[net-next PATCH v2 0/6] i40e: Add VF Port representator support for SR-IOV VFs

@@ -215,6 +215,7 @@ config I40E
 	tristate "Intel(R) Ethernet Controller XL710 Family support"
 	imply PTP_1588_CLOCK
 	depends on PCI
+	depends on MAY_USE_DEVLINK
 	---help---
 	  This driver supports Intel(R) Ethernet Controller XL710 Family of
 	  devices.  For more information on how to identify your adapter, go

@@ -54,6 +54,8 @@
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/devlink.h>
+
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #ifdef I40E_FCOE

@@ -448,6 +450,7 @@ struct i40e_pf {
 	u32 ioremap_len;
 	u32 fd_inv;
 	u16 phy_led_val;
+	enum devlink_eswitch_mode eswitch_mode;
 };
 
 /**

@@ -10910,6 +10910,57 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 }
 
 /**
+ * i40e_devlink_eswitch_mode_get
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode pointer
+ *
+ * Returns the switch mode of the associated PF in the @mode pointer.
+ */
+static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	*mode = pf->eswitch_mode;
+
+	return 0;
+}
+
+/**
+ * i40e_devlink_eswitch_mode_set
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode
+ *
+ * Set the switch mode of the associated PF.
+ * Returns 0 on success and -EOPNOTSUPP on error.
+ */
+static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+	int err = 0;
+
+	if (mode == pf->eswitch_mode)
+		goto done;
+
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+		pf->eswitch_mode = mode;
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+done:
+	return err;
+}
+
+static const struct devlink_ops i40e_devlink_ops = {
+	.eswitch_mode_get = i40e_devlink_eswitch_mode_get,
+	.eswitch_mode_set = i40e_devlink_eswitch_mode_set,
+};
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl

@@ -10926,6 +10977,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct i40e_pf *pf;
 	struct i40e_hw *hw;
 	static u16 pfs_found;
+	struct devlink *devlink;
 	u16 wol_nvm_bits;
 	u16 link_status;
 	int err;

@@ -10959,20 +11011,28 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_enable_pcie_error_reporting(pdev);
 	pci_set_master(pdev);
 
+	devlink = devlink_alloc(&i40e_devlink_ops, sizeof(*pf));
+	if (!devlink) {
+		dev_err(&pdev->dev, "devlink_alloc failed\n");
+		err = -ENOMEM;
+		goto err_devlink_alloc;
+	}
+
 	/* Now that we have a PCI connection, we need to do the
 	 * low level device setup.  This is primarily setting up
 	 * the Admin Queue structures and then querying for the
 	 * device's current profile information.
 	 */
-	pf = kzalloc(sizeof(*pf), GFP_KERNEL);
-	if (!pf) {
-		err = -ENOMEM;
-		goto err_pf_alloc;
-	}
+	pf = devlink_priv(devlink);
 	pf->next_vsi = 0;
 	pf->pdev = pdev;
 	set_bit(__I40E_DOWN, &pf->state);
 
+	pf->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	err = devlink_register(devlink, &pdev->dev);
+	if (err)
+		goto err_devlink_register;
+
 	hw = &pf->hw;
 	hw->back = pf;
 

@@ -11445,8 +11505,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_pf_reset:
 	iounmap(hw->hw_addr);
 err_ioremap:
-	kfree(pf);
-err_pf_alloc:
+	devlink_unregister(devlink);
+err_devlink_register:
+	devlink_free(devlink);
+err_devlink_alloc:
 	pci_disable_pcie_error_reporting(pdev);
 	pci_release_mem_regions(pdev);
 err_pci_reg:

@@ -11468,6 +11530,7 @@ static void i40e_remove(struct pci_dev *pdev)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
+	struct devlink *devlink = priv_to_devlink(pf);
 	i40e_status ret_code;
 	int i;
 

@@ -11554,7 +11617,8 @@ static void i40e_remove(struct pci_dev *pdev)
 	kfree(pf->vsi);
 
 	iounmap(hw->hw_addr);
-	kfree(pf);
+	devlink_unregister(devlink);
+	devlink_free(devlink);
 	pci_release_mem_regions(pdev);
 
 	pci_disable_pcie_error_reporting(pdev);

