New upstream version 18.08upstream/18.08

Change-Id: I32fdf5e5016556d9c0a6d88ddaf1fc468961790a
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

16 files changed, 1230 insertions, 434 deletions

diff --git a/drivers/net/virtio/meson.build b/drivers/net/virtio/meson.build
new file mode 100644
index 00000000..e43ce6bb
--- /dev/null
+++ b/drivers/net/virtio/meson.build
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 Intel Corporation
+
+allow_experimental_apis = true
+sources += files('virtio_ethdev.c',
+	'virtio_pci.c',
+	'virtio_rxtx.c',
+	'virtio_rxtx_simple.c',
+	'virtqueue.c')
+deps += ['kvargs', 'bus_pci']
+
+if arch_subdir == 'x86'
+	sources += files('virtio_rxtx_simple_sse.c')
+elif arch_subdir == 'arm' and host_machine.cpu_family().startswith('aarch64')
+	sources += files('virtio_rxtx_simple_neon.c')
+endif
+
+if host_machine.system() == 'linux'
+	dpdk_conf.set('RTE_VIRTIO_USER', 1)
+
+	sources += files('virtio_user_ethdev.c',
+		'virtio_user/vhost_kernel.c',
+		'virtio_user/vhost_kernel_tap.c',
+		'virtio_user/vhost_user.c',
+		'virtio_user/virtio_user_dev.c')
+	deps += ['bus_vdev']
+endif
diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 884f74ad..614357da 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -14,7 +14,6 @@
 #include <rte_string_fns.h>
 #include <rte_memzone.h>
 #include <rte_malloc.h>
-#include <rte_atomic.h>
 #include <rte_branch_prediction.h>
 #include <rte_pci.h>
 #include <rte_bus_pci.h>
@@ -29,6 +28,7 @@
 #include <rte_eal.h>
 #include <rte_dev.h>
 #include <rte_cycles.h>
+#include <rte_kvargs.h>
 
 #include "virtio_ethdev.h"
 #include "virtio_pci.h"
@@ -68,7 +68,7 @@ static int virtio_mac_addr_add(struct rte_eth_dev *dev,
 				struct 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 void virtio_mac_addr_set(struct rte_eth_dev *dev,
+static int virtio_mac_addr_set(struct rte_eth_dev *dev,
 				struct ether_addr *mac_addr);
 
 static int virtio_intr_enable(struct rte_eth_dev *dev);
@@ -392,8 +392,8 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 		     size, vq->vq_ring_size);
 
 	mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size,
-					 SOCKET_ID_ANY,
-					 0, VIRTIO_PCI_VRING_ALIGN);
+			SOCKET_ID_ANY, RTE_MEMZONE_IOVA_CONTIG,
+			VIRTIO_PCI_VRING_ALIGN);
 	if (mz == NULL) {
 		if (rte_errno == EEXIST)
 			mz = rte_memzone_lookup(vq_name);
@@ -418,8 +418,8 @@ 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, 0,
-						     RTE_CACHE_LINE_SIZE);
+				SOCKET_ID_ANY, RTE_MEMZONE_IOVA_CONTIG,
+				RTE_CACHE_LINE_SIZE);
 		if (hdr_mz == NULL) {
 			if (rte_errno == EEXIST)
 				hdr_mz = rte_memzone_lookup(vq_hdr_name);
@@ -774,46 +774,6 @@ static const struct eth_dev_ops virtio_eth_dev_ops = {
 	.mac_addr_set            = virtio_mac_addr_set,
 };
 
-static inline int
-virtio_dev_atomic_read_link_status(struct rte_eth_dev *dev,
-				struct rte_eth_link *link)
-{
-	struct rte_eth_link *dst = link;
-	struct rte_eth_link *src = &(dev->data->dev_link);
-
-	if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst,
-			*(uint64_t *)src) == 0)
-		return -1;
-
-	return 0;
-}
-
-/**
- * Atomically writes the link status information into global
- * structure rte_eth_dev.
- *
- * @param dev
- *   - Pointer to the structure rte_eth_dev to read from.
- *   - Pointer to the buffer to be saved with the link status.
- *
- * @return
- *   - On success, zero.
- *   - On failure, negative value.
- */
-static inline int
-virtio_dev_atomic_write_link_status(struct rte_eth_dev *dev,
-		struct rte_eth_link *link)
-{
-	struct rte_eth_link *dst = &(dev->data->dev_link);
-	struct rte_eth_link *src = link;
-
-	if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst,
-					*(uint64_t *)src) == 0)
-		return -1;
-
-	return 0;
-}
-
 static void
 virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
@@ -1097,7 +1057,7 @@ virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 	virtio_mac_table_set(hw, uc, mc);
 }
 
-static void
+static int
 virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
@@ -1113,9 +1073,14 @@ virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
 		ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET;
 
 		memcpy(ctrl.data, mac_addr, ETHER_ADDR_LEN);
-		virtio_send_command(hw->cvq, &ctrl, &len, 1);
-	} else if (vtpci_with_feature(hw, VIRTIO_NET_F_MAC))
-		virtio_set_hwaddr(hw);
+		return virtio_send_command(hw->cvq, &ctrl, &len, 1);
+	}
+
+	if (!vtpci_with_feature(hw, VIRTIO_NET_F_MAC))
+		return -ENOTSUP;
+
+	virtio_set_hwaddr(hw);
+	return 0;
 }
 
 static int
@@ -1273,9 +1238,16 @@ static void
 virtio_notify_peers(struct rte_eth_dev *dev)
 {
 	struct virtio_hw *hw = dev->data->dev_private;
-	struct virtnet_rx *rxvq = dev->data->rx_queues[0];
+	struct virtnet_rx *rxvq;
 	struct rte_mbuf *rarp_mbuf;
 
+	if (!dev->data->rx_queues)
+		return;
+
+	rxvq = dev->data->rx_queues[0];
+	if (!rxvq)
+		return;
+
 	rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool,
 			(struct ether_addr *)hw->mac_addr);
 	if (rarp_mbuf == NULL) {
@@ -1333,7 +1305,8 @@ virtio_interrupt_handler(void *param)
 
 	if (isr & VIRTIO_NET_S_ANNOUNCE) {
 		virtio_notify_peers(dev);
-		virtio_ack_link_announce(dev);
+		if (hw->cvq)
+			virtio_ack_link_announce(dev);
 	}
 }
 
@@ -1347,6 +1320,11 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 		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)) {
 		PMD_INIT_LOG(INFO,
 			"virtio: using mergeable buffer Rx path on port %u",
@@ -1358,10 +1336,10 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev)
 		eth_dev->rx_pkt_burst = &virtio_recv_pkts;
 	}
 
-	if (hw->use_simple_tx) {
-		PMD_INIT_LOG(INFO, "virtio: using simple Tx path on port %u",
+	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_simple;
+		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);
@@ -1744,9 +1722,51 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
 	return 0;
 }
 
+static int vdpa_check_handler(__rte_unused const char *key,
+		const char *value, __rte_unused void *opaque)
+{
+	if (strcmp(value, "1"))
+		return -1;
+
+	return 0;
+}
+
+static int
+vdpa_mode_selected(struct rte_devargs *devargs)
+{
+	struct rte_kvargs *kvlist;
+	const char *key = "vdpa";
+	int ret = 0;
+
+	if (devargs == NULL)
+		return 0;
+
+	kvlist = rte_kvargs_parse(devargs->args, NULL);
+	if (kvlist == NULL)
+		return 0;
+
+	if (!rte_kvargs_count(kvlist, key))
+		goto exit;
+
+	/* vdpa mode selected when there's a key-value pair: vdpa=1 */
+	if (rte_kvargs_process(kvlist, key,
+				vdpa_check_handler, NULL) < 0) {
+		goto exit;
+	}
+	ret = 1;
+
+exit:
+	rte_kvargs_free(kvlist);
+	return ret;
+}
+
 static int eth_virtio_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
 	struct rte_pci_device *pci_dev)
 {
+	/* virtio pmd skips probe if device needs to work in vdpa mode */
+	if (vdpa_mode_selected(pci_dev->device.devargs))
+		return 1;
+
 	return rte_eth_dev_pci_generic_probe(pci_dev, sizeof(struct virtio_hw),
 		eth_virtio_dev_init);
 }
@@ -1766,9 +1786,7 @@ static struct rte_pci_driver rte_virtio_pmd = {
 	.remove = eth_virtio_pci_remove,
 };
 
-RTE_INIT(rte_virtio_pmd_init);
-static void
-rte_virtio_pmd_init(void)
+RTE_INIT(rte_virtio_pmd_init)
 {
 	if (rte_eal_iopl_init() != 0) {
 		PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
@@ -1778,6 +1796,22 @@ rte_virtio_pmd_init(void)
 	rte_pci_register(&rte_virtio_pmd);
 }
 
+static bool
+rx_offload_enabled(struct virtio_hw *hw)
+{
+	return vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM) ||
+		vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
+		vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6);
+}
+
+static bool
+tx_offload_enabled(struct virtio_hw *hw)
+{
+	return vtpci_with_feature(hw, VIRTIO_NET_F_CSUM) ||
+		vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO4) ||
+		vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO6);
+}
+
 /*
  * Configure virtio device
  * It returns 0 on success.
@@ -1786,7 +1820,10 @@ static int
 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;
+	uint64_t rx_offloads = rxmode->offloads;
+	uint64_t tx_offloads = txmode->offloads;
 	uint64_t req_features;
 	int ret;
 
@@ -1799,18 +1836,24 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return ret;
 	}
 
-	/* The name hw_ip_checksum is a bit confusing since it can be
-	 * set by the application to request L3 and/or L4 checksums. In
-	 * case of virtio, only L4 checksum is supported.
-	 */
-	if (rxmode->hw_ip_checksum)
+	if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+			   DEV_RX_OFFLOAD_TCP_CKSUM))
 		req_features |= (1ULL << VIRTIO_NET_F_GUEST_CSUM);
 
-	if (rxmode->enable_lro)
+	if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO)
 		req_features |=
 			(1ULL << VIRTIO_NET_F_GUEST_TSO4) |
 			(1ULL << VIRTIO_NET_F_GUEST_TSO6);
 
+	if (tx_offloads & (DEV_TX_OFFLOAD_UDP_CKSUM |
+			   DEV_TX_OFFLOAD_TCP_CKSUM))
+		req_features |= (1ULL << VIRTIO_NET_F_CSUM);
+
+	if (tx_offloads & DEV_TX_OFFLOAD_TCP_TSO)
+		req_features |=
+			(1ULL << VIRTIO_NET_F_HOST_TSO4) |
+			(1ULL << VIRTIO_NET_F_HOST_TSO6);
+
 	/* if request features changed, reinit the device */
 	if (req_features != hw->req_guest_features) {
 		ret = virtio_init_device(dev, req_features);
@@ -1818,14 +1861,15 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 			return ret;
 	}
 
-	if (rxmode->hw_ip_checksum &&
+	if ((rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+			    DEV_RX_OFFLOAD_TCP_CKSUM)) &&
 		!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) {
 		PMD_DRV_LOG(ERR,
 			"rx checksum not available on this host");
 		return -ENOTSUP;
 	}
 
-	if (rxmode->enable_lro &&
+	if ((rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) &&
 		(!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
 		 !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6))) {
 		PMD_DRV_LOG(ERR,
@@ -1837,15 +1881,19 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ))
 		virtio_dev_cq_start(dev);
 
-	hw->vlan_strip = rxmode->hw_vlan_strip;
+	if (rx_offloads & DEV_RX_OFFLOAD_VLAN_STRIP)
+		hw->vlan_strip = 1;
 
-	if (rxmode->hw_vlan_filter
+	if ((rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER)
 	    && !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
 		PMD_DRV_LOG(ERR,
 			    "vlan filtering not available on this host");
 		return -ENOTSUP;
 	}
 
