Initial commit: Linux kernel 4.19 for Unplugged OS

net/openvswitch/Kconfig

@@ -0,0 +1,75 @@
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+	tristate "Open vSwitch"
+	depends on INET
+	depends on !NF_CONNTRACK || \
+		   (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \
+				     (!NF_NAT || NF_NAT) && \
+				     (!NF_NAT_IPV4 || NF_NAT_IPV4) && \
+				     (!NF_NAT_IPV6 || NF_NAT_IPV6) && \
+				     (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
+	select LIBCRC32C
+	select MPLS
+	select NET_MPLS_GSO
+	select DST_CACHE
+	select NET_NSH
+	---help---
+	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
+	  environments.  In addition to supporting a variety of features
+	  expected in a traditional hardware switch, it enables fine-grained
+	  programmatic extension and flow-based control of the network.  This
+	  control is useful in a wide variety of applications but is
+	  particularly important in multi-server virtualization deployments,
+	  which are often characterized by highly dynamic endpoints and the
+	  need to maintain logical abstractions for multiple tenants.
+
+	  The Open vSwitch datapath provides an in-kernel fast path for packet
+	  forwarding.  It is complemented by a userspace daemon, ovs-vswitchd,
+	  which is able to accept configuration from a variety of sources and
+	  translate it into packet processing rules.
+
+	  See http://openvswitch.org for more information and userspace
+	  utilities.
+
+	  To compile this code as a module, choose M here: the module will be
+	  called openvswitch.
+
+	  If unsure, say N.
+
+config OPENVSWITCH_GRE
+	tristate "Open vSwitch GRE tunneling support"
+	depends on OPENVSWITCH
+	depends on NET_IPGRE
+	default OPENVSWITCH
+	---help---
+	  If you say Y here, then the Open vSwitch will be able create GRE
+	  vport.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.
+
+config OPENVSWITCH_VXLAN
+	tristate "Open vSwitch VXLAN tunneling support"
+	depends on OPENVSWITCH
+	depends on VXLAN
+	default OPENVSWITCH
+	---help---
+	  If you say Y here, then the Open vSwitch will be able create vxlan vport.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+	tristate "Open vSwitch Geneve tunneling support"
+	depends on OPENVSWITCH
+	depends on GENEVE
+	default OPENVSWITCH
+	---help---
+	  If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+	  Say N to exclude this support and reduce the binary size.

net/openvswitch/Makefile

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+	actions.o \
+	datapath.o \
+	dp_notify.o \
+	flow.o \
+	flow_netlink.o \
+	flow_table.o \
+	meter.o \
+	vport.o \
+	vport-internal_dev.o \
+	vport-netdev.o
+
+ifneq ($(CONFIG_NF_CONNTRACK),)
+openvswitch-y += conntrack.o
+endif
+
+obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o
+obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o
+obj-$(CONFIG_OPENVSWITCH_GRE)	+= vport-gre.o

net/openvswitch/conntrack.h

@@ -0,0 +1,112 @@
+/*
+ * Copyright (c) 2015 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef OVS_CONNTRACK_H
+#define OVS_CONNTRACK_H 1
+
+#include "flow.h"
+
+struct ovs_conntrack_info;
+struct ovs_ct_limit_info;
+enum ovs_key_attr;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+int ovs_ct_init(struct net *);
+void ovs_ct_exit(struct net *);
+bool ovs_ct_verify(struct net *, enum ovs_key_attr attr);
+int ovs_ct_copy_action(struct net *, const struct nlattr *,
+		       const struct sw_flow_key *, struct sw_flow_actions **,
+		       bool log);
+int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
+
+int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
+		   const struct ovs_conntrack_info *);
+int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
+
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_ct_put_key(const struct sw_flow_key *swkey,
+		   const struct sw_flow_key *output, struct sk_buff *skb);
+void ovs_ct_free_action(const struct nlattr *a);
+
+#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \
+			   OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \
+			   OVS_CS_F_INVALID | OVS_CS_F_TRACKED | \
+			   OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT)
+#else
+#include <linux/errno.h>
+
+static inline int ovs_ct_init(struct net *net) { return 0; }
+
+static inline void ovs_ct_exit(struct net *net) { }
+
+static inline bool ovs_ct_verify(struct net *net, int attr)
+{
+	return false;
+}
+
+static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla,
+				     const struct sw_flow_key *key,
+				     struct sw_flow_actions **acts, bool log)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info,
+					struct sk_buff *skb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
+				 struct sw_flow_key *key,
+				 const struct ovs_conntrack_info *info)
+{
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_clear(struct sk_buff *skb,
+			       struct sw_flow_key *key)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ovs_ct_fill_key(const struct sk_buff *skb,
+				   struct sw_flow_key *key)
+{
+	key->ct_state = 0;
+	key->ct_zone = 0;
+	key->ct.mark = 0;
+	memset(&key->ct.labels, 0, sizeof(key->ct.labels));
+	/* Clear 'ct_orig_proto' to mark the non-existence of original
+	 * direction key fields.
+	 */
+	key->ct_orig_proto = 0;
+}
+
+static inline int ovs_ct_put_key(const struct sw_flow_key *swkey,
+				 const struct sw_flow_key *output,
+				 struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline void ovs_ct_free_action(const struct nlattr *a) { }
+
+#define CT_SUPPORTED_MASK 0
+#endif /* CONFIG_NF_CONNTRACK */
+
+#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+extern struct genl_family dp_ct_limit_genl_family;
+#endif
+#endif /* ovs_conntrack.h */

net/openvswitch/datapath.h

@@ -0,0 +1,261 @@
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef DATAPATH_H
+#define DATAPATH_H 1
+
+#include <asm/page.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+#include <net/ip_tunnels.h>
+
+#include "conntrack.h"
+#include "flow.h"
+#include "flow_table.h"
+#include "meter.h"
+#include "vport-internal_dev.h"
+
+#define DP_MAX_PORTS           USHRT_MAX
+#define DP_VPORT_HASH_BUCKETS  1024
+
+/**
+ * struct dp_stats_percpu - per-cpu packet processing statistics for a given
+ * datapath.
+ * @n_hit: Number of received packets for which a matching flow was found in
+ * the flow table.
+ * @n_miss: Number of received packets that had no matching flow in the flow
+ * table.  The sum of @n_hit and @n_miss is the number of packets that have
+ * been received by the datapath.
+ * @n_lost: Number of received packets that had no matching flow in the flow
+ * table that could not be sent to userspace (normally due to an overflow in
+ * one of the datapath's queues).
+ * @n_mask_hit: Number of masks looked up for flow match.
+ *   @n_mask_hit / (@n_hit + @n_missed)  will be the average masks looked
+ *   up per packet.
+ */
+struct dp_stats_percpu {
+	u64 n_hit;
+	u64 n_missed;
+	u64 n_lost;
+	u64 n_mask_hit;
+	struct u64_stats_sync syncp;
+};
+
+/**
+ * struct datapath - datapath for flow-based packet switching
+ * @rcu: RCU callback head for deferred destruction.
+ * @list_node: Element in global 'dps' list.
+ * @table: flow table.
+ * @ports: Hash table for ports.  %OVSP_LOCAL port always exists.  Protected by
+ * ovs_mutex and RCU.
+ * @stats_percpu: Per-CPU datapath statistics.
+ * @net: Reference to net namespace.
+ * @max_headroom: the maximum headroom of all vports in this datapath; it will
+ * be used by all the internal vports in this dp.
+ *
+ * Context: See the comment on locking at the top of datapath.c for additional
+ * locking information.
+ */
+struct datapath {
+	struct rcu_head rcu;
+	struct list_head list_node;
+
+	/* Flow table. */
+	struct flow_table table;
+
+	/* Switch ports. */
+	struct hlist_head *ports;
+
+	/* Stats. */
+	struct dp_stats_percpu __percpu *stats_percpu;
+
+	/* Network namespace ref. */
+	possible_net_t net;
+
+	u32 user_features;
+
+	u32 max_headroom;
+
+	/* Switch meters. */
+	struct hlist_head *meters;
+};
+
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @input_vport: The original vport packet came in on. This value is cached
+ * when a packet is received by OVS.
+ * @mru: The maximum received fragement size; 0 if the packet is not
+ * fragmented.
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
+ * @cutlen: The number of bytes from the packet end to be removed.
+ */
+struct ovs_skb_cb {
+	struct vport		*input_vport;
+	u16			mru;
+	u16			acts_origlen;
+	u32			cutlen;
+};
+#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
+
+/**
+ * struct dp_upcall - metadata to include with a packet to send to userspace
+ * @cmd: One of %OVS_PACKET_CMD_*.
+ * @userdata: If nonnull, its variable-length value is passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @portid: Netlink portid to which packet should be sent.  If @portid is 0
+ * then no packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
+ * @mru: If not zero, Maximum received IP fragment size.
+ */
+struct dp_upcall_info {
+	struct ip_tunnel_info *egress_tun_info;
+	const struct nlattr *userdata;
+	const struct nlattr *actions;
+	int actions_len;
+	u32 portid;
+	u8 cmd;
+	u16 mru;
+};
+
+/**
+ * struct ovs_net - Per net-namespace data for ovs.
+ * @dps: List of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ */
+struct ovs_net {
+	struct list_head dps;
+	struct work_struct dp_notify_work;
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+	struct ovs_ct_limit_info *ct_limit_info;
+#endif
+
+	/* Module reference for configuring conntrack. */
+	bool xt_label;
+};
+
+extern unsigned int ovs_net_id;
+void ovs_lock(void);
+void ovs_unlock(void);
+
+#ifdef CONFIG_LOCKDEP
+int lockdep_ovsl_is_held(void);
+#else
+#define lockdep_ovsl_is_held()	1
+#endif
+
+#define ASSERT_OVSL()		WARN_ON(!lockdep_ovsl_is_held())
+#define ovsl_dereference(p)					\
+	rcu_dereference_protected(p, lockdep_ovsl_is_held())
+#define rcu_dereference_ovsl(p)					\
+	rcu_dereference_check(p, lockdep_ovsl_is_held())
+
+static inline struct net *ovs_dp_get_net(const struct datapath *dp)
+{
+	return read_pnet(&dp->net);
+}
+
+static inline void ovs_dp_set_net(struct datapath *dp, struct net *net)
+{
+	write_pnet(&dp->net, net);
+}
+
+struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no);
+
+static inline struct vport *ovs_vport_rcu(const struct datapath *dp, int port_no)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_ovsl_rcu(const struct datapath *dp, int port_no)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_no)
+{
+	ASSERT_OVSL();
+	return ovs_lookup_vport(dp, port_no);
+}
+
+/* Must be called with rcu_read_lock. */
+static inline struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
+{
+	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
+
+	if (dev) {
+		struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+		if (vport)
+			return vport->dp;
+	}
+
+	return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+	struct datapath *dp;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	rcu_read_lock();
+	dp = get_dp_rcu(net, dp_ifindex);
+	rcu_read_unlock();
+
+	return dp;
+}
+
+extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_family dp_vport_genl_family;
+
+void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
+void ovs_dp_detach_port(struct vport *);
+int ovs_dp_upcall(struct datapath *, struct sk_buff *,
+		  const struct sw_flow_key *, const struct dp_upcall_info *,
+		  uint32_t cutlen);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+					 u32 portid, u32 seq, u8 cmd);
+
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct sw_flow_actions *, struct sw_flow_key *);
+
+void ovs_dp_notify_wq(struct work_struct *work);
+
+int action_fifos_init(void);
+void action_fifos_exit(void);
+
+/* 'KEY' must not have any bits set outside of the 'MASK' */
+#define OVS_MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
+#define OVS_SET_MASKED(OLD, KEY, MASK) ((OLD) = OVS_MASKED(OLD, KEY, MASK))
+
+#define OVS_NLERR(logging_allowed, fmt, ...)			\
+do {								\
+	if (logging_allowed && net_ratelimit())			\
+		pr_info("netlink: " fmt "\n", ##__VA_ARGS__);	\
+} while (0)
+#endif /* datapath.h */