@@ -10938,15 +10938,34 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 {
 	struct i40e_pf *pf = devlink_priv(devlink);
-	int err = 0;
+	struct i40e_vf *vf;
+	int i, j, err = 0;
 
 	if (mode == pf->eswitch_mode)
 		goto done;
 
 	switch (mode) {
 	case DEVLINK_ESWITCH_MODE_LEGACY:
+		for (i = 0; i < pf->num_alloc_vfs; i++) {
+			vf = &(pf->vf[i]);
+			i40e_free_vfpr_netdev(vf);
+		}
 		pf->eswitch_mode = mode;
 		break;
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		for (i = 0; i < pf->num_alloc_vfs; i++) {
+			vf = &(pf->vf[i]);
+			err = i40e_alloc_vfpr_netdev(vf, i);
+			if (err) {
+				for (j = 0; j < i; j++) {
+					vf = &(pf->vf[j]);
+					i40e_free_vfpr_netdev(vf);
+				}
+				goto done;
+			}
+		}
+                pf->eswitch_mode = mode;
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;

@@ -697,12 +697,16 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 					 "Could not add MAC filter %pM for VF %d\n",
 					vf->default_lan_addr.addr, vf->vf_id);
 		}
-		eth_broadcast_addr(broadcast);
-		f = i40e_add_filter(vsi, broadcast,
-				    vf->port_vlan_id ? vf->port_vlan_id : -1);
-		if (!f)
-			dev_info(&pf->pdev->dev,
-				 "Could not allocate VF broadcast filter\n");
+
+		/* Add VF broadcast filter only in 'legacy' mode */
+		if (vsi->back->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) {
+			eth_broadcast_addr(broadcast);
+			f = i40e_add_filter(vsi, broadcast,
+					    vf->port_vlan_id ? vf->port_vlan_id : -1);
+			if (!f)
+				dev_info(&pf->pdev->dev,
+					 "Could not allocate VF broadcast filter\n");
+		}
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
 		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
 				  (u32)hena);

