtqueue *vq;
+
+	ctrl->status = status;
+
+	if (!cvq || !cvq->vq) {
+		PMD_INIT_LOG(ERR, "Control queue is not supported.");
+		return -1;
+	}
+
+	rte_spinlock_lock(&cvq->lock);
+	vq = cvq->vq;
+
+	PMD_INIT_LOG(DEBUG, "vq->vq_desc_head_idx = %d, status = %d, "
+		"vq->hw->cvq = %p vq = %p",
+		vq->vq_desc_head_idx, status, vq->hw->cvq, vq);
+
+	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));
+
+	if (vtpci_packed_queue(vq->hw))
+		result = virtio_send_command_packed(cvq, ctrl, dlen, pkt_num);
+	else
+		result = virtio_send_command_split(cvq, ctrl, dlen, pkt_num);
 
 	rte_spinlock_unlock(&cvq->lock);
 	return result->status;
@@ -294,25 +406,28 @@ 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);
+	if (vtpci_packed_queue(vq->hw)) {
+		vring_init_packed(&vq->vq_packed.ring, ring_mem,
+				  VIRTIO_PCI_VRING_ALIGN, size);
+		vring_desc_init_packed(vq, size);
+	} else {
+		struct vring *vr = &vq->vq_split.ring;
 
-	vring_desc_init(vr->desc, size);
-
+		vring_init_split(vr, ring_mem, VIRTIO_PCI_VRING_ALIGN, size);
+		vring_desc_init_split(vr->desc, size);
+	}
 	/*
 	 * Disable device(host) interrupting guest
 	 */
@@ -335,8 +450,10 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 	void *sw_ring = NULL;
 	int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx);
 	int ret;
+	int numa_node = dev->device->numa_node;
 
-	PMD_INIT_LOG(DEBUG, "setting up queue: %u", vtpci_queue_idx);
+	PMD_INIT_LOG(INFO, "setting up queue: %u on NUMA node %d",
+			vtpci_queue_idx, numa_node);
 
 	/*
 	 * Read the virtqueue size from the Queue Size field
@@ -372,7 +489,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 	}
 
 	vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE,
-				SOCKET_ID_ANY);
+				numa_node);
 	if (vq == NULL) {
 		PMD_INIT_LOG(ERR, "can not allocate vq");
 		return -ENOMEM;
@@ -382,17 +499,24 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 	vq->hw = hw;
 	vq->vq_queue_index = vtpci_queue_idx;
 	vq->vq_nentries = vq_size;
+	if (vtpci_packed_queue(hw)) {
+		vq->vq_packed.used_wrap_counter = 1;
+		vq->vq_packed.cached_flags = VRING_PACKED_DESC_F_AVAIL;
+		vq->vq_packed.event_flags_shadow = 0;
+		if (queue_type == VTNET_RQ)
+			vq->vq_packed.cached_flags |= VRING_DESC_F_WRITE;
+	}
 
 	/*
 	 * Reserve a memzone for vring elements
 	 */
-	size = vring_size(vq_size, VIRTIO_PCI_VRING_ALIGN);
+	size = vring_size(hw, 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);
 
 	mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size,
-			SOCKET_ID_ANY, RTE_MEMZONE_IOVA_CONTIG,
+			numa_node, RTE_MEMZONE_IOVA_CONTIG,
 			VIRTIO_PCI_VRING_ALIGN);
 	if (mz == NULL) {
 		if (rte_errno == EEXIST)
@@ -418,7 +542,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_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_ANY, RTE_MEMZONE_IOVA_CONTIG,
+				numa_node, RTE_MEMZONE_IOVA_CONTIG,
 				RTE_CACHE_LINE_SIZE);
 		if (hdr_mz == NULL) {
 			if (rte_errno == EEXIST)
@@ -435,7 +559,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 			       sizeof(vq->sw_ring[0]);
 
 		sw_ring = rte_zmalloc_socket("sw_ring", sz_sw,
-				RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+				RTE_CACHE_LINE_SIZE, numa_node);
 		if (!sw_ring) {
 			PMD_INIT_LOG(ERR, "can not allocate RX soft ring");
 			ret = -ENOMEM;
@@ -489,15 +613,17 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 		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_packed_queue(hw)) {
+				vring_desc_init_split(start_dp,
+						      RTE_DIM(txr[i].tx_indir));
+				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;
+			}
 		}
 	}
 