+	hw->has_tx_offload = tx_offload_enabled(hw);
+	hw->has_rx_offload = rx_offload_enabled(hw);
+
 	if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
 		/* Enable vector (0) for Link State Intrerrupt */
 		if (VTPCI_OPS(hw)->set_config_irq(hw, 0) ==
@@ -1857,20 +1905,30 @@ virtio_dev_configure(struct rte_eth_dev *dev)
 	rte_spinlock_init(&hw->state_lock);
 
 	hw->use_simple_rx = 1;
-	hw->use_simple_tx = 1;
+
+	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;
+		}
+	}
 
 #if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM
 	if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) {
 		hw->use_simple_rx = 0;
-		hw->use_simple_tx = 0;
 	}
 #endif
 	if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
-		hw->use_simple_rx = 0;
-		hw->use_simple_tx = 0;
+		 hw->use_simple_rx = 0;
 	}
 
-	if (rxmode->hw_ip_checksum)
+	if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+			   DEV_RX_OFFLOAD_TCP_CKSUM |
+			   DEV_RX_OFFLOAD_TCP_LRO |
+			   DEV_RX_OFFLOAD_VLAN_STRIP))
 		hw->use_simple_rx = 0;
 
 	return 0;
@@ -2028,21 +2086,21 @@ virtio_dev_stop(struct rte_eth_dev *dev)
 
 	hw->started = 0;
 	memset(&link, 0, sizeof(link));
-	virtio_dev_atomic_write_link_status(dev, &link);
+	rte_eth_linkstatus_set(dev, &link);
 	rte_spinlock_unlock(&hw->state_lock);
 }
 
 static int
 virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complete)
 {
-	struct rte_eth_link link, old;
+	struct rte_eth_link link;
 	uint16_t status;
 	struct virtio_hw *hw = dev->data->dev_private;
+
 	memset(&link, 0, sizeof(link));
-	virtio_dev_atomic_read_link_status(dev, &link);
-	old = link;
 	link.link_duplex = ETH_LINK_FULL_DUPLEX;
 	link.link_speed  = ETH_SPEED_NUM_10G;
+	link.link_autoneg = ETH_LINK_FIXED;
 
 	if (hw->started == 0) {
 		link.link_status = ETH_LINK_DOWN;
@@ -2063,9 +2121,8 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet
 	} else {
 		link.link_status = ETH_LINK_UP;
 	}
-	virtio_dev_atomic_write_link_status(dev, &link);
 
-	return (old.link_status == link.link_status) ? -1 : 0;
+	return rte_eth_linkstatus_set(dev, &link);
 }
 
 static int
@@ -2073,9 +2130,10 @@ virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask)
 {
 	const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 	struct virtio_hw *hw = dev->data->dev_private;
+	uint64_t offloads = rxmode->offloads;
 
 	if (mask & ETH_VLAN_FILTER_MASK) {
-		if (rxmode->hw_vlan_filter &&
+		if ((offloads & DEV_RX_OFFLOAD_VLAN_FILTER) &&
 				!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
 
 			PMD_DRV_LOG(NOTICE,
@@ -2086,7 +2144,7 @@ virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask)
 	}
 
 	if (mask & ETH_VLAN_STRIP_MASK)
-		hw->vlan_strip = rxmode->hw_vlan_strip;
+		hw->vlan_strip = !!(offloads & DEV_RX_OFFLOAD_VLAN_STRIP);
 
 	return 0;
 }
@@ -2099,7 +2157,6 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 
 	dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */
 
-	dev_info->pci_dev = dev->device ? RTE_ETH_DEV_TO_PCI(dev) : NULL;
 	dev_info->max_rx_queues =
 		RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES);
 	dev_info->max_tx_queues =
@@ -2107,31 +2164,32 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 	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
-	};
 
 	host_features = VTPCI_OPS(hw)->get_features(hw);
-	dev_info->rx_offload_capa = 0;
+	dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |
+				    DEV_RX_OFFLOAD_CRC_STRIP;
 	if (host_features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) {
 		dev_info->rx_offload_capa |=
 			DEV_RX_OFFLOAD_TCP_CKSUM |
 			DEV_RX_OFFLOAD_UDP_CKSUM;
 	}
+	if (host_features & (1ULL << VIRTIO_NET_F_CTRL_VLAN))
+		dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_VLAN_FILTER;
 	tso_mask = (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
 		(1ULL << VIRTIO_NET_F_GUEST_TSO6);
 	if ((host_features & tso_mask) == tso_mask)
 		dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO;
 
-	dev_info->tx_offload_capa = 0;
-	if (hw->guest_features & (1ULL << VIRTIO_NET_F_CSUM)) {
+	dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |
+				    DEV_TX_OFFLOAD_VLAN_INSERT;
+	if (host_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)
+	if ((host_features & tso_mask) == tso_mask)
 		dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO;
 }
 
@@ -2150,9 +2208,7 @@ 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-pci");
 
-RTE_INIT(virtio_init_log);
-static void
-virtio_init_log(void)
+RTE_INIT(virtio_init_log)
 {
 	virtio_logtype_init = rte_log_register("pmd.net.virtio.init");
 	if (virtio_logtype_init >= 0)
diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
index 4539d2e4..b726ad10 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -28,14 +28,12 @@
 	 1u << VIRTIO_NET_F_CTRL_VQ	  |	\
 	 1u << VIRTIO_NET_F_CTRL_RX	  |	\
 	 1u << VIRTIO_NET_F_CTRL_VLAN	  |	\
-	 1u << VIRTIO_NET_F_CSUM	  |	\
-	 1u << VIRTIO_NET_F_HOST_TSO4	  |	\
-	 1u << VIRTIO_NET_F_HOST_TSO6	  |	\
 	 1u << VIRTIO_NET_F_MRG_RXBUF	  |	\
 	 1u << VIRTIO_NET_F_MTU	| \
 	 1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE |	\
 	 1u << VIRTIO_RING_F_INDIRECT_DESC |    \
 	 1ULL << VIRTIO_F_VERSION_1       |	\
+	 1ULL << VIRTIO_F_IN_ORDER        |	\
 	 1ULL << VIRTIO_F_IOMMU_PLATFORM)
 
 #define VIRTIO_PMD_SUPPORTED_GUEST_FEATURES	\
@@ -43,6 +41,7 @@
 	 1u << VIRTIO_NET_F_GUEST_CSUM	   |	\
 	 1u << VIRTIO_NET_F_GUEST_TSO4     |	\
 	 1u << VIRTIO_NET_F_GUEST_TSO6)
+
 /*
  * CQ function prototype
  */
@@ -75,9 +74,15 @@ uint16_t virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 uint16_t virtio_recv_mergeable_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		uint16_t nb_pkts);
 
+uint16_t virtio_recv_mergeable_pkts_inorder(void *rx_queue,
+		struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+
 uint16_t virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		uint16_t nb_pkts);
 
+uint16_t virtio_xmit_pkts_inorder(void *tx_queue, struct rte_mbuf **tx_pkts,
+		uint16_t nb_pkts);
+
 uint16_t virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 		uint16_t nb_pkts);
 
diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h
index a28ba833..58fdd3d4 100644
--- a/drivers/net/virtio/virtio_pci.h
+++ b/drivers/net/virtio/virtio_pci.h
@@ -6,6 +6,7 @@
 #define _VIRTIO_PCI_H_
 
 #include <stdint.h>
+#include <stdbool.h>
 
 #include <rte_pci.h>
 #include <rte_bus_pci.h>
@@ -121,6 +122,12 @@ struct virtnet_ctl;
 #define VIRTIO_TRANSPORT_F_START 28
 #define VIRTIO_TRANSPORT_F_END   34
 
+/*
+ * Inorder feature indicates that all buffers are used by the device
+ * in the same order in which they have been made available.
+ */
+#define VIRTIO_F_IN_ORDER 35
+
 /* The Guest publishes the used index for which it expects an interrupt
  * at the end of the avail ring. Host should ignore the avail->flags field. */
 /* The Host publishes the avail index for which it expects a kick
@@ -232,7 +239,10 @@ struct virtio_hw {
 	uint8_t	    use_msix;
 	uint8_t     modern;
 	uint8_t     use_simple_rx;
-	uint8_t     use_simple_tx;
+	uint8_t     use_inorder_rx;
+	uint8_t     use_inorder_tx;
+	bool        has_tx_offload;
+	bool        has_rx_offload;
 	uint16_t    port_id;
 	uint8_t     mac_addr[ETHER_ADDR_LEN];
 	uint32_t    notify_off_multiplier;
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index 8dbf2a30..eb891433 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -38,10 +38,6 @@
 #define  VIRTIO_DUMP_PACKET(m, len) do { } while (0)
 #endif
 
-
-#define VIRTIO_SIMPLE_FLAGS ((uint32_t)ETH_TXQ_FLAGS_NOMULTSEGS | \
-	ETH_TXQ_FLAGS_NOOFFLOADS)
-
 int
 virtio_dev_rx_queue_done(void *rxq, uint16_t offset)
 {
@@ -52,6 +48,13 @@ virtio_dev_rx_queue_done(void *rxq, uint16_t offset)
 }
 
 void
+vq_ring_free_inorder(struct virtqueue *vq, uint16_t desc_idx, uint16_t num)
+{
+	vq->vq_free_cnt += num;
+	vq->vq_desc_tail_idx = desc_idx & (vq->vq_nentries - 1);
+}
+
+void
 vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx)
 {
 	struct vring_desc *dp, *dp_tail;
@@ -119,6 +122,44 @@ virtqueue_dequeue_burst_rx(struct virtqueue *vq, struct rte_mbuf **rx_pkts,
 	return i;
 }
 
+static uint16_t
+virtqueue_dequeue_rx_inorder(struct virtqueue *vq,
+			struct rte_mbuf **rx_pkts,
+			uint32_t *len,
+			uint16_t num)
+{
+	struct vring_used_elem *uep;
+	struct rte_mbuf *cookie;
+	uint16_t used_idx = 0;
+	uint16_t i;
+
+	if (unlikely(num == 0))
+		return 0;
+
+	for (i = 0; i < num; i++) {
+		used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1);
+		/* Desc idx same as used idx */
+		uep = &vq->vq_ring.used->ring[used_idx];
+		len[i] = uep->len;
+		cookie = (struct rte_mbuf *)vq->vq_descx[used_idx].cookie;
+
+		if (unlikely(cookie == NULL)) {
+			PMD_DRV_LOG(ERR, "vring descriptor with no mbuf cookie at %u",
+				vq->vq_used_cons_idx);
+			break;
+		}
+
+		rte_prefetch0(cookie);
+		rte_packet_prefetch(rte_pktmbuf_mtod(cookie, void *));
+		rx_pkts[i]  = cookie;
+		vq->vq_used_cons_idx++;
+		vq->vq_descx[used_idx].cookie = NULL;
+	}
+
+	vq_ring_free_inorder(vq, used_idx, i);
+	return i;
+}
+
 #ifndef DEFAULT_TX_FREE_THRESH
 #define DEFAULT_TX_FREE_THRESH 32
 #endif
@@ -147,6 +188,83 @@ virtio_xmit_cleanup(struct virtqueue *vq, uint16_t num)
 	}
 }
 