@@ -1020,6 +1024,136 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 }
 
 /**
+ * i40e_vfpr_netdev_open
+ * @dev: network interface device structure
+ *
+ * Called when vfpr netdevice is brought up.
+ **/
+static int i40e_vfpr_netdev_open(struct net_device *dev)
+{
+	return 0;
+}
+
+/**
+ * i40e_vfpr_netdev_stop
+ * @dev: network interface device structure
+ *
+ * Called when vfpr netdevice is brought down.
+ **/
+static int i40e_vfpr_netdev_stop(struct net_device *dev)
+{
+	return 0;
+}
+
+static const struct net_device_ops i40e_vfpr_netdev_ops = {
+	.ndo_open       	= i40e_vfpr_netdev_open,
+	.ndo_stop       	= i40e_vfpr_netdev_stop,
+};
+
+/**
+ * i40e_update_vf_broadcast_filter
+ * @vf: pointer to the VF structure
+ * @enable: boolean flag indicating add/delete
+ *
+ * add/delete VFs broadcast filter
+ **/
+void i40e_update_vf_broadcast_filter(struct i40e_vf *vf, bool enable)
+{
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
+	u8 broadcast[ETH_ALEN];
+	int err;
+
+	spin_lock_bh(&vsi->mac_filter_hash_lock);
+	eth_broadcast_addr(broadcast);
+	if (enable)
+		i40e_add_filter(vsi, broadcast, vf->port_vlan_id ? vf->port_vlan_id : -1);
+	else
+		i40e_del_filter(vsi, broadcast, vf->port_vlan_id ? vf->port_vlan_id : -1);
+	spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+	/* update broadcast filter */
+	err = i40e_sync_vsi_filters(vsi);
+	if (err)
+		dev_err(&pf->pdev->dev, "Unable to program bcast filter\n");
+}
+
+/**
+ * i40e_alloc_vfpr_netdev
+ * @vf: pointer to the VF structure
+ * @vf_num: VF number
+ *
+ * Create VF Port representor netdev
+ **/
+int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
+{
+	struct net_device *vfpr_netdev;
+	char netdev_name[IFNAMSIZ];
+	struct i40e_vfpr_netdev_priv *priv;
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	int err;
+
+	snprintf(netdev_name, IFNAMSIZ, "%s-vf%d", vsi->netdev->name, vf_num);
+	vfpr_netdev = alloc_netdev(sizeof(struct i40e_vfpr_netdev_priv),
+				   netdev_name, NET_NAME_UNKNOWN, ether_setup);
+	if (!vfpr_netdev) {
+		dev_err(&pf->pdev->dev, "alloc_netdev failed for vf:%d\n",
+			vf_num);
+		return -ENOMEM;
+	}
+
+	pf->vf[vf_num].vfpr_netdev = vfpr_netdev;
+
+	priv = netdev_priv(vfpr_netdev);
+	priv->vf = &(pf->vf[vf_num]);
+
+	vfpr_netdev->netdev_ops = &i40e_vfpr_netdev_ops;
+
+	netif_carrier_off(vfpr_netdev);
+	netif_tx_disable(vfpr_netdev);
+
+	err = register_netdev(vfpr_netdev);
+	if (err) {
+		dev_err(&pf->pdev->dev, "register_netdev failed for vf: %s\n",
+			vf->vfpr_netdev->name);
+		free_netdev(vfpr_netdev);
+		return err;
+	}
+
+	dev_info(&pf->pdev->dev, "VF Port representor(%s) created for VF %d\n",
+		 vf->vfpr_netdev->name, vf_num);
+
+	/* Delete broadcast filter for VF */
+	i40e_update_vf_broadcast_filter(vf, false);
+
+	return 0;
+}
+
+/**
+ * i40e_free_vfpr_netdev
+ * @vf: pointer to the VF structure
+ *
+ * Free VF Port representor netdev
+ **/
+void i40e_free_vfpr_netdev(struct i40e_vf *vf)
+{
+	struct i40e_pf *pf = vf->pf;
+
+	if (!vf->vfpr_netdev)
+		return;
+
+	dev_info(&pf->pdev->dev, "Freeing VF Port representor(%s)\n",
+		 vf->vfpr_netdev->name);
+
+	unregister_netdev(vf->vfpr_netdev);
+	free_netdev(vf->vfpr_netdev);
+
+	/* Add broadcast filter to VF */
+	i40e_update_vf_broadcast_filter(vf, true);
+}
+
+/**
  * i40e_free_vfs
  * @pf: pointer to the PF structure
  *

@@ -1060,6 +1194,9 @@ void i40e_free_vfs(struct i40e_pf *pf)
 			i40e_free_vf_res(&pf->vf[i]);
 		/* disable qp mappings */
 		i40e_disable_vf_mappings(&pf->vf[i]);
+
+		if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+			i40e_free_vfpr_netdev(&pf->vf[i]);
 	}
 
 	kfree(pf->vf);

@@ -1127,6 +1264,11 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 		/* VF resources get allocated during reset */
 		i40e_reset_vf(&vfs[i], false);
 
+		if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
+			ret = i40e_alloc_vfpr_netdev(&vfs[i], i);
+			if (ret)
+				goto err_alloc;
+		}
 	}
 	pf->num_alloc_vfs = num_alloc_vfs;
 

@@ -72,10 +72,21 @@ enum i40e_vf_capabilities {
 	I40E_VIRTCHNL_VF_CAP_IWARP,
 };
 
+/* VF Port representator netdev private structure */
+struct i40e_vfpr_netdev_priv {
+	struct i40e_vf *vf;
+};
+
 /* VF information structure */
 struct i40e_vf {
 	struct i40e_pf *pf;
 
+	/* VF Port representator netdev that allows control and configuration
+	 * of VFs from the host. Enables returning VF stats, configuring link
+	 * state, mtu, fdb/vlans etc.
+	 */
+	struct net_device *vfpr_netdev;
+
 	/* VF id in the PF space */
 	s16 vf_id;
 	/* all VF vsis connect to the same parent */

@@ -142,4 +153,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable);
 void i40e_vc_notify_link_state(struct i40e_pf *pf);
 void i40e_vc_notify_reset(struct i40e_pf *pf);
 