net/openvswitch/dp_notify.c

@@ -0,0 +1,99 @@
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static void dp_detach_port_notify(struct vport *vport)
+{
+	struct sk_buff *notify;
+	struct datapath *dp;
+
+	dp = vport->dp;
+	notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp),
+					  0, 0, OVS_VPORT_CMD_DEL);
+	ovs_dp_detach_port(vport);
+	if (IS_ERR(notify)) {
+		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
+			     0, PTR_ERR(notify));
+		return;
+	}
+
+	genlmsg_multicast_netns(&dp_vport_genl_family,
+				ovs_dp_get_net(dp), notify, 0,
+				0, GFP_KERNEL);
+}
+
+void ovs_dp_notify_wq(struct work_struct *work)
+{
+	struct ovs_net *ovs_net = container_of(work, struct ovs_net, dp_notify_work);
+	struct datapath *dp;
+
+	ovs_lock();
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
+		int i;
+
+		for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+			struct vport *vport;
+			struct hlist_node *n;
+
+			hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
+				if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
+					continue;
+
+				if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
+					dp_detach_port_notify(vport);
+			}
+		}
+	}
+	ovs_unlock();
+}
+
+static int dp_device_event(struct notifier_block *unused, unsigned long event,
+			   void *ptr)
+{
+	struct ovs_net *ovs_net;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct vport *vport = NULL;
+
+	if (!ovs_is_internal_dev(dev))
+		vport = ovs_netdev_get_vport(dev);
+
+	if (!vport)
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_UNREGISTER) {
+		/* upper_dev_unlink and decrement promisc immediately */
+		ovs_netdev_detach_dev(vport);
+
+		/* schedule vport destroy, dev_put and genl notification */
+		ovs_net = net_generic(dev_net(dev), ovs_net_id);
+		queue_work(system_wq, &ovs_net->dp_notify_work);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ovs_dp_device_notifier = {
+	.notifier_call = dp_device_event
+};

