Imported Upstream version 16.11.1

Change-Id: I1e965265578efaaf08e5628607f53d2386d2df9f
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>

9 files changed, 212 insertions, 92 deletions

diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 079fd6c8..f5961ab7 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -152,6 +152,8 @@ static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = {
 #define VIRTIO_NB_TXQ_XSTATS (sizeof(rte_virtio_txq_stat_strings) / \
 			    sizeof(rte_virtio_txq_stat_strings[0]))
 
+struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
+
 static int
 virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
 		int *dlen, int pkt_num)
@@ -360,7 +362,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 	 * Read the virtqueue size from the Queue Size field
 	 * Always power of 2 and if 0 virtqueue does not exist
 	 */
-	vq_size = hw->vtpci_ops->get_queue_num(hw, vtpci_queue_idx);
+	vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx);
 	PMD_INIT_LOG(DEBUG, "vq_size: %u", vq_size);
 	if (vq_size == 0) {
 		PMD_INIT_LOG(ERR, "virtqueue does not exist");
@@ -519,7 +521,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
 		}
 	}
 
-	if (hw->vtpci_ops->setup_queue(hw, vq) < 0) {
+	if (VTPCI_OPS(hw)->setup_queue(hw, vq) < 0) {
 		PMD_INIT_LOG(ERR, "setup_queue failed");
 		return -EINVAL;
 	}
@@ -893,6 +895,7 @@ virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
 		for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
 			xstats[count].value = *(uint64_t *)(((char *)rxvq) +
 				rte_virtio_rxq_stat_strings[t].offset);
+			xstats[count].id = count;
 			count++;
 		}
 	}
@@ -908,6 +911,7 @@ virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
 		for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
 			xstats[count].value = *(uint64_t *)(((char *)txvq) +
 				rte_virtio_txq_stat_strings[t].offset);
+			xstats[count].id = count;
 			count++;
 		}
 	}
@@ -1114,7 +1118,7 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features)
 		req_features);
 
 	/* Read device(host) feature bits */
-	host_features = hw->vtpci_ops->get_features(hw);
+	host_features = VTPCI_OPS(hw)->get_features(hw);
 	PMD_INIT_LOG(DEBUG, "host_features before negotiate = %" PRIx64,
 		host_features);
 
@@ -1204,14 +1208,14 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	if (virtio_negotiate_features(hw, req_features) < 0)
 		return -1;
 
+	rte_eth_copy_pci_info(eth_dev, pci_dev);
+
 	/* If host does not support status then disable LSC */
 	if (!vtpci_with_feature(hw, VIRTIO_NET_F_STATUS))
 		eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
 	else
 		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
 
-	rte_eth_copy_pci_info(eth_dev, pci_dev);
-
 	rx_func_get(eth_dev);
 
 	/* Setting up rx_header size for the device */
@@ -1287,6 +1291,52 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 }
 
 /*
+ * Remap the PCI device again (IO port map for legacy device and
+ * memory map for modern device), so that the secondary process
+ * could have the PCI initiated correctly.
+ */
+static int
+virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw)
+{
+	if (hw->modern) {
+		/*
+		 * We don't have to re-parse the PCI config space, since
+		 * rte_eal_pci_map_device() makes sure the mapped address
+		 * in secondary process would equal to the one mapped in
+		 * the primary process: error will be returned if that
+		 * requirement is not met.
+		 *
+		 * That said, we could simply reuse all cap pointers
+		 * (such as dev_cfg, common_cfg, etc.) parsed from the
+		 * primary process, which is stored in shared memory.
+		 */
+		if (rte_eal_pci_map_device(pci_dev)) {
+			PMD_INIT_LOG(DEBUG, "failed to map pci device!");
+			return -1;
+		}
+	} else {
+		if (rte_eal_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void
+virtio_set_vtpci_ops(struct virtio_hw *hw)
+{
+#ifdef RTE_VIRTIO_USER
+	if (hw->virtio_user_dev)
+		VTPCI_OPS(hw) = &virtio_user_ops;
+	else
+#endif
+	if (hw->modern)
+		VTPCI_OPS(hw) = &modern_ops;
+	else
+		VTPCI_OPS(hw) = &legacy_ops;
+}
+
+/*
  * This function is based on probe() function in virtio_pci.c
  * It returns 0 on success.
  */
@@ -1304,7 +1354,19 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	eth_dev->tx_pkt_burst = &virtio_xmit_pkts;
 