+/* Cleanup from completed inorder transmits. */
+static void
+virtio_xmit_cleanup_inorder(struct virtqueue *vq, uint16_t num)
+{
+	uint16_t i, used_idx, desc_idx = 0, last_idx;
+	int16_t free_cnt = 0;
+	struct vq_desc_extra *dxp = NULL;
+
+	if (unlikely(num == 0))
+		return;
+
+	for (i = 0; i < num; i++) {
+		struct vring_used_elem *uep;
+
+		used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1);
+		uep = &vq->vq_ring.used->ring[used_idx];
+		desc_idx = (uint16_t)uep->id;
+
+		dxp = &vq->vq_descx[desc_idx];
+		vq->vq_used_cons_idx++;
+
+		if (dxp->cookie != NULL) {
+			rte_pktmbuf_free(dxp->cookie);
+			dxp->cookie = NULL;
+		}
+	}
+
+	last_idx = desc_idx + dxp->ndescs - 1;
+	free_cnt = last_idx - vq->vq_desc_tail_idx;
+	if (free_cnt <= 0)
+		free_cnt += vq->vq_nentries;
+
+	vq_ring_free_inorder(vq, last_idx, free_cnt);
+}
+
+static inline int
+virtqueue_enqueue_refill_inorder(struct virtqueue *vq,
+			struct rte_mbuf **cookies,
+			uint16_t num)
+{
+	struct vq_desc_extra *dxp;
+	struct virtio_hw *hw = vq->hw;
+	struct vring_desc *start_dp;
+	uint16_t head_idx, idx, i = 0;
+
+	if (unlikely(vq->vq_free_cnt == 0))
+		return -ENOSPC;
+	if (unlikely(vq->vq_free_cnt < num))
+		return -EMSGSIZE;
+
+	head_idx = vq->vq_desc_head_idx & (vq->vq_nentries - 1);
+	start_dp = vq->vq_ring.desc;
+
+	while (i < num) {
+		idx = head_idx & (vq->vq_nentries - 1);
+		dxp = &vq->vq_descx[idx];
+		dxp->cookie = (void *)cookies[i];
+		dxp->ndescs = 1;
+
+		start_dp[idx].addr =
+				VIRTIO_MBUF_ADDR(cookies[i], vq) +
+				RTE_PKTMBUF_HEADROOM - hw->vtnet_hdr_size;
+		start_dp[idx].len =
+				cookies[i]->buf_len -
+				RTE_PKTMBUF_HEADROOM +
+				hw->vtnet_hdr_size;
+		start_dp[idx].flags =  VRING_DESC_F_WRITE;
+
+		vq_update_avail_ring(vq, idx);
+		head_idx++;
+		i++;
+	}
+
+	vq->vq_desc_head_idx += num;
+	vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - num);
+	return 0;
+}
 
 static inline int
 virtqueue_enqueue_recv_refill(struct virtqueue *vq, struct rte_mbuf *cookie)
@@ -229,13 +347,6 @@ virtio_tso_fix_cksum(struct rte_mbuf *m)
 	}
 }
 
-static inline int
-tx_offload_enabled(struct virtio_hw *hw)
-{
-	return vtpci_with_feature(hw, VIRTIO_NET_F_CSUM) ||
-		vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO4) ||
-		vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO6);
-}
 
 /* avoid write operation when necessary, to lessen cache issues */
 #define ASSIGN_UNLESS_EQUAL(var, val) do {	\
@@ -244,8 +355,111 @@ tx_offload_enabled(struct virtio_hw *hw)
 } while (0)
 
 static inline void
+virtqueue_xmit_offload(struct virtio_net_hdr *hdr,
+			struct rte_mbuf *cookie,
+			bool offload)
+{
+	if (offload) {
+		if (cookie->ol_flags & PKT_TX_TCP_SEG)
+			cookie->ol_flags |= PKT_TX_TCP_CKSUM;
+
+		switch (cookie->ol_flags & PKT_TX_L4_MASK) {
+		case PKT_TX_UDP_CKSUM:
+			hdr->csum_start = cookie->l2_len + cookie->l3_len;
+			hdr->csum_offset = offsetof(struct udp_hdr,
+				dgram_cksum);
+			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+			break;
+
+		case PKT_TX_TCP_CKSUM:
+			hdr->csum_start = cookie->l2_len + cookie->l3_len;
+			hdr->csum_offset = offsetof(struct tcp_hdr, cksum);
+			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+			break;
+
+		default:
+			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
+			break;
+		}
+
+		/* TCP Segmentation Offload */
+		if (cookie->ol_flags & PKT_TX_TCP_SEG) {
+			virtio_tso_fix_cksum(cookie);
+			hdr->gso_type = (cookie->ol_flags & PKT_TX_IPV6) ?
+				VIRTIO_NET_HDR_GSO_TCPV6 :
+				VIRTIO_NET_HDR_GSO_TCPV4;
+			hdr->gso_size = cookie->tso_segsz;
+			hdr->hdr_len =
+				cookie->l2_len +
+				cookie->l3_len +
+				cookie->l4_len;
+		} else {
+			ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0);
+		}
+	}
+}
+
+static inline void
+virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq,
+			struct rte_mbuf **cookies,
+			uint16_t num)
+{
+	struct vq_desc_extra *dxp;
+	struct virtqueue *vq = txvq->vq;
+	struct vring_desc *start_dp;
+	struct virtio_net_hdr *hdr;
+	uint16_t idx;
+	uint16_t head_size = vq->hw->vtnet_hdr_size;
+	uint16_t i = 0;
+
+	idx = vq->vq_desc_head_idx;
+	start_dp = vq->vq_ring.desc;
+
+	while (i < num) {
+		idx = idx & (vq->vq_nentries - 1);
+		dxp = &vq->vq_descx[idx];
+		dxp->cookie = (void *)cookies[i];
+		dxp->ndescs = 1;
+
+		hdr = (struct virtio_net_hdr *)
+			rte_pktmbuf_prepend(cookies[i], head_size);
+		cookies[i]->pkt_len -= head_size;
+
+		/* if offload disabled, it is not zeroed below, do it now */
+		if (!vq->hw->has_tx_offload) {
+			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0);
+		}
+
+		virtqueue_xmit_offload(hdr, cookies[i],
+				vq->hw->has_tx_offload);
+
+		start_dp[idx].addr  = VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq);
+		start_dp[idx].len   = cookies[i]->data_len;
+		start_dp[idx].flags = 0;
+
+		vq_update_avail_ring(vq, idx);
+
+		idx++;
+		i++;
+	};
+
+	vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - num);
+	vq->vq_desc_head_idx = idx & (vq->vq_nentries - 1);
+}
+
+static inline void
 virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
-		       uint16_t needed, int use_indirect, int can_push)
+			uint16_t needed, int use_indirect, int can_push,
+			int in_order)
 {
 	struct virtio_tx_region *txr = txvq->virtio_net_hdr_mz->addr;
 	struct vq_desc_extra *dxp;
@@ -255,9 +469,7 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 	uint16_t head_idx, idx;
 	uint16_t head_size = vq->hw->vtnet_hdr_size;
 	struct virtio_net_hdr *hdr;
-	int offload;
 
-	offload = tx_offload_enabled(vq->hw);
 	head_idx = vq->vq_desc_head_idx;
 	idx = head_idx;
 	dxp = &vq->vq_descx[idx];
@@ -274,8 +486,9 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 		 * which is wrong. Below subtract restores correct pkt size.
 		 */
 		cookie->pkt_len -= head_size;
+
 		/* if offload disabled, it is not zeroed below, do it now */
-		if (offload == 0) {
+		if (!vq->hw->has_tx_offload) {
 			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
 			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
 			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
@@ -312,49 +525,7 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 		idx = start_dp[idx].next;
 	}
 
-	/* Checksum Offload / TSO */
-	if (offload) {
-		if (cookie->ol_flags & PKT_TX_TCP_SEG)
-			cookie->ol_flags |= PKT_TX_TCP_CKSUM;
-
-		switch (cookie->ol_flags & PKT_TX_L4_MASK) {
-		case PKT_TX_UDP_CKSUM:
-			hdr->csum_start = cookie->l2_len + cookie->l3_len;
-			hdr->csum_offset = offsetof(struct udp_hdr,
-				dgram_cksum);
-			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			break;
-
-		case PKT_TX_TCP_CKSUM:
-			hdr->csum_start = cookie->l2_len + cookie->l3_len;
-			hdr->csum_offset = offsetof(struct tcp_hdr, cksum);
-			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			break;
-
-		default:
-			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
-			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
-			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
-			break;
-		}
-
-		/* TCP Segmentation Offload */
-		if (cookie->ol_flags & PKT_TX_TCP_SEG) {
-			virtio_tso_fix_cksum(cookie);
-			hdr->gso_type = (cookie->ol_flags & PKT_TX_IPV6) ?
-				VIRTIO_NET_HDR_GSO_TCPV6 :
-				VIRTIO_NET_HDR_GSO_TCPV4;
-			hdr->gso_size = cookie->tso_segsz;
-			hdr->hdr_len =
-				cookie->l2_len +
-				cookie->l3_len +
-				cookie->l4_len;
-		} else {
-			ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0);
-			ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0);
-			ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0);
-		}
-	}
+	virtqueue_xmit_offload(hdr, cookie, vq->hw->has_tx_offload);
 
 	do {
 		start_dp[idx].addr  = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
@@ -366,11 +537,15 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 	if (use_indirect)
 		idx = vq->vq_ring.desc[head_idx].next;
 
-	vq->vq_desc_head_idx = idx;
-	if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END)
-		vq->vq_desc_tail_idx = idx;
 	vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - needed);
+
+	vq->vq_desc_head_idx = idx;
 	vq_update_avail_ring(vq, head_idx);
+
+	if (!in_order) {
+		if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END)
+			vq->vq_desc_tail_idx = idx;
+	}
 }
 
 void
@@ -389,7 +564,7 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			uint16_t queue_idx,
 			uint16_t nb_desc,
 			unsigned int socket_id __rte_unused,
-			__rte_unused const struct rte_eth_rxconf *rx_conf,
+			const struct rte_eth_rxconf *rx_conf __rte_unused,
 			struct rte_mempool *mp)
 {
 	uint16_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_RQ_QUEUE_IDX;
@@ -410,6 +585,7 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 		rte_exit(EXIT_FAILURE,
 			"Cannot allocate mbufs for rx virtqueue");
 	}
+
 	dev->data->rx_queues[queue_idx] = rxvq;
 
 	return 0;
@@ -424,7 +600,7 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx)
 	struct virtnet_rx *rxvq = &vq->rxq;
 	struct rte_mbuf *m;
 	uint16_t desc_idx;
-	int error, nbufs;
+	int error, nbufs, i;
 
 	PMD_INIT_FUNC_TRACE();
 
@@ -454,6 +630,25 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx)
 			virtio_rxq_rearm_vec(rxvq);
 			nbufs += RTE_VIRTIO_VPMD_RX_REARM_THRESH;
 		}
+	} else if (hw->use_inorder_rx) {
+		if ((!virtqueue_full(vq))) {
+			uint16_t free_cnt = vq->vq_free_cnt;
+			struct rte_mbuf *pkts[free_cnt];
+
+			if (!rte_pktmbuf_alloc_bulk(rxvq->mpool, pkts,
+				free_cnt)) {
+				error = virtqueue_enqueue_refill_inorder(vq,
+						pkts,
+						free_cnt);
+				if (unlikely(error)) {
+					for (i = 0; i < free_cnt; i++)
+						rte_pktmbuf_free(pkts[i]);
+				}
+			}
+
+			nbufs += free_cnt;
+			vq_update_avail_idx(vq);
+		}
 	} else {
 		while (!virtqueue_full(vq)) {
 			m = rte_mbuf_raw_alloc(rxvq->mpool);
@@ -501,10 +696,6 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
 
 	PMD_INIT_FUNC_TRACE();
 
-	/* cannot use simple rxtx funcs with multisegs or offloads */
-	if ((tx_conf->txq_flags & VIRTIO_SIMPLE_FLAGS) != VIRTIO_SIMPLE_FLAGS)
-		hw->use_simple_tx = 0;
-
 	if (nb_desc == 0 || nb_desc > vq->vq_nentries)
 		nb_desc = vq->vq_nentries;
 	vq->vq_free_cnt = RTE_MIN(vq->vq_free_cnt, nb_desc);
@@ -539,31 +730,11 @@ virtio_dev_tx_queue_setup_finish(struct rte_eth_dev *dev,
 	uint8_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_TQ_QUEUE_IDX;
 	struct virtio_hw *hw = dev->data->dev_private;
 	struct virtqueue *vq = hw->vqs[vtpci_queue_idx];
-	uint16_t mid_idx = vq->vq_nentries >> 1;
-	struct virtnet_tx *txvq = &vq->txq;
-	uint16_t desc_idx;
 