net/openvswitch/flow.c

@@ -0,0 +1,918 @@
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/uaccess.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/llc_pdu.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.h>
+#include <linux/cpumask.h>
+#include <linux/if_arp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/mpls.h>
+#include <linux/sctp.h>
+#include <linux/smp.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/rculist.h>
+#include <net/ip.h>
+#include <net/ip_tunnels.h>
+#include <net/ipv6.h>
+#include <net/mpls.h>
+#include <net/ndisc.h>
+#include <net/nsh.h>
+
+#include "conntrack.h"
+#include "datapath.h"
+#include "flow.h"
+#include "flow_netlink.h"
+#include "vport.h"
+
+u64 ovs_flow_used_time(unsigned long flow_jiffies)
+{
+	struct timespec64 cur_ts;
+	u64 cur_ms, idle_ms;
+
+	ktime_get_ts64(&cur_ts);
+	idle_ms = jiffies_to_msecs(jiffies - flow_jiffies);
+	cur_ms = (u64)(u32)cur_ts.tv_sec * MSEC_PER_SEC +
+		 cur_ts.tv_nsec / NSEC_PER_MSEC;
+
+	return cur_ms - idle_ms;
+}
+
+#define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
+
+void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
+			   const struct sk_buff *skb)
+{
+	struct flow_stats *stats;
+	unsigned int cpu = smp_processor_id();
+	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
+
+	stats = rcu_dereference(flow->stats[cpu]);
+
+	/* Check if already have CPU-specific stats. */
+	if (likely(stats)) {
+		spin_lock(&stats->lock);
+		/* Mark if we write on the pre-allocated stats. */
+		if (cpu == 0 && unlikely(flow->stats_last_writer != cpu))
+			flow->stats_last_writer = cpu;
+	} else {
+		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+		spin_lock(&stats->lock);
+
+		/* If the current CPU is the only writer on the
+		 * pre-allocated stats keep using them.
+		 */
+		if (unlikely(flow->stats_last_writer != cpu)) {
+			/* A previous locker may have already allocated the
+			 * stats, so we need to check again.  If CPU-specific
+			 * stats were already allocated, we update the pre-
+			 * allocated stats as we have already locked them.
+			 */
+			if (likely(flow->stats_last_writer != -1) &&
+			    likely(!rcu_access_pointer(flow->stats[cpu]))) {
+				/* Try to allocate CPU-specific stats. */
+				struct flow_stats *new_stats;
+
+				new_stats =
+					kmem_cache_alloc_node(flow_stats_cache,
+							      GFP_NOWAIT |
+							      __GFP_THISNODE |
+							      __GFP_NOWARN |
+							      __GFP_NOMEMALLOC,
+							      numa_node_id());
+				if (likely(new_stats)) {
+					new_stats->used = jiffies;
+					new_stats->packet_count = 1;
+					new_stats->byte_count = len;
+					new_stats->tcp_flags = tcp_flags;
+					spin_lock_init(&new_stats->lock);
+
+					rcu_assign_pointer(flow->stats[cpu],
+							   new_stats);
+					cpumask_set_cpu(cpu, &flow->cpu_used_mask);
+					goto unlock;
+				}
+			}
+			flow->stats_last_writer = cpu;
+		}
+	}
+
+	stats->used = jiffies;
+	stats->packet_count++;
+	stats->byte_count += len;
+	stats->tcp_flags |= tcp_flags;
+unlock:
+	spin_unlock(&stats->lock);
+}
+
+/* Must be called with rcu_read_lock or ovs_mutex. */
+void ovs_flow_stats_get(const struct sw_flow *flow,
+			struct ovs_flow_stats *ovs_stats,
+			unsigned long *used, __be16 *tcp_flags)
+{
+	int cpu;
+
+	*used = 0;
+	*tcp_flags = 0;
+	memset(ovs_stats, 0, sizeof(*ovs_stats));
+
+	/* We open code this to make sure cpu 0 is always considered */
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
+		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
+
+		if (stats) {
+			/* Local CPU may write on non-local stats, so we must
+			 * block bottom-halves here.
+			 */
+			spin_lock_bh(&stats->lock);
+			if (!*used || time_after(stats->used, *used))
+				*used = stats->used;
+			*tcp_flags |= stats->tcp_flags;
+			ovs_stats->n_packets += stats->packet_count;
+			ovs_stats->n_bytes += stats->byte_count;
+			spin_unlock_bh(&stats->lock);
+		}
+	}
+}
+
+/* Called with ovs_mutex. */
+void ovs_flow_stats_clear(struct sw_flow *flow)
+{
+	int cpu;
+
+	/* We open code this to make sure cpu 0 is always considered */
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
+		struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
+
+		if (stats) {
+			spin_lock_bh(&stats->lock);
+			stats->used = 0;
+			stats->packet_count = 0;
+			stats->byte_count = 0;
+			stats->tcp_flags = 0;
+			spin_unlock_bh(&stats->lock);
+		}
+	}
+}
+
+static int check_header(struct sk_buff *skb, int len)
+{
+	if (unlikely(skb->len < len))
+		return -EINVAL;
+	if (unlikely(!pskb_may_pull(skb, len)))
+		return -ENOMEM;
+	return 0;
+}
+
+static bool arphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_network_offset(skb) +
+				  sizeof(struct arp_eth_header));
+}
+
+static int check_iphdr(struct sk_buff *skb)
+{
+	unsigned int nh_ofs = skb_network_offset(skb);
+	unsigned int ip_len;
+	int err;
+
+	err = check_header(skb, nh_ofs + sizeof(struct iphdr));
+	if (unlikely(err))
+		return err;
+
+	ip_len = ip_hdrlen(skb);
+	if (unlikely(ip_len < sizeof(struct iphdr) ||
+		     skb->len < nh_ofs + ip_len))
+		return -EINVAL;
+
+	skb_set_transport_header(skb, nh_ofs + ip_len);
+	return 0;
+}
+
+static bool tcphdr_ok(struct sk_buff *skb)
+{
+	int th_ofs = skb_transport_offset(skb);
+	int tcp_len;
+
+	if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr))))
+		return false;
+
+	tcp_len = tcp_hdrlen(skb);
+	if (unlikely(tcp_len < sizeof(struct tcphdr) ||
+		     skb->len < th_ofs + tcp_len))
+		return false;
+
+	return true;
+}
+
+static bool udphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct udphdr));
+}
+
+static bool sctphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct sctphdr));
+}
+
+static bool icmphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct icmphdr));
+}
+
+static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	unsigned int nh_ofs = skb_network_offset(skb);
+	unsigned int nh_len;
+	int payload_ofs;
+	struct ipv6hdr *nh;
+	uint8_t nexthdr;
+	__be16 frag_off;
+	int err;
+
+	err = check_header(skb, nh_ofs + sizeof(*nh));
+	if (unlikely(err))
+		return err;
+
+	nh = ipv6_hdr(skb);
+	nexthdr = nh->nexthdr;
+	payload_ofs = (u8 *)(nh + 1) - skb->data;
+
+	key->ip.proto = NEXTHDR_NONE;
+	key->ip.tos = ipv6_get_dsfield(nh);
+	key->ip.ttl = nh->hop_limit;
+	key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+	key->ipv6.addr.src = nh->saddr;
+	key->ipv6.addr.dst = nh->daddr;
+
+	payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off);
+
+	if (frag_off) {
+		if (frag_off & htons(~0x7))
+			key->ip.frag = OVS_FRAG_TYPE_LATER;
+		else
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+	} else {
+		key->ip.frag = OVS_FRAG_TYPE_NONE;
+	}
+
+	/* Delayed handling of error in ipv6_skip_exthdr() as it
+	 * always sets frag_off to a valid value which may be
+	 * used to set key->ip.frag above.
+	 */
+	if (unlikely(payload_ofs < 0))
+		return -EPROTO;
+
+	nh_len = payload_ofs - nh_ofs;
+	skb_set_transport_header(skb, nh_ofs + nh_len);
+	key->ip.proto = nexthdr;
+	return nh_len;
+}
+
+static bool icmp6hdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct icmp6hdr));
+}
+
+/**
+ * Parse vlan tag from vlan header.
+ * Returns ERROR on memory error.
+ * Returns 0 if it encounters a non-vlan or incomplete packet.
+ * Returns 1 after successfully parsing vlan tag.
+ */
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+			  bool untag_vlan)
+{
+	struct vlan_head *vh = (struct vlan_head *)skb->data;
+
+	if (likely(!eth_type_vlan(vh->tpid)))
+		return 0;
+
+	if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16)))
+		return 0;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) +
+				 sizeof(__be16))))
+		return -ENOMEM;
+
+	vh = (struct vlan_head *)skb->data;
+	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
+	key_vh->tpid = vh->tpid;
+
+	if (unlikely(untag_vlan)) {
+		int offset = skb->data - skb_mac_header(skb);
+		u16 tci;
+		int err;
+
+		__skb_push(skb, offset);
+		err = __skb_vlan_pop(skb, &tci);
+		__skb_pull(skb, offset);
+		if (err)
+			return err;
+		__vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+	} else {
+		__skb_pull(skb, sizeof(struct vlan_head));
+	}
+	return 1;
+}
+
+static void clear_vlan(struct sw_flow_key *key)
+{
+	key->eth.vlan.tci = 0;
+	key->eth.vlan.tpid = 0;
+	key->eth.cvlan.tci = 0;
+	key->eth.cvlan.tpid = 0;
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int res;
+
+	if (skb_vlan_tag_present(skb)) {
+		key->eth.vlan.tci = htons(skb->vlan_tci);
+		key->eth.vlan.tpid = skb->vlan_proto;
+	} else {
+		/* Parse outer vlan tag in the non-accelerated case. */
+		res = parse_vlan_tag(skb, &key->eth.vlan, true);
+		if (res <= 0)
+			return res;
+	}
+
+	/* Parse inner vlan tag. */
+	res = parse_vlan_tag(skb, &key->eth.cvlan, false);
+	if (res <= 0)
+		return res;
+
+	return 0;
+}
+
+static __be16 parse_ethertype(struct sk_buff *skb)
+{
+	struct llc_snap_hdr {
+		u8  dsap;  /* Always 0xAA */
+		u8  ssap;  /* Always 0xAA */
+		u8  ctrl;
+		u8  oui[3];
+		__be16 ethertype;
+	};
+	struct llc_snap_hdr *llc;
+	__be16 proto;
+
+	proto = *(__be16 *) skb->data;
+	__skb_pull(skb, sizeof(__be16));
+
+	if (eth_proto_is_802_3(proto))
+		return proto;
+
+	if (skb->len < sizeof(struct llc_snap_hdr))
+		return htons(ETH_P_802_2);
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr))))
+		return htons(0);
+
+	llc = (struct llc_snap_hdr *) skb->data;
+	if (llc->dsap != LLC_SAP_SNAP ||
+	    llc->ssap != LLC_SAP_SNAP ||
+	    (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0)
+		return htons(ETH_P_802_2);
+
+	__skb_pull(skb, sizeof(struct llc_snap_hdr));
+
+	if (eth_proto_is_802_3(llc->ethertype))
+		return llc->ethertype;
+
+	return htons(ETH_P_802_2);
+}
+
+static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
+			int nh_len)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+
+	/* The ICMPv6 type and code fields use the 16-bit transport port
+	 * fields, so we need to store them in 16-bit network byte order.
+	 */
+	key->tp.src = htons(icmp->icmp6_type);
+	key->tp.dst = htons(icmp->icmp6_code);
+	memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd));
+
+	if (icmp->icmp6_code == 0 &&
+	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+	     icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+		int icmp_len = skb->len - skb_transport_offset(skb);
+		struct nd_msg *nd;
+		int offset;
+
+		/* In order to process neighbor discovery options, we need the
+		 * entire packet.
+		 */
+		if (unlikely(icmp_len < sizeof(*nd)))
+			return 0;
+
+		if (unlikely(skb_linearize(skb)))
+			return -ENOMEM;
+
+		nd = (struct nd_msg *)skb_transport_header(skb);
+		key->ipv6.nd.target = nd->target;
+
+		icmp_len -= sizeof(*nd);
+		offset = 0;
+		while (icmp_len >= 8) {
+			struct nd_opt_hdr *nd_opt =
+				 (struct nd_opt_hdr *)(nd->opt + offset);
+			int opt_len = nd_opt->nd_opt_len * 8;
+
+			if (unlikely(!opt_len || opt_len > icmp_len))
+				return 0;
+
+			/* Store the link layer address if the appropriate
+			 * option is provided.  It is considered an error if
+			 * the same link layer option is specified twice.
+			 */
+			if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR
+			    && opt_len == 8) {
+				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
+					goto invalid;
+				ether_addr_copy(key->ipv6.nd.sll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