@@ -608,6 +734,17 @@ virtio_dev_close(struct rte_eth_dev *dev)
 	vtpci_reset(hw);
 	virtio_dev_free_mbufs(dev);
 	virtio_free_queues(hw);
+
+#ifdef RTE_VIRTIO_USER
+	if (hw->virtio_user_dev)
+		virtio_user_dev_uninit(hw->virtio_user_dev);
+	else
+#endif
+	if (dev->device) {
+		rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(dev));
+		if (!hw->modern)
+			rte_pci_ioport_unmap(VTPCI_IO(hw));
+	}
 }
 
 static void
@@ -707,16 +844,16 @@ 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 +
+	uint32_t ether_hdr_len = RTE_ETHER_HDR_LEN + VLAN_TAG_LEN +
 				 hw->vtnet_hdr_size;
 	uint32_t frame_size = mtu + ether_hdr_len;
 	uint32_t max_frame_size = hw->max_mtu + ether_hdr_len;
 
 	max_frame_size = RTE_MIN(max_frame_size, VIRTIO_MAX_RX_PKTLEN);
 
-	if (mtu < ETHER_MIN_MTU || frame_size > max_frame_size) {
+	if (mtu < RTE_ETHER_MIN_MTU || frame_size > max_frame_size) {
 		PMD_INIT_LOG(ERR, "MTU should be between %d and %d",
-			ETHER_MIN_MTU, max_frame_size - ether_hdr_len);
+			RTE_ETHER_MIN_MTU, max_frame_size - ether_hdr_len);
 		return -EINVAL;
 	}
 	return 0;
@@ -725,10 +862,12 @@ virtio_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 static int
 virtio_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id)
 {
+	struct virtio_hw *hw = dev->data->dev_private;
 	struct virtnet_rx *rxvq = dev->data->rx_queues[queue_id];
 	struct virtqueue *vq = rxvq->vq;
 
 	virtqueue_enable_intr(vq);
+	virtio_mb(hw->weak_barriers);
 	return 0;
 }
 
@@ -778,6 +917,21 @@ static const struct eth_dev_ops virtio_eth_dev_ops = {
 	.mac_addr_set            = virtio_mac_addr_set,
 };
 
+/*
+ * dev_ops for virtio-user in secondary processes, as we just have
+ * some limited supports currently.
+ */
+const struct eth_dev_ops virtio_user_secondary_eth_dev_ops = {
+	.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,
+	/* collect stats per queue */
+	.queue_stats_mapping_set = virtio_dev_queue_stats_mapping_set,
+};
+
 static void
 virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
@@ -955,7 +1109,7 @@ virtio_set_hwaddr(struct virtio_hw *hw)
 {
 	vtpci_write_dev_config(hw,
 			offsetof(struct virtio_net_config, mac),
-			&hw->mac_addr, ETHER_ADDR_LEN);
+			&hw->mac_addr, RTE_ETHER_ADDR_LEN);
 }
 
 static void
@@ -964,9 +1118,9 @@ virtio_get_hwaddr(struct virtio_hw *hw)
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_MAC)) {
 		vtpci_read_dev_config(hw,
 			offsetof(struct virtio_net_config, mac),
-			&hw->mac_addr, ETHER_ADDR_LEN);
+			&hw->mac_addr, RTE_ETHER_ADDR_LEN);
 	} else {
-		eth_random_addr(&hw->mac_addr[0]);
+		rte_eth_random_addr(&hw->mac_addr[0]);
 		virtio_set_hwaddr(hw);
 	}
 }
@@ -987,10 +1141,10 @@ virtio_mac_table_set(struct virtio_hw *hw,
 	ctrl.hdr.class = VIRTIO_NET_CTRL_MAC;
 	ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_TABLE_SET;
 
-	len[0] = uc->entries * ETHER_ADDR_LEN + sizeof(uc->entries);
+	len[0] = uc->entries * RTE_ETHER_ADDR_LEN + sizeof(uc->entries);
 	memcpy(ctrl.data, uc, len[0]);
 
-	len[1] = mc->entries * ETHER_ADDR_LEN + sizeof(mc->entries);
+	len[1] = mc->entries * RTE_ETHER_ADDR_LEN + sizeof(mc->entries);
 	memcpy(ctrl.data + len[0], mc, len[1]);
 
 	err = virtio_send_command(hw->cvq, &ctrl, len, 2);
@@ -1000,11 +1154,11 @@ virtio_mac_table_set(struct virtio_hw *hw,
 }
 
 static int
-virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
+virtio_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr,
 		    uint32_t index, uint32_t vmdq __rte_unused)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
-	const struct ether_addr *addrs = dev->data->mac_addrs;
+	const struct rte_ether_addr *addrs = dev->data->mac_addrs;
 	unsigned int i;
 	struct virtio_net_ctrl_mac *uc, *mc;
 