+int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num);
+void i40e_free_vfpr_netdev(struct i40e_vf *vf);
+
 #endif /* _I40E_VIRTCHNL_PF_H_ */

@@ -1031,6 +1031,13 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
  **/
 static int i40e_vfpr_netdev_open(struct net_device *dev)
 {
+	struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+	struct i40e_vf *vf = priv->vf;
+
+	vf->link_forced = true;
+	vf->link_up = true;
+	i40e_vc_notify_vf_link_state(vf);
+
 	return 0;
 }
 

@@ -1042,6 +1049,13 @@ static int i40e_vfpr_netdev_open(struct net_device *dev)
  **/
 static int i40e_vfpr_netdev_stop(struct net_device *dev)
 {
+	struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+	struct i40e_vf *vf = priv->vf;
+
+	vf->link_forced = true;
+	vf->link_up = false;
+	i40e_vc_notify_vf_link_state(vf);
+
 	return 0;
 }
 

@@ -1127,6 +1141,13 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
 	/* Delete broadcast filter for VF */
 	i40e_update_vf_broadcast_filter(vf, false);
 
+	/* Reset VF link as we are changing the mode to 'switchdev'. VFPR netdev
+	 * needs to be brought up to enable VF link.
+	 */
+	vf->link_forced = true;
+	vf->link_up = false;
+	i40e_vc_notify_vf_link_state(vf);
+
 	return 0;
 }
 

@@ -1151,6 +1172,10 @@ void i40e_free_vfpr_netdev(struct i40e_vf *vf)
 
 	/* Add broadcast filter to VF */
 	i40e_update_vf_broadcast_filter(vf, true);
+
+	/* In legacy mode, VF link is not controlled by VFPR */
+	vf->link_forced = false;
+	i40e_vc_notify_vf_link_state(vf);
 }
 
 /**

@@ -1910,6 +1935,10 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
 		aq_ret = I40E_ERR_TIMEOUT;
+
+	if ((0 == aq_ret) && vf->vfpr_netdev)
+		netif_carrier_on(vf->vfpr_netdev);
+
 error_param:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ENABLE_QUEUES,

@@ -1949,6 +1978,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
 
+	if ((0 == aq_ret) && vf->vfpr_netdev)
+		netif_carrier_off(vf->vfpr_netdev);
+
 error_param:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DISABLE_QUEUES,

@@ -3189,6 +3221,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_virtchnl_pf_event pfe;
+	struct net_device *vfpr_netdev;
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_vf *vf;
 	int abs_vf_id;

@@ -3231,6 +3264,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 		ret = -EINVAL;
 		goto error_out;
 	}
+
+	vfpr_netdev = vf->vfpr_netdev;
+	if (vfpr_netdev) {
+		unsigned int flags = vfpr_netdev->flags;
+
+		if (vf->link_up)
+			dev_change_flags(vfpr_netdev, flags | IFF_UP);
+		else
+			dev_change_flags(vfpr_netdev, flags & ~IFF_UP);
+	}
+
 	/* Notify the VF of its new link state */
 	i40e_aq_send_msg_to_vf(hw, abs_vf_id, I40E_VIRTCHNL_OP_EVENT,
 			       0, (u8 *)&pfe, sizeof(pfe), NULL);

@@ -55,6 +55,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
+#include <net/dst_metadata.h>
 
 #include "i40e_type.h"
 #include "i40e_prototype.h"

@@ -10938,6 +10938,7 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 {
 	struct i40e_pf *pf = devlink_priv(devlink);
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_vf *vf;
 	int i, j, err = 0;
 

@@ -10951,6 +10952,8 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 			i40e_free_vfpr_netdev(vf);
 		}
 		pf->eswitch_mode = mode;
+		vsi->netdev->priv_flags |=
+			(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
 		for (i = 0; i < pf->num_alloc_vfs; i++) {

@@ -10965,6 +10968,7 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 			}
 		}
                 pf->eswitch_mode = mode;
+		netif_keep_dst(vsi->netdev);
 		break;
 	default:
 		err = -EOPNOTSUPP;

