[PATCH v3] add GENEVE netdev tunnel driver

[PATCH v3] add GENEVE netdev tunnel driver

[John W. Linville]

This 5-patch kernel series adds a netdev implementation of a GENEVE
tunnel driver, and the single iproute2 patch enables creation and
such for those netdevs.  This makes use of the existing GENEVE
infrastructure already used by the OVS code.  The net/ipv4/geneve.c
file is renamed as net/ipv4/geneve_core.c as part of these changes.

 drivers/net/Kconfig            |   14 +
 drivers/net/Makefile           |    1 
 drivers/net/geneve.c           |  503 +++++++++++++++++++++++++++++++++++++++++
 include/net/geneve.h           |    5 
 include/uapi/linux/if_link.h   |    9 
 net/ipv4/Kconfig               |    4 
 net/ipv4/Makefile              |    2 
 net/ipv4/geneve.c              |    6 
 net/ipv4/geneve_core.c         |    4 
 net/openvswitch/Kconfig        |    2 
 net/openvswitch/vport-geneve.c |    5 
 11 files changed, 538 insertions(+), 17 deletions(-)

The overall structure of the GENEVE netdev driver is strongly
influenced by the VXLAN netdev driver.  This is not surprising, as the
two drivers are intended to serve similar purposes.  As development of
the GENEVE driver continues, it is likely that those similarities will
grow stronger.  This will include both simple configuration options
(e.g. TOS and TTL settings) and new control plane support.

The current implementation is very simple, restricting itself to point
to point links over IPv4.  This is due only to the simplicity of the
implementation, and no such limit is inherent to GENEVE in any way.
Support for IPv6 links and more sophisticated control plane options
are predictable enhancements.

Using the included iproute2 patch, a GENEVE tunnel is created thusly:

        ip link add dev gnv0 type geneve remote 192.168.22.1 vni 1234
        ip link set gnv0 up
        ip addr add 10.1.1.1/24 dev gnv0

After a corresponding tunnel interface is created at the link partner,
traffic should proceed as expected.

Please let me know if anyone has problems...thanks!

John
--
John W. Linville		Someday the world will need a hero, and you
linville@tuxdriver.com			might be all we have.  Be ready.

[PATCH v3 1/5] geneve: remove MODULE_ALIAS_RTNL_LINK from net/ipv4/geneve.c

[John W. Linville]

This file is essentially a library for implementing the geneve
encapsulation protocol.  The file does not register any rtnl_link_ops,
so the MODULE_ALIAS_RTNL_LINK macro is inappropriate here.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
v2: skipped
v3: repost complete series for clarity

 net/ipv4/geneve.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 8986e63f3bda..8e6a7fe27a4c 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -450,4 +450,3 @@ module_exit(geneve_cleanup_module);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>");
 MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic");
-MODULE_ALIAS_RTNL_LINK("geneve");
-- 
2.1.0

[PATCH v3 2/5] geneve: move definition of geneve_hdr() to geneve.h

[John W. Linville]

This is a static inline with identical definitions in multiple places...

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
v2: skipped
v3: repost complete series for clarity

 include/net/geneve.h           | 5 +++++
 net/ipv4/geneve.c              | 5 -----
 net/openvswitch/vport-geneve.c | 5 -----
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/include/net/geneve.h b/include/net/geneve.h
index 14fb8d3390b4..2a0543a1899d 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -62,6 +62,11 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
 #ifdef CONFIG_INET
 struct geneve_sock;
 
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 8e6a7fe27a4c..001843d41135 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -60,11 +60,6 @@ struct geneve_net {
 
 static int geneve_net_id;
 
-static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
-{
-	return (struct genevehdr *)(udp_hdr(skb) + 1);
-}
-
 static struct geneve_sock *geneve_find_sock(struct net *net,
 					    sa_family_t family, __be16 port)
 {
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index bf02fd5808c9..208c576bd1b6 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -46,11 +46,6 @@ static inline struct geneve_port *geneve_vport(const struct vport *vport)
 	return vport_priv(vport);
 }
 
-static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
-{
-	return (struct genevehdr *)(udp_hdr(skb) + 1);
-}
-
 /* Convert 64 bit tunnel ID to 24 bit VNI. */
 static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
 {
-- 
2.1.0

[PATCH v3 3/5] geneve: Rename support library as geneve_core

[John W. Linville]

net/ipv4/geneve.c -> net/ipv4/geneve_core.c

This name better reflects the purpose of the module.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
Also, it prevents name resolution issues with module loading for the
geneve netdev coming later in this series...

v2: skipped
v3: repost complete series for clarity

 net/ipv4/Kconfig                     | 4 ++--
 net/ipv4/Makefile                    | 2 +-
 net/ipv4/{geneve.c => geneve_core.c} | 0
 net/openvswitch/Kconfig              | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)
 rename net/ipv4/{geneve.c => geneve_core.c} (100%)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index bd2901604842..d83071dccd74 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -331,8 +331,8 @@ config NET_FOU_IP_TUNNELS
 	  When this option is enabled IP tunnels can be configured to use
 	  FOU or GUE encapsulation.
 
-config GENEVE
-	tristate "Generic Network Virtualization Encapsulation (Geneve)"
+config GENEVE_CORE
+	tristate "Generic Network Virtualization Encapsulation library"
 	depends on INET
 	select NET_UDP_TUNNEL
 	---help---
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 518c04ed666e..b36236dd6014 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -56,7 +56,7 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
 obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
-obj-$(CONFIG_GENEVE) += geneve.o
+obj-$(CONFIG_GENEVE_CORE) += geneve_core.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
 		      xfrm4_output.o xfrm4_protocol.o
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve_core.c
similarity index 100%
rename from net/ipv4/geneve.c
rename to net/ipv4/geneve_core.c
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index ed6b0f8dd1bb..15840401a2ce 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -59,7 +59,7 @@ config OPENVSWITCH_VXLAN
 config OPENVSWITCH_GENEVE
 	tristate "Open vSwitch Geneve tunneling support"
 	depends on OPENVSWITCH
-	depends on GENEVE
+	depends on GENEVE_CORE
 	default OPENVSWITCH
 	---help---
 	  If you say Y here, then the Open vSwitch will be able create geneve vport.
-- 
2.1.0