@@ -1013,18 +1167,20 @@ virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
 		return -EINVAL;
 	}
 
-	uc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(uc->entries));
+	uc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN +
+		sizeof(uc->entries));
 	uc->entries = 0;
-	mc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(mc->entries));
+	mc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN +
+		sizeof(mc->entries));
 	mc->entries = 0;
 
 	for (i = 0; i < VIRTIO_MAX_MAC_ADDRS; i++) {
-		const struct ether_addr *addr
+		const struct rte_ether_addr *addr
 			= (i == index) ? mac_addr : addrs + i;
 		struct virtio_net_ctrl_mac *tbl
-			= is_multicast_ether_addr(addr) ? mc : uc;
+			= rte_is_multicast_ether_addr(addr) ? mc : uc;
 
-		memcpy(&tbl->macs[tbl->entries++], addr, ETHER_ADDR_LEN);
+		memcpy(&tbl->macs[tbl->entries++], addr, RTE_ETHER_ADDR_LEN);
 	}
 
 	return virtio_mac_table_set(hw, uc, mc);
@@ -1034,7 +1190,7 @@ static void
 virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
-	struct ether_addr *addrs = dev->data->mac_addrs;
+	struct rte_ether_addr *addrs = dev->data->mac_addrs;
 	struct virtio_net_ctrl_mac *uc, *mc;
 	unsigned int i;
 
@@ -1043,40 +1199,43 @@ virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 		return;
 	}
 
-	uc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(uc->entries));
+	uc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN +
+		sizeof(uc->entries));
 	uc->entries = 0;
-	mc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(mc->entries));
+	mc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN +
+		sizeof(mc->entries));
 	mc->entries = 0;
 
 	for (i = 0; i < VIRTIO_MAX_MAC_ADDRS; i++) {
 		struct virtio_net_ctrl_mac *tbl;
 
-		if (i == index || is_zero_ether_addr(addrs + i))
+		if (i == index || rte_is_zero_ether_addr(addrs + i))
 			continue;
 
-		tbl = is_multicast_ether_addr(addrs + i) ? mc : uc;
-		memcpy(&tbl->macs[tbl->entries++], addrs + i, ETHER_ADDR_LEN);
+		tbl = rte_is_multicast_ether_addr(addrs + i) ? mc : uc;
+		memcpy(&tbl->macs[tbl->entries++], addrs + i,
+			RTE_ETHER_ADDR_LEN);
 	}
 
 	virtio_mac_table_set(hw, uc, mc);
 }
 
 static int
-virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
+virtio_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
 
-	memcpy(hw->mac_addr, mac_addr, ETHER_ADDR_LEN);
+	memcpy(hw->mac_addr, mac_addr, RTE_ETHER_ADDR_LEN);
 
 	/* Use atomic update if available */
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
 		struct virtio_pmd_ctrl ctrl;
-		int len = ETHER_ADDR_LEN;
+		int len = RTE_ETHER_ADDR_LEN;
 
 		ctrl.hdr.class = VIRTIO_NET_CTRL_MAC;
 		ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET;
 
-		memcpy(ctrl.data, mac_addr, ETHER_ADDR_LEN);
+		memcpy(ctrl.data, mac_addr, RTE_ETHER_ADDR_LEN);
 		return virtio_send_command(hw->cvq, &ctrl, &len, 1);
 	}
 
@@ -1155,7 +1314,7 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 			offsetof(struct virtio_net_config, mtu),
 			&config.mtu, sizeof(config.mtu));
 
-		if (config.mtu < ETHER_MIN_MTU)
+		if (config.mtu < RTE_ETHER_MIN_MTU)
 			req_features &= ~(1ULL << VIRTIO_NET_F_MTU);
 	}
 
@@ -1253,7 +1412,7 @@ virtio_notify_peers(struct rte_eth_dev *dev)
 		return;
 
 	rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool,
-			(struct ether_addr *)hw->mac_addr);
+			(struct rte_ether_addr *)hw->mac_addr);
 	if (rarp_mbuf == NULL) {
 		PMD_DRV_LOG(ERR, "failed to make RARP packet.");
 		return;
@@ -1326,35 +1485,60 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 {
 	struct virtio_hw *hw = eth_dev->data->dev_private;
 
-	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 (hw->use_inorder_rx) {
-		PMD_INIT_LOG(INFO,
-			"virtio: using inorder mergeable buffer Rx path on port %u",
-			eth_dev->data->port_id);
-		eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts_inorder;
-	} else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+	eth_dev->tx_pkt_prepare = virtio_xmit_pkts_prepare;
+	if (vtpci_packed_queue(hw)) {
 		PMD_INIT_LOG(INFO,
-			"virtio: using mergeable buffer Rx path on port %u",
+			"virtio: using packed ring %s Tx path on port %u",
+			hw->use_inorder_tx ? "inorder" : "standard",
 			eth_dev->data->port_id);
-		eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts;
+		eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed;
 	} 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_inorder_tx) {
+			PMD_INIT_LOG(INFO, "virtio: using inorder Tx path on port %u",
+				eth_dev->data->port_id);
+			eth_dev->tx_pkt_burst = virtio_xmit_pkts_inorder;
+		} 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;
+		}
 	}
 
-	if (hw->use_inorder_tx) {
-		PMD_INIT_LOG(INFO, "virtio: using inorder Tx path on port %u",
-			eth_dev->data->port_id);
-		eth_dev->tx_pkt_burst = virtio_xmit_pkts_inorder;
+	if (vtpci_packed_queue(hw)) {
+		if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+			PMD_INIT_LOG(INFO,
+				"virtio: using packed ring mergeable buffer Rx path on port %u",
+				eth_dev->data->port_id);
+			eth_dev->rx_pkt_burst =
+				&virtio_recv_mergeable_pkts_packed;
+		} else {
+			PMD_INIT_LOG(INFO,
+				"virtio: using packed ring standard Rx path on port %u",
+				eth_dev->data->port_id);
+			eth_dev->rx_pkt_burst = &virtio_recv_pkts_packed;
+		}
 	} 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;
+		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 (hw->use_inorder_rx) {
+			PMD_INIT_LOG(INFO,
+				"virtio: using inorder Rx path on port %u",
+				eth_dev->data->port_id);
+			eth_dev->rx_pkt_burst =	&virtio_recv_pkts_inorder;
+		} 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 {
+			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;
+		}
 	}
+
 }
 
 /* Only support 1:1 queue/interrupt mapping so far.
@@ -1472,10 +1656,10 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	if (virtio_negotiate_features(hw, req_features) < 0)
 		return -1;
 
-	if (!hw->virtio_user_dev) {
+	hw->weak_barriers = !vtpci_with_feature(hw, VIRTIO_F_ORDER_PLATFORM);
+
+	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) &&
@@ -1486,14 +1670,15 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 
 	/* 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))
+	    vtpci_with_feature(hw, VIRTIO_F_VERSION_1) ||
+	    vtpci_with_feature(hw, VIRTIO_F_RING_PACKED))
 		hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	else
 		hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr);
 
 	/* Copy the permanent MAC address to: virtio_hw */
 	virtio_get_hwaddr(hw);
-	ether_addr_copy((struct ether_addr *) hw->mac_addr,
+	rte_ether_addr_copy((struct rte_ether_addr *)hw->mac_addr,
 			&eth_dev->data->mac_addrs[0]);
 	PMD_INIT_LOG(DEBUG,
 		     "PORT MAC: %02X:%02X:%02X:%02X:%02X:%02X",
@@ -1541,7 +1726,7 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 			 * time, but check again in case it has changed since
 			 * then, which should not happen.
 			 */
-			if (config->mtu < ETHER_MIN_MTU) {
+			if (config->mtu < RTE_ETHER_MIN_MTU) {
 				PMD_INIT_LOG(ERR, "invalid max MTU value (%u)",
 						config->mtu);
 				return -1;
@@ -1552,7 +1737,7 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 			eth_dev->data->mtu = config->mtu;
 
 		} else {
-			hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN -
+			hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - RTE_ETHER_HDR_LEN -
 				VLAN_TAG_LEN - hw->vtnet_hdr_size;
 		}
 
@@ -1567,7 +1752,7 @@ 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 -
+		hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - RTE_ETHER_HDR_LEN -
 			VLAN_TAG_LEN - hw->vtnet_hdr_size;
 	}
 