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
-		rx_func_get(eth_dev);
+		if (!hw->virtio_user_dev) {
+			ret = virtio_remap_pci(eth_dev->pci_dev, hw);
+			if (ret)
+				return ret;
+		}
+
+		virtio_set_vtpci_ops(hw);
+		if (hw->use_simple_rxtx) {
+			eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple;
+			eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
+		} else {
+			rx_func_get(eth_dev);
+		}
 		return 0;
 	}
 
@@ -1318,6 +1380,7 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
 	}
 
 	pci_dev = eth_dev->pci_dev;
+	hw->port_id = eth_dev->data->port_id;
 
 	if (pci_dev) {
 		ret = vtpci_init(pci_dev, hw, &dev_flags);
diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
index 27d9a190..4feccf93 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -70,6 +70,11 @@
 	 1ULL << VIRTIO_F_VERSION_1       |	\
 	 1ULL << VIRTIO_F_IOMMU_PLATFORM)
 
+#define VIRTIO_PMD_SUPPORTED_GUEST_FEATURES	\
+	(VIRTIO_PMD_DEFAULT_GUEST_FEATURES |	\
+	 1u << VIRTIO_NET_F_GUEST_CSUM	   |	\
+	 1u << VIRTIO_NET_F_GUEST_TSO4     |	\
+	 1u << VIRTIO_NET_F_GUEST_TSO6)
 /*
  * CQ function prototype
  */
diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c
index 9b47165d..8d5355c7 100644
--- a/drivers/net/virtio/virtio_pci.c
+++ b/drivers/net/virtio/virtio_pci.c
@@ -92,17 +92,17 @@ legacy_read_dev_config(struct virtio_hw *hw, size_t offset,
 	while (length > 0) {
 		if (length >= 4) {
 			size = 4;
-			rte_eal_pci_ioport_read(&hw->io, dst, size,
+			rte_eal_pci_ioport_read(VTPCI_IO(hw), dst, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 			*(uint32_t *)dst = rte_be_to_cpu_32(*(uint32_t *)dst);
 		} else if (length >= 2) {
 			size = 2;
-			rte_eal_pci_ioport_read(&hw->io, dst, size,
+			rte_eal_pci_ioport_read(VTPCI_IO(hw), dst, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 			*(uint16_t *)dst = rte_be_to_cpu_16(*(uint16_t *)dst);
 		} else {
 			size = 1;
-			rte_eal_pci_ioport_read(&hw->io, dst, size,
+			rte_eal_pci_ioport_read(VTPCI_IO(hw), dst, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 		}
 
@@ -111,7 +111,7 @@ legacy_read_dev_config(struct virtio_hw *hw, size_t offset,
 		length -= size;
 	}
 #else
-	rte_eal_pci_ioport_read(&hw->io, dst, length,
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), dst, length,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 #endif
 }
@@ -131,16 +131,16 @@ legacy_write_dev_config(struct virtio_hw *hw, size_t offset,
 		if (length >= 4) {
 			size = 4;
 			tmp.u32 = rte_cpu_to_be_32(*(const uint32_t *)src);
-			rte_eal_pci_ioport_write(&hw->io, &tmp.u32, size,
+			rte_eal_pci_ioport_write(VTPCI_IO(hw), &tmp.u32, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 		} else if (length >= 2) {
 			size = 2;
 			tmp.u16 = rte_cpu_to_be_16(*(const uint16_t *)src);
-			rte_eal_pci_ioport_write(&hw->io, &tmp.u16, size,
+			rte_eal_pci_ioport_write(VTPCI_IO(hw), &tmp.u16, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 		} else {
 			size = 1;
-			rte_eal_pci_ioport_write(&hw->io, src, size,
+			rte_eal_pci_ioport_write(VTPCI_IO(hw), src, size,
 				VIRTIO_PCI_CONFIG(hw) + offset);
 		}
 
@@ -149,7 +149,7 @@ legacy_write_dev_config(struct virtio_hw *hw, size_t offset,
 		length -= size;
 	}
 #else
-	rte_eal_pci_ioport_write(&hw->io, src, length,
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), src, length,
 				 VIRTIO_PCI_CONFIG(hw) + offset);
 #endif
 }
@@ -159,7 +159,8 @@ legacy_get_features(struct virtio_hw *hw)
 {
 	uint32_t dst;
 
-	rte_eal_pci_ioport_read(&hw->io, &dst, 4, VIRTIO_PCI_HOST_FEATURES);
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), &dst, 4,
+				VIRTIO_PCI_HOST_FEATURES);
 	return dst;
 }
 
@@ -171,7 +172,7 @@ legacy_set_features(struct virtio_hw *hw, uint64_t features)
 			"only 32 bit features are allowed for legacy virtio!");
 		return;
 	}
-	rte_eal_pci_ioport_write(&hw->io, &features, 4,
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &features, 4,
 				 VIRTIO_PCI_GUEST_FEATURES);
 }
 
@@ -180,14 +181,14 @@ legacy_get_status(struct virtio_hw *hw)
 {
 	uint8_t dst;
 
-	rte_eal_pci_ioport_read(&hw->io, &dst, 1, VIRTIO_PCI_STATUS);
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), &dst, 1, VIRTIO_PCI_STATUS);
 	return dst;
 }
 
 static void
 legacy_set_status(struct virtio_hw *hw, uint8_t status)
 {
-	rte_eal_pci_ioport_write(&hw->io, &status, 1, VIRTIO_PCI_STATUS);
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &status, 1, VIRTIO_PCI_STATUS);
 }
 
 static void
@@ -201,7 +202,7 @@ legacy_get_isr(struct virtio_hw *hw)
 {
 	uint8_t dst;
 
-	rte_eal_pci_ioport_read(&hw->io, &dst, 1, VIRTIO_PCI_ISR);
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), &dst, 1, VIRTIO_PCI_ISR);
 	return dst;
 }
 
@@ -211,8 +212,10 @@ legacy_set_config_irq(struct virtio_hw *hw, uint16_t vec)
 {
 	uint16_t dst;
 
-	rte_eal_pci_ioport_write(&hw->io, &vec, 2, VIRTIO_MSI_CONFIG_VECTOR);
-	rte_eal_pci_ioport_read(&hw->io, &dst, 2, VIRTIO_MSI_CONFIG_VECTOR);
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &vec, 2,
+				 VIRTIO_MSI_CONFIG_VECTOR);
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), &dst, 2,
+				VIRTIO_MSI_CONFIG_VECTOR);
 	return dst;
 }
 
@@ -221,8 +224,9 @@ legacy_get_queue_num(struct virtio_hw *hw, uint16_t queue_id)
 {
 	uint16_t dst;
 
-	rte_eal_pci_ioport_write(&hw->io, &queue_id, 2, VIRTIO_PCI_QUEUE_SEL);
-	rte_eal_pci_ioport_read(&hw->io, &dst, 2, VIRTIO_PCI_QUEUE_NUM);
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &queue_id, 2,
+				 VIRTIO_PCI_QUEUE_SEL);
+	rte_eal_pci_ioport_read(VTPCI_IO(hw), &dst, 2, VIRTIO_PCI_QUEUE_NUM);
 	return dst;
 }
 
@@ -234,10 +238,10 @@ legacy_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
 	if (!check_vq_phys_addr_ok(vq))
 		return -1;
 
-	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
 			 VIRTIO_PCI_QUEUE_SEL);
 	src = vq->vq_ring_mem >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
-	rte_eal_pci_ioport_write(&hw->io, &src, 4, VIRTIO_PCI_QUEUE_PFN);
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &src, 4, VIRTIO_PCI_QUEUE_PFN);
 
 	return 0;
 }
@@ -247,15 +251,15 @@ legacy_del_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
 	uint32_t src = 0;
 
-	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
 			 VIRTIO_PCI_QUEUE_SEL);
-	rte_eal_pci_ioport_write(&hw->io, &src, 4, VIRTIO_PCI_QUEUE_PFN);
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &src, 4, VIRTIO_PCI_QUEUE_PFN);
 }
 
 static void
 legacy_notify_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
-	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+	rte_eal_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
 			 VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
@@ -289,7 +293,7 @@ static int
 legacy_virtio_resource_init(struct rte_pci_device *pci_dev,
 			    struct virtio_hw *hw, uint32_t *dev_flags)
 {
-	if (rte_eal_pci_ioport_map(pci_dev, 0, &hw->io) < 0)
+	if (rte_eal_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0)
 		return -1;
 
 	if (pci_dev->intr_handle.type != RTE_INTR_HANDLE_UNKNOWN)
@@ -300,7 +304,7 @@ legacy_virtio_resource_init(struct rte_pci_device *pci_dev,
 	return 0;
 }
 
-static const struct virtio_pci_ops legacy_ops = {
+const struct virtio_pci_ops legacy_ops = {
 	.read_dev_cfg	= legacy_read_dev_config,
 	.write_dev_cfg	= legacy_write_dev_config,
 	.reset		= legacy_reset,
@@ -516,7 +520,7 @@ modern_notify_queue(struct virtio_hw *hw __rte_unused, struct virtqueue *vq)
 	io_write16(1, vq->notify_addr);
 }
 
-static const struct virtio_pci_ops modern_ops = {
+const struct virtio_pci_ops modern_ops = {
 	.read_dev_cfg	= modern_read_dev_config,
 	.write_dev_cfg	= modern_write_dev_config,
 	.reset		= modern_reset,
@@ -537,14 +541,14 @@ void
 vtpci_read_dev_config(struct virtio_hw *hw, size_t offset,
 		      void *dst, int length)
 {
-	hw->vtpci_ops->read_dev_cfg(hw, offset, dst, length);
+	VTPCI_OPS(hw)->read_dev_cfg(hw, offset, dst, length);
 }
 
 void
 vtpci_write_dev_config(struct virtio_hw *hw, size_t offset,
 		       const void *src, int length)
 {
-	hw->vtpci_ops->write_dev_cfg(hw, offset, src, length);
+	VTPCI_OPS(hw)->write_dev_cfg(hw, offset, src, length);
 }
 
 uint64_t
@@ -557,7 +561,7 @@ vtpci_negotiate_features(struct virtio_hw *hw, uint64_t host_features)
 	 * host all support.
 	 */
 	features = host_features & hw->guest_features;
-	hw->vtpci_ops->set_features(hw, features);
+	VTPCI_OPS(hw)->set_features(hw, features);
 
 	return features;
 }
@@ -565,9 +569,9 @@ vtpci_negotiate_features(struct virtio_hw *hw, uint64_t host_features)
 void
 vtpci_reset(struct virtio_hw *hw)
 {
-	hw->vtpci_ops->set_status(hw, VIRTIO_CONFIG_STATUS_RESET);
+	VTPCI_OPS(hw)->set_status(hw, VIRTIO_CONFIG_STATUS_RESET);
 	/* flush status write */
-	hw->vtpci_ops->get_status(hw);
+	VTPCI_OPS(hw)->get_status(hw);
 }
 
 void
@@ -580,21 +584,21 @@ void
 vtpci_set_status(struct virtio_hw *hw, uint8_t status)
 {
 	if (status != VIRTIO_CONFIG_STATUS_RESET)
-		status |= hw->vtpci_ops->get_status(hw);
+		status |= VTPCI_OPS(hw)->get_status(hw);
 
-	hw->vtpci_ops->set_status(hw, status);
+	VTPCI_OPS(hw)->set_status(hw, status);
 }
 
 uint8_t
 vtpci_get_status(struct virtio_hw *hw)
 {
-	return hw->vtpci_ops->get_status(hw);
+	return VTPCI_OPS(hw)->get_status(hw);
 }
 
 uint8_t
 vtpci_isr(struct virtio_hw *hw)
 {
-	return hw->vtpci_ops->get_isr(hw);
+	return VTPCI_OPS(hw)->get_isr(hw);
 }
 
 
@@ -602,7 +606,7 @@ vtpci_isr(struct virtio_hw *hw)
 uint16_t
 vtpci_irq_config(struct virtio_hw *hw, uint16_t vec)
 {
-	return hw->vtpci_ops->set_config_irq(hw, vec);
+	return VTPCI_OPS(hw)->set_config_irq(hw, vec);
 }
 
 static void *
@@ -736,8 +740,8 @@ vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw,
 	 */
 	if (virtio_read_caps(dev, hw) == 0) {
 		PMD_INIT_LOG(INFO, "modern virtio pci detected.");
-		hw->vtpci_ops = &modern_ops;
-		hw->modern    = 1;
+		virtio_hw_internal[hw->port_id].vtpci_ops = &modern_ops;
+		hw->modern = 1;
 		*dev_flags |= RTE_ETH_DEV_INTR_LSC;
 		return 0;
 	}
@@ -755,7 +759,7 @@ vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw,
 		return -1;
 	}
 
-	hw->vtpci_ops = &legacy_ops;
+	virtio_hw_internal[hw->port_id].vtpci_ops = &legacy_ops;
 	hw->use_msix = legacy_virtio_has_msix(&dev->addr);
 	hw->modern   = 0;
 
diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h
index de271bfe..511a1c87 100644
--- a/drivers/net/virtio/virtio_pci.h
+++ b/drivers/net/virtio/virtio_pci.h
@@ -245,7 +245,6 @@ struct virtio_net_config;
 
 struct virtio_hw {
 	struct virtnet_ctl *cvq;
-	struct rte_pci_ioport io;
 	uint64_t    req_guest_features;
 	uint64_t    guest_features;
 	uint32_t    max_queue_pairs;
@@ -254,6 +253,7 @@ struct virtio_hw {
 	uint8_t	    use_msix;
 	uint8_t     modern;
 	uint8_t     use_simple_rxtx;
+	uint8_t     port_id;
 	uint8_t     mac_addr[ETHER_ADDR_LEN];
 	uint32_t    notify_off_multiplier;
 	uint8_t     *isr;
@@ -261,12 +261,28 @@ struct virtio_hw {
 	struct rte_pci_device *dev;
 	struct virtio_pci_common_cfg *common_cfg;
 	struct virtio_net_config *dev_cfg;
-	const struct virtio_pci_ops *vtpci_ops;
 	void	    *virtio_user_dev;
 
 	struct virtqueue **vqs;
 };
 
+
+/*
+ * While virtio_hw is stored in shared memory, this structure stores
+ * some infos that may vary in the multiple process model locally.
+ * For example, the vtpci_ops pointer.
+ */
+struct virtio_hw_internal {
+	const struct virtio_pci_ops *vtpci_ops;
+	struct rte_pci_ioport io;
+};
+
+#define VTPCI_OPS(hw)	(virtio_hw_internal[(hw)->port_id].vtpci_ops)
+#define VTPCI_IO(hw)	(&virtio_hw_internal[(hw)->port_id].io)
+
+extern struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
+
+
 /*
  * This structure is just a reference to read
  * net device specific config space; it just a chodu structure
@@ -317,4 +333,8 @@ uint8_t vtpci_isr(struct virtio_hw *);
 
 uint16_t vtpci_irq_config(struct virtio_hw *, uint16_t);
 
+extern const struct virtio_pci_ops legacy_ops;
+extern const struct virtio_pci_ops modern_ops;
+extern const struct virtio_pci_ops virtio_user_ops;
+
 #endif /* _VIRTIO_PCI_H_ */
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index 22d97a4e..a33ef1a8 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -258,6 +258,12 @@ tx_offload_enabled(struct virtio_hw *hw)
 		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 {	\
+	if ((var) != (val))			\
+		(var) = (val);			\
+} while (0)
+
 static inline void
 virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 		       uint16_t needed, int use_indirect, int can_push)
@@ -286,8 +292,14 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 		hdr = (struct virtio_net_hdr *)
 			rte_pktmbuf_prepend(cookie, head_size);
 		/* if offload disabled, it is not zeroed below, do it now */
-		if (offload == 0)
-			memset(hdr, 0, head_size);
+		if (offload == 0) {
+			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);
+		}
 	} else if (use_indirect) {
 		/* setup tx ring slot to point to indirect
 		 * descriptor list stored in reserved region.
@@ -337,9 +349,9 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 			break;
 
 		default:
-			hdr->csum_start = 0;
-			hdr->csum_offset = 0;
-			hdr->flags = 0;
+			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
 			break;
 		}
 
@@ -355,9 +367,9 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 				cookie->l3_len +
 				cookie->l4_len;
 		} else {
-			hdr->gso_type = 0;
-			hdr->gso_size = 0;
-			hdr->hdr_len = 0;
+			ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0);
+			ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0);
 		}
 	}
 
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
index e239e0eb..a38398b8 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -148,12 +148,13 @@ virtio_user_start_device(struct virtio_user_dev *dev)
 
 	/* Step 1: set features
 	 * Make sure VHOST_USER_F_PROTOCOL_FEATURES is added if mq is enabled,
-	 * and VIRTIO_NET_F_MAC is stripped.
+	 * VIRTIO_NET_F_MAC and VIRTIO_NET_F_CTRL_VQ is stripped.
 	 */
 	features = dev->features;
 	if (dev->max_queue_pairs > 1)
 		features |= VHOST_USER_MQ;
 	features &= ~(1ull << VIRTIO_NET_F_MAC);
+	features &= ~(1ull << VIRTIO_NET_F_CTRL_VQ);
 	ret = vhost_user_sock(dev->vhostfd, VHOST_USER_SET_FEATURES, &features);
 	if (ret < 0)
 		goto error;
@@ -181,7 +182,17 @@ error:
 
 int virtio_user_stop_device(struct virtio_user_dev *dev)
 {
-	return vhost_user_sock(dev->vhostfd, VHOST_USER_RESET_OWNER, NULL);
+	uint32_t i;
+
+	for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
+		close(dev->callfds[i]);
+		close(dev->kickfds[i]);
+	}
+
+	for (i = 0; i < dev->max_queue_pairs; ++i)
+		vhost_user_enable_queue_pair(dev->vhostfd, i, 0);
+
+	return 0;
 }
 
 static inline void
@@ -209,6 +220,8 @@ int
 virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 		     int cq, int queue_size, const char *mac)
 {
+	uint32_t i;
+
 	snprintf(dev->path, PATH_MAX, "%s", path);
 	dev->max_queue_pairs = queues;
 	dev->queue_pairs = 1; /* mq disabled by default */
@@ -217,6 +230,11 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 	parse_mac(dev, mac);
 	dev->vhostfd = -1;
 
+	for (i = 0; i < VIRTIO_MAX_VIRTQUEUES * 2 + 1; ++i) {
+		dev->kickfds[i] = -1;
+		dev->callfds[i] = -1;
+	}
+
 	dev->vhostfd = vhost_user_setup(dev->path);
 	if (dev->vhostfd < 0) {
 		PMD_INIT_LOG(ERR, "backend set up fails");
@@ -228,29 +246,26 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 	}
 
 	if (vhost_user_sock(dev->vhostfd, VHOST_USER_GET_FEATURES,
-			    &dev->features) < 0) {
+			    &dev->device_features) < 0) {
 		PMD_INIT_LOG(ERR, "get_features failed: %s", strerror(errno));
 		return -1;
 	}
 	if (dev->mac_specified)
-		dev->features |= (1ull << VIRTIO_NET_F_MAC);
+		dev->device_features |= (1ull << VIRTIO_NET_F_MAC);
 
-	if (!cq) {
-		dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_VQ);
-		/* Also disable features depends on VIRTIO_NET_F_CTRL_VQ */
-		dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_RX);
-		dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_VLAN);
-		dev->features &= ~(1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
-		dev->features &= ~(1ull << VIRTIO_NET_F_MQ);
-		dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
-	} else {
-		/* vhost user backend does not need to know ctrl-q, so
-		 * actually we need add this bit into features. However,
-		 * DPDK vhost-user does send features with this bit, so we
-		 * check it instead of OR it for now.
+	if (cq) {
+		/* device does not really need to know anything about CQ,
+		 * so if necessary, we just claim to support CQ
 		 */
-		if (!(dev->features & (1ull << VIRTIO_NET_F_CTRL_VQ)))
-			PMD_INIT_LOG(INFO, "vhost does not support ctrl-q");
+		dev->device_features |= (1ull << VIRTIO_NET_F_CTRL_VQ);
+	} else {
+		dev->device_features &= ~(1ull << VIRTIO_NET_F_CTRL_VQ);
+		/* Also disable features depends on VIRTIO_NET_F_CTRL_VQ */
+		dev->device_features &= ~(1ull << VIRTIO_NET_F_CTRL_RX);
+		dev->device_features &= ~(1ull << VIRTIO_NET_F_CTRL_VLAN);
+		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);
 	}
 
 	if (dev->max_queue_pairs > 1) {
@@ -266,13 +281,6 @@ virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
 void
 virtio_user_dev_uninit(struct virtio_user_dev *dev)
 {
-	uint32_t i;
-
-	for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
-		close(dev->callfds[i]);
-		close(dev->kickfds[i]);
-	}
-
 	close(dev->vhostfd);
 }
 
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.h b/drivers/net/virtio/virtio_user/virtio_user_dev.h
index 33690b5c..28fc788e 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.h
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.h
@@ -46,7 +46,10 @@ struct virtio_user_dev {
 	uint32_t	max_queue_pairs;
 	uint32_t	queue_pairs;
 	uint32_t	queue_size;
-	uint64_t	features;
+	uint64_t	features; /* the negotiated features with driver,
+				   * and will be sync with device
+				   */
+	uint64_t	device_features; /* supported features by device */
 	uint8_t		status;
 	uint8_t		mac_addr[ETHER_ADDR_LEN];
 	char		path[PATH_MAX];
diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
index 406beeac..013600e4 100644
--- a/drivers/net/virtio/virtio_user_ethdev.c
+++ b/drivers/net/virtio/virtio_user_ethdev.c
@@ -87,21 +87,24 @@ virtio_user_write_dev_config(struct virtio_hw *hw, size_t offset,
 }
 
 static void
-virtio_user_set_status(struct virtio_hw *hw, uint8_t status)
+virtio_user_reset(struct virtio_hw *hw)
 {
 	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	if (status & VIRTIO_CONFIG_STATUS_DRIVER_OK)
-		virtio_user_start_device(dev);
-	dev->status = status;
+	if (dev->status & VIRTIO_CONFIG_STATUS_DRIVER_OK)
+		virtio_user_stop_device(dev);
 }
 
 static void
-virtio_user_reset(struct virtio_hw *hw)
+virtio_user_set_status(struct virtio_hw *hw, uint8_t status)
 {
 	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	virtio_user_stop_device(dev);
+	if (status & VIRTIO_CONFIG_STATUS_DRIVER_OK)
+		virtio_user_start_device(dev);
+	else if (status == VIRTIO_CONFIG_STATUS_RESET)
+		virtio_user_reset(hw);
+	dev->status = status;
 }
 
 static uint8_t
@@ -117,7 +120,8 @@ virtio_user_get_features(struct virtio_hw *hw)
 {
 	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	return dev->features;
+	/* unmask feature bits defined in vhost user protocol */
+	return dev->device_features & VIRTIO_PMD_SUPPORTED_GUEST_FEATURES;
 }
 
 static void
@@ -125,7 +129,7 @@ virtio_user_set_features(struct virtio_hw *hw, uint64_t features)
 {
 	struct virtio_user_dev *dev = virtio_user_get_dev(hw);
 
-	dev->features = features;
+	dev->features = features & dev->device_features;
 }
 
 static uint8_t
@@ -212,7 +216,7 @@ virtio_user_notify_queue(struct virtio_hw *hw, struct virtqueue *vq)
 			    strerror(errno));
 }
 
-static const struct virtio_pci_ops virtio_user_ops = {
+const struct virtio_pci_ops virtio_user_ops = {
 	.read_dev_cfg	= virtio_user_read_dev_config,
 	.write_dev_cfg	= virtio_user_write_dev_config,
 	.reset		= virtio_user_reset,
@@ -301,7 +305,8 @@ virtio_user_eth_dev_alloc(const char *name)
 		return NULL;
 	}
 
-	hw->vtpci_ops = &virtio_user_ops;
+	hw->port_id = data->port_id;
+	virtio_hw_internal[hw->port_id].vtpci_ops = &virtio_user_ops;
 	hw->use_msix = 0;
 	hw->modern   = 0;
 	hw->use_simple_rxtx = 0;
diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h
index f0bb0899..b1070e05 100644
--- a/drivers/net/virtio/virtqueue.h
+++ b/drivers/net/virtio/virtqueue.h
@@ -330,7 +330,7 @@ virtqueue_notify(struct virtqueue *vq)
 	 * For virtio on IA, the notificaiton is through io port operation
 	 * which is a serialization instruction itself.
 	 */
-	vq->hw->vtpci_ops->notify_queue(vq->hw, vq);
+	VTPCI_OPS(vq->hw)->notify_queue(vq->hw, vq);
 }
 
 #ifdef RTE_LIBRTE_VIRTIO_DEBUG_DUMP