@@ -1176,16 +1176,37 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
  * @rx_ring:  rx ring in play
  * @skb: packet to send up
  * @vlan_tag: vlan tag for packet
+ * @lpbk: is it a loopback frame?
  **/
 static void i40e_receive_skb(struct i40e_ring *rx_ring,
-			     struct sk_buff *skb, u16 vlan_tag)
+			     struct sk_buff *skb, u16 vlan_tag, bool lpbk)
 {
 	struct i40e_q_vector *q_vector = rx_ring->q_vector;
+	struct i40e_pf *pf = rx_ring->vsi->back;
+	struct i40e_vf *vf;
+	struct ethhdr *eth;
+	int vf_id;
 
 	if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    (vlan_tag & VLAN_VID_MASK))
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 
+	if ((pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) || !lpbk)
+		goto gro_receive;
+
+	/* If a loopback packet is received from a VF in switchdev mode, pass the
+	 * frame to the corresponding VFPR netdev based on the source MAC in the frame.
+	 */
+	eth = (struct ethhdr *)skb_mac_header(skb);
+	for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
+		vf = &pf->vf[vf_id];
+		if (ether_addr_equal(eth->h_source, vf->default_lan_addr.addr)) {
+			skb->dev = vf->vfpr_netdev;
+			break;
+		}
+	}
+
+gro_receive:
 	napi_gro_receive(&q_vector->napi, skb);
 }
 

@@ -1394,6 +1415,7 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
  * @rx_ptype: the packet type decoded by hardware
+ * @lpbk: is it a loopback frame?
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and

@@ -1402,7 +1424,7 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
 static inline
 void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 			     union i40e_rx_desc *rx_desc, struct sk_buff *skb,
-			     u8 rx_ptype)
+			     u8 rx_ptype, bool *lpbk)
 {
 	u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 	u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>

@@ -1411,6 +1433,9 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 	u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
 		   I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT;
 
+	*lpbk = !!((rx_status & I40E_RXD_QW1_STATUS_LPBK_MASK) >>
+		   I40E_RXD_QW1_STATUS_LPBK_SHIFT);
+
 	if (unlikely(tsynvalid))
 		i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn);
 

@@ -1736,6 +1761,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < budget)) {
 		union i40e_rx_desc *rx_desc;
 		struct sk_buff *skb;
+		bool lpbk;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;

@@ -1794,7 +1820,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 			   I40E_RXD_QW1_PTYPE_SHIFT;
 
 		/* populate checksum, VLAN, and protocol */
-		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype, &lpbk);
 
 #ifdef I40E_FCOE
 		if (unlikely(

@@ -1808,7 +1834,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
-		i40e_receive_skb(rx_ring, skb, vlan_tag);
+		i40e_receive_skb(rx_ring, skb, vlan_tag, lpbk);
 
 		/* update budget accounting */
 		total_rx_packets++;

@@ -2346,6 +2372,27 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 }
 
 /**
+ * i40e_tvsi - set up the target vsi in TX context descriptor
+ * @tx_ring:  ptr to the target vsi
+ * @cd_type_cmd_tso_mss: Quad Word 1
+ *
+ * Returns 0
+ **/
+static int i40e_tvsi(struct i40e_vsi *tvsi, u64 *cd_type_cmd_tso_mss)
+{
+	u64 cd_cmd, cd_tvsi;
+
+	cd_cmd = I40E_TX_CTX_DESC_SWTCH_VSI;
+	cd_tvsi = tvsi->id;
+	cd_tvsi = (cd_tvsi << I40E_TXD_CTX_QW1_VSI_SHIFT) &
+		   I40E_TXD_CTX_QW1_VSI_MASK;
+	*cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
+				 cd_tvsi;
+
+	return 0;
+}
+
+/**
  * i40e_tsyn - set up the tsyn context descriptor
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending

@@ -2887,8 +2934,12 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 					struct i40e_ring *tx_ring)
 {
 	u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT;
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	u32 cd_tunneling = 0, cd_l2tag2 = 0;
 	struct i40e_tx_buffer *first;
+	struct i40e_vsi *t_vsi = NULL;
+	struct i40e_vf *t_vf;
+	struct i40e_pf *pf;
 	u32 td_offset = 0;
 	u32 tx_flags = 0;
 	__be16 protocol;

@@ -2935,7 +2986,22 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(skb, &hdr_len, &cd_type_cmd_tso_mss);
+	/* If skb metadata dst points to a VF id, do a directed transmit to
+	 * that VSI. TSO is mutually exclusive with this option. So TSO is not
+	 * enabled when doing a directed transmit.
+	 */
+	if (md_dst && (md_dst->type == METADATA_HW_PORT_MUX)) {
+		pf = tx_ring->vsi->back;
+		if (md_dst->u.port_info.port_id < pf->num_alloc_vfs) {
+			t_vf = &pf->vf[md_dst->u.port_info.port_id];
+			t_vsi = pf->vsi[t_vf->lan_vsi_idx];
+		}
+	}
+
+	if (t_vsi)
+		tso = i40e_tvsi(t_vsi, &cd_type_cmd_tso_mss);
+	else
+		tso = i40e_tso(skb, &hdr_len, &cd_type_cmd_tso_mss);
 
 	if (tso < 0)
 		goto out_drop;

@@ -2998,3 +3064,19 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 	return i40e_xmit_frame_ring(skb, tx_ring);
 }
+
+netdev_tx_t i40e_vfpr_netdev_start_xmit(struct sk_buff *skb,
+				        struct net_device *dev)
+{
+	struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+	struct i40e_vf *vf = priv->vf;
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+
+	skb_dst_drop(skb);
+	dst_hold(&priv->vfpr_dst->dst);
+	skb_dst_set(skb, &priv->vfpr_dst->dst);
+	skb->dev = vsi->netdev;
+
+	return dev_queue_xmit(skb);
+}

@@ -366,6 +366,7 @@ struct i40e_ring_container {
 
 bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
 netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+netdev_tx_t i40e_vfpr_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev);
 void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring);
 int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring);

@@ -728,6 +728,9 @@ enum i40e_rx_desc_status_bits {
 #define I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT  I40E_RX_DESC_STATUS_TSYNVALID_SHIFT
 #define I40E_RXD_QW1_STATUS_TSYNVALID_MASK \
 				    BIT_ULL(I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT)
+#define I40E_RXD_QW1_STATUS_LPBK_SHIFT  I40E_RX_DESC_STATUS_LPBK_SHIFT
+#define I40E_RXD_QW1_STATUS_LPBK_MASK \
+				BIT_ULL(I40E_RXD_QW1_STATUS_LPBK_SHIFT)
 
 enum i40e_rx_desc_fltstat_values {
 	I40E_RX_DESC_FLTSTAT_NO_DATA	= 0,

@@ -1062,6 +1062,7 @@ static int i40e_vfpr_netdev_stop(struct net_device *dev)
 static const struct net_device_ops i40e_vfpr_netdev_ops = {
 	.ndo_open       	= i40e_vfpr_netdev_open,
 	.ndo_stop       	= i40e_vfpr_netdev_stop,
+	.ndo_start_xmit		= i40e_vfpr_netdev_start_xmit,
 };
 
 /**

@@ -1121,16 +1122,22 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
 
 	priv = netdev_priv(vfpr_netdev);
 	priv->vf = &(pf->vf[vf_num]);
+	priv->vfpr_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL);
+	priv->vfpr_dst->u.port_info.lower_dev = vsi->netdev;
+	priv->vfpr_dst->u.port_info.port_id = vf->vf_id;
 
 	vfpr_netdev->netdev_ops = &i40e_vfpr_netdev_ops;
 
 	netif_carrier_off(vfpr_netdev);
 	netif_tx_disable(vfpr_netdev);
 
+	eth_hw_addr_inherit(vfpr_netdev, vsi->netdev);
+
 	err = register_netdev(vfpr_netdev);
 	if (err) {
 		dev_err(&pf->pdev->dev, "register_netdev failed for vf: %s\n",
 			vf->vfpr_netdev->name);
+		dst_release((struct dst_entry *)priv->vfpr_dst);
 		free_netdev(vfpr_netdev);
 		return err;
 	}