@@ -1578,6 +1763,7 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	if (eth_dev->data->dev_conf.intr_conf.rxq) {
 		if (virtio_configure_intr(eth_dev) < 0) {
 			PMD_INIT_LOG(ERR, "failed to configure interrupt");
+			virtio_free_queues(hw);
 			return -1;
 		}
 	}
@@ -1665,12 +1851,19 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 		return 0;
 	}
 
+	/*
+	 * Pass the information to the rte_eth_dev_close() that it should also
+	 * release the private port resources.
+	 */
+	eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
+
 	/* Allocate memory for storing MAC addresses */
-	eth_dev->data->mac_addrs = rte_zmalloc("virtio", VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN, 0);
+	eth_dev->data->mac_addrs = rte_zmalloc("virtio",
+				VIRTIO_MAX_MAC_ADDRS * RTE_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);
+			VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN);
 		return -ENOMEM;
 	}
 
@@ -1681,18 +1874,27 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	if (!hw->virtio_user_dev) {
 		ret = vtpci_init(RTE_ETH_DEV_TO_PCI(eth_dev), hw);
 		if (ret)
-			goto out;
+			goto err_vtpci_init;
 	}
 
 	/* reset device and negotiate default features */
 	ret = virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES);
 	if (ret < 0)
-		goto out;
+		goto err_virtio_init;
+
+	hw->opened = true;
 
 	return 0;
 
-out:
+err_virtio_init:
+	if (!hw->virtio_user_dev) {
+		rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev));
+		if (!hw->modern)
+			rte_pci_ioport_unmap(VTPCI_IO(hw));
+	}
+err_vtpci_init:
 	rte_free(eth_dev->data->mac_addrs);
+	eth_dev->data->mac_addrs = NULL;
 	return ret;
 }
 
@@ -1711,9 +1913,6 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 	eth_dev->tx_pkt_burst = NULL;
 	eth_dev->rx_pkt_burst = NULL;
 
-	if (eth_dev->device)
-		rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev));
-
 	PMD_INIT_LOG(DEBUG, "dev_uninit completed");
 
 	return 0;
@@ -1775,7 +1974,13 @@ static int eth_virtio_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
 
 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);
+	int ret;
+
+	ret = rte_eth_dev_pci_generic_remove(pci_dev, eth_virtio_dev_uninit);
+	/* Port has already been released by close. */
+	if (ret == -ENODEV)
+		ret = 0;
+	return ret;
 }
 
 static struct rte_pci_driver rte_virtio_pmd = {
@@ -1820,6 +2025,8 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 	const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 	const struct rte_eth_txmode *txmode = &dev->data->dev_conf.txmode;
 	struct virtio_hw *hw = dev->data->dev_private;
+	uint32_t ether_hdr_len = RTE_ETHER_HDR_LEN + VLAN_TAG_LEN +
+		hw->vtnet_hdr_size;
 	uint64_t rx_offloads = rxmode->offloads;
 	uint64_t tx_offloads = txmode->offloads;
 	uint64_t req_features;
@@ -1834,6 +2041,9 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return ret;
 	}
 
+	if (rxmode->max_rx_pkt_len > hw->max_mtu + ether_hdr_len)
+		req_features &= ~(1ULL << VIRTIO_NET_F_MTU);
+
 	if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
 			   DEV_RX_OFFLOAD_TCP_CKSUM))
 		req_features |= (1ULL << VIRTIO_NET_F_GUEST_CSUM);
@@ -1906,12 +2116,13 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 
 	if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) {
 		hw->use_inorder_tx = 1;
-		if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
-			hw->use_inorder_rx = 1;
-			hw->use_simple_rx = 0;
-		} else {
-			hw->use_inorder_rx = 0;
-		}
+		hw->use_inorder_rx = 1;
+		hw->use_simple_rx = 0;
+	}
+
+	if (vtpci_packed_queue(hw)) {
+		hw->use_simple_rx = 0;
+		hw->use_inorder_rx = 0;
 	}
 
 #if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM
@@ -1929,8 +2140,6 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			   DEV_RX_OFFLOAD_VLAN_STRIP))
 		hw->use_simple_rx = 0;
 
-	hw->opened = true;
-
 	return 0;
 }
 
@@ -2185,6 +2394,7 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 
 	host_features = VTPCI_OPS(hw)->get_features(hw);
 	dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
+	dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	if (host_features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) {
 		dev_info->rx_offload_capa |=
 			DEV_RX_OFFLOAD_TCP_CKSUM |