 	PMD_INIT_FUNC_TRACE();
 
-	if (hw->use_simple_tx) {
-		for (desc_idx = 0; desc_idx < mid_idx; desc_idx++) {
-			vq->vq_ring.avail->ring[desc_idx] =
-				desc_idx + mid_idx;
-			vq->vq_ring.desc[desc_idx + mid_idx].next =
-				desc_idx;
-			vq->vq_ring.desc[desc_idx + mid_idx].addr =
-				txvq->virtio_net_hdr_mem +
-				offsetof(struct virtio_tx_region, tx_hdr);
-			vq->vq_ring.desc[desc_idx + mid_idx].len =
-				vq->hw->vtnet_hdr_size;
-			vq->vq_ring.desc[desc_idx + mid_idx].flags =
-				VRING_DESC_F_NEXT;
-			vq->vq_ring.desc[desc_idx].flags = 0;
-		}
-		for (desc_idx = mid_idx; desc_idx < vq->vq_nentries;
-		     desc_idx++)
-			vq->vq_ring.avail->ring[desc_idx] = desc_idx;
-	}
+	if (hw->use_inorder_tx)
+		vq->vq_ring.desc[vq->vq_nentries - 1].next = 0;
 
 	VIRTQUEUE_DUMP(vq);
 
@@ -579,6 +750,19 @@ virtio_discard_rxbuf(struct virtqueue *vq, struct rte_mbuf *m)
 	 * successful since it was just dequeued.
 	 */
 	error = virtqueue_enqueue_recv_refill(vq, m);
+
+	if (unlikely(error)) {
+		RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf");
+		rte_pktmbuf_free(m);
+	}
+}
+
+static void
+virtio_discard_rxbuf_inorder(struct virtqueue *vq, struct rte_mbuf *m)
+{
+	int error;
+
+	error = virtqueue_enqueue_refill_inorder(vq, &m, 1);
 	if (unlikely(error)) {
 		RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf");
 		rte_pktmbuf_free(m);
@@ -617,6 +801,15 @@ virtio_update_packet_stats(struct virtnet_stats *stats, struct rte_mbuf *mbuf)
 	}
 }
 
+static inline void
+virtio_rx_stats_updated(struct virtnet_rx *rxvq, struct rte_mbuf *m)
+{
+	VIRTIO_DUMP_PACKET(m, m->data_len);
+
+	rxvq->stats.bytes += m->pkt_len;
+	virtio_update_packet_stats(&rxvq->stats, m);
+}
+
 /* Optionally fill offload information in structure */
 static int
 virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr)
@@ -689,14 +882,6 @@ virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr)
 	return 0;
 }
 
-static inline int
-rx_offload_enabled(struct virtio_hw *hw)
-{
-	return vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM) ||
-		vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
-		vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6);
-}
-
 #define VIRTIO_MBUF_BURST_SZ 64
 #define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc))
 uint16_t
@@ -712,7 +897,6 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	int error;
 	uint32_t i, nb_enqueued;
 	uint32_t hdr_size;
-	int offload;
 	struct virtio_net_hdr *hdr;
 
 	nb_rx = 0;
@@ -734,7 +918,6 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 
 	nb_enqueued = 0;
 	hdr_size = hw->vtnet_hdr_size;
-	offload = rx_offload_enabled(hw);
 
 	for (i = 0; i < num ; i++) {
 		rxm = rcv_pkts[i];
@@ -763,24 +946,20 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		if (hw->vlan_strip)
 			rte_vlan_strip(rxm);
 
-		if (offload && virtio_rx_offload(rxm, hdr) < 0) {
+		if (hw->has_rx_offload && virtio_rx_offload(rxm, hdr) < 0) {
 			virtio_discard_rxbuf(vq, rxm);
 			rxvq->stats.errors++;
 			continue;
 		}
 
-		VIRTIO_DUMP_PACKET(rxm, rxm->data_len);
+		virtio_rx_stats_updated(rxvq, rxm);
 
 		rx_pkts[nb_rx++] = rxm;
-
-		rxvq->stats.bytes += rxm->pkt_len;
-		virtio_update_packet_stats(&rxvq->stats, rxm);
 	}
 
 	rxvq->stats.packets += nb_rx;
 
 	/* Allocate new mbuf for the used descriptor */
-	error = ENOSPC;
 	while (likely(!virtqueue_full(vq))) {
 		new_mbuf = rte_mbuf_raw_alloc(rxvq->mpool);
 		if (unlikely(new_mbuf == NULL)) {
@@ -810,6 +989,193 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 }
 
 uint16_t
+virtio_recv_mergeable_pkts_inorder(void *rx_queue,
+			struct rte_mbuf **rx_pkts,
+			uint16_t nb_pkts)
+{
+	struct virtnet_rx *rxvq = rx_queue;
+	struct virtqueue *vq = rxvq->vq;
+	struct virtio_hw *hw = vq->hw;
+	struct rte_mbuf *rxm;
+	struct rte_mbuf *prev;
+	uint16_t nb_used, num, nb_rx;
+	uint32_t len[VIRTIO_MBUF_BURST_SZ];
+	struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ];
+	int error;
+	uint32_t nb_enqueued;
+	uint32_t seg_num;
+	uint32_t seg_res;
+	uint32_t hdr_size;
+	int32_t i;
+
+	nb_rx = 0;
+	if (unlikely(hw->started == 0))
+		return nb_rx;
+
+	nb_used = VIRTQUEUE_NUSED(vq);
+	nb_used = RTE_MIN(nb_used, nb_pkts);
+	nb_used = RTE_MIN(nb_used, VIRTIO_MBUF_BURST_SZ);
+
+	virtio_rmb();
+
+	PMD_RX_LOG(DEBUG, "used:%d", nb_used);
+
+	nb_enqueued = 0;
+	seg_num = 1;
+	seg_res = 0;
+	hdr_size = hw->vtnet_hdr_size;
+
+	num = virtqueue_dequeue_rx_inorder(vq, rcv_pkts, len, nb_used);
+
+	for (i = 0; i < num; i++) {
+		struct virtio_net_hdr_mrg_rxbuf *header;
+
+		PMD_RX_LOG(DEBUG, "dequeue:%d", num);
+		PMD_RX_LOG(DEBUG, "packet len:%d", len[i]);
+
+		rxm = rcv_pkts[i];
+
+		if (unlikely(len[i] < hdr_size + ETHER_HDR_LEN)) {
+			PMD_RX_LOG(ERR, "Packet drop");
+			nb_enqueued++;
+			virtio_discard_rxbuf_inorder(vq, rxm);
+			rxvq->stats.errors++;
+			continue;
+		}
+
+		header = (struct virtio_net_hdr_mrg_rxbuf *)
+			 ((char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM
+			 - hdr_size);
+		seg_num = header->num_buffers;
+
+		if (seg_num == 0)
+			seg_num = 1;
+
+		rxm->data_off = RTE_PKTMBUF_HEADROOM;
+		rxm->nb_segs = seg_num;
+		rxm->ol_flags = 0;
+		rxm->vlan_tci = 0;
+		rxm->pkt_len = (uint32_t)(len[i] - hdr_size);
+		rxm->data_len = (uint16_t)(len[i] - hdr_size);
+
+		rxm->port = rxvq->port_id;
+
+		rx_pkts[nb_rx] = rxm;
+		prev = rxm;
+
+		if (vq->hw->has_rx_offload &&
+				virtio_rx_offload(rxm, &header->hdr) < 0) {
+			virtio_discard_rxbuf_inorder(vq, rxm);
+			rxvq->stats.errors++;
+			continue;
+		}
+
+		if (hw->vlan_strip)
+			rte_vlan_strip(rx_pkts[nb_rx]);
+
+		seg_res = seg_num - 1;
+
+		/* Merge remaining segments */
+		while (seg_res != 0 && i < (num - 1)) {
+			i++;
+
+			rxm = rcv_pkts[i];
+			rxm->data_off = RTE_PKTMBUF_HEADROOM - hdr_size;
+			rxm->pkt_len = (uint32_t)(len[i]);
+			rxm->data_len = (uint16_t)(len[i]);
+
+			rx_pkts[nb_rx]->pkt_len += (uint32_t)(len[i]);
+			rx_pkts[nb_rx]->data_len += (uint16_t)(len[i]);
+
+			if (prev)
+				prev->next = rxm;
+
+			prev = rxm;
+			seg_res -= 1;
+		}
+
+		if (!seg_res) {
+			virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]);
+			nb_rx++;
+		}
+	}
+
+	/* Last packet still need merge segments */
+	while (seg_res != 0) {
+		uint16_t rcv_cnt = RTE_MIN((uint16_t)seg_res,
+					VIRTIO_MBUF_BURST_SZ);
+
+		prev = rcv_pkts[nb_rx];
+		if (likely(VIRTQUEUE_NUSED(vq) >= rcv_cnt)) {
+			num = virtqueue_dequeue_rx_inorder(vq, rcv_pkts, len,
+							   rcv_cnt);
+			uint16_t extra_idx = 0;
+
+			rcv_cnt = num;
+			while (extra_idx < rcv_cnt) {
+				rxm = rcv_pkts[extra_idx];
+				rxm->data_off =
+					RTE_PKTMBUF_HEADROOM - hdr_size;
+				rxm->pkt_len = (uint32_t)(len[extra_idx]);
+				rxm->data_len = (uint16_t)(len[extra_idx]);
+				prev->next = rxm;
+				prev = rxm;
+				rx_pkts[nb_rx]->pkt_len += len[extra_idx];
+				rx_pkts[nb_rx]->data_len += len[extra_idx];
+				extra_idx += 1;
+			};
+			seg_res -= rcv_cnt;
+
+			if (!seg_res) {
+				virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]);
+				nb_rx++;
+			}
+		} else {
+			PMD_RX_LOG(ERR,
+					"No enough segments for packet.");
+			virtio_discard_rxbuf_inorder(vq, prev);
+			rxvq->stats.errors++;
+			break;
+		}
+	}
+
+	rxvq->stats.packets += nb_rx;
+
+	/* Allocate new mbuf for the used descriptor */
+
+	if (likely(!virtqueue_full(vq))) {
+		/* free_cnt may include mrg descs */
+		uint16_t free_cnt = vq->vq_free_cnt;
+		struct rte_mbuf *new_pkts[free_cnt];
+
+		if (!rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts, free_cnt)) {
+			error = virtqueue_enqueue_refill_inorder(vq, new_pkts,
+					free_cnt);
+			if (unlikely(error)) {
+				for (i = 0; i < free_cnt; i++)
+					rte_pktmbuf_free(new_pkts[i]);
+			}
+			nb_enqueued += free_cnt;
+		} else {
+			struct rte_eth_dev *dev =
+				&rte_eth_devices[rxvq->port_id];
+			dev->data->rx_mbuf_alloc_failed += free_cnt;
+		}
+	}
+
+	if (likely(nb_enqueued)) {
+		vq_update_avail_idx(vq);
+
+		if (unlikely(virtqueue_kick_prepare(vq))) {
+			virtqueue_notify(vq);
+			PMD_RX_LOG(DEBUG, "Notified");
+		}
+	}
+
+	return nb_rx;
+}
+
+uint16_t
 virtio_recv_mergeable_pkts(void *rx_queue,
 			struct rte_mbuf **rx_pkts,
 			uint16_t nb_pkts)
@@ -828,7 +1194,6 @@ virtio_recv_mergeable_pkts(void *rx_queue,
 	uint16_t extra_idx;
 	uint32_t seg_res;
 	uint32_t hdr_size;
-	int offload;
 
 	nb_rx = 0;
 	if (unlikely(hw->started == 0))
@@ -846,7 +1211,6 @@ virtio_recv_mergeable_pkts(void *rx_queue,
 	extra_idx = 0;
 	seg_res = 0;
 	hdr_size = hw->vtnet_hdr_size;
-	offload = rx_offload_enabled(hw);
 
 	while (i < nb_used) {
 		struct virtio_net_hdr_mrg_rxbuf *header;
@@ -891,7 +1255,8 @@ virtio_recv_mergeable_pkts(void *rx_queue,
 		rx_pkts[nb_rx] = rxm;
 		prev = rxm;
 
-		if (offload && virtio_rx_offload(rxm, &header->hdr) < 0) {
+		if (hw->has_rx_offload &&
+				virtio_rx_offload(rxm, &header->hdr) < 0) {
 			virtio_discard_rxbuf(vq, rxm);
 			rxvq->stats.errors++;
 			continue;
@@ -953,7 +1318,6 @@ virtio_recv_mergeable_pkts(void *rx_queue,
 	rxvq->stats.packets += nb_rx;
 
 	/* Allocate new mbuf for the used descriptor */
-	error = ENOSPC;
 	while (likely(!virtqueue_full(vq))) {
 		new_mbuf = rte_mbuf_raw_alloc(rxvq->mpool);
 		if (unlikely(new_mbuf == NULL)) {
@@ -1056,7 +1420,8 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		}
 
 		/* Enqueue Packet buffers */
-		virtqueue_enqueue_xmit(txvq, txm, slots, use_indirect, can_push);
+		virtqueue_enqueue_xmit(txvq, txm, slots, use_indirect,
+			can_push, 0);
 
 		txvq->stats.bytes += txm->pkt_len;
 		virtio_update_packet_stats(&txvq->stats, txm);
@@ -1075,3 +1440,116 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 
 	return nb_tx;
 }
+
+uint16_t
+virtio_xmit_pkts_inorder(void *tx_queue,
+			struct rte_mbuf **tx_pkts,
+			uint16_t nb_pkts)
+{
+	struct virtnet_tx *txvq = tx_queue;
+	struct virtqueue *vq = txvq->vq;
+	struct virtio_hw *hw = vq->hw;
+	uint16_t hdr_size = hw->vtnet_hdr_size;
+	uint16_t nb_used, nb_avail, nb_tx = 0, nb_inorder_pkts = 0;
+	struct rte_mbuf *inorder_pkts[nb_pkts];
+	int error;
+
+	if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts))
+		return nb_tx;
+
+	if (unlikely(nb_pkts < 1))
+		return nb_pkts;
+
+	VIRTQUEUE_DUMP(vq);
+	PMD_TX_LOG(DEBUG, "%d packets to xmit", nb_pkts);
+	nb_used = VIRTQUEUE_NUSED(vq);
+
+	virtio_rmb();
+	if (likely(nb_used > vq->vq_nentries - vq->vq_free_thresh))
+		virtio_xmit_cleanup_inorder(vq, nb_used);
+
+	if (unlikely(!vq->vq_free_cnt))
+		virtio_xmit_cleanup_inorder(vq, nb_used);
+
+	nb_avail = RTE_MIN(vq->vq_free_cnt, nb_pkts);
+
+	for (nb_tx = 0; nb_tx < nb_avail; nb_tx++) {
+		struct rte_mbuf *txm = tx_pkts[nb_tx];
+		int slots, need;
+
+		/* Do VLAN tag insertion */
+		if (unlikely(txm->ol_flags & PKT_TX_VLAN_PKT)) {
+			error = rte_vlan_insert(&txm);
+			if (unlikely(error)) {
+				rte_pktmbuf_free(txm);
+				continue;
+			}
+		}
+
+		/* optimize ring usage */
+		if ((vtpci_with_feature(hw, VIRTIO_F_ANY_LAYOUT) ||
+		     vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) &&
+		     rte_mbuf_refcnt_read(txm) == 1 &&
+		     RTE_MBUF_DIRECT(txm) &&
+		     txm->nb_segs == 1 &&
+		     rte_pktmbuf_headroom(txm) >= hdr_size &&
+		     rte_is_aligned(rte_pktmbuf_mtod(txm, char *),
+				__alignof__(struct virtio_net_hdr_mrg_rxbuf))) {
+			inorder_pkts[nb_inorder_pkts] = txm;
+			nb_inorder_pkts++;
+
+			txvq->stats.bytes += txm->pkt_len;
+			virtio_update_packet_stats(&txvq->stats, txm);
+			continue;
+		}
+
+		if (nb_inorder_pkts) {
+			virtqueue_enqueue_xmit_inorder(txvq, inorder_pkts,
+							nb_inorder_pkts);
+			nb_inorder_pkts = 0;
+		}
+
+		slots = txm->nb_segs + 1;
+		need = slots - vq->vq_free_cnt;
+		if (unlikely(need > 0)) {
+			nb_used = VIRTQUEUE_NUSED(vq);
+			virtio_rmb();
+			need = RTE_MIN(need, (int)nb_used);
+
+			virtio_xmit_cleanup_inorder(vq, need);
+
+			need = slots - vq->vq_free_cnt;
+
+			if (unlikely(need > 0)) {
+				PMD_TX_LOG(ERR,
+					"No free tx descriptors to transmit");
+				break;
+			}
+		}
+		/* Enqueue Packet buffers */
+		virtqueue_enqueue_xmit(txvq, txm, slots, 0, 0, 1);
+
+		txvq->stats.bytes += txm->pkt_len;
+		virtio_update_packet_stats(&txvq->stats, txm);
+	}
+
+	/* Transmit all inorder packets */
+	if (nb_inorder_pkts)
+		virtqueue_enqueue_xmit_inorder(txvq, inorder_pkts,
+						nb_inorder_pkts);
+
+	txvq->stats.packets += nb_tx;
+
+	if (likely(nb_tx)) {
+		vq_update_avail_idx(vq);
+
+		if (unlikely(virtqueue_kick_prepare(vq))) {
+			virtqueue_notify(vq);
+			PMD_TX_LOG(DEBUG, "Notified backend after xmit");
+		}
+	}
+
+	VIRTQUEUE_DUMP(vq);
+
+	return nb_tx;
+}
diff --git a/drivers/net/virtio/virtio_rxtx_simple.c b/drivers/net/virtio/virtio_rxtx_simple.c
index 51520758..31e565b4 100644
--- a/drivers/net/virtio/virtio_rxtx_simple.c
+++ b/drivers/net/virtio/virtio_rxtx_simple.c
@@ -27,73 +27,6 @@
 #pragma GCC diagnostic ignored "-Wcast-qual"
 #endif
 
-uint16_t
-virtio_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
-	uint16_t nb_pkts)
-{
-	struct virtnet_tx *txvq = tx_queue;
-	struct virtqueue *vq = txvq->vq;
-	struct virtio_hw *hw = vq->hw;
-	uint16_t nb_used;
-	uint16_t desc_idx;
-	struct vring_desc *start_dp;
-	uint16_t nb_tail, nb_commit;
-	int i;
-	uint16_t desc_idx_max = (vq->vq_nentries >> 1) - 1;
-	uint16_t nb_tx = 0;
-
-	if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts))
-		return nb_tx;
-
-	nb_used = VIRTQUEUE_NUSED(vq);
-	rte_compiler_barrier();
-
-	if (nb_used >= VIRTIO_TX_FREE_THRESH)
-		virtio_xmit_cleanup_simple(vq);
-
-	nb_commit = nb_pkts = RTE_MIN((vq->vq_free_cnt >> 1), nb_pkts);
-	desc_idx = (uint16_t)(vq->vq_avail_idx & desc_idx_max);
-	start_dp = vq->vq_ring.desc;
-	nb_tail = (uint16_t) (desc_idx_max + 1 - desc_idx);
-
-	if (nb_commit >= nb_tail) {
-		for (i = 0; i < nb_tail; i++)
-			vq->vq_descx[desc_idx + i].cookie = tx_pkts[i];
-		for (i = 0; i < nb_tail; i++) {
-			start_dp[desc_idx].addr =
-				VIRTIO_MBUF_DATA_DMA_ADDR(*tx_pkts, vq);
-			start_dp[desc_idx].len = (*tx_pkts)->pkt_len;
-			tx_pkts++;
-			desc_idx++;
-		}
-		nb_commit -= nb_tail;
-		desc_idx = 0;
-	}
-	for (i = 0; i < nb_commit; i++)
-		vq->vq_descx[desc_idx + i].cookie = tx_pkts[i];
-	for (i = 0; i < nb_commit; i++) {
-		start_dp[desc_idx].addr =
-			VIRTIO_MBUF_DATA_DMA_ADDR(*tx_pkts, vq);
-		start_dp[desc_idx].len = (*tx_pkts)->pkt_len;
-		tx_pkts++;
-		desc_idx++;
-	}
-
-	rte_compiler_barrier();
-
-	vq->vq_free_cnt -= (uint16_t)(nb_pkts << 1);
-	vq->vq_avail_idx += nb_pkts;
-	vq->vq_ring.avail->idx = vq->vq_avail_idx;
-	txvq->stats.packets += nb_pkts;
-
-	if (likely(nb_pkts)) {
-		if (unlikely(virtqueue_kick_prepare(vq)))
-			virtqueue_notify(vq);
-	}
-
-	return nb_pkts;
-}
-
 int __attribute__((cold))
 virtio_rxq_vec_setup(struct virtnet_rx *rxq)
 {
diff --git a/drivers/net/virtio/virtio_rxtx_simple.h b/drivers/net/virtio/virtio_rxtx_simple.h
index 303904d6..dc97e4cc 100644
--- a/drivers/net/virtio/virtio_rxtx_simple.h
+++ b/drivers/net/virtio/virtio_rxtx_simple.h
@@ -55,53 +55,4 @@ virtio_rxq_rearm_vec(struct virtnet_rx *rxvq)
 	vq_update_avail_idx(vq);
 }
 
-#define VIRTIO_TX_FREE_THRESH 32
-#define VIRTIO_TX_MAX_FREE_BUF_SZ 32
-#define VIRTIO_TX_FREE_NR 32
-/* TODO: vq->tx_free_cnt could mean num of free slots so we could avoid shift */
-static inline void
-virtio_xmit_cleanup_simple(struct virtqueue *vq)
-{
-	uint16_t i, desc_idx;
-	uint32_t nb_free = 0;
-	struct rte_mbuf *m, *free[VIRTIO_TX_MAX_FREE_BUF_SZ];
-
-	desc_idx = (uint16_t)(vq->vq_used_cons_idx &
-		   ((vq->vq_nentries >> 1) - 1));
-	m = (struct rte_mbuf *)vq->vq_descx[desc_idx++].cookie;
-	m = rte_pktmbuf_prefree_seg(m);
-	if (likely(m != NULL)) {
-		free[0] = m;
-		nb_free = 1;
-		for (i = 1; i < VIRTIO_TX_FREE_NR; i++) {
-			m = (struct rte_mbuf *)vq->vq_descx[desc_idx++].cookie;
-			m = rte_pktmbuf_prefree_seg(m);
-			if (likely(m != NULL)) {
-				if (likely(m->pool == free[0]->pool))
-					free[nb_free++] = m;
-				else {
-					rte_mempool_put_bulk(free[0]->pool,
-						(void **)free,
-						RTE_MIN(RTE_DIM(free),
-							nb_free));
-					free[0] = m;
-					nb_free = 1;
-				}
-			}
-		}
-		rte_mempool_put_bulk(free[0]->pool, (void **)free,
-			RTE_MIN(RTE_DIM(free), nb_free));
-	} else {
-		for (i = 1; i < VIRTIO_TX_FREE_NR; i++) {
-			m = (struct rte_mbuf *)vq->vq_descx[desc_idx++].cookie;
-			m = rte_pktmbuf_prefree_seg(m);
-			if (m != NULL)
-				rte_mempool_put(m->pool, m);
-		}
-	}
-
-	vq->vq_used_cons_idx += VIRTIO_TX_FREE_NR;
-	vq->vq_free_cnt += (VIRTIO_TX_FREE_NR << 1);
-}
-
 #endif /* _VIRTIO_RXTX_SIMPLE_H_ */
diff --git a/drivers/net/virtio/virtio_user/vhost_kernel.c b/drivers/net/virtio/virtio_user/vhost_kernel.c
index 8d0a1ab2..b2444096 100644
--- a/drivers/net/virtio/virtio_user/vhost_kernel.c
+++ b/drivers/net/virtio/virtio_user/vhost_kernel.c
@@ -70,6 +70,32 @@ static uint64_t vhost_req_user_to_kernel[] = {
 	[VHOST_USER_SET_MEM_TABLE] = VHOST_SET_MEM_TABLE,
 };
 
