From 009146d117b9b816193fce0f1ed75f015a398721 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Tue, 3 Jan 2017 12:47:16 -0800 Subject: ipvlan: assign unique dev-id for each slave device. IPvlan setup uses one mac-address (of master). The IPv6 link-local addresses are derived using the mac-address on the link. Lack of dev-ids makes these link-local addresses same for all slaves including that of master device. dev-ids are necessary to add differentiation when L2 address is shared. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ipvlan/ipvlan.h') diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index dbfbb33ac66c..0a9068fdee0f 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -97,6 +97,7 @@ struct ipvl_port { struct work_struct wq; struct sk_buff_head backlog; int count; + struct ida ida; }; struct ipvl_skb_cb { -- cgit v1.2.3 From da36e13cf653541e385a8d2ec2637fff6ea3461a Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 9 Jan 2017 15:05:54 -0800 Subject: ipvlan: improvise dev_id generation logic in IPvlan The patch 009146d117b ("ipvlan: assign unique dev-id for each slave device.") used ida_simple_get() to generate dev_ids assigned to the slave devices. However (Eric has pointed out that) there is a shortcoming with that approach as it always uses the first available ID. This becomes a problem when a slave gets deleted and a new slave gets added. The ID gets reassigned causing the new slave to get the same link-local address. This side-effect is undesirable. This patch adds a per-port variable that keeps track of the IDs assigned and used as the stat-base for the IDR api. This base will be wrapped around when it reaches the MAX (0xFFFE) value possibly on a busy system where slaves are added and deleted routinely. Fixes: 009146d117b ("ipvlan: assign unique dev-id for each slave device.") Signed-off-by: Mahesh Bandewar CC: Eric Dumazet CC: David Miller Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan.h | 1 + drivers/net/ipvlan/ipvlan_main.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'drivers/net/ipvlan/ipvlan.h') diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 0a9068fdee0f..406ae4ff0ae8 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -94,6 +94,7 @@ struct ipvl_port { struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; + u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; int count; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 1cdb8c5ec403..92b221a03350 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -120,6 +120,7 @@ static int ipvlan_port_create(struct net_device *dev) skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); + port->dev_id_start = 1; err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port); if (err) @@ -534,15 +535,25 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); + /* If the port-id base is at the MAX value, then wrap it around and + * begin from 0x1 again. This may be due to a busy system where lots + * of slaves are getting created and deleted. + */ + if (port->dev_id_start == 0xFFFE) + port->dev_id_start = 0x1; + /* Since L2 address is shared among all IPvlan slaves including * master, use unique 16 bit dev-ids to diffentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ - err = ida_simple_get(&port->ida, 1, 0xFFFE, GFP_KERNEL); + err = ida_simple_get(&port->ida, port->dev_id_start, 0xFFFE, + GFP_KERNEL); if (err < 0) goto destroy_ipvlan_port; dev->dev_id = err; + /* Increment id-base to the next slot for the future assignment */ + port->dev_id_start = err + 1; /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing -- cgit v1.2.3 From 235a9d89da976e2975b3de9afc0bed7b72557983 Mon Sep 17 00:00:00 2001 From: Sainath Grandhi Date: Fri, 10 Feb 2017 16:03:52 -0800 Subject: ipvtap: IP-VLAN based tap driver This patch adds a tap character device driver that is based on the IP-VLAN network interface, called ipvtap. An ipvtap device can be created in the same way as an ipvlan device, using 'type ipvtap', and then accessed using the tap user space interface. Signed-off-by: Sainath Grandhi Signed-off-by: David S. Miller --- drivers/net/Kconfig | 13 +++ drivers/net/Makefile | 1 + drivers/net/ipvlan/Makefile | 1 + drivers/net/ipvlan/ipvlan.h | 7 ++ drivers/net/ipvlan/ipvlan_core.c | 3 +- drivers/net/ipvlan/ipvlan_main.c | 27 +++-- drivers/net/ipvlan/ipvtap.c | 241 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 280 insertions(+), 13 deletions(-) create mode 100644 drivers/net/ipvlan/ipvtap.c (limited to 'drivers/net/ipvlan/ipvlan.h') diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 5763503fe4e6..823bc2fd201f 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 7dd86ca02d0d..98ed4d96987c 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 df79910192d6..8a2c64dc9641 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 406ae4ff0ae8..800a46c8d26c 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 8ae335d73d38..1f3295e274d0 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 95b18f4602cf..aa8575ccbce3 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -496,8 +496,8 @@ err: 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 @@ destroy_ipvlan_port: 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 000000000000..2b713b63b62c --- /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"); -- cgit v1.2.3