tap: Abstract type of virtual interface from tap implementation

macvlan object is re-structured to hold tap related elements in a separate
entity, tap_dev. Upon NETDEV_REGISTER device_event, tap_dev is registered with
idr and fetched again on tap_open. Few of the tap functions are modified to
accepted tap_dev as argument. tap_dev object includes callbacks to be used by
underlying virtual interface to take care of tx and rx accounting.
Signed-off-by: Sainath Grandhi <sainath.grandhi@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/macvlan.c

@@ -1525,7 +1525,6 @@ static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
 int macvlan_link_register(struct rtnl_link_ops *ops)
 {
 	/* common fields */
-	ops->priv_size		= sizeof(struct macvlan_dev);
 	ops->validate		= macvlan_validate;
 	ops->maxtype		= IFLA_MACVLAN_MAX;
 	ops->policy		= macvlan_policy;
@@ -1548,6 +1547,7 @@ static struct rtnl_link_ops macvlan_link_ops = {
 	.newlink	= macvlan_newlink,
 	.dellink	= macvlan_dellink,
 	.get_link_net	= macvlan_get_link_net,
+	.priv_size      = sizeof(struct macvlan_dev),
 };
 
 static int macvlan_device_event(struct notifier_block *unused,

drivers/net/macvtap_main.c

@@ -24,6 +24,11 @@
 #include <linux/virtio_net.h>
 #include <linux/skb_array.h>
 
+struct macvtap_dev {
+	struct macvlan_dev vlan;
+	struct tap_dev    tap;
+};
+
 /*
  * Variables for dealing with macvtaps device numbers.
  */
@@ -46,22 +51,55 @@ static struct cdev macvtap_cdev;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
 		      NETIF_F_TSO6 | NETIF_F_UFO)
 
+static void macvtap_count_tx_dropped(struct tap_dev *tap)
+{
+	struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap);
+	struct macvlan_dev *vlan = &vlantap->vlan;
+
+	this_cpu_inc(vlan->pcpu_stats->tx_dropped);
+}
+
+static void macvtap_count_rx_dropped(struct tap_dev *tap)
+{
+	struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap);
+	struct macvlan_dev *vlan = &vlantap->vlan;
+
+	macvlan_count_rx(vlan, 0, 0, 0);
+}
+
+static void macvtap_update_features(struct tap_dev *tap,
+				    netdev_features_t features)
+{
+	struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap);
+	struct macvlan_dev *vlan = &vlantap->vlan;
+
+	vlan->set_features = features;
+	netdev_update_features(vlan->dev);
+}
+
 static int macvtap_newlink(struct net *src_net,
 			   struct net_device *dev,
 			   struct nlattr *tb[],
 			   struct nlattr *data[])
 {
-	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct macvtap_dev *vlantap = netdev_priv(dev);
 	int err;
 
-	INIT_LIST_HEAD(&vlan->queue_list);
+	INIT_LIST_HEAD(&vlantap->tap.queue_list);
 
 	/* Since macvlan supports all offloads by default, make
 	 * tap support all offloads also.
 	 */
-	vlan->tap_features = TUN_OFFLOADS;
+	vlantap->tap.tap_features = TUN_OFFLOADS;
 
-	err = netdev_rx_handler_register(dev, tap_handle_frame, vlan);
+	/* Register callbacks for rx/tx drops accounting and updating
+	 * net_device features
+	 */
+	vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped;
+	vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped;
+	vlantap->tap.update_features  = macvtap_update_features;
+
+	err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap);
 	if (err)
 		return err;
 
@@ -74,14 +112,18 @@ static int macvtap_newlink(struct net *src_net,
 		return err;
 	}
 
+	vlantap->tap.dev = vlantap->vlan.dev;
+
 	return 0;
 }
 
 static void macvtap_dellink(struct net_device *dev,
 			    struct list_head *head)
 {
+	struct macvtap_dev *vlantap = netdev_priv(dev);
+
 	netdev_rx_handler_unregister(dev);
-	tap_del_queues(dev);
+	tap_del_queues(&vlantap->tap);
 	macvlan_dellink(dev, head);
 }
 
@@ -96,13 +138,14 @@ static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
 	.setup		= macvtap_setup,
 	.newlink	= macvtap_newlink,
 	.dellink	= macvtap_dellink,
+	.priv_size      = sizeof(struct macvtap_dev),
 };
 
 static int macvtap_device_event(struct notifier_block *unused,
 				unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct macvlan_dev *vlan;
+	struct macvtap_dev *vlantap;
 	struct device *classdev;
 	dev_t devt;
 	int err;
@@ -112,7 +155,7 @@ static int macvtap_device_event(struct notifier_block *unused,
 		return NOTIFY_DONE;
 
 	snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex);
-	vlan = netdev_priv(dev);
+	vlantap = netdev_priv(dev);
 
 	switch (event) {
 	case NETDEV_REGISTER:
@@ -120,15 +163,15 @@ static int macvtap_device_event(struct notifier_block *unused,
 		 * been registered but before register_netdevice has
 		 * finished running.
 		 */
-		err = tap_get_minor(vlan);
+		err = tap_get_minor(&vlantap->tap);
 		if (err)
 			return notifier_from_errno(err);
 
-		devt = MKDEV(MAJOR(macvtap_major), vlan->minor);
+		devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor);
 		classdev = device_create(&macvtap_class, &dev->dev, devt,
 					 dev, tap_name);
 		if (IS_ERR(classdev)) {
-			tap_free_minor(vlan);
+			tap_free_minor(&vlantap->tap);
 			return notifier_from_errno(PTR_ERR(classdev));
 		}
 		err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj,
@@ -138,15 +181,15 @@ static int macvtap_device_event(struct notifier_block *unused,
 		break;
 	case NETDEV_UNREGISTER:
 		/* vlan->minor == 0 if NETDEV_REGISTER above failed */
-		if (vlan->minor == 0)
+		if (vlantap->tap.minor == 0)
 			break;
 		sysfs_remove_link(&dev->dev.kobj, tap_name);
-		devt = MKDEV(MAJOR(macvtap_major), vlan->minor);
+		devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor);
 		device_destroy(&macvtap_class, devt);
-		tap_free_minor(vlan);
+		tap_free_minor(&vlantap->tap);
 		break;
 	case NETDEV_CHANGE_TX_QUEUE_LEN:
-		if (tap_queue_resize(vlan))
+		if (tap_queue_resize(&vlantap->tap))
 			return NOTIFY_BAD;
 		break;
 	}

include/linux/if_tap.h

@@ -14,11 +14,60 @@ static inline struct socket *tap_get_socket(struct file *f)
 }
 #endif /* CONFIG_MACVTAP */
 
+#include <net/sock.h>
+#include <linux/skb_array.h>
+
+#define MAX_TAP_QUEUES 256
+
+struct tap_queue;
+
+struct tap_dev {
+	struct net_device	*dev;
+	u16			flags;
+	/* This array tracks active taps. */
+	struct tap_queue    __rcu *taps[MAX_TAP_QUEUES];
+	/* This list tracks all taps (both enabled and disabled) */
+	struct list_head	queue_list;
+	int			numvtaps;
+	int			numqueues;
+	netdev_features_t	tap_features;
+	int			minor;
+
+	void (*update_features)(struct tap_dev *tap, netdev_features_t features);
+	void (*count_tx_dropped)(struct tap_dev *tap);
+	void (*count_rx_dropped)(struct tap_dev *tap);
+};
+
+/*
+ * A tap queue is the central object of tap module, it connects
+ * an open character device to virtual interface. There can be
+ * multiple queues on one interface, which map back to queues
+ * implemented in hardware on the underlying device.
+ *
+ * tap_proto is used to allocate queues through the sock allocation
+ * mechanism.
+ *
+ */
+
+struct tap_queue {
+	struct sock sk;
+	struct socket sock;
+	struct socket_wq wq;
+	int vnet_hdr_sz;
+	struct tap_dev __rcu *tap;
+	struct file *file;
+	unsigned int flags;
+	u16 queue_index;
+	bool enabled;
+	struct list_head next;
+	struct skb_array skb_array;
+};
+
 rx_handler_result_t tap_handle_frame(struct sk_buff **pskb);
-void tap_del_queues(struct net_device *dev);
-int tap_get_minor(struct macvlan_dev *vlan);
-void tap_free_minor(struct macvlan_dev *vlan);
-int tap_queue_resize(struct macvlan_dev *vlan);
+void tap_del_queues(struct tap_dev *tap);
+int tap_get_minor(struct tap_dev *tap);
+void tap_free_minor(struct tap_dev *tap);
+int tap_queue_resize(struct tap_dev *tap);
 int tap_create_cdev(struct cdev *tap_cdev,
 		    dev_t *tap_major, const char *device_name);
 void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev);