diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 5763503fe4e640a5041788fb360fadd51007a3c3..823bc2fd201ff022f28f08800694fab19ae3c9e8 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -166,6 +166,19 @@ config IPVLAN To compile this driver as a module, choose M here: the module will be called ipvlan. +config IPVTAP + tristate "IP-VLAN based tap driver" + depends on IPVLAN + depends on INET + select TAP + ---help--- + This adds a specialized tap character device driver that is based + on the IP-VLAN network interface, called ipvtap. An ipvtap device + can be added in the same way as a ipvlan device, using 'type + ipvtap', and then be accessed through the tap user space interface. + + To compile this driver as a module, choose M here: the module + will be called ipvtap. config VXLAN tristate "Virtual eXtensible Local Area Network (VXLAN)" diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 7dd86ca02d0d4c48f53f0e7846bae0a366748f51..98ed4d96987c87fda074a219a234cbf8e48f2b9a 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -7,6 +7,7 @@ # obj-$(CONFIG_BONDING) += bonding/ obj-$(CONFIG_IPVLAN) += ipvlan/ +obj-$(CONFIG_IPVTAP) += ipvlan/ obj-$(CONFIG_DUMMY) += dummy.o obj-$(CONFIG_EQUALIZER) += eql.o obj-$(CONFIG_IFB) += ifb.o diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile index df79910192d6c92b489c6c71f2f5fbdc795a7782..8a2c64dc964105d378b56be5a99477599e011b57 100644 --- a/drivers/net/ipvlan/Makefile +++ b/drivers/net/ipvlan/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_IPVLAN) += ipvlan.o +obj-$(CONFIG_IPVTAP) += ipvtap.o ipvlan-objs := ipvlan_core.o ipvlan_main.o diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 406ae4ff0ae891aa6bd1522bbb367699f16109b1..800a46c8d26c25f74244ee30872097982ebc775e 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -135,4 +135,11 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, u16 proto); unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +void ipvlan_count_rx(const struct ipvl_dev *ipvlan, + unsigned int len, bool success, bool mcast); +int ipvlan_link_new(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]); +void ipvlan_link_delete(struct net_device *dev, struct list_head *head); +void ipvlan_link_setup(struct net_device *dev); +int ipvlan_link_register(struct rtnl_link_ops *ops); #endif /* __IPVLAN_H */ diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 8ae335d73d3886a0f7a91f55a428059120288de6..1f3295e274d0f5fbb36211b71023320327a86f12 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -16,7 +16,7 @@ void ipvlan_init_secret(void) net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret)); } -static void ipvlan_count_rx(const struct ipvl_dev *ipvlan, +void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast) { if (likely(success)) { @@ -33,6 +33,7 @@ static void ipvlan_count_rx(const struct ipvl_dev *ipvlan, this_cpu_inc(ipvlan->pcpu_stats->rx_errs); } } +EXPORT_SYMBOL_GPL(ipvlan_count_rx); static u8 ipvlan_get_v6_hash(const void *iaddr) { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 95b18f4602cf1d9653fd740c56f8644d764189a4..aa8575ccbce392426ab1ceb65ecadee5175dcb1b 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -496,8 +496,8 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb, return ret; } -static int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +int ipvlan_link_new(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port; @@ -594,8 +594,9 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan_port_destroy(phy_dev); return err; } +EXPORT_SYMBOL_GPL(ipvlan_link_new); -static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) +void ipvlan_link_delete(struct net_device *dev, struct list_head *head) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; @@ -611,8 +612,9 @@ static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); } +EXPORT_SYMBOL_GPL(ipvlan_link_delete); -static void ipvlan_link_setup(struct net_device *dev) +void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); @@ -623,6 +625,7 @@ static void ipvlan_link_setup(struct net_device *dev) dev->header_ops = &ipvlan_header_ops; dev->ethtool_ops = &ipvlan_ethtool_ops; } +EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { @@ -633,22 +636,22 @@ static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), - .get_size = ipvlan_nl_getsize, - .policy = ipvlan_nl_policy, - .validate = ipvlan_nl_validate, - .fill_info = ipvlan_nl_fillinfo, - .changelink = ipvlan_nl_changelink, - .maxtype = IFLA_IPVLAN_MAX, - .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, }; -static int ipvlan_link_register(struct rtnl_link_ops *ops) +int ipvlan_link_register(struct rtnl_link_ops *ops) { + ops->get_size = ipvlan_nl_getsize; + ops->policy = ipvlan_nl_policy; + ops->validate = ipvlan_nl_validate; + ops->fill_info = ipvlan_nl_fillinfo; + ops->changelink = ipvlan_nl_changelink; + ops->maxtype = IFLA_IPVLAN_MAX; return rtnl_link_register(ops); } +EXPORT_SYMBOL_GPL(ipvlan_link_register); static int ipvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c new file mode 100644 index 0000000000000000000000000000000000000000..2b713b63b62c2d3edfce1128ffd417444f566c51 --- /dev/null +++ b/drivers/net/ipvlan/ipvtap.c @@ -0,0 +1,241 @@ +#include +#include "ipvlan.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ + NETIF_F_TSO6 | NETIF_F_UFO) + +static dev_t ipvtap_major; +static struct cdev ipvtap_cdev; + +static const void *ipvtap_net_namespace(struct device *d) +{ + struct net_device *dev = to_net_dev(d->parent); + return dev_net(dev); +} + +static struct class ipvtap_class = { + .name = "ipvtap", + .owner = THIS_MODULE, + .ns_type = &net_ns_type_operations, + .namespace = ipvtap_net_namespace, +}; + +struct ipvtap_dev { + struct ipvl_dev vlan; + struct tap_dev tap; +}; + +static void ipvtap_count_tx_dropped(struct tap_dev *tap) +{ + struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); + struct ipvl_dev *vlan = &vlantap->vlan; + + this_cpu_inc(vlan->pcpu_stats->tx_drps); +} + +static void ipvtap_count_rx_dropped(struct tap_dev *tap) +{ + struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); + struct ipvl_dev *vlan = &vlantap->vlan; + + ipvlan_count_rx(vlan, 0, 0, 0); +} + +static void ipvtap_update_features(struct tap_dev *tap, + netdev_features_t features) +{ + struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); + struct ipvl_dev *vlan = &vlantap->vlan; + + vlan->sfeatures = features; + netdev_update_features(vlan->dev); +} + +static int ipvtap_newlink(struct net *src_net, + struct net_device *dev, + struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ipvtap_dev *vlantap = netdev_priv(dev); + int err; + + INIT_LIST_HEAD(&vlantap->tap.queue_list); + + /* Since macvlan supports all offloads by default, make + * tap support all offloads also. + */ + vlantap->tap.tap_features = TUN_OFFLOADS; + vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; + vlantap->tap.update_features = ipvtap_update_features; + vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; + + err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); + if (err) + return err; + + /* Don't put anything that may fail after macvlan_common_newlink + * because we can't undo what it does. + */ + err = ipvlan_link_new(src_net, dev, tb, data); + if (err) { + netdev_rx_handler_unregister(dev); + return err; + } + + vlantap->tap.dev = vlantap->vlan.dev; + + return err; +} + +static void ipvtap_dellink(struct net_device *dev, + struct list_head *head) +{ + struct ipvtap_dev *vlan = netdev_priv(dev); + + netdev_rx_handler_unregister(dev); + tap_del_queues(&vlan->tap); + ipvlan_link_delete(dev, head); +} + +static void ipvtap_setup(struct net_device *dev) +{ + ipvlan_link_setup(dev); + dev->tx_queue_len = TUN_READQ_SIZE; + dev->priv_flags &= ~IFF_NO_QUEUE; +} + +static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { + .kind = "ipvtap", + .setup = ipvtap_setup, + .newlink = ipvtap_newlink, + .dellink = ipvtap_dellink, + .priv_size = sizeof(struct ipvtap_dev), +}; + +static int ipvtap_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ipvtap_dev *vlantap; + struct device *classdev; + dev_t devt; + int err; + char tap_name[IFNAMSIZ]; + + if (dev->rtnl_link_ops != &ipvtap_link_ops) + return NOTIFY_DONE; + + snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); + vlantap = netdev_priv(dev); + + switch (event) { + case NETDEV_REGISTER: + /* Create the device node here after the network device has + * been registered but before register_netdevice has + * finished running. + */ + err = tap_get_minor(ipvtap_major, &vlantap->tap); + if (err) + return notifier_from_errno(err); + + devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); + classdev = device_create(&ipvtap_class, &dev->dev, devt, + dev, tap_name); + if (IS_ERR(classdev)) { + tap_free_minor(ipvtap_major, &vlantap->tap); + return notifier_from_errno(PTR_ERR(classdev)); + } + err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, + tap_name); + if (err) + return notifier_from_errno(err); + break; + case NETDEV_UNREGISTER: + /* vlan->minor == 0 if NETDEV_REGISTER above failed */ + if (vlantap->tap.minor == 0) + break; + sysfs_remove_link(&dev->dev.kobj, tap_name); + devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); + device_destroy(&ipvtap_class, devt); + tap_free_minor(ipvtap_major, &vlantap->tap); + break; + case NETDEV_CHANGE_TX_QUEUE_LEN: + if (tap_queue_resize(&vlantap->tap)) + return NOTIFY_BAD; + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block ipvtap_notifier_block __read_mostly = { + .notifier_call = ipvtap_device_event, +}; + +static int ipvtap_init(void) +{ + int err; + + err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap"); + + if (err) + goto out1; + + err = class_register(&ipvtap_class); + if (err) + goto out2; + + err = register_netdevice_notifier(&ipvtap_notifier_block); + if (err) + goto out3; + + err = ipvlan_link_register(&ipvtap_link_ops); + if (err) + goto out4; + + return 0; + +out4: + unregister_netdevice_notifier(&ipvtap_notifier_block); +out3: + class_unregister(&ipvtap_class); +out2: + tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); +out1: + return err; +} +module_init(ipvtap_init); + +static void ipvtap_exit(void) +{ + rtnl_link_unregister(&ipvtap_link_ops); + unregister_netdevice_notifier(&ipvtap_notifier_block); + class_unregister(&ipvtap_class); + tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); +} +module_exit(ipvtap_exit); +MODULE_ALIAS_RTNL_LINK("ipvtap"); +MODULE_AUTHOR("Sainath Grandhi "); +MODULE_LICENSE("GPL");