@@ -1159,14 +1166,18 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
  **/
 void i40e_free_vfpr_netdev(struct i40e_vf *vf)
 {
+	struct i40e_vfpr_netdev_priv *priv;
 	struct i40e_pf *pf = vf->pf;
 
 	if (!vf->vfpr_netdev)
 		return;
 
+	priv = netdev_priv(vf->vfpr_netdev);
+
 	dev_info(&pf->pdev->dev, "Freeing VF Port representor(%s)\n",
 		 vf->vfpr_netdev->name);
 
+	dst_release((struct dst_entry *)priv->vfpr_dst);
 	unregister_netdev(vf->vfpr_netdev);
 	free_netdev(vf->vfpr_netdev);
 

@@ -1936,8 +1947,10 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
 		aq_ret = I40E_ERR_TIMEOUT;
 
-	if ((0 == aq_ret) && vf->vfpr_netdev)
+	if ((0 == aq_ret) && vf->vfpr_netdev) {
+		netif_tx_start_all_queues(vf->vfpr_netdev);
 		netif_carrier_on(vf->vfpr_netdev);
+	}
 
 error_param:
 	/* send the response to the VF */

@@ -1978,8 +1991,10 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
 
-	if ((0 == aq_ret) && vf->vfpr_netdev)
+	if ((0 == aq_ret) && vf->vfpr_netdev) {
+		netif_tx_stop_all_queues(vf->vfpr_netdev);
 		netif_carrier_off(vf->vfpr_netdev);
+	}
 
 error_param:
 	/* send the response to the VF */

@@ -74,6 +74,7 @@ enum i40e_vf_capabilities {
 
 /* VF Port representator netdev private structure */
 struct i40e_vfpr_netdev_priv {
+	struct metadata_dst *vfpr_dst;
 	struct i40e_vf *vf;
 };
 

@@ -1172,6 +1172,32 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 }
 
 /**
+ * i40e_vfpr_receive_skb
+ * @vf: pointer to VF
+ * @skb: packet to send up
+ *
+ * Update skb dev to vfpr netdev and rx stats.
+ **/
+static void i40e_vfpr_receive_skb(struct i40e_vf *vf, struct sk_buff *skb)
+{
+	struct i40e_vfpr_netdev_priv *priv;
+	struct vfpr_pcpu_stats *vfpr_stats;
+
+	if (!vf->vfpr_netdev)
+		return;
+
+	skb->dev = vf->vfpr_netdev;
+
+	priv = netdev_priv(vf->vfpr_netdev);
+	vfpr_stats = this_cpu_ptr(priv->vfpr_stats);
+
+	u64_stats_update_begin(&vfpr_stats->syncp);
+	vfpr_stats->rx_packets++;
+	vfpr_stats->rx_bytes += skb->len;
+	u64_stats_update_end(&vfpr_stats->syncp);
+}
+
+/**
  * i40e_receive_skb - Send a completed packet up the stack
  * @rx_ring:  rx ring in play
  * @skb: packet to send up

@@ -1201,7 +1227,7 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring,
 	for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
 		vf = &pf->vf[vf_id];
 		if (ether_addr_equal(eth->h_source, vf->default_lan_addr.addr)) {
-			skb->dev = vf->vfpr_netdev;
+			i40e_vfpr_receive_skb(vf, skb);
 			break;
 		}
 	}

@@ -3072,11 +3098,25 @@ netdev_tx_t i40e_vfpr_netdev_start_xmit(struct sk_buff *skb,
 	struct i40e_vf *vf = priv->vf;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	int ret;
 
 	skb_dst_drop(skb);
 	dst_hold(&priv->vfpr_dst->dst);
 	skb_dst_set(skb, &priv->vfpr_dst->dst);
 	skb->dev = vsi->netdev;
 
-	return dev_queue_xmit(skb);
+	ret = dev_queue_xmit(skb);
+
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
+		struct vfpr_pcpu_stats *vfpr_stats = this_cpu_ptr(priv->vfpr_stats);
+
+		u64_stats_update_begin(&vfpr_stats->syncp);
+		vfpr_stats->tx_packets++;
+		vfpr_stats->tx_bytes += skb->len;
+		u64_stats_update_end(&vfpr_stats->syncp);
+	} else {
+		this_cpu_inc(priv->vfpr_stats->tx_drops);
+	}
+
+	return ret;
 }