[PATCH v3 4/5] geneve_core: identify as driver library in modules description

[John W. Linville]

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
v2: skipped
v3: repost complete series for clarity

 net/ipv4/geneve_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/geneve_core.c b/net/ipv4/geneve_core.c
index 001843d41135..311a4ba6950a 100644
--- a/net/ipv4/geneve_core.c
+++ b/net/ipv4/geneve_core.c
@@ -430,7 +430,7 @@ static int __init geneve_init_module(void)
 	if (rc)
 		return rc;
 
-	pr_info("Geneve driver\n");
+	pr_info("Geneve core logic\n");
 
 	return 0;
 }
@@ -444,4 +444,4 @@ module_exit(geneve_cleanup_module);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>");
-MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic");
+MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic");
-- 
2.1.0

[PATCH v3 5/5] geneve: add initial netdev driver for GENEVE tunnels

[John W. Linville]

This is an initial implementation of a netdev driver for GENEVE
tunnels.  This implementation uses a fixed UDP port, and only supports
point-to-point links with specific partner endpoints.  Only IPv4
links are supported at this time.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
v2:
 - removal of unneeded special lock for vni_list
 - removal of geneve_net_vni_add/del (replaced by open code)
 - break out of vni search loop in geneve_rx after match found
 - no longer deferring socket open at ndo_init(), now doing it in ndo_open()
 - check for non-multicast, non-zero remote link partner in newlink()
 - remove now unused workqueue stuff

v3: repost complete series for clarity

 drivers/net/Kconfig          |  14 ++
 drivers/net/Makefile         |   1 +
 drivers/net/geneve.c         | 503 +++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/if_link.h |   9 +
 4 files changed, 527 insertions(+)
 create mode 100644 drivers/net/geneve.c

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index df51d6025a90..019fceffc9e5 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -179,6 +179,20 @@ config VXLAN
 	  To compile this driver as a module, choose M here: the module
 	  will be called vxlan.
 
+config GENEVE
+       tristate "Generic Network Virtualization Encapsulation netdev"
+       depends on INET && GENEVE_CORE
+       select NET_IP_TUNNEL
+       ---help---
+	  This allows one to create geneve virtual interfaces that provide
+	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
+	  to tunnel virtual network infrastructure in virtualized environments.
+	  For more information see:
+	    http://tools.ietf.org/html/draft-gross-geneve-02
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called geneve.
+
 config NETCONSOLE
 	tristate "Network console logging support"
 	---help---
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index e25fdd7d905e..c12cb22478a7 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_TUN) += tun.o
 obj-$(CONFIG_VETH) += veth.o
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
 obj-$(CONFIG_VXLAN) += vxlan.o
+obj-$(CONFIG_GENEVE) += geneve.o
 obj-$(CONFIG_NLMON) += nlmon.o
 
 #
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
new file mode 100644
index 000000000000..b7eafa4c1a67
--- /dev/null
+++ b/drivers/net/geneve.c
@@ -0,0 +1,503 @@
+/*
+ * GENEVE: Generic Network Virtualization Encapsulation
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/hash.h>
+#include <net/rtnetlink.h>
+#include <net/geneve.h>
+
+#define GENEVE_NETDEV_VER	"0.6"
+
+#define GENEVE_UDP_PORT		6081
+
+#define GENEVE_N_VID		(1u << 24)
+#define GENEVE_VID_MASK		(GENEVE_N_VID - 1)
+
+#define VNI_HASH_BITS		10
+#define VNI_HASH_SIZE		(1<<VNI_HASH_BITS)
+
+static bool log_ecn_error = true;
+module_param(log_ecn_error, bool, 0644);
+MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
+
+/* per-network namespace private data for this module */
+struct geneve_net {
+	struct list_head  geneve_list;
+	struct hlist_head vni_list[VNI_HASH_SIZE];
+};
+
+/* Pseudo network device */
+struct geneve_dev {
+	struct hlist_node  hlist;	/* vni hash table */
+	struct net	   *net;	/* netns for packet i/o */
+	struct net_device  *dev;	/* netdev for geneve tunnel */
+	struct geneve_sock *sock;	/* socket used for geneve tunnel */
+	u8 vni[3];			/* virtual network ID for tunnel */
+	struct sockaddr_in remote;	/* IPv4 address for link partner */
+	struct list_head   next;	/* geneve's per namespace list */
+};
+
+static int geneve_net_id;
+
+static inline __u32 geneve_net_vni_hash(u8 vni[3])
+{
+	__u32 vnid;
+
+	vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
+	return hash_32(vnid, VNI_HASH_BITS);
+}
+
+/* geneve receive/decap routine */
+static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
+{
+	struct genevehdr *gnvh = geneve_hdr(skb);
+	struct geneve_dev *dummy, *geneve = NULL;
+	struct geneve_net *gn;
+	struct iphdr *iph = NULL;
+	struct pcpu_sw_netstats *stats;
+	struct hlist_head *vni_list_head;
+	int err = 0;
+	__u32 hash;
+
+	iph = ip_hdr(skb); /* Still outer IP header... */
+
+	gn = gs->rcv_data;
+
+	/* Find the device for this VNI */
+	hash = geneve_net_vni_hash(gnvh->vni);
+	vni_list_head = &gn->vni_list[hash];
+	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
+		if (!memcmp(gnvh->vni, dummy->vni, sizeof(dummy->vni)) &&
+		    iph->saddr == dummy->remote.sin_addr.s_addr) {
+			geneve = dummy;
+			break;
+		}
+	}
+	if (!geneve)
+		goto drop;
+
+	/* Drop packets w/ critical options,
+	 * since we don't support any...
+	 */
+	if (gnvh->critical)
+		goto drop;
+
+	skb_reset_mac_header(skb);
+	skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
+	skb->protocol = eth_type_trans(skb, geneve->dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+
+	/* Ignore packet loops (and multicast echo) */
+	if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
+		goto drop;
+
+	skb_reset_network_header(skb);
+
+	iph = ip_hdr(skb); /* Now inner IP header... */
+	err = IP_ECN_decapsulate(iph, skb);
+
+	if (unlikely(err)) {
+		if (log_ecn_error)
+			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+					     &iph->saddr, iph->tos);
+		if (err > 1) {
+			++geneve->dev->stats.rx_frame_errors;
+			++geneve->dev->stats.rx_errors;
+			goto drop;
+		}
+	}
+
+	stats = this_cpu_ptr(geneve->dev->tstats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	netif_rx(skb);
+
+	return;
+drop:
+	/* Consume bad packet */
+	kfree_skb(skb);
+}
+
+/* Setup stats when device is created */
+static int geneve_init(struct net_device *dev)
+{
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void geneve_uninit(struct net_device *dev)
+{
+	free_percpu(dev->tstats);
+}
+
+static int geneve_open(struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct net *net = geneve->net;
+	struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
+	struct geneve_sock *gs;
+
+	gs = geneve_sock_add(net, htons(GENEVE_UDP_PORT), geneve_rx, gn,
+	                     false, false);
+	if (IS_ERR(gs))
+		return PTR_ERR(gs);
+
+	geneve->sock = gs;
+
+	return 0;
+}
+
+static int geneve_stop(struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_sock *gs = geneve->sock;
+
+	geneve_sock_release(gs);
+
+	return 0;
+}
+
+static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_sock *gs = geneve->sock;
+	struct rtable *rt = NULL;
+	const struct iphdr *iip; /* interior IP header */
+	struct flowi4 fl4;
+	int err;
+	__be16 sport;
+	__u8 tos, ttl = 0;
+
+	iip = ip_hdr(skb);
+
+	skb_reset_mac_header(skb);
+
+	/* TODO: port min/max limits should be configurable */
+	sport = udp_flow_src_port(dev_net(dev), skb, 0, 0, true);
+
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.daddr = geneve->remote.sin_addr.s_addr;
+	rt = ip_route_output_key(geneve->net, &fl4);
+	if (IS_ERR(rt)) {
+		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+		dev->stats.tx_carrier_errors++;
+		goto tx_error;
+	}
+	if (rt->dst.dev == dev) { /* is this necessary? */
+		netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
+		dev->stats.collisions++;
+		goto rt_tx_error;
+	}
+
+	/* TODO: tos and ttl should be configurable */
+
+	tos = ip_tunnel_ecn_encap(0, iip, skb);
+
+	if (IN_MULTICAST(ntohl(fl4.daddr)))
+		ttl = 1;
+
+	ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+	/* no need to handle local destination and encap bypass...yet... */
+
+	err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr,
+	                      tos, ttl, 0, sport, htons(GENEVE_UDP_PORT), 0,
+	                      geneve->vni, 0, NULL, false,
+	                      !net_eq(geneve->net, dev_net(geneve->dev)));
+	if (err < 0)
+		ip_rt_put(rt);
+
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+
+	return NETDEV_TX_OK;
+
+rt_tx_error:
+	ip_rt_put(rt);
+tx_error:
+	dev->stats.tx_errors++;
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops geneve_netdev_ops = {
+	.ndo_init		= geneve_init,
+	.ndo_uninit		= geneve_uninit,
+	.ndo_open		= geneve_open,
+	.ndo_stop		= geneve_stop,
+	.ndo_start_xmit		= geneve_xmit,
+	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
+};
+
+static void geneve_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version));
+	strlcpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver));
+}
+
+static const struct ethtool_ops geneve_ethtool_ops = {
+	.get_drvinfo	= geneve_get_drvinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+/* Info for udev, that this is a virtual tunnel endpoint */
+static struct device_type geneve_type = {
+	.name = "geneve",
+};
+
+/* Initialize the device structure. */
+static void geneve_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->netdev_ops = &geneve_netdev_ops;
+	dev->ethtool_ops = &geneve_ethtool_ops;
+	dev->destructor = free_netdev;
+
+	SET_NETDEV_DEVTYPE(dev, &geneve_type);
+
+	dev->tx_queue_len = 0;
+	dev->features    |= NETIF_F_LLTX;
+	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM;
+	dev->features    |= NETIF_F_RXCSUM;
+	dev->features    |= NETIF_F_GSO_SOFTWARE;
+
+	dev->vlan_features = dev->features;
+	dev->features    |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+
+	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+
+	netif_keep_dst(dev);
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+}
+
+static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
+	[IFLA_GENEVE_ID]		= { .type = NLA_U32 },
+	[IFLA_GENEVE_REMOTE]		= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+};
+
+static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	if (data[IFLA_GENEVE_ID]) {
+		__u32 vni =  nla_get_u32(data[IFLA_GENEVE_ID]);
+
+		if (vni >= GENEVE_VID_MASK)
+			return -ERANGE;
+	}
+
+	return 0;
+}
+
+static int geneve_newlink(struct net *net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[])
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev *dummy, *geneve = netdev_priv(dev);
+	struct hlist_head *vni_list_head;
+	struct sockaddr_in remote;	/* IPv4 address for link partner */
+	__u32 vni, hash;
+	int err;
+
+	if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
+		return -EINVAL;
+
+	geneve->net = net;
+	geneve->dev = dev;
+
+	vni = nla_get_u32(data[IFLA_GENEVE_ID]);
+	geneve->vni[0] = (vni & 0x00ff0000) >> 16;
+	geneve->vni[1] = (vni & 0x0000ff00) >> 8;
+	geneve->vni[2] =  vni & 0x000000ff;
+
+	geneve->remote.sin_addr.s_addr =
+		nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);
+	if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr)))
+		return -EINVAL;
+
+	remote = geneve->remote;
+	hash = geneve_net_vni_hash(geneve->vni);
+	vni_list_head = &gn->vni_list[hash];
+	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
+		if (!memcmp(geneve->vni, dummy->vni, sizeof(dummy->vni)) &&
+		    !memcmp(&remote, &dummy->remote, sizeof(dummy->remote)))
+			return -EBUSY;
+	}
+
+	if (tb[IFLA_ADDRESS] == NULL)
+		eth_hw_addr_random(dev);
+
+	err = register_netdevice(dev);
+	if (err)
+		return err;
+
+	list_add(&geneve->next, &gn->geneve_list);
+
+	hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]);
+
+	return 0;
+}
+
+static void geneve_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+
+	if (!hlist_unhashed(&geneve->hlist))
+		hlist_del_rcu(&geneve->hlist);
+
+	list_del(&geneve->next);
+	unregister_netdevice_queue(dev, head);
+}
+
+static size_t geneve_get_size(const struct net_device *dev)
+{
+	return nla_total_size(sizeof(__u32)) +	/* IFLA_GENEVE_ID */
+		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
+		0;
+}
+
+static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	__u32 vni;
+
+	vni = (geneve->vni[0] << 16) | (geneve->vni[1] << 8) | geneve->vni[2];
+	if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
+		goto nla_put_failure;
+
+	if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
+			    geneve->remote.sin_addr.s_addr))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops geneve_link_ops __read_mostly = {
+	.kind		= "geneve",
+	.maxtype	= IFLA_GENEVE_MAX,
+	.policy		= geneve_policy,
+	.priv_size	= sizeof(struct geneve_dev),
+	.setup		= geneve_setup,
+	.validate	= geneve_validate,
+	.newlink	= geneve_newlink,
+	.dellink	= geneve_dellink,
+	.get_size	= geneve_get_size,
+	.fill_info	= geneve_fill_info,
+};
+
+static __net_init int geneve_init_net(struct net *net)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	unsigned int h;
+
+	INIT_LIST_HEAD(&gn->geneve_list);
+
+	for (h = 0; h < VNI_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&gn->vni_list[h]);
+
+	return 0;
+}
+
+static void __net_exit geneve_exit_net(struct net *net)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev *geneve, *next;
+	struct net_device *dev, *aux;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+
+	/* gather any geneve devices that were moved into this ns */
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &geneve_link_ops)
+			unregister_netdevice_queue(dev, &list);
+
+	/* now gather any other geneve devices that were created in this ns */
+	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
+		/* If geneve->dev is in the same netns, it was already added
+		 * to the list by the previous loop.
+		 */
+		if (!net_eq(dev_net(geneve->dev), net))
+			unregister_netdevice_queue(geneve->dev, &list);
+	}
+
+	/* unregister the devices gathered above */
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
+static struct pernet_operations geneve_net_ops = {
+	.init = geneve_init_net,
+	.exit = geneve_exit_net,
+	.id   = &geneve_net_id,
+	.size = sizeof(struct geneve_net),
+};
+
+static int __init geneve_init_module(void)
+{
+	int rc;
+
+	rc = register_pernet_subsys(&geneve_net_ops);
+	if (rc)
+		goto out1;
+
+	rc = rtnl_link_register(&geneve_link_ops);
+	if (rc)
+		goto out2;
+
+	return 0;
+out2:
+	unregister_pernet_subsys(&geneve_net_ops);
+out1:
+	return rc;
+}
+late_initcall(geneve_init_module);
+
+static void __exit geneve_cleanup_module(void)
+{
+	rtnl_link_unregister(&geneve_link_ops);
+	unregister_pernet_subsys(&geneve_net_ops);
+}
+module_exit(geneve_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_VERSION(GENEVE_NETDEV_VER);
+MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>");
+MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic");
+MODULE_ALIAS_RTNL_LINK("geneve");
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index d9cd19214b98..2ca17d1cff3f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -390,6 +390,15 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+/* GENEVE section */
+enum {
+	IFLA_GENEVE_UNSPEC,
+	IFLA_GENEVE_ID,
+	IFLA_GENEVE_REMOTE,
+	__IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
+
 /* Bonding section */
 
 enum {
-- 
2.1.0

[PATCH v3] iproute2: GENEVE support

[John W. Linville]

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
This includes the include/linux/if_link.h bits, that will need to be
dropped after iproute2 does the 4.1 update for that file...

v2 - spelling correction identified by Jesse Gross
v3 - repost with complete kernel series for clarity

 include/linux/if_link.h |   9 ++++
 ip/Makefile             |   3 +-
 ip/iplink.c             |   2 +-
 ip/iplink_geneve.c      | 122 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 134 insertions(+), 2 deletions(-)
 create mode 100644 ip/iplink_geneve.c

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 3d0d61317733..86058638c4d9 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -388,6 +388,15 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+/* GENEVE section */
+enum {
+	IFLA_GENEVE_UNSPEC,
+	IFLA_GENEVE_ID,
+	IFLA_GENEVE_REMOTE,
+	__IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
+
 /* Bonding section */
 
 enum {
diff --git a/ip/Makefile b/ip/Makefile
index 2c742f305fef..77653ecc5785 100644
--- a/ip/Makefile
+++ b/ip/Makefile
@@ -6,7 +6,8 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
     iplink_macvlan.o iplink_macvtap.o ipl2tp.o link_vti.o link_vti6.o \
     iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o \
     link_iptnl.o link_gre6.o iplink_bond.o iplink_bond_slave.o iplink_hsr.o \
-    iplink_bridge.o iplink_bridge_slave.o ipfou.o iplink_ipvlan.o
+    iplink_bridge.o iplink_bridge_slave.o ipfou.o iplink_ipvlan.o \
+    iplink_geneve.o
 
 RTMONOBJ=rtmon.o
 
diff --git a/ip/iplink.c b/ip/iplink.c
index bb437b96239a..39c76e778020 100644
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -93,7 +93,7 @@ void iplink_usage(void)
 		fprintf(stderr, "TYPE := { vlan | veth | vcan | dummy | ifb | macvlan | macvtap |\n");
 		fprintf(stderr, "          bridge | bond | ipoib | ip6tnl | ipip | sit | vxlan |\n");
 		fprintf(stderr, "          gre | gretap | ip6gre | ip6gretap | vti | nlmon |\n");
-		fprintf(stderr, "          bond_slave | ipvlan }\n");
+		fprintf(stderr, "          bond_slave | ipvlan | geneve }\n");
 	}
 	exit(-1);
 }
diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
new file mode 100644
index 000000000000..8b4cf57bdec2
--- /dev/null
+++ b/ip/iplink_geneve.c
@@ -0,0 +1,122 @@
+/*
+ * iplink_geneve.c	GENEVE device support
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Authors:     John W. Linville <linville@tuxdriver.com>
+ */
+
+#include <stdio.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+	fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
+	fprintf(f, "\n");
+	fprintf(f, "Where: VNI  := 0-16777215\n");
+	fprintf(f, "       ADDR := IP_ADDRESS\n");
+}
+
+static void explain(void)
+{
+	print_explain(stderr);
+}
+
+static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
+			  struct nlmsghdr *n)
+{
+	__u32 vni = 0;
+	int vni_set = 0;
+	__u32 daddr = 0;
+	struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
+
+
+	while (argc > 0) {
+		if (!matches(*argv, "id") ||
+		    !matches(*argv, "vni")) {
+			NEXT_ARG();
+			if (get_u32(&vni, *argv, 0) ||
+			    vni >= 1u << 24)
+				invarg("invalid id", *argv);
+			vni_set = 1;
+		} else if (!matches(*argv, "remote")) {
+			NEXT_ARG();
+			if (!inet_get_addr(*argv, &daddr, &daddr6)) {
+				fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+				return -1;
+			}
+			if (IN_MULTICAST(ntohl(daddr)))
+				invarg("invalid remote address", *argv);
+		} else if (matches(*argv, "help") == 0) {
+			explain();
+			return -1;
+		} else {
+			fprintf(stderr, "geneve: unknown command \"%s\"?\n", *argv);
+			explain();
+			return -1;
+		}
+		argc--, argv++;
+	}
+
+	if (!vni_set) {
+		fprintf(stderr, "geneve: missing virtual network identifier\n");
+		return -1;
+	}
+
+	if (!daddr) {
+		fprintf(stderr, "geneve: remote link partner not specified\n");
+		return -1;
+	}
+	if (memcmp(&daddr6, &in6addr_any, sizeof(daddr6)) != 0) {
+		fprintf(stderr, "geneve: remote link over IPv6 not supported\n");
+		return -1;
+	}
+
+	addattr32(n, 1024, IFLA_GENEVE_ID, vni);
+	if (daddr)
+		addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
+
+	return 0;
+}
+
+static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+	__u32 vni;
+	char s1[1024];
+
+	if (!tb)
+		return;
+
+	if (!tb[IFLA_GENEVE_ID] ||
+	    RTA_PAYLOAD(tb[IFLA_GENEVE_ID]) < sizeof(__u32))
+		return;
+
+	vni = rta_getattr_u32(tb[IFLA_GENEVE_ID]);
+	fprintf(f, "id %u ", vni);
+
+	if (tb[IFLA_GENEVE_REMOTE]) {
+		__be32 addr = rta_getattr_u32(tb[IFLA_GENEVE_REMOTE]);
+		if (addr)
+			fprintf(f, "remote %s ",
+				format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+	}
+}
+
+static void geneve_print_help(struct link_util *lu, int argc, char **argv,
+	FILE *f)
+{
+	print_explain(f);
+}
+
+struct link_util geneve_link_util = {
+	.id		= "geneve",
+	.maxattr	= IFLA_GENEVE_MAX,
+	.parse_opt	= geneve_parse_opt,
+	.print_opt	= geneve_print_opt,
+	.print_help	= geneve_print_help,
+};
-- 
2.1.0

Re: [PATCH v3] add GENEVE netdev tunnel driver

[David Miller]

From: "John W. Linville" <linville@tuxdriver.com>
Date: Wed, 13 May 2015 12:57:25 -0400

> This 5-patch kernel series adds a netdev implementation of a GENEVE
> tunnel driver, and the single iproute2 patch enables creation and
> such for those netdevs.  This makes use of the existing GENEVE
> infrastructure already used by the OVS code.  The net/ipv4/geneve.c
> file is renamed as net/ipv4/geneve_core.c as part of these changes.
 ...
> The overall structure of the GENEVE netdev driver is strongly
> influenced by the VXLAN netdev driver.  This is not surprising, as the
> two drivers are intended to serve similar purposes.  As development of
> the GENEVE driver continues, it is likely that those similarities will
> grow stronger.  This will include both simple configuration options
> (e.g. TOS and TTL settings) and new control plane support.
> 
> The current implementation is very simple, restricting itself to point
> to point links over IPv4.  This is due only to the simplicity of the
> implementation, and no such limit is inherent to GENEVE in any way.
> Support for IPv6 links and more sophisticated control plane options
> are predictable enhancements.
> 
> Using the included iproute2 patch, a GENEVE tunnel is created thusly:
> 
>         ip link add dev gnv0 type geneve remote 192.168.22.1 vni 1234
>         ip link set gnv0 up
>         ip addr add 10.1.1.1/24 dev gnv0
> 
> After a corresponding tunnel interface is created at the link partner,
> traffic should proceed as expected.
> 
> Please let me know if anyone has problems...thanks!

Looks good, series applied, thanks John!

Re: [PATCH v3] iproute2: GENEVE support

[Stephen Hemminger]

On Wed, 13 May 2015 13:02:28 -0400
"John W. Linville" <linville@tuxdriver.com> wrote:

> Signed-off-by: John W. Linville <linville@tuxdriver.com>

Applied.
Please send update to man pages as well.

Re: [PATCH v3] iproute2: GENEVE support

[John W. Linville]

On Thu, May 21, 2015 at 03:19:01PM -0700, Stephen Hemminger wrote:
> On Wed, 13 May 2015 13:02:28 -0400
> "John W. Linville" <linville@tuxdriver.com> wrote:
> 
> > Signed-off-by: John W. Linville <linville@tuxdriver.com>
> 
> Applied.
> Please send update to man pages as well.

Sorry for that oversight...coming right up!

John
-- 
John W. Linville		Someday the world will need a hero, and you
linville@tuxdriver.com			might be all we have.  Be ready.

[PATCH] iproute2: update ip-link.8 for geneve tunnels

[John W. Linville]

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 man/man8/ip-link.8.in | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index 714aab488d4a..8cac246d7296 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -76,7 +76,8 @@ ip-link \- network device configuration
 .BR vti " |"
 .BR nlmon " |"
 .BR ipvlan " |"
-.BR lowpan " ]"
+.BR lowpan " |"
+.BR geneve " ]"
 
 .ti -8
 .BR "ip link delete " {
@@ -247,6 +248,9 @@ Link types:
 .sp
 .BR lowpan
 - Interface for 6LoWPAN (IPv6) over IEEE 802.15.4 / Bluetooth
+.sp
+.BR geneve
+- GEneric NEtwork Virtualization Encapsulation
 .in -8
 
 .TP
@@ -594,6 +598,26 @@ the following additional arguments are supported:
 .BI  mode " MODE "
 - specifies the mode (datagram or connected) to use.
 
+.TP
+GENEVE Type Support
+For a link of type
+.I GENEVE
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BI type " geneve " id " ID " remote " IPADDR"
+
+.in +8
+.sp
+.BI  id " VNI "
+- specifies the Virtual Network Identifer to use.
+
+.sp
+.BI remote " IPADDR"
+- specifies the unicast destination IP address to use in outgoing packets.
+
+.in -8
+
 .SS ip link delete - delete virtual link
 
 .TP
-- 
2.1.0

[PATCH 0/2] iplink_geneve: add ttl and tos configuration bits

[John W. Linville]

This pair of patches add configuration of TTL and TOS settings for
GENEVE tunnel packets.  These settings follow the same conventions
as the VXLAN counterparts.

These patches include man page changes.  Therefore, they depend on
the preceding "iproute2: update ip-link.8 for geneve tunnels" patch,
posted to netdev on 22 May 2015.

Thanks,

John

[PATCH 1/2] iplink_geneve: add ttl configuration at link creation

[John W. Linville]

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/if_link.h |  1 +
 ip/iplink_geneve.c      | 23 ++++++++++++++++++++++-
 man/man8/ip-link.8.in   |  7 +++++++
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 7720ad34c6b3..2b5268531bef 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -393,6 +393,7 @@ enum {
 	IFLA_GENEVE_UNSPEC,
 	IFLA_GENEVE_ID,
 	IFLA_GENEVE_REMOTE,
+	IFLA_GENEVE_TTL,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
index 74703e1ee156..dff08a62d9a9 100644
--- a/ip/iplink_geneve.c
+++ b/ip/iplink_geneve.c
@@ -17,9 +17,11 @@
 static void print_explain(FILE *f)
 {
 	fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
+	fprintf(f, "                 [ ttl TTL ]\n");
 	fprintf(f, "\n");
 	fprintf(f, "Where: VNI  := 0-16777215\n");
 	fprintf(f, "       ADDR := IP_ADDRESS\n");
+	fprintf(f, "       TTL  := { 1..255 | inherit }\n");
 }
 
 static void explain(void)
@@ -34,7 +36,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 	int vni_set = 0;
 	__u32 daddr = 0;
 	struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
-
+	__u8 ttl = 0;
 
 	while (argc > 0) {
 		if (!matches(*argv, "id") ||
@@ -52,6 +54,18 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 			}
 			if (IN_MULTICAST(ntohl(daddr)))
 				invarg("invalid remote address", *argv);
+		} else if (!matches(*argv, "ttl") ||
+			   !matches(*argv, "hoplimit")) {
+			unsigned uval;
+
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0) {
+				if (get_unsigned(&uval, *argv, 0))
+					invarg("invalid TTL", *argv);
+				if (uval > 255)
+					invarg("TTL must be <= 255", *argv);
+				ttl = uval;
+			}
 		} else if (matches(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -80,6 +94,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 	addattr32(n, 1024, IFLA_GENEVE_ID, vni);
 	if (daddr)
 		addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
+	addattr8(n, 1024, IFLA_GENEVE_TTL, ttl);
 
 	return 0;
 }
@@ -105,6 +120,12 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 			fprintf(f, "remote %s ",
 				format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
 	}
+
+	if (tb[IFLA_GENEVE_TTL]) {
+		__u8 ttl = rta_getattr_u8(tb[IFLA_GENEVE_TTL]);
+		if (ttl)
+			fprintf(f, "ttl %d ", ttl);
+	}
 }
 
 static void geneve_print_help(struct link_util *lu, int argc, char **argv,
diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index 8cac246d7296..51d0c624a023 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -606,6 +606,9 @@ the following additional arguments are supported:
 
 .BI "ip link add " DEVICE
 .BI type " geneve " id " ID " remote " IPADDR"
+.R " [ "
+.BI ttl " TTL "
+.R " ]"
 
 .in +8
 .sp
@@ -616,6 +619,10 @@ the following additional arguments are supported:
 .BI remote " IPADDR"
 - specifies the unicast destination IP address to use in outgoing packets.
 
+.sp
+.BI ttl " TTL"
+- specifies the TTL value to use in outgoing packets.
+
 .in -8
 
 .SS ip link delete - delete virtual link
-- 
2.1.0

[PATCH 2/2] iplink_geneve: add tos configuration at link creation

[John W. Linville]

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/if_link.h |  1 +
 ip/iplink_geneve.c      | 26 +++++++++++++++++++++++++-
 man/man8/ip-link.8.in   |  6 ++++++
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 2b5268531bef..59b987407533 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -394,6 +394,7 @@ enum {
 	IFLA_GENEVE_ID,
 	IFLA_GENEVE_REMOTE,
 	IFLA_GENEVE_TTL,
+	IFLA_GENEVE_TOS,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
index dff08a62d9a9..331240a6a3d9 100644
--- a/ip/iplink_geneve.c
+++ b/ip/iplink_geneve.c
@@ -11,16 +11,18 @@
 
 #include <stdio.h>
 
+#include "rt_names.h"
 #include "utils.h"
 #include "ip_common.h"
 
 static void print_explain(FILE *f)
 {
 	fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
-	fprintf(f, "                 [ ttl TTL ]\n");
+	fprintf(f, "                 [ ttl TTL ] [ tos TOS ]\n");
 	fprintf(f, "\n");
 	fprintf(f, "Where: VNI  := 0-16777215\n");
 	fprintf(f, "       ADDR := IP_ADDRESS\n");
+	fprintf(f, "       TOS  := { NUMBER | inherit }\n");
 	fprintf(f, "       TTL  := { 1..255 | inherit }\n");
 }
 
@@ -37,6 +39,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 	__u32 daddr = 0;
 	struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
 	__u8 ttl = 0;
+	__u8 tos = 0;
 
 	while (argc > 0) {
 		if (!matches(*argv, "id") ||
@@ -66,6 +69,17 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 					invarg("TTL must be <= 255", *argv);
 				ttl = uval;
 			}
+		} else if (!matches(*argv, "tos") ||
+			   !matches(*argv, "dsfield")) {
+			__u32 uval;
+
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0) {
+				if (rtnl_dsfield_a2n(&uval, *argv))
+					invarg("bad TOS value", *argv);
+				tos = uval;
+			} else
+				tos = 1;
 		} else if (matches(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -95,6 +109,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
 	if (daddr)
 		addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
 	addattr8(n, 1024, IFLA_GENEVE_TTL, ttl);
+	addattr8(n, 1024, IFLA_GENEVE_TOS, tos);
 
 	return 0;
 }
@@ -103,6 +118,7 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 {
 	__u32 vni;
 	char s1[1024];
+	__u8 tos;
 
 	if (!tb)
 		return;
@@ -126,6 +142,14 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 		if (ttl)
 			fprintf(f, "ttl %d ", ttl);
 	}
+
+	if (tb[IFLA_GENEVE_TOS] &&
+	    (tos = rta_getattr_u8(tb[IFLA_GENEVE_TOS]))) {
+		if (tos == 1)
+			fprintf(f, "tos inherit ");
+		else
+			fprintf(f, "tos %#x ", tos);
+	}
 }
 
 static void geneve_print_help(struct link_util *lu, int argc, char **argv,
diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index 51d0c624a023..372e6c6faf29 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -608,6 +608,8 @@ the following additional arguments are supported:
 .BI type " geneve " id " ID " remote " IPADDR"
 .R " [ "
 .BI ttl " TTL "
+.R " ] [ "
+.BI tos " TOS "
 .R " ]"
 
 .in +8
@@ -623,6 +625,10 @@ the following additional arguments are supported:
 .BI ttl " TTL"
 - specifies the TTL value to use in outgoing packets.
 
+.sp
+.BI tos " TOS"
+- specifies the TOS value to use in outgoing packets.
+
 .in -8
 
 .SS ip link delete - delete virtual link
-- 
2.1.0

Re: [PATCH 1/2] iplink_geneve: add ttl configuration at link creation

[John W. Linville]

On Mon, Jun 15, 2015 at 02:37:15PM -0400, John W. Linville wrote:
> Signed-off-by: John W. Linville <linville@tuxdriver.com>
> ---
>  include/linux/if_link.h |  1 +

This includes the include/linux/if_link.h bits, that will need to be
dropped after iproute2 does the 4.1 update for that file.

>  ip/iplink_geneve.c      | 23 ++++++++++++++++++++++-
>  man/man8/ip-link.8.in   |  7 +++++++
>  3 files changed, 30 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
> index 7720ad34c6b3..2b5268531bef 100644
> --- a/include/linux/if_link.h
> +++ b/include/linux/if_link.h
> @@ -393,6 +393,7 @@ enum {
>  	IFLA_GENEVE_UNSPEC,
>  	IFLA_GENEVE_ID,
>  	IFLA_GENEVE_REMOTE,
> +	IFLA_GENEVE_TTL,
>  	__IFLA_GENEVE_MAX
>  };
>  #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
> diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
> index 74703e1ee156..dff08a62d9a9 100644
> --- a/ip/iplink_geneve.c
> +++ b/ip/iplink_geneve.c
> @@ -17,9 +17,11 @@
>  static void print_explain(FILE *f)
>  {
>  	fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
> +	fprintf(f, "                 [ ttl TTL ]\n");
>  	fprintf(f, "\n");
>  	fprintf(f, "Where: VNI  := 0-16777215\n");
>  	fprintf(f, "       ADDR := IP_ADDRESS\n");
> +	fprintf(f, "       TTL  := { 1..255 | inherit }\n");
>  }
>  
>  static void explain(void)
> @@ -34,7 +36,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  	int vni_set = 0;
>  	__u32 daddr = 0;
>  	struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
> -
> +	__u8 ttl = 0;
>  
>  	while (argc > 0) {
>  		if (!matches(*argv, "id") ||
> @@ -52,6 +54,18 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  			}
>  			if (IN_MULTICAST(ntohl(daddr)))
>  				invarg("invalid remote address", *argv);
> +		} else if (!matches(*argv, "ttl") ||
> +			   !matches(*argv, "hoplimit")) {
> +			unsigned uval;
> +
> +			NEXT_ARG();
> +			if (strcmp(*argv, "inherit") != 0) {
> +				if (get_unsigned(&uval, *argv, 0))
> +					invarg("invalid TTL", *argv);
> +				if (uval > 255)
> +					invarg("TTL must be <= 255", *argv);
> +				ttl = uval;
> +			}
>  		} else if (matches(*argv, "help") == 0) {
>  			explain();
>  			return -1;
> @@ -80,6 +94,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  	addattr32(n, 1024, IFLA_GENEVE_ID, vni);
>  	if (daddr)
>  		addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
> +	addattr8(n, 1024, IFLA_GENEVE_TTL, ttl);
>  
>  	return 0;
>  }
> @@ -105,6 +120,12 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
>  			fprintf(f, "remote %s ",
>  				format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
>  	}
> +
> +	if (tb[IFLA_GENEVE_TTL]) {
> +		__u8 ttl = rta_getattr_u8(tb[IFLA_GENEVE_TTL]);
> +		if (ttl)
> +			fprintf(f, "ttl %d ", ttl);
> +	}
>  }
>  
>  static void geneve_print_help(struct link_util *lu, int argc, char **argv,
> diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
> index 8cac246d7296..51d0c624a023 100644
> --- a/man/man8/ip-link.8.in
> +++ b/man/man8/ip-link.8.in
> @@ -606,6 +606,9 @@ the following additional arguments are supported:
>  
>  .BI "ip link add " DEVICE
>  .BI type " geneve " id " ID " remote " IPADDR"
> +.R " [ "
> +.BI ttl " TTL "
> +.R " ]"
>  
>  .in +8
>  .sp
> @@ -616,6 +619,10 @@ the following additional arguments are supported:
>  .BI remote " IPADDR"
>  - specifies the unicast destination IP address to use in outgoing packets.
>  
> +.sp
> +.BI ttl " TTL"
> +- specifies the TTL value to use in outgoing packets.
> +
>  .in -8
>  
>  .SS ip link delete - delete virtual link
> -- 
> 2.1.0
> 
> 

-- 
John W. Linville		Someday the world will need a hero, and you
linville@tuxdriver.com			might be all we have.  Be ready.

Re: [PATCH 2/2] iplink_geneve: add tos configuration at link creation

[John W. Linville]

On Mon, Jun 15, 2015 at 02:37:16PM -0400, John W. Linville wrote:
> Signed-off-by: John W. Linville <linville@tuxdriver.com>
> ---
>  include/linux/if_link.h |  1 +

This includes the include/linux/if_link.h bits, that will need to be
dropped after iproute2 does the 4.1 update for that file.

>  ip/iplink_geneve.c      | 26 +++++++++++++++++++++++++-
>  man/man8/ip-link.8.in   |  6 ++++++
>  3 files changed, 32 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
> index 2b5268531bef..59b987407533 100644
> --- a/include/linux/if_link.h
> +++ b/include/linux/if_link.h
> @@ -394,6 +394,7 @@ enum {
>  	IFLA_GENEVE_ID,
>  	IFLA_GENEVE_REMOTE,
>  	IFLA_GENEVE_TTL,
> +	IFLA_GENEVE_TOS,
>  	__IFLA_GENEVE_MAX
>  };
>  #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
> diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
> index dff08a62d9a9..331240a6a3d9 100644
> --- a/ip/iplink_geneve.c
> +++ b/ip/iplink_geneve.c
> @@ -11,16 +11,18 @@
>  
>  #include <stdio.h>
>  
> +#include "rt_names.h"
>  #include "utils.h"
>  #include "ip_common.h"
>  
>  static void print_explain(FILE *f)
>  {
>  	fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
> -	fprintf(f, "                 [ ttl TTL ]\n");
> +	fprintf(f, "                 [ ttl TTL ] [ tos TOS ]\n");
>  	fprintf(f, "\n");
>  	fprintf(f, "Where: VNI  := 0-16777215\n");
>  	fprintf(f, "       ADDR := IP_ADDRESS\n");
> +	fprintf(f, "       TOS  := { NUMBER | inherit }\n");
>  	fprintf(f, "       TTL  := { 1..255 | inherit }\n");
>  }
>  
> @@ -37,6 +39,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  	__u32 daddr = 0;
>  	struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
>  	__u8 ttl = 0;
> +	__u8 tos = 0;
>  
>  	while (argc > 0) {
>  		if (!matches(*argv, "id") ||
> @@ -66,6 +69,17 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  					invarg("TTL must be <= 255", *argv);
>  				ttl = uval;
>  			}
> +		} else if (!matches(*argv, "tos") ||
> +			   !matches(*argv, "dsfield")) {
> +			__u32 uval;
> +
> +			NEXT_ARG();
> +			if (strcmp(*argv, "inherit") != 0) {
> +				if (rtnl_dsfield_a2n(&uval, *argv))
> +					invarg("bad TOS value", *argv);
> +				tos = uval;
> +			} else
> +				tos = 1;
>  		} else if (matches(*argv, "help") == 0) {
>  			explain();
>  			return -1;
> @@ -95,6 +109,7 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
>  	if (daddr)
>  		addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
>  	addattr8(n, 1024, IFLA_GENEVE_TTL, ttl);
> +	addattr8(n, 1024, IFLA_GENEVE_TOS, tos);
>  
>  	return 0;
>  }
> @@ -103,6 +118,7 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
>  {
>  	__u32 vni;
>  	char s1[1024];
> +	__u8 tos;
>  
>  	if (!tb)
>  		return;
> @@ -126,6 +142,14 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
>  		if (ttl)
>  			fprintf(f, "ttl %d ", ttl);
>  	}
> +
> +	if (tb[IFLA_GENEVE_TOS] &&
> +	    (tos = rta_getattr_u8(tb[IFLA_GENEVE_TOS]))) {
> +		if (tos == 1)
> +			fprintf(f, "tos inherit ");
> +		else
> +			fprintf(f, "tos %#x ", tos);
> +	}
>  }
>  
>  static void geneve_print_help(struct link_util *lu, int argc, char **argv,
> diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
> index 51d0c624a023..372e6c6faf29 100644
> --- a/man/man8/ip-link.8.in
> +++ b/man/man8/ip-link.8.in
> @@ -608,6 +608,8 @@ the following additional arguments are supported:
>  .BI type " geneve " id " ID " remote " IPADDR"
>  .R " [ "
>  .BI ttl " TTL "
> +.R " ] [ "
> +.BI tos " TOS "
>  .R " ]"
>  
>  .in +8
> @@ -623,6 +625,10 @@ the following additional arguments are supported:
>  .BI ttl " TTL"
>  - specifies the TTL value to use in outgoing packets.
>  
> +.sp
> +.BI tos " TOS"
> +- specifies the TOS value to use in outgoing packets.
> +
>  .in -8
>  
>  .SS ip link delete - delete virtual link
> -- 
> 2.1.0
> 
> 

-- 
John W. Linville		Someday the world will need a hero, and you
linville@tuxdriver.com			might be all we have.  Be ready.