+struct walk_arg {
+	struct vhost_memory_kernel *vm;
+	uint32_t region_nr;
+};
+static int
+add_memory_region(const struct rte_memseg_list *msl __rte_unused,
+		const struct rte_memseg *ms, size_t len, void *arg)
+{
+	struct walk_arg *wa = arg;
+	struct vhost_memory_region *mr;
+	void *start_addr;
+
+	if (wa->region_nr >= max_regions)
+		return -1;
+
+	mr = &wa->vm->regions[wa->region_nr++];
+	start_addr = ms->addr;
+
+	mr->guest_phys_addr = (uint64_t)(uintptr_t)start_addr;
+	mr->userspace_addr = (uint64_t)(uintptr_t)start_addr;
+	mr->memory_size = len;
+	mr->mmap_offset = 0;
+
+	return 0;
+}
+
 /* By default, vhost kernel module allows 64 regions, but DPDK allows
  * 256 segments. As a relief, below function merges those virtually
  * adjacent memsegs into one region.
@@ -77,63 +103,24 @@ static uint64_t vhost_req_user_to_kernel[] = {
 static struct vhost_memory_kernel *
 prepare_vhost_memory_kernel(void)
 {
-	uint32_t i, j, k = 0;
-	struct rte_memseg *seg;
-	struct vhost_memory_region *mr;
 	struct vhost_memory_kernel *vm;
+	struct walk_arg wa;
 
 	vm = malloc(sizeof(struct vhost_memory_kernel) +
-		    max_regions *
-		    sizeof(struct vhost_memory_region));
+			max_regions *
+			sizeof(struct vhost_memory_region));
 	if (!vm)
 		return NULL;
 
-	for (i = 0; i < RTE_MAX_MEMSEG; ++i) {
-		seg = &rte_eal_get_configuration()->mem_config->memseg[i];
-		if (!seg->addr)
-			break;
-
-		int new_region = 1;
-
-		for (j = 0; j < k; ++j) {
-			mr = &vm->regions[j];
-
-			if (mr->userspace_addr + mr->memory_size ==
-			    (uint64_t)(uintptr_t)seg->addr) {
-				mr->memory_size += seg->len;
-				new_region = 0;
-				break;
-			}
-
-			if ((uint64_t)(uintptr_t)seg->addr + seg->len ==
-			    mr->userspace_addr) {
-				mr->guest_phys_addr =
-					(uint64_t)(uintptr_t)seg->addr;
-				mr->userspace_addr =
-					(uint64_t)(uintptr_t)seg->addr;
-				mr->memory_size += seg->len;
-				new_region = 0;
-				break;
-			}
-		}
-
-		if (new_region == 0)
-			continue;
-
-		mr = &vm->regions[k++];
-		/* use vaddr here! */
-		mr->guest_phys_addr = (uint64_t)(uintptr_t)seg->addr;
-		mr->userspace_addr = (uint64_t)(uintptr_t)seg->addr;
-		mr->memory_size = seg->len;
-		mr->mmap_offset = 0;
+	wa.region_nr = 0;
+	wa.vm = vm;
 
-		if (k >= max_regions) {
-			free(vm);
-			return NULL;
-		}
+	if (rte_memseg_contig_walk(add_memory_region, &wa) < 0) {
+		free(vm);
+		return NULL;
 	}
 
-	vm->nregions = k;
+	vm->nregions = wa.region_nr;
 	vm->padding = 0;
 	return vm;
 }
@@ -351,7 +338,8 @@ vhost_kernel_enable_queue_pair(struct virtio_user_dev *dev,
 	else
 		hdr_size = sizeof(struct virtio_net_hdr);
 
-	tapfd = vhost_kernel_open_tap(&dev->ifname, hdr_size, req_mq);
+	tapfd = vhost_kernel_open_tap(&dev->ifname, hdr_size, req_mq,
+			 (char *)dev->mac_addr);
 	if (tapfd < 0) {
 		PMD_DRV_LOG(ERR, "fail to open tap for vhost kernel");
 		return -1;
diff --git a/drivers/net/virtio/virtio_user/vhost_kernel_tap.c b/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
index 1a47a348..9ea7ade7 100644
--- a/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
+++ b/drivers/net/virtio/virtio_user/vhost_kernel_tap.c
@@ -7,15 +7,19 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <net/if.h>
+#include <net/if_arp.h>
 #include <errno.h>
 #include <string.h>
 #include <limits.h>
 
+#include <rte_ether.h>
+
 #include "vhost_kernel_tap.h"
 #include "../virtio_logs.h"
 
 int
-vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq)
+vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq,
+			 const char *mac)
 {
 	unsigned int tap_features;
 	int sndbuf = INT_MAX;
@@ -94,6 +98,14 @@ vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq)
 		PMD_DRV_LOG(ERR, "TUNSETOFFLOAD ioctl() failed: %s",
 			   strerror(errno));
 
+	memset(&ifr, 0, sizeof(ifr));
+	ifr.ifr_hwaddr.sa_family = ARPHRD_ETHER;
+	memcpy(ifr.ifr_hwaddr.sa_data, mac, ETHER_ADDR_LEN);
+	if (ioctl(tapfd, SIOCSIFHWADDR, (void *)&ifr) == -1) {
+		PMD_DRV_LOG(ERR, "SIOCSIFHWADDR failed: %s", strerror(errno));
+		goto error;
+	}
+
 	if (!(*p_ifname))
 		*p_ifname = strdup(ifr.ifr_name);
 
diff --git a/drivers/net/virtio/virtio_user/vhost_kernel_tap.h b/drivers/net/virtio/virtio_user/vhost_kernel_tap.h
index 7d52e6b7..01a026f5 100644
--- a/drivers/net/virtio/virtio_user/vhost_kernel_tap.h
+++ b/drivers/net/virtio/virtio_user/vhost_kernel_tap.h
@@ -35,4 +35,5 @@
 /* Constants */
 #define PATH_NET_TUN	"/dev/net/tun"
 
-int vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq);
+int vhost_kernel_open_tap(char **p_ifname, int hdr_size, int req_mq,
+			 const char *mac);
diff --git a/drivers/net/virtio/virtio_user/vhost_user.c b/drivers/net/virtio/virtio_user/vhost_user.c
index 91c6449b..ef6e43df 100644
--- a/drivers/net/virtio/virtio_user/vhost_user.c
+++ b/drivers/net/virtio/virtio_user/vhost_user.c
@@ -138,12 +138,13 @@ struct hugepage_file_info {
 static int
 get_hugepage_file_info(struct hugepage_file_info huges[], int max)
 {
-	int idx;
+	int idx, k, exist;
 	FILE *f;
 	char buf[BUFSIZ], *tmp, *tail;
 	char *str_underline, *str_start;
 	int huge_index;
 	uint64_t v_start, v_end;
+	struct stat stats;
 
 	f = fopen("/proc/self/maps", "r");
 	if (!f) {
@@ -183,16 +184,39 @@ get_hugepage_file_info(struct hugepage_file_info huges[], int max)
 		if (sscanf(str_start, "map_%d", &huge_index) != 1)
 			continue;
 
+		/* skip duplicated file which is mapped to different regions */
+		for (k = 0, exist = -1; k < idx; ++k) {
+			if (!strcmp(huges[k].path, tmp)) {
+				exist = k;
+				break;
+			}
+		}
+		if (exist >= 0)
+			continue;
+
 		if (idx >= max) {
 			PMD_DRV_LOG(ERR, "Exceed maximum of %d", max);
 			goto error;
 		}
+
 		huges[idx].addr = v_start;
-		huges[idx].size = v_end - v_start;
+		huges[idx].size = v_end - v_start; /* To be corrected later */
 		snprintf(huges[idx].path, PATH_MAX, "%s", tmp);
 		idx++;
 	}
 
+	/* correct the size for files who have many regions */
+	for (k = 0; k < idx; ++k) {
+		if (stat(huges[k].path, &stats) < 0) {
+			PMD_DRV_LOG(ERR, "Failed to stat %s, %s\n",
+				    huges[k].path, strerror(errno));
+			continue;
+		}
+		huges[k].size = stats.st_size;
+		PMD_DRV_LOG(INFO, "file %s, size %zx\n",
+			    huges[k].path, huges[k].size);
+	}
+
 	fclose(f);
 	return idx;
 
@@ -263,6 +287,9 @@ vhost_user_sock(struct virtio_user_dev *dev,
 
 	PMD_DRV_LOG(INFO, "%s", vhost_msg_strings[req]);
 
+	if (dev->is_server && vhostfd < 0)
+		return -1;
+
 	msg.request = req;
 	msg.flags = VHOST_USER_VERSION;
 	msg.size = 0;
@@ -378,6 +405,30 @@ vhost_user_sock(struct virtio_user_dev *dev,
 	return 0;
 }
 
+#define MAX_VIRTIO_USER_BACKLOG 1
+static int
+virtio_user_start_server(struct virtio_user_dev *dev, struct sockaddr_un *un)
+{
+	int ret;
+	int flag;
+	int fd = dev->listenfd;
+
+	ret = bind(fd, (struct sockaddr *)un, sizeof(*un));
+	if (ret < 0) {
+		PMD_DRV_LOG(ERR, "failed to bind to %s: %s; remove it and try again\n",
+			    dev->path, strerror(errno));
+		return -1;
+	}
+	ret = listen(fd, MAX_VIRTIO_USER_BACKLOG);
+	if (ret < 0)
+		return -1;
+
+	flag = fcntl(fd, F_GETFL);
+	fcntl(fd, F_SETFL, flag | O_NONBLOCK);
+
+	return 0;
+}
+
 /**
  * Set up environment to talk with a vhost user backend.
  *
@@ -405,13 +456,24 @@ vhost_user_setup(struct virtio_user_dev *dev)
 	memset(&un, 0, sizeof(un));
 	un.sun_family = AF_UNIX;
 	snprintf(un.sun_path, sizeof(un.sun_path), "%s", dev->path);
-	if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
-		PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
-		close(fd);
-		return -1;
+
+	if (dev->is_server) {
+		dev->listenfd = fd;
+		if (virtio_user_start_server(dev, &un) < 0) {
+			PMD_DRV_LOG(ERR, "virtio-user startup fails in server mode");
+			close(fd);
+			return -1;
+		}
+		dev->vhostfd = -1;
+	} else {
+		if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
+			PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
+			close(fd);
+			return -1;
+		}
+		dev->vhostfd = fd;
 	}
 
-	dev->vhostfd = fd;
 	return 0;
 }
 
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
index f90fee9e..7df600b0 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -17,6 +17,8 @@
 #include "virtio_user_dev.h"
 #include "../virtio_ethdev.h"
 
+#define VIRTIO_USER_MEM_EVENT_CLB_NAME "virtio_user_mem_event_clb"
+
 static int
 virtio_user_create_queue(struct virtio_user_dev *dev, uint32_t queue_sel)
 {
@@ -94,11 +96,27 @@ virtio_user_queue_setup(struct virtio_user_dev *dev,
 }
 
 int
+is_vhost_user_by_type(const char *path)
+{
+	struct stat sb;
+
+	if (stat(path, &sb) == -1)
+		return 0;
+
+	return S_ISSOCK(sb.st_mode);
+}
+
+int
 virtio_user_start_device(struct virtio_user_dev *dev)
 {
 	uint64_t features;
 	int ret;
 
+	pthread_mutex_lock(&dev->mutex);
+
+	if (is_vhost_user_by_type(dev->path) && dev->vhostfd < 0)
+		goto error;
+
 	/* Do not check return as already done in init, or reset in stop */
 	dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL);
 
@@ -132,8 +150,12 @@ virtio_user_start_device(struct virtio_user_dev *dev)
 	 */
 	dev->ops->enable_qp(dev, 0, 1);
 
+	dev->started = true;
+	pthread_mutex_unlock(&dev->mutex);
+
 	return 0;
 error:
+	pthread_mutex_unlock(&dev->mutex);
 	/* TODO: free resource here or caller to check */
 	return -1;
 }
@@ -142,13 +164,17 @@ int virtio_user_stop_device(struct virtio_user_dev *dev)
 {
 	uint32_t i;
 
+	pthread_mutex_lock(&dev->mutex);
 	for (i = 0; i < dev->max_queue_pairs; ++i)
 		dev->ops->enable_qp(dev, i, 0);
 
 	if (dev->ops->send_request(dev, VHOST_USER_RESET_OWNER, NULL) < 0) {
 		PMD_DRV_LOG(INFO, "Failed to reset the device\n");
+		pthread_mutex_unlock(&dev->mutex);
 		return -1;
 	}
+	dev->started = false;
+	pthread_mutex_unlock(&dev->mutex);
 
 	return 0;
 }
@@ -174,17 +200,6 @@ parse_mac(struct virtio_user_dev *dev, const char *mac)
 	}
 }
 
-int
-is_vhost_user_by_type(const char *path)
-{
-	struct stat sb;
-
-	if (stat(path, &sb) == -1)
-		return 0;
-
-	return S_ISSOCK(sb.st_mode);
-}
-
 static int
 virtio_user_dev_init_notify(struct virtio_user_dev *dev)
 {
@@ -254,10 +269,41 @@ virtio_user_fill_intr_handle(struct virtio_user_dev *dev)
 	eth_dev->intr_handle->fd = -1;
 	if (dev->vhostfd >= 0)
 		eth_dev->intr_handle->fd = dev->vhostfd;
+	else if (dev->is_server)
+		eth_dev->intr_handle->fd = dev->listenfd;
 
 	return 0;
 }
 
+static void
+virtio_user_mem_event_cb(enum rte_mem_event type __rte_unused,
+						 const void *addr __rte_unused,
+						 size_t len __rte_unused,
+						 void *arg)
+{
+	struct virtio_user_dev *dev = arg;
+	uint16_t i;
+
+	pthread_mutex_lock(&dev->mutex);
+
+	if (dev->started == false)
+		goto exit;
+
+	/* Step 1: pause the active queues */
+	for (i = 0; i < dev->queue_pairs; i++)
+		dev->ops->enable_qp(dev, i, 0);
+
+	/* Step 2: update memory regions */
+	dev->ops->send_request(dev, VHOST_USER_SET_MEM_TABLE, NULL);
+
+	/* Step 3: resume the active queues */
+	for (i = 0; i < dev->queue_pairs; i++)
+		dev->ops->enable_qp(dev, i, 1);
+
+exit:
+	pthread_mutex_unlock(&dev->mutex);
+}
+
 static int
 virtio_user_dev_setup(struct virtio_user_dev *dev)
 {
@@ -267,21 +313,32 @@ virtio_user_dev_setup(struct virtio_user_dev *dev)
 	dev->vhostfds = NULL;
 	dev->tapfds = NULL;
 
-	if (is_vhost_user_by_type(dev->path)) {
-		dev->ops = &ops_user;
-	} else {
-		dev->ops = &ops_kernel;
-
-		dev->vhostfds = malloc(dev->max_queue_pairs * sizeof(int));
-		dev->tapfds = malloc(dev->max_queue_pairs * sizeof(int));
-		if (!dev->vhostfds || !dev->tapfds) {
-			PMD_INIT_LOG(ERR, "Failed to malloc");
+	if (dev->is_server) {
+		if (access(dev->path, F_OK) == 0 &&
+		    !is_vhost_user_by_type(dev->path)) {
+			PMD_DRV_LOG(ERR, "Server mode doesn't support vhost-kernel!");
 			return -1;
 		}
-
-		for (q = 0; q < dev->max_queue_pairs; ++q) {
-			dev->vhostfds[q] = -1;
-			dev->tapfds[q] = -1;
+		dev->ops = &ops_user;
+	} else {
+		if (is_vhost_user_by_type(dev->path)) {
+			dev->ops = &ops_user;
+		} else {
+			dev->ops = &ops_kernel;
+
+			dev->vhostfds = malloc(dev->max_queue_pairs *
+					       sizeof(int));
+			dev->tapfds = malloc(dev->max_queue_pairs *
+					     sizeof(int));
+			if (!dev->vhostfds || !dev->tapfds) {
+				PMD_INIT_LOG(ERR, "Failed to malloc");
+				return -1;
+			}
+
+			for (q = 0; q < dev->max_queue_pairs; ++q) {
+				dev->vhostfds[q] = -1;
+				dev->tapfds[q] = -1;
+			}
 		}
 	}
 
@@ -314,17 +371,22 @@ virtio_user_dev_setup(struct virtio_user_dev *dev)
 	 1ULL << VIRTIO_NET_F_GUEST_CSUM	|	\
 	 1ULL << VIRTIO_NET_F_GUEST_TSO4	|	\
 	 1ULL << VIRTIO_NET_F_GUEST_TSO6	|	\
+	 1ULL << VIRTIO_F_IN_ORDER		|	\
 	 1ULL << VIRTIO_F_VERSION_1)
 
 int
 virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
-		     int cq, int queue_size, const char *mac, char **ifname)
+		     int cq, int queue_size, const char *mac, char **ifname,
+		     int mrg_rxbuf, int in_order)
 {
+	pthread_mutex_init(&dev->mutex, NULL);
 	snprintf(dev->path, PATH_MAX, "%s", path);
+	dev->started = 0;
 	dev->max_queue_pairs = queues;
 	dev->queue_pairs = 1; /* mq disabled by default */
 	dev->queue_size = queue_size;
 	dev->mac_specified = 0;
+	dev->unsupported_features = 0;
 	parse_mac(dev, mac);
 
 	if (*ifname) {
@@ -337,18 +399,45 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 		return -1;
 	}
 
-	if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL) < 0) {
-		PMD_INIT_LOG(ERR, "set_owner fails: %s", strerror(errno));
-		return -1;
+	if (!dev->is_server) {
+		if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER,
+					   NULL) < 0) {
+			PMD_INIT_LOG(ERR, "set_owner fails: %s",
+				     strerror(errno));
+			return -1;
+		}
+
+		if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
+					   &dev->device_features) < 0) {
+			PMD_INIT_LOG(ERR, "get_features failed: %s",
+				     strerror(errno));
+			return -1;
+		}
+	} else {
+		/* We just pretend vhost-user can support all these features.
+		 * Note that this could be problematic that if some feature is
+		 * negotiated but not supported by the vhost-user which comes
+		 * later.
+		 */
+		dev->device_features = VIRTIO_USER_SUPPORTED_FEATURES;
 	}
 
-	if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
-			    &dev->device_features) < 0) {
-		PMD_INIT_LOG(ERR, "get_features failed: %s", strerror(errno));
-		return -1;
+	if (!mrg_rxbuf) {
+		dev->device_features &= ~(1ull << VIRTIO_NET_F_MRG_RXBUF);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_MRG_RXBUF);
+	}
+
+	if (!in_order) {
+		dev->device_features &= ~(1ull << VIRTIO_F_IN_ORDER);
+		dev->unsupported_features |= (1ull << VIRTIO_F_IN_ORDER);
 	}
-	if (dev->mac_specified)
+
+	if (dev->mac_specified) {
 		dev->device_features |= (1ull << VIRTIO_NET_F_MAC);
+	} else {
+		dev->device_features &= ~(1ull << VIRTIO_NET_F_MAC);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_MAC);
+	}
 
 	if (cq) {
 		/* device does not really need to know anything about CQ,
@@ -363,6 +452,14 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 		dev->device_features &= ~(1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
 		dev->device_features &= ~(1ull << VIRTIO_NET_F_MQ);
 		dev->device_features &= ~(1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_VQ);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_RX);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_VLAN);
+		dev->unsupported_features |=
+			(1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
+		dev->unsupported_features |= (1ull << VIRTIO_NET_F_MQ);
+		dev->unsupported_features |=
+			(1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
 	}
 
 	/* The backend will not report this feature, we add it explicitly */
@@ -370,6 +467,16 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 		dev->device_features |= (1ull << VIRTIO_NET_F_STATUS);
 
 	dev->device_features &= VIRTIO_USER_SUPPORTED_FEATURES;
+	dev->unsupported_features |= ~VIRTIO_USER_SUPPORTED_FEATURES;
+
+	if (rte_mem_event_callback_register(VIRTIO_USER_MEM_EVENT_CLB_NAME,
+				virtio_user_mem_event_cb, dev)) {
+		if (rte_errno != ENOTSUP) {
+			PMD_INIT_LOG(ERR, "Failed to register mem event"
+					" callback\n");
+			return -1;
+		}
+	}
 
 	return 0;
 }
@@ -381,6 +488,8 @@ virtio_user_dev_uninit(struct virtio_user_dev *dev)
 
 	virtio_user_stop_device(dev);
 
+	rte_mem_event_callback_unregister(VIRTIO_USER_MEM_EVENT_CLB_NAME, dev);
+
 	for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
 		close(dev->callfds[i]);
 		close(dev->kickfds[i]);
@@ -388,6 +497,11 @@ virtio_user_dev_uninit(struct virtio_user_dev *dev)
 
 	close(dev->vhostfd);
 
+	if (dev->is_server && dev->listenfd >= 0) {
+		close(dev->listenfd);
+		dev->listenfd = -1;
+	}
+
 	if (dev->vhostfds) {
 		for (i = 0; i < dev->max_queue_pairs; ++i)
 			close(dev->vhostfds[i]);
@@ -396,9 +510,12 @@ virtio_user_dev_uninit(struct virtio_user_dev *dev)
 	}
 
 	free(dev->ifname);
+
+	if (dev->is_server)
+		unlink(dev->path);
 }
 
-static uint8_t
+uint8_t
 virtio_user_handle_mq(struct virtio_user_dev *dev, uint16_t q_pairs)
 {
 	uint16_t i;
@@ -410,11 +527,17 @@ virtio_user_handle_mq(struct virtio_user_dev *dev, uint16_t q_pairs)
 		return -1;
 	}
 
-	for (i = 0; i < q_pairs; ++i)
-		ret |= dev->ops->enable_qp(dev, i, 1);
-	for (i = q_pairs; i < dev->max_queue_pairs; ++i)
-		ret |= dev->ops->enable_qp(dev, i, 0);
-
+	/* Server mode can't enable queue pairs if vhostfd is invalid,
+	 * always return 0 in this case.
+	 */
+	if (dev->vhostfd >= 0) {
+		for (i = 0; i < q_pairs; ++i)
+			ret |= dev->ops->enable_qp(dev, i, 1);
+		for (i = q_pairs; i < dev->max_queue_pairs; ++i)
+			ret |= dev->ops->enable_qp(dev, i, 0);
+	} else if (!dev->is_server) {
+		ret = ~0;
+	}
 	dev->queue_pairs = q_pairs;
 
 	return ret;
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.h b/drivers/net/virtio/virtio_user/virtio_user_dev.h
index 64467b4f..d6e0e137 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.h
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.h
@@ -6,6 +6,7 @@
 #define _VIRTIO_USER_DEV_H
 
 #include <limits.h>
+#include <stdbool.h>
 #include "../virtio_pci.h"
 #include "../virtio_ring.h"
 #include "vhost.h"
@@ -13,6 +14,8 @@
 struct virtio_user_dev {
 	/* for vhost_user backend */
 	int		vhostfd;
+	int		listenfd;   /* listening fd */
+	bool		is_server;  /* server or client mode */
 
 	/* for vhost_kernel backend */
 	char		*ifname;
@@ -30,19 +33,24 @@ struct virtio_user_dev {
 				   * and will be sync with device
 				   */
 	uint64_t	device_features; /* supported features by device */
+	uint64_t	unsupported_features; /* unsupported features mask */
 	uint8_t		status;
-	uint8_t		port_id;
+	uint16_t	port_id;
 	uint8_t		mac_addr[ETHER_ADDR_LEN];
 	char		path[PATH_MAX];
 	struct vring	vrings[VIRTIO_MAX_VIRTQUEUES];
 	struct virtio_user_backend_ops *ops;
+	pthread_mutex_t	mutex;
+	bool		started;
 };
 
 int is_vhost_user_by_type(const char *path);
 int virtio_user_start_device(struct virtio_user_dev *dev);
 int virtio_user_stop_device(struct virtio_user_dev *dev);
 int virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
-			 int cq, int queue_size, const char *mac, char **ifname);
+			 int cq, int queue_size, const char *mac, char **ifname,
+			 int mrg_rxbuf, int in_order);
 void virtio_user_dev_uninit(struct virtio_user_dev *dev);
 void virtio_user_handle_cq(struct virtio_user_dev *dev, uint16_t queue_idx);
+uint8_t virtio_user_handle_mq(struct virtio_user_dev *dev, uint16_t q_pairs);
 #endif
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index 26364900..525d16ca 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -24,15 +24,92 @@
 #define virtio_user_get_dev(hw) \
 	((struct virtio_user_dev *)(hw)->virtio_user_dev)
 
+static int
+virtio_user_server_reconnect(struct virtio_user_dev *dev)
+{
+	int ret;
+	int flag;
+	int connectfd;
+	struct rte_eth_dev *eth_dev = &rte_eth_devices[dev->port_id];
+
+	connectfd = accept(dev->listenfd, NULL, NULL);
+	if (connectfd < 0)
+		return -1;
+
+	dev->vhostfd = connectfd;
+	if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
+				   &dev->device_features) < 0) {
+		PMD_INIT_LOG(ERR, "get_features failed: %s",
+			     strerror(errno));
+		return -1;
+	}
+
+	/* umask vhost-user unsupported features */
+	dev->device_features &= ~(dev->unsupported_features);
+
+	dev->features &= dev->device_features;
+
+	flag = fcntl(connectfd, F_GETFD);
+	fcntl(connectfd, F_SETFL, flag | O_NONBLOCK);
+
+	ret = virtio_user_start_device(dev);
+	if (ret < 0)
+		return -1;
+
+	if (dev->queue_pairs > 1) {
+		ret = virtio_user_handle_mq(dev, dev->queue_pairs);
+		if (ret != 0) {
+			PMD_INIT_LOG(ERR, "Fails to enable multi-queue pairs!");
+			return -1;
+		}
+	}
+	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) {
+		if (rte_intr_disable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt disable failed");
+			return -1;
+		}
+		rte_intr_callback_unregister(eth_dev->intr_handle,
+					     virtio_interrupt_handler,
+					     eth_dev);
+		eth_dev->intr_handle->fd = connectfd;
+		rte_intr_callback_register(eth_dev->intr_handle,
+					   virtio_interrupt_handler, eth_dev);
+
+		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt enable failed");
+			return -1;
+		}
+	}
+	PMD_INIT_LOG(NOTICE, "server mode virtio-user reconnection succeeds!");
+	return 0;
+}
+
 static void
 virtio_user_delayed_handler(void *param)
 {
 	struct virtio_hw *hw = (struct virtio_hw *)param;
-	struct rte_eth_dev *dev = &rte_eth_devices[hw->port_id];
+	struct rte_eth_dev *eth_dev = &rte_eth_devices[hw->port_id];
+	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	rte_intr_callback_unregister(dev->intr_handle,
-				     virtio_interrupt_handler,
-				     dev);
+	if (rte_intr_disable(eth_dev->intr_handle) < 0) {
+		PMD_DRV_LOG(ERR, "interrupt disable failed");
+		return;
+	}
+	rte_intr_callback_unregister(eth_dev->intr_handle,
+				     virtio_interrupt_handler, eth_dev);
+	if (dev->is_server) {
+		if (dev->vhostfd >= 0) {
+			close(dev->vhostfd);
+			dev->vhostfd = -1;
+		}
+		eth_dev->intr_handle->fd = dev->listenfd;
+		rte_intr_callback_register(eth_dev->intr_handle,
+					   virtio_interrupt_handler, eth_dev);
+		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
+			PMD_DRV_LOG(ERR, "interrupt enable failed");
+			return;
+		}
+	}
 }
 
 static void
@@ -67,12 +144,10 @@ virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
 				dev->status &= (~VIRTIO_NET_S_LINK_UP);
 				PMD_DRV_LOG(ERR, "virtio-user port %u is down",
 					    hw->port_id);
-				/* Only client mode is available now. Once the
-				 * connection is broken, it can never be up
-				 * again. Besides, this function could be called
-				 * in the process of interrupt handling,
-				 * callback cannot be unregistered here, set an
-				 * alarm to do it.
+
+				/* This function could be called in the process
+				 * of interrupt handling, callback cannot be
+				 * unregistered here, set an alarm to do it.
 				 */
 				rte_eal_alarm_set(1,
 						  virtio_user_delayed_handler,
@@ -85,7 +160,12 @@ virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
 				PMD_DRV_LOG(ERR, "error clearing O_NONBLOCK flag");
 				return;
 			}
+		} else if (dev->is_server) {
+			dev->status &= (~VIRTIO_NET_S_LINK_UP);
+			if (virtio_user_server_reconnect(dev) >= 0)
+				dev->status |= VIRTIO_NET_S_LINK_UP;
 		}
+
 		*(uint16_t *)dst = dev->status;
 	}
 
@@ -278,12 +358,19 @@ static const char *valid_args[] = {
 	VIRTIO_USER_ARG_QUEUE_SIZE,
 #define VIRTIO_USER_ARG_INTERFACE_NAME "iface"
 	VIRTIO_USER_ARG_INTERFACE_NAME,
+#define VIRTIO_USER_ARG_SERVER_MODE    "server"
+	VIRTIO_USER_ARG_SERVER_MODE,
+#define VIRTIO_USER_ARG_MRG_RXBUF      "mrg_rxbuf"
+	VIRTIO_USER_ARG_MRG_RXBUF,
+#define VIRTIO_USER_ARG_IN_ORDER       "in_order"
+	VIRTIO_USER_ARG_IN_ORDER,
 	NULL
 };
 
 #define VIRTIO_USER_DEF_CQ_EN	0
 #define VIRTIO_USER_DEF_Q_NUM	1
 #define VIRTIO_USER_DEF_Q_SZ	256
+#define VIRTIO_USER_DEF_SERVER_MODE	0
 
 static int
 get_string_arg(const char *key __rte_unused,
@@ -349,7 +436,8 @@ virtio_user_eth_dev_alloc(struct rte_vdev_device *vdev)
 	hw->use_msix = 1;
 	hw->modern   = 0;
 	hw->use_simple_rx = 0;
-	hw->use_simple_tx = 0;
+	hw->use_inorder_rx = 0;
+	hw->use_inorder_tx = 0;
 	hw->virtio_user_dev = dev;
 	return eth_dev;
 }
@@ -378,6 +466,9 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 	uint64_t queues = VIRTIO_USER_DEF_Q_NUM;
 	uint64_t cq = VIRTIO_USER_DEF_CQ_EN;
 	uint64_t queue_size = VIRTIO_USER_DEF_Q_SZ;
+	uint64_t server_mode = VIRTIO_USER_DEF_SERVER_MODE;
+	uint64_t mrg_rxbuf = 1;
+	uint64_t in_order = 1;
 	char *path = NULL;
 	char *ifname = NULL;
 	char *mac_addr = NULL;
@@ -445,6 +536,15 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		}
 	}
 
+	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_SERVER_MODE) == 1) {
+		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_SERVER_MODE,
+				       &get_integer_arg, &server_mode) < 0) {
+			PMD_INIT_LOG(ERR, "error to parse %s",
+				     VIRTIO_USER_ARG_SERVER_MODE);
+			goto end;
+		}
+	}
+
 	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_CQ_NUM) == 1) {
 		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_CQ_NUM,
 				       &get_integer_arg, &cq) < 0) {
@@ -468,7 +568,27 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		goto end;
 	}
 
+	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_MRG_RXBUF) == 1) {
+		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_MRG_RXBUF,
+				       &get_integer_arg, &mrg_rxbuf) < 0) {
+			PMD_INIT_LOG(ERR, "error to parse %s",
+				     VIRTIO_USER_ARG_MRG_RXBUF);
+			goto end;
+		}
+	}
+
+	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_IN_ORDER) == 1) {
+		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_IN_ORDER,
+				       &get_integer_arg, &in_order) < 0) {
+			PMD_INIT_LOG(ERR, "error to parse %s",
+				     VIRTIO_USER_ARG_IN_ORDER);
+			goto end;
+		}
+	}
+
 	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+		struct virtio_user_dev *vu_dev;
+
 		eth_dev = virtio_user_eth_dev_alloc(dev);
 		if (!eth_dev) {
 			PMD_INIT_LOG(ERR, "virtio_user fails to alloc device");
@@ -476,12 +596,19 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		}
 
 		hw = eth_dev->data->dev_private;
+		vu_dev = virtio_user_get_dev(hw);
+		if (server_mode == 1)
+			vu_dev->is_server = true;
+		else
+			vu_dev->is_server = false;
 		if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq,
-				 queue_size, mac_addr, &ifname) < 0) {
+				 queue_size, mac_addr, &ifname, mrg_rxbuf,
+				 in_order) < 0) {
 			PMD_INIT_LOG(ERR, "virtio_user_dev_init fails");
 			virtio_user_eth_dev_free(eth_dev);
 			goto end;
 		}
+
 	} else {
 		eth_dev = rte_eth_dev_attach_secondary(rte_vdev_device_name(dev));
 		if (!eth_dev)
@@ -494,6 +621,8 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
 		virtio_user_eth_dev_free(eth_dev);
 		goto end;
 	}
+
+	rte_eth_dev_probing_finish(eth_dev);
 	ret = 0;
 
 end:
@@ -552,4 +681,7 @@ RTE_PMD_REGISTER_PARAM_STRING(net_virtio_user,
 	"cq=<int> "
 	"queue_size=<int> "
 	"queues=<int> "
-	"iface=<string>");
+	"iface=<string> "
+	"server=<0|1> "
+	"mrg_rxbuf=<0|1> "
+	"in_order=<0|1>");
diff --git a/drivers/net/virtio/virtqueue.c b/drivers/net/virtio/virtqueue.c
index a7d0a9cb..56a77cc7 100644
--- a/drivers/net/virtio/virtqueue.c
+++ b/drivers/net/virtio/virtqueue.c
@@ -74,6 +74,14 @@ virtqueue_rxvq_flush(struct virtqueue *vq)
 			desc_idx = used_idx;
 			rte_pktmbuf_free(vq->sw_ring[desc_idx]);
 			vq->vq_free_cnt++;
+		} else if (hw->use_inorder_rx) {
+			desc_idx = (uint16_t)uep->id;
+			dxp = &vq->vq_descx[desc_idx];
+			if (dxp->cookie != NULL) {
+				rte_pktmbuf_free(dxp->cookie);
+				dxp->cookie = NULL;
+			}
+			vq_ring_free_inorder(vq, desc_idx, 1);
 		} else {
 			desc_idx = (uint16_t)uep->id;
 			dxp = &vq->vq_descx[desc_idx];
diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h
index 14364f35..26518ed9 100644
--- a/drivers/net/virtio/virtqueue.h
+++ b/drivers/net/virtio/virtqueue.h
@@ -306,6 +306,8 @@ virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx)
 #define VIRTQUEUE_NUSED(vq) ((uint16_t)((vq)->vq_ring.used->idx - (vq)->vq_used_cons_idx))
 
 void vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx);
+void vq_ring_free_inorder(struct virtqueue *vq, uint16_t desc_idx,
+			  uint16_t num);
 
 static inline void
 vq_update_avail_idx(struct virtqueue *vq)