@@ -1059,10 +1059,113 @@ static int i40e_vfpr_netdev_stop(struct net_device *dev)
 	return 0;
 }
 
+/**
+ * i40e_vfpr_netdev_get_stats64
+ * @dev: network interface device structure
+ * @stats: netlink stats structure
+ *
+ * Returns the hw statistics from the VSI corresponding to the associated VFPR
+ **/
+static struct rtnl_link_stats64 *
+i40e_vfpr_netdev_get_stats64(struct net_device *netdev,
+			     struct rtnl_link_stats64 *stats)
+{
+	struct i40e_vfpr_netdev_priv *priv = netdev_priv(netdev);
+	struct i40e_vf *vf = priv->vf;
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_vsi *vsi;
+	struct i40e_eth_stats *estats;
+
+	vsi = pf->vsi[vf->lan_vsi_idx];
+	i40e_update_stats(vsi);
+
+	estats = &vsi->eth_stats;
+
+	/* TX and RX stats are flipped as we are returning the stats as seen
+	 * at the switch port correspoding to the VF.
+	 */
+	stats->rx_packets = estats->tx_unicast + estats->tx_multicast +
+			    estats->tx_broadcast;
+	stats->tx_packets = estats->rx_unicast + estats->rx_multicast +
+			    estats->rx_broadcast;
+	stats->rx_bytes = estats->tx_bytes;
+	stats->tx_bytes = estats->rx_bytes;
+	stats->rx_dropped = estats->tx_discards;
+	stats->tx_dropped = estats->rx_discards;
+
+	return stats;
+}
+
+
+/**
+ * i40e_vfpr_get_cpu_hit_stats64
+ * @dev: network interface device structure
+ * @stats: netlink stats structure
+ *
+ * stats are filled from the priv structure. correspond to the packets
+ * that are seen by the cpu and sent/received via vfpr netdev.
+ **/
+static int
+i40e_vfpr_get_cpu_hit_stats64(const struct net_device *dev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct vfpr_pcpu_stats *vfpr_stats;
+		u64 tbytes, tpkts, tdrops, rbytes, rpkts;
+		unsigned int start;
+
+		vfpr_stats = per_cpu_ptr(priv->vfpr_stats, i);
+		do {
+			start = u64_stats_fetch_begin_irq(&vfpr_stats->syncp);
+			tbytes = vfpr_stats->tx_bytes;
+			tpkts = vfpr_stats->tx_packets;
+			tdrops = vfpr_stats->tx_drops;
+			rbytes = vfpr_stats->rx_bytes;
+			rpkts = vfpr_stats->rx_packets;
+		} while (u64_stats_fetch_retry_irq(&vfpr_stats->syncp, start));
+		stats->tx_bytes += tbytes;
+		stats->tx_packets += tpkts;
+		stats->tx_dropped += tdrops;
+		stats->rx_bytes += rbytes;
+		stats->rx_packets += rpkts;
+	}
+
+	return 0;
+}
+
+static bool
+i40e_vfpr_netdev_has_offload_stats(const struct net_device *dev, int attr_id)
+{
+	switch (attr_id) {
+	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
+		return true;
+	}
+
+	return false;
+}
+
+static int
+i40e_vfpr_netdev_get_offload_stats(int attr_id, const struct net_device *dev,
+				   void *sp)
+{
+	switch (attr_id) {
+	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
+		return i40e_vfpr_get_cpu_hit_stats64(dev, sp);
+	}
+
+	return -EINVAL;
+}
+
 static const struct net_device_ops i40e_vfpr_netdev_ops = {
 	.ndo_open       	= i40e_vfpr_netdev_open,
 	.ndo_stop       	= i40e_vfpr_netdev_stop,
 	.ndo_start_xmit		= i40e_vfpr_netdev_start_xmit,
+	.ndo_get_stats64	= i40e_vfpr_netdev_get_stats64,
+	.ndo_has_offload_stats	= i40e_vfpr_netdev_has_offload_stats,
+	.ndo_get_offload_stats	= i40e_vfpr_netdev_get_offload_stats,
 };
 
 /**