+			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
+				   && opt_len == 8) {
+				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
+					goto invalid;
+				ether_addr_copy(key->ipv6.nd.tll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
+			}
+
+			icmp_len -= opt_len;
+			offset += opt_len;
+		}
+	}
+
+	return 0;
+
+invalid:
+	memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target));
+	memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll));
+	memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll));
+
+	return 0;
+}
+
+static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct nshhdr *nh;
+	unsigned int nh_ofs = skb_network_offset(skb);
+	u8 version, length;
+	int err;
+
+	err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN);
+	if (unlikely(err))
+		return err;
+
+	nh = nsh_hdr(skb);
+	version = nsh_get_ver(nh);
+	length = nsh_hdr_len(nh);
+
+	if (version != 0)
+		return -EINVAL;
+
+	err = check_header(skb, nh_ofs + length);
+	if (unlikely(err))
+		return err;
+
+	nh = nsh_hdr(skb);
+	key->nsh.base.flags = nsh_get_flags(nh);
+	key->nsh.base.ttl = nsh_get_ttl(nh);
+	key->nsh.base.mdtype = nh->mdtype;
+	key->nsh.base.np = nh->np;
+	key->nsh.base.path_hdr = nh->path_hdr;
+	switch (key->nsh.base.mdtype) {
+	case NSH_M_TYPE1:
+		if (length != NSH_M_TYPE1_LEN)
+			return -EINVAL;
+		memcpy(key->nsh.context, nh->md1.context,
+		       sizeof(nh->md1));
+		break;
+	case NSH_M_TYPE2:
+		memset(key->nsh.context, 0,
+		       sizeof(nh->md1));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * key_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @key: output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Returns 0 if successful, otherwise a negative errno value.
+ *
+ * Initializes @skb header fields as follows:
+ *
+ *    - skb->mac_header: the L2 header.
+ *
+ *    - skb->network_header: just past the L2 header, or just past the
+ *      VLAN header, to the first byte of the L2 payload.
+ *
+ *    - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
+ *      on output, then just past the IP header, if one is present and
+ *      of a correct length, otherwise the same as skb->network_header.
+ *      For other key->eth.type values it is left untouched.
+ *
+ *    - skb->protocol: the type of the data starting at skb->network_header.
+ *      Equals to key->eth.type.
+ */
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int error;
+	struct ethhdr *eth;
+
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
+	skb_reset_mac_header(skb);
+
+	/* Link layer. */
+	clear_vlan(key);
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+		if (unlikely(eth_type_vlan(skb->protocol)))
+			return -EINVAL;
+
+		skb_reset_network_header(skb);
+		key->eth.type = skb->protocol;
+	} else {
+		eth = eth_hdr(skb);
+		ether_addr_copy(key->eth.src, eth->h_source);
+		ether_addr_copy(key->eth.dst, eth->h_dest);
+
+		__skb_pull(skb, 2 * ETH_ALEN);
+		/* We are going to push all headers that we pull, so no need to
+		* update skb->csum here.
+		*/
+
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+		key->eth.type = parse_ethertype(skb);
+		if (unlikely(key->eth.type == htons(0)))
+			return -ENOMEM;
+
+		/* Multiple tagged packets need to retain TPID to satisfy
+		 * skb_vlan_pop(), which will later shift the ethertype into
+		 * skb->protocol.
+		 */
+		if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT))
+			skb->protocol = key->eth.cvlan.tpid;
+		else
+			skb->protocol = key->eth.type;
+
+		skb_reset_network_header(skb);
+		__skb_push(skb, skb->data - skb_mac_header(skb));
+	}
+	skb_reset_mac_len(skb);
+
+	/* Network layer. */
+	if (key->eth.type == htons(ETH_P_IP)) {
+		struct iphdr *nh;
+		__be16 offset;
+
+		error = check_iphdr(skb);
+		if (unlikely(error)) {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv4, 0, sizeof(key->ipv4));
+			if (error == -EINVAL) {
+				skb->transport_header = skb->network_header;
+				error = 0;
+			}
+			return error;
+		}
+
+		nh = ip_hdr(skb);
+		key->ipv4.addr.src = nh->saddr;
+		key->ipv4.addr.dst = nh->daddr;
+
+		key->ip.proto = nh->protocol;
+		key->ip.tos = nh->tos;
+		key->ip.ttl = nh->ttl;
+
+		offset = nh->frag_off & htons(IP_OFFSET);
+		if (offset) {
+			key->ip.frag = OVS_FRAG_TYPE_LATER;
+			return 0;
+		}
+		if (nh->frag_off & htons(IP_MF) ||
+			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+		else
+			key->ip.frag = OVS_FRAG_TYPE_NONE;
+
+		/* Transport layer. */
+		if (key->ip.proto == IPPROTO_TCP) {
+			if (tcphdr_ok(skb)) {
+				struct tcphdr *tcp = tcp_hdr(skb);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+
+		} else if (key->ip.proto == IPPROTO_UDP) {
+			if (udphdr_ok(skb)) {
+				struct udphdr *udp = udp_hdr(skb);
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		} else if (key->ip.proto == IPPROTO_SCTP) {
+			if (sctphdr_ok(skb)) {
+				struct sctphdr *sctp = sctp_hdr(skb);
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		} else if (key->ip.proto == IPPROTO_ICMP) {
+			if (icmphdr_ok(skb)) {
+				struct icmphdr *icmp = icmp_hdr(skb);
+				/* The ICMP type and code fields use the 16-bit
+				 * transport port fields, so we need to store
+				 * them in 16-bit network byte order. */
+				key->tp.src = htons(icmp->type);
+				key->tp.dst = htons(icmp->code);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		}
+
+	} else if (key->eth.type == htons(ETH_P_ARP) ||
+		   key->eth.type == htons(ETH_P_RARP)) {
+		struct arp_eth_header *arp;
+		bool arp_available = arphdr_ok(skb);
+
+		arp = (struct arp_eth_header *)skb_network_header(skb);
+
+		if (arp_available &&
+		    arp->ar_hrd == htons(ARPHRD_ETHER) &&
+		    arp->ar_pro == htons(ETH_P_IP) &&
+		    arp->ar_hln == ETH_ALEN &&
+		    arp->ar_pln == 4) {
+
+			/* We only match on the lower 8 bits of the opcode. */
+			if (ntohs(arp->ar_op) <= 0xff)
+				key->ip.proto = ntohs(arp->ar_op);
+			else
+				key->ip.proto = 0;
+
+			memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
+			memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
+			ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
+			ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
+		} else {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv4, 0, sizeof(key->ipv4));
+		}
+	} else if (eth_p_mpls(key->eth.type)) {
+		size_t stack_len = MPLS_HLEN;
+
+		skb_set_inner_network_header(skb, skb->mac_len);
+		while (1) {
+			__be32 lse;
+
+			error = check_header(skb, skb->mac_len + stack_len);
+			if (unlikely(error))
+				return 0;
+
+			memcpy(&lse, skb_inner_network_header(skb), MPLS_HLEN);
+
+			if (stack_len == MPLS_HLEN)
+				memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+
+			skb_set_inner_network_header(skb, skb->mac_len + stack_len);
+			if (lse & htonl(MPLS_LS_S_MASK))
+				break;
+
+			stack_len += MPLS_HLEN;
+		}
+	} else if (key->eth.type == htons(ETH_P_IPV6)) {
+		int nh_len;             /* IPv6 Header + Extensions */
+
+		nh_len = parse_ipv6hdr(skb, key);
+		if (unlikely(nh_len < 0)) {
+			switch (nh_len) {
+			case -EINVAL:
+				memset(&key->ip, 0, sizeof(key->ip));
+				memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
+				/* fall-through */
+			case -EPROTO:
+				skb->transport_header = skb->network_header;
+				error = 0;
+				break;
+			default:
+				error = nh_len;
+			}
+			return error;
+		}
+
+		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+			return 0;
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
+		/* Transport layer. */
+		if (key->ip.proto == NEXTHDR_TCP) {
+			if (tcphdr_ok(skb)) {
+				struct tcphdr *tcp = tcp_hdr(skb);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		} else if (key->ip.proto == NEXTHDR_UDP) {
+			if (udphdr_ok(skb)) {
+				struct udphdr *udp = udp_hdr(skb);
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		} else if (key->ip.proto == NEXTHDR_SCTP) {
+			if (sctphdr_ok(skb)) {
+				struct sctphdr *sctp = sctp_hdr(skb);
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		} else if (key->ip.proto == NEXTHDR_ICMP) {
+			if (icmp6hdr_ok(skb)) {
+				error = parse_icmpv6(skb, key, nh_len);
+				if (error)
+					return error;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
+			}
+		}
+	} else if (key->eth.type == htons(ETH_P_NSH)) {
+		error = parse_nsh(skb, key);
+		if (error)
+			return error;
+	}
+	return 0;
+}
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int res;
+
+	res = key_extract(skb, key);
+	if (!res)
+		key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+	return res;
+}
+
+static int key_extract_mac_proto(struct sk_buff *skb)
+{
+	switch (skb->dev->type) {
+	case ARPHRD_ETHER:
+		return MAC_PROTO_ETHERNET;
+	case ARPHRD_NONE:
+		if (skb->protocol == htons(ETH_P_TEB))
+			return MAC_PROTO_ETHERNET;
+		return MAC_PROTO_NONE;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
+int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
+			 struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int res, err;
+
+	/* Extract metadata from packet. */
+	if (tun_info) {
+		key->tun_proto = ip_tunnel_info_af(tun_info);
+		memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key));
+
+		if (tun_info->options_len) {
+			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+						   8)) - 1
+					> sizeof(key->tun_opts));
+
+			ip_tunnel_info_opts_get(TUN_METADATA_OPTS(key, tun_info->options_len),
+						tun_info);
+			key->tun_opts_len = tun_info->options_len;
+		} else {
+			key->tun_opts_len = 0;
+		}
+	} else  {
+		key->tun_proto = 0;
+		key->tun_opts_len = 0;
+		memset(&key->tun_key, 0, sizeof(key->tun_key));
+	}
+
+	key->phy.priority = skb->priority;
+	key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
+	key->phy.skb_mark = skb->mark;
+	key->ovs_flow_hash = 0;
+	res = key_extract_mac_proto(skb);
+	if (res < 0)
+		return res;
+	key->mac_proto = res;
+	key->recirc_id = 0;
+
+	err = key_extract(skb, key);
+	if (!err)
+		ovs_ct_fill_key(skb, key);   /* Must be after key_extract(). */
+	return err;
+}
+
+int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key, bool log)
+{
+	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
+	u64 attrs = 0;
+	int err;
+
+	err = parse_flow_nlattrs(attr, a, &attrs, log);
+	if (err)
+		return -EINVAL;
+
+	/* Extract metadata from netlink attributes. */
+	err = ovs_nla_get_flow_metadata(net, a, attrs, key, log);
+	if (err)
+		return err;
+
+	/* key_extract assumes that skb->protocol is set-up for
+	 * layer 3 packets which is the case for other callers,
+	 * in particular packets received from the network stack.
+	 * Here the correct value can be set from the metadata
+	 * extracted above.
+	 * For L2 packet key eth type would be zero. skb protocol
+	 * would be set to correct value later during key-extact.
+	 */
+
+	skb->protocol = key->eth.type;
+	err = key_extract(skb, key);
+	if (err)
+		return err;
+
+	/* Check that we have conntrack original direction tuple metadata only
+	 * for packets for which it makes sense.  Otherwise the key may be
+	 * corrupted due to overlapping key fields.
+	 */
+	if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) &&
+	    key->eth.type != htons(ETH_P_IP))
+		return -EINVAL;
+	if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) &&
+	    (key->eth.type != htons(ETH_P_IPV6) ||
+	     sw_flow_key_is_nd(key)))
+		return -EINVAL;
+
+	return 0;
+}

net/openvswitch/flow.h

@@ -0,0 +1,295 @@
+/*
+ * Copyright (c) 2007-2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef FLOW_H
+#define FLOW_H 1
+
+#include <linux/cache.h>
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+#include <linux/cpumask.h>
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+#include <net/dst_metadata.h>
+#include <net/nsh.h>
+
+struct sk_buff;
+
+enum sw_flow_mac_proto {
+	MAC_PROTO_NONE = 0,
+	MAC_PROTO_ETHERNET,
+};
+#define SW_FLOW_KEY_INVALID	0x80
+
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define TUN_METADATA_OFFSET(opt_len) \
+	(FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len)
+#define TUN_METADATA_OPTS(flow_key, opt_len) \
+	((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
+
+struct ovs_tunnel_info {
+	struct metadata_dst	*tun_dst;
+};
+
+struct vlan_head {
+	__be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/
+	__be16 tci;  /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
+};
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
+	(offsetof(struct sw_flow_key, recirc_id) +	\
+	FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
+struct ovs_key_nsh {
+	struct ovs_nsh_key_base base;
+	__be32 context[NSH_MD1_CONTEXT_SIZE];
+};
+
+struct sw_flow_key {
+	u8 tun_opts[IP_TUNNEL_OPTS_MAX];
+	u8 tun_opts_len;
+	struct ip_tunnel_key tun_key;	/* Encapsulating tunnel key. */
+	struct {
+		u32	priority;	/* Packet QoS priority. */
+		u32	skb_mark;	/* SKB mark. */
+		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
+	} __packed phy; /* Safe when right after 'tun_key'. */
+	u8 mac_proto;			/* MAC layer protocol (e.g. Ethernet). */
+	u8 tun_proto;			/* Protocol of encapsulating tunnel. */
+	u32 ovs_flow_hash;		/* Datapath computed hash value.  */
+	u32 recirc_id;			/* Recirculation ID.  */
+	struct {
+		u8     src[ETH_ALEN];	/* Ethernet source address. */
+		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
+		struct vlan_head vlan;
+		struct vlan_head cvlan;
+		__be16 type;		/* Ethernet frame type. */
+	} eth;
+	/* Filling a hole of two bytes. */
+	u8 ct_state;
+	u8 ct_orig_proto;		/* CT original direction tuple IP
+					 * protocol.
+					 */
+	union {
+		struct {
+			__be32 top_lse;	/* top label stack entry */
+		} mpls;
+		struct {
+			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
+			u8     tos;	    /* IP ToS. */
+			u8     ttl;	    /* IP TTL/hop limit. */
+			u8     frag;	/* One of OVS_FRAG_TYPE_*. */
+		} ip;
+	};
+	u16 ct_zone;			/* Conntrack zone. */
+	struct {
+		__be16 src;		/* TCP/UDP/SCTP source port. */
+		__be16 dst;		/* TCP/UDP/SCTP destination port. */
+		__be16 flags;		/* TCP flags. */
+	} tp;
+	union {
+		struct {
+			struct {
+				__be32 src;	/* IP source address. */
+				__be32 dst;	/* IP destination address. */
+			} addr;
+			union {
+				struct {
+					__be32 src;
+					__be32 dst;
+				} ct_orig;	/* Conntrack original direction fields. */
+				struct {
+					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
+					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
+				} arp;
+			};
+		} ipv4;
+		struct {
+			struct {
+				struct in6_addr src;	/* IPv6 source address. */
+				struct in6_addr dst;	/* IPv6 destination address. */
+			} addr;
+			__be32 label;			/* IPv6 flow label. */
+			union {
+				struct {
+					struct in6_addr src;
+					struct in6_addr dst;
+				} ct_orig;	/* Conntrack original direction fields. */
+				struct {
+					struct in6_addr target;	/* ND target address. */
+					u8 sll[ETH_ALEN];	/* ND source link layer address. */
+					u8 tll[ETH_ALEN];	/* ND target link layer address. */
+				} nd;
+			};
+		} ipv6;
+		struct ovs_key_nsh nsh;         /* network service header */
+	};
+	struct {
+		/* Connection tracking fields not packed above. */
+		struct {
+			__be16 src;	/* CT orig tuple tp src port. */
+			__be16 dst;	/* CT orig tuple tp dst port. */
+		} orig_tp;
+		u32 mark;
+		struct ovs_key_ct_labels labels;
+	} ct;
+
+} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
+
+static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key)
+{
+	return key->eth.type == htons(ETH_P_IPV6) &&
+		key->ip.proto == NEXTHDR_ICMP &&
+		key->tp.dst == 0 &&
+		(key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+		 key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT));
+}
+
+struct sw_flow_key_range {
+	unsigned short int start;
+	unsigned short int end;
+};
+
+struct sw_flow_mask {
+	int ref_count;
+	struct rcu_head rcu;
+	struct list_head list;
+	struct sw_flow_key_range range;
+	struct sw_flow_key key;
+};
+
+struct sw_flow_match {
+	struct sw_flow_key *key;
+	struct sw_flow_key_range range;
+	struct sw_flow_mask *mask;
+};
+
+#define MAX_UFID_LENGTH 16 /* 128 bits */
+
+struct sw_flow_id {
+	u32 ufid_len;
+	union {
+		u32 ufid[MAX_UFID_LENGTH / 4];
+		struct sw_flow_key *unmasked_key;
+	};
+};
+
+struct sw_flow_actions {
+	struct rcu_head rcu;
+	size_t orig_len;	/* From flow_cmd_new netlink actions size */
+	u32 actions_len;
+	struct nlattr actions[];
+};
+
+struct flow_stats {
+	u64 packet_count;		/* Number of packets matched. */
+	u64 byte_count;			/* Number of bytes matched. */
+	unsigned long used;		/* Last used time (in jiffies). */
+	spinlock_t lock;		/* Lock for atomic stats update. */
+	__be16 tcp_flags;		/* Union of seen TCP flags. */
+};
+
+struct sw_flow {
+	struct rcu_head rcu;
+	struct {
+		struct hlist_node node[2];
+		u32 hash;
+	} flow_table, ufid_table;
+	int stats_last_writer;		/* CPU id of the last writer on
+					 * 'stats[0]'.
+					 */
+	struct sw_flow_key key;
+	struct sw_flow_id id;
+	struct cpumask cpu_used_mask;
+	struct sw_flow_mask *mask;
+	struct sw_flow_actions __rcu *sf_acts;
+	struct flow_stats __rcu *stats[]; /* One for each CPU.  First one
+					   * is allocated at flow creation time,
+					   * the rest are allocated on demand
+					   * while holding the 'stats[0].lock'.
+					   */
+};
+
+struct arp_eth_header {
+	__be16      ar_hrd;	/* format of hardware address   */
+	__be16      ar_pro;	/* format of protocol address   */
+	unsigned char   ar_hln;	/* length of hardware address   */
+	unsigned char   ar_pln;	/* length of protocol address   */
+	__be16      ar_op;	/* ARP opcode (command)     */
+
+	/* Ethernet+IPv4 specific members. */
+	unsigned char       ar_sha[ETH_ALEN];	/* sender hardware address  */
+	unsigned char       ar_sip[4];		/* sender IP address        */
+	unsigned char       ar_tha[ETH_ALEN];	/* target hardware address  */
+	unsigned char       ar_tip[4];		/* target IP address        */
+} __packed;
+
+static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key)
+{
+	return key->mac_proto & ~SW_FLOW_KEY_INVALID;
+}
+
+static inline u16 __ovs_mac_header_len(u8 mac_proto)
+{
+	return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0;
+}
+
+static inline u16 ovs_mac_header_len(const struct sw_flow_key *key)
+{
+	return __ovs_mac_header_len(ovs_key_mac_proto(key));
+}
+
+static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
+{
+	return sfid->ufid_len;
+}
+
+static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid)
+{
+	return !ovs_identifier_is_ufid(sfid);
+}
+
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+			   const struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
+			unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *);
+u64 ovs_flow_used_time(unsigned long flow_jiffies);
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
+			 struct sk_buff *skb,
+			 struct sw_flow_key *key);
+/* Extract key from packet coming from userspace. */
+int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key, bool log);
+
+#endif /* flow.h */

net/openvswitch/flow_netlink.h

@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2007-2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+
+#ifndef FLOW_NETLINK_H
+#define FLOW_NETLINK_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+size_t ovs_tun_key_attr_size(void);
+size_t ovs_key_attr_size(void);
+
+void ovs_match_init(struct sw_flow_match *match,
+		    struct sw_flow_key *key, bool reset_key,
+		    struct sw_flow_mask *mask);
+
+int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *,
+		    int attr, bool is_mask, struct sk_buff *);
+int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[],
+		       u64 *attrsp, bool log);
+int ovs_nla_get_flow_metadata(struct net *net,
+			      const struct nlattr *a[OVS_KEY_ATTR_MAX + 1],
+			      u64 attrs, struct sw_flow_key *key, bool log);
+
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
+
+int ovs_nla_get_match(struct net *, struct sw_flow_match *,
+		      const struct nlattr *key, const struct nlattr *mask,
+		      bool log);
+
+int ovs_nla_put_tunnel_info(struct sk_buff *skb,
+			    struct ip_tunnel_info *tun_info);
+
+bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log);
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr);
+
+int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa, bool log);
+int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype,
+		       void *data, int len, bool log);
+int ovs_nla_put_actions(const struct nlattr *attr,
+			int len, struct sk_buff *skb);
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
+
+int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh,
+			struct ovs_key_nsh *nsh_mask);
+int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh,
+			size_t size);
+
+#endif /* flow_netlink.h */

net/openvswitch/flow_table.c

@@ -0,0 +1,777 @@
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include "flow.h"
+#include "datapath.h"
+#include "flow_netlink.h"
+#include <linux/uaccess.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/llc_pdu.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.h>
+#include <linux/cpumask.h>
+#include <linux/if_arp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/sctp.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/rculist.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+
+#define TBL_MIN_BUCKETS		1024
+#define REHASH_INTERVAL		(10 * 60 * HZ)
+
+static struct kmem_cache *flow_cache;
+struct kmem_cache *flow_stats_cache __read_mostly;
+
+static u16 range_n_bytes(const struct sw_flow_key_range *range)
+{
+	return range->end - range->start;
+}
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+		       bool full, const struct sw_flow_mask *mask)
+{
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
+	int i;
+
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
+	 */
+	for (i = 0; i < len; i += sizeof(long))
+		*d++ = *s++ & *m++;
+}
+
+struct sw_flow *ovs_flow_alloc(void)
+{
+	struct sw_flow *flow;
+	struct flow_stats *stats;
+
+	flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	flow->stats_last_writer = -1;
+
+	/* Initialize the default stat node. */
+	stats = kmem_cache_alloc_node(flow_stats_cache,
+				      GFP_KERNEL | __GFP_ZERO,
+				      node_online(0) ? 0 : NUMA_NO_NODE);
+	if (!stats)
+		goto err;
+
+	spin_lock_init(&stats->lock);
+
+	RCU_INIT_POINTER(flow->stats[0], stats);
+
+	cpumask_set_cpu(0, &flow->cpu_used_mask);
+
+	return flow;
+err:
+	kmem_cache_free(flow_cache, flow);
+	return ERR_PTR(-ENOMEM);
+}
+
+int ovs_flow_tbl_count(const struct flow_table *table)
+{
+	return table->count;
+}
+
+static struct flex_array *alloc_buckets(unsigned int n_buckets)
+{
+	struct flex_array *buckets;
+	int i, err;
+
+	buckets = flex_array_alloc(sizeof(struct hlist_head),
+				   n_buckets, GFP_KERNEL);
+	if (!buckets)
+		return NULL;
+
+	err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
+	if (err) {
+		flex_array_free(buckets);
+		return NULL;
+	}
+
+	for (i = 0; i < n_buckets; i++)
+		INIT_HLIST_HEAD((struct hlist_head *)
+					flex_array_get(buckets, i));
+
+	return buckets;
+}
+
+static void flow_free(struct sw_flow *flow)
+{
+	int cpu;
+
+	if (ovs_identifier_is_key(&flow->id))
+		kfree(flow->id.unmasked_key);
+	if (flow->sf_acts)
+		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
+	/* We open code this to make sure cpu 0 is always considered */
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
+		if (flow->stats[cpu])
+			kmem_cache_free(flow_stats_cache,
+					(struct flow_stats __force *)flow->stats[cpu]);
+	kmem_cache_free(flow_cache, flow);
+}
+
+static void rcu_free_flow_callback(struct rcu_head *rcu)
+{
+	struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);
+
+	flow_free(flow);
+}
+
+void ovs_flow_free(struct sw_flow *flow, bool deferred)
+{
+	if (!flow)
+		return;
+
+	if (deferred)
+		call_rcu(&flow->rcu, rcu_free_flow_callback);
+	else
+		flow_free(flow);
+}
+
+static void free_buckets(struct flex_array *buckets)
+{
+	flex_array_free(buckets);
+}
+
+
+static void __table_instance_destroy(struct table_instance *ti)
+{
+	free_buckets(ti->buckets);
+	kfree(ti);
+}
+
+static struct table_instance *table_instance_alloc(int new_size)
+{
+	struct table_instance *ti = kmalloc(sizeof(*ti), GFP_KERNEL);
+
+	if (!ti)
+		return NULL;
+
+	ti->buckets = alloc_buckets(new_size);
+
+	if (!ti->buckets) {
+		kfree(ti);
+		return NULL;
+	}
+	ti->n_buckets = new_size;
+	ti->node_ver = 0;
+	ti->keep_flows = false;
+	get_random_bytes(&ti->hash_seed, sizeof(u32));
+
+	return ti;
+}
+
+int ovs_flow_tbl_init(struct flow_table *table)
+{
+	struct table_instance *ti, *ufid_ti;
+
+	ti = table_instance_alloc(TBL_MIN_BUCKETS);
+
+	if (!ti)
+		return -ENOMEM;
+
+	ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!ufid_ti)
+		goto free_ti;
+
+	rcu_assign_pointer(table->ti, ti);
+	rcu_assign_pointer(table->ufid_ti, ufid_ti);
+	INIT_LIST_HEAD(&table->mask_list);
+	table->last_rehash = jiffies;
+	table->count = 0;
+	table->ufid_count = 0;
+	return 0;
+
+free_ti:
+	__table_instance_destroy(ti);
+	return -ENOMEM;
+}
+
+static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
+{
+	struct table_instance *ti = container_of(rcu, struct table_instance, rcu);
+
+	__table_instance_destroy(ti);
+}
+
+static void table_instance_destroy(struct table_instance *ti,
+				   struct table_instance *ufid_ti,
+				   bool deferred)
+{
+	int i;
+
+	if (!ti)
+		return;
+
+	BUG_ON(!ufid_ti);
+	if (ti->keep_flows)
+		goto skip_flows;
+
+	for (i = 0; i < ti->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head = flex_array_get(ti->buckets, i);
+		struct hlist_node *n;
+		int ver = ti->node_ver;
+		int ufid_ver = ufid_ti->node_ver;
+
+		hlist_for_each_entry_safe(flow, n, head, flow_table.node[ver]) {
+			hlist_del_rcu(&flow->flow_table.node[ver]);
+			if (ovs_identifier_is_ufid(&flow->id))
+				hlist_del_rcu(&flow->ufid_table.node[ufid_ver]);
+			ovs_flow_free(flow, deferred);
+		}
+	}
+
+skip_flows:
+	if (deferred) {
+		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+		call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);
+	} else {
+		__table_instance_destroy(ti);
+		__table_instance_destroy(ufid_ti);
+	}
+}
+
+/* No need for locking this function is called from RCU callback or
+ * error path.
+ */
+void ovs_flow_tbl_destroy(struct flow_table *table)
+{
+	struct table_instance *ti = rcu_dereference_raw(table->ti);
+	struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);
+
+	table_instance_destroy(ti, ufid_ti, false);
+}
+
+struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
+				       u32 *bucket, u32 *last)
+{
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	int ver;
+	int i;
+
+	ver = ti->node_ver;
+	while (*bucket < ti->n_buckets) {
+		i = 0;
+		head = flex_array_get(ti->buckets, *bucket);
+		hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
+			if (i < *last) {
+				i++;
+				continue;
+			}
+			*last = i + 1;
+			return flow;
+		}
+		(*bucket)++;
+		*last = 0;
+	}
+
+	return NULL;
+}
+
+static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash)
+{
+	hash = jhash_1word(hash, ti->hash_seed);
+	return flex_array_get(ti->buckets,
+				(hash & (ti->n_buckets - 1)));
+}
+
+static void table_instance_insert(struct table_instance *ti,
+				  struct sw_flow *flow)
+{
+	struct hlist_head *head;
+
+	head = find_bucket(ti, flow->flow_table.hash);
+	hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);
+}
+
+static void ufid_table_instance_insert(struct table_instance *ti,
+				       struct sw_flow *flow)
+{
+	struct hlist_head *head;
+
+	head = find_bucket(ti, flow->ufid_table.hash);
+	hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);
+}
+
+static void flow_table_copy_flows(struct table_instance *old,
+				  struct table_instance *new, bool ufid)
+{
+	int old_ver;
+	int i;
+
+	old_ver = old->node_ver;
+	new->node_ver = !old_ver;
+
+	/* Insert in new table. */
+	for (i = 0; i < old->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head;
+
+		head = flex_array_get(old->buckets, i);
+
+		if (ufid)
+			hlist_for_each_entry(flow, head,
+					     ufid_table.node[old_ver])
+				ufid_table_instance_insert(new, flow);
+		else
+			hlist_for_each_entry(flow, head,
+					     flow_table.node[old_ver])
+				table_instance_insert(new, flow);
+	}
+
+	old->keep_flows = true;
+}
+
+static struct table_instance *table_instance_rehash(struct table_instance *ti,
+						    int n_buckets, bool ufid)
+{
+	struct table_instance *new_ti;
+
+	new_ti = table_instance_alloc(n_buckets);
+	if (!new_ti)
+		return NULL;
+
+	flow_table_copy_flows(ti, new_ti, ufid);
+
+	return new_ti;
+}
+
+int ovs_flow_tbl_flush(struct flow_table *flow_table)
+{
+	struct table_instance *old_ti, *new_ti;
+	struct table_instance *old_ufid_ti, *new_ufid_ti;
+
+	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!new_ti)
+		return -ENOMEM;
+	new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!new_ufid_ti)
+		goto err_free_ti;
+
+	old_ti = ovsl_dereference(flow_table->ti);
+	old_ufid_ti = ovsl_dereference(flow_table->ufid_ti);
+
+	rcu_assign_pointer(flow_table->ti, new_ti);
+	rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
+	flow_table->last_rehash = jiffies;
+	flow_table->count = 0;
+	flow_table->ufid_count = 0;
+
+	table_instance_destroy(old_ti, old_ufid_ti, true);
+	return 0;
+
+err_free_ti:
+	__table_instance_destroy(new_ti);
+	return -ENOMEM;
+}
+
+static u32 flow_hash(const struct sw_flow_key *key,
+		     const struct sw_flow_key_range *range)
+{
+	int key_start = range->start;
+	int key_end = range->end;
+	const u32 *hash_key = (const u32 *)((const u8 *)key + key_start);
+	int hash_u32s = (key_end - key_start) >> 2;
+
+	/* Make sure number of hash bytes are multiple of u32. */
+	BUILD_BUG_ON(sizeof(long) % sizeof(u32));
+
+	return jhash2(hash_key, hash_u32s, 0);
+}
+
+static int flow_key_start(const struct sw_flow_key *key)
+{
+	if (key->tun_proto)
+		return 0;
+	else
+		return rounddown(offsetof(struct sw_flow_key, phy),
+					  sizeof(long));
+}
+
+static bool cmp_key(const struct sw_flow_key *key1,
+		    const struct sw_flow_key *key2,
+		    int key_start, int key_end)
+{
+	const long *cp1 = (const long *)((const u8 *)key1 + key_start);
+	const long *cp2 = (const long *)((const u8 *)key2 + key_start);
+	long diffs = 0;
+	int i;
+
+	for (i = key_start; i < key_end;  i += sizeof(long))
+		diffs |= *cp1++ ^ *cp2++;
+
+	return diffs == 0;
+}
+
+static bool flow_cmp_masked_key(const struct sw_flow *flow,
+				const struct sw_flow_key *key,
+				const struct sw_flow_key_range *range)
+{
+	return cmp_key(&flow->key, key, range->start, range->end);
+}
+
+static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+				      const struct sw_flow_match *match)
+{
+	struct sw_flow_key *key = match->key;
+	int key_start = flow_key_start(key);
+	int key_end = match->range.end;
+
+	BUG_ON(ovs_identifier_is_ufid(&flow->id));
+	return cmp_key(flow->id.unmasked_key, key, key_start, key_end);
+}
+
+static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
+					  const struct sw_flow_key *unmasked,
+					  const struct sw_flow_mask *mask)
+{
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	u32 hash;
+	struct sw_flow_key masked_key;
+
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
+	hash = flow_hash(&masked_key, &mask->range);
+	head = find_bucket(ti, hash);
+	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+		if (flow->mask == mask && flow->flow_table.hash == hash &&
+		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
+			return flow;
+	}
+	return NULL;
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
+				    const struct sw_flow_key *key,
+				    u32 *n_mask_hit)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	struct sw_flow_mask *mask;
+	struct sw_flow *flow;
+
+	*n_mask_hit = 0;
+	list_for_each_entry_rcu(mask, &tbl->mask_list, list) {
+		(*n_mask_hit)++;
+		flow = masked_flow_lookup(ti, key, mask);
+		if (flow)  /* Found */
+			return flow;
+	}
+	return NULL;
+}
+
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+				    const struct sw_flow_key *key)
+{
+	u32 __always_unused n_mask_hit;
+
+	return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  const struct sw_flow_match *match)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	struct sw_flow_mask *mask;
+	struct sw_flow *flow;
+
+	/* Always called under ovs-mutex. */
+	list_for_each_entry(mask, &tbl->mask_list, list) {
+		flow = masked_flow_lookup(ti, match->key, mask);
+		if (flow && ovs_identifier_is_key(&flow->id) &&
+		    ovs_flow_cmp_unmasked_key(flow, match))
+			return flow;
+	}
+	return NULL;
+}
+
+static u32 ufid_hash(const struct sw_flow_id *sfid)
+{
+	return jhash(sfid->ufid, sfid->ufid_len, 0);
+}
+
+static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
+			      const struct sw_flow_id *sfid)
+{
+	if (flow->id.ufid_len != sfid->ufid_len)
+		return false;
+
+	return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
+}
+
+bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
+{
+	if (ovs_identifier_is_ufid(&flow->id))
+		return flow_cmp_masked_key(flow, match->key, &match->range);
+
+	return ovs_flow_cmp_unmasked_key(flow, match);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
+					 const struct sw_flow_id *ufid)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti);
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	u32 hash;
+
+	hash = ufid_hash(ufid);
+	head = find_bucket(ti, hash);
+	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+		if (flow->ufid_table.hash == hash &&
+		    ovs_flow_cmp_ufid(flow, ufid))
+			return flow;
+	}
+	return NULL;
+}
+
+int ovs_flow_tbl_num_masks(const struct flow_table *table)
+{
+	struct sw_flow_mask *mask;
+	int num = 0;
+
+	list_for_each_entry(mask, &table->mask_list, list)
+		num++;
+
+	return num;
+}
+
+static struct table_instance *table_instance_expand(struct table_instance *ti,
+						    bool ufid)
+{
+	return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
+}
+
+/* Remove 'mask' from the mask list, if it is not needed any more. */
+static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
+{
+	if (mask) {
+		/* ovs-lock is required to protect mask-refcount and
+		 * mask list.
+		 */
+		ASSERT_OVSL();
+		BUG_ON(!mask->ref_count);
+		mask->ref_count--;
+
+		if (!mask->ref_count) {
+			list_del_rcu(&mask->list);
+			kfree_rcu(mask, rcu);
+		}
+	}
+}
+
+/* Must be called with OVS mutex held. */
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
+{
+	struct table_instance *ti = ovsl_dereference(table->ti);
+	struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);
+
+	BUG_ON(table->count == 0);
+	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
+	table->count--;
+	if (ovs_identifier_is_ufid(&flow->id)) {
+		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);
+		table->ufid_count--;
+	}
+
+	/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
+	 * accessible as long as the RCU read lock is held.
+	 */
+	flow_mask_remove(table, flow->mask);
+}
+
+static struct sw_flow_mask *mask_alloc(void)
+{
+	struct sw_flow_mask *mask;
+
+	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
+	if (mask)
+		mask->ref_count = 1;
+
+	return mask;
+}
+
+static bool mask_equal(const struct sw_flow_mask *a,
+		       const struct sw_flow_mask *b)
+{
+	const u8 *a_ = (const u8 *)&a->key + a->range.start;
+	const u8 *b_ = (const u8 *)&b->key + b->range.start;
+
+	return  (a->range.end == b->range.end)
+		&& (a->range.start == b->range.start)
+		&& (memcmp(a_, b_, range_n_bytes(&a->range)) == 0);
+}
+
+static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
+					   const struct sw_flow_mask *mask)
+{
+	struct list_head *ml;
+
+	list_for_each(ml, &tbl->mask_list) {
+		struct sw_flow_mask *m;
+		m = container_of(ml, struct sw_flow_mask, list);
+		if (mask_equal(mask, m))
+			return m;
+	}
+
+	return NULL;
+}
+
+/* Add 'mask' into the mask list, if it is not already there. */
+static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
+			    const struct sw_flow_mask *new)
+{
+	struct sw_flow_mask *mask;
+	mask = flow_mask_find(tbl, new);
+	if (!mask) {
+		/* Allocate a new mask if none exsits. */
+		mask = mask_alloc();
+		if (!mask)
+			return -ENOMEM;
+		mask->key = new->key;
+		mask->range = new->range;
+		list_add_rcu(&mask->list, &tbl->mask_list);
+	} else {
+		BUG_ON(!mask->ref_count);
+		mask->ref_count++;
+	}
+
+	flow->mask = mask;
+	return 0;
+}
+
+/* Must be called with OVS mutex held. */
+static void flow_key_insert(struct flow_table *table, struct sw_flow *flow)
+{
+	struct table_instance *new_ti = NULL;
+	struct table_instance *ti;
+
+	flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range);
+	ti = ovsl_dereference(table->ti);
+	table_instance_insert(ti, flow);
+	table->count++;
+
+	/* Expand table, if necessary, to make room. */
+	if (table->count > ti->n_buckets)
+		new_ti = table_instance_expand(ti, false);
+	else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
+		new_ti = table_instance_rehash(ti, ti->n_buckets, false);
+
+	if (new_ti) {
+		rcu_assign_pointer(table->ti, new_ti);
+		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+		table->last_rehash = jiffies;
+	}
+}
+
+/* Must be called with OVS mutex held. */
+static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow)
+{
+	struct table_instance *ti;
+
+	flow->ufid_table.hash = ufid_hash(&flow->id);
+	ti = ovsl_dereference(table->ufid_ti);
+	ufid_table_instance_insert(ti, flow);
+	table->ufid_count++;
+
+	/* Expand table, if necessary, to make room. */
+	if (table->ufid_count > ti->n_buckets) {
+		struct table_instance *new_ti;
+
+		new_ti = table_instance_expand(ti, true);
+		if (new_ti) {
+			rcu_assign_pointer(table->ufid_ti, new_ti);
+			call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+		}
+	}
+}
+
+/* Must be called with OVS mutex held. */
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			const struct sw_flow_mask *mask)
+{
+	int err;
+
+	err = flow_mask_insert(table, flow, mask);
+	if (err)
+		return err;
+	flow_key_insert(table, flow);
+	if (ovs_identifier_is_ufid(&flow->id))
+		flow_ufid_insert(table, flow);
+
+	return 0;
+}
+
+/* Initializes the flow module.
+ * Returns zero if successful or a negative error code. */
+int ovs_flow_init(void)
+{
+	BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
+	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
+
+	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+				       + (nr_cpu_ids
+					  * sizeof(struct flow_stats *)),
+				       0, 0, NULL);
+	if (flow_cache == NULL)
+		return -ENOMEM;
+
+	flow_stats_cache
+		= kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+				    0, SLAB_HWCACHE_ALIGN, NULL);
+	if (flow_stats_cache == NULL) {
+		kmem_cache_destroy(flow_cache);
+		flow_cache = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/* Uninitializes the flow module. */
+void ovs_flow_exit(void)
+{
+	kmem_cache_destroy(flow_stats_cache);
+	kmem_cache_destroy(flow_cache);
+}

net/openvswitch/flow_table.h

@@ -0,0 +1,90 @@
+/*
+ * Copyright (c) 2007-2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef FLOW_TABLE_H
+#define FLOW_TABLE_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+struct table_instance {
+	struct flex_array *buckets;
+	unsigned int n_buckets;
+	struct rcu_head rcu;
+	int node_ver;
+	u32 hash_seed;
+	bool keep_flows;
+};
+
+struct flow_table {
+	struct table_instance __rcu *ti;
+	struct table_instance __rcu *ufid_ti;
+	struct list_head mask_list;
+	unsigned long last_rehash;
+	unsigned int count;
+	unsigned int ufid_count;
+};
+
+extern struct kmem_cache *flow_stats_cache;
+
+int ovs_flow_init(void);
+void ovs_flow_exit(void);
+
+struct sw_flow *ovs_flow_alloc(void);
+void ovs_flow_free(struct sw_flow *, bool deferred);
+
+int ovs_flow_tbl_init(struct flow_table *);
+int ovs_flow_tbl_count(const struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table);
+int ovs_flow_tbl_flush(struct flow_table *flow_table);
+
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			const struct sw_flow_mask *mask);
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+int  ovs_flow_tbl_num_masks(const struct flow_table *table);
+struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
+				       u32 *bucket, u32 *idx);
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
+				    const struct sw_flow_key *,
+				    u32 *n_mask_hit);
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+				    const struct sw_flow_key *);
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  const struct sw_flow_match *match);
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
+					 const struct sw_flow_id *);
+
+bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+		       bool full, const struct sw_flow_mask *mask);
+#endif /* flow_table.h */

net/openvswitch/meter.c

@@ -0,0 +1,603 @@
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/openvswitch.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "meter.h"
+
+#define METER_HASH_BUCKETS 1024
+
+static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = {
+	[OVS_METER_ATTR_ID] = { .type = NLA_U32, },
+	[OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+	[OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED },
+	[OVS_METER_ATTR_USED] = { .type = NLA_U64 },
+	[OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 },
+	[OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = {
+	[OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_RATE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_BURST] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+};
+
+static void ovs_meter_free(struct dp_meter *meter)
+{
+	if (!meter)
+		return;
+
+	kfree_rcu(meter, rcu);
+}
+
+static struct hlist_head *meter_hash_bucket(const struct datapath *dp,
+					    u32 meter_id)
+{
+	return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)];
+}
+
+/* Call with ovs_mutex or RCU read lock. */
+static struct dp_meter *lookup_meter(const struct datapath *dp,
+				     u32 meter_id)
+{
+	struct dp_meter *meter;
+	struct hlist_head *head;
+
+	head = meter_hash_bucket(dp, meter_id);
+	hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
+		if (meter->id == meter_id)
+			return meter;
+	}
+	return NULL;
+}
+
+static void attach_meter(struct datapath *dp, struct dp_meter *meter)
+{
+	struct hlist_head *head = meter_hash_bucket(dp, meter->id);
+
+	hlist_add_head_rcu(&meter->dp_hash_node, head);
+}
+
+static void detach_meter(struct dp_meter *meter)
+{
+	ASSERT_OVSL();
+	if (meter)
+		hlist_del_rcu(&meter->dp_hash_node);
+}
+
+static struct sk_buff *
+ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd,
+			  struct ovs_header **ovs_reply_header)
+{
+	struct sk_buff *skb;
+	struct ovs_header *ovs_header = info->userhdr;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	*ovs_reply_header = genlmsg_put(skb, info->snd_portid,
+					info->snd_seq,
+					&dp_meter_genl_family, 0, cmd);
+	if (!*ovs_reply_header) {
+		nlmsg_free(skb);
+		return ERR_PTR(-EMSGSIZE);
+	}
+	(*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex;
+
+	return skb;
+}
+
+static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
+				     struct dp_meter *meter)
+{
+	struct nlattr *nla;
+	struct dp_meter_band *band;
+	u16 i;
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id))
+		goto error;
+
+	if (!meter)
+		return 0;
+
+	if (nla_put(reply, OVS_METER_ATTR_STATS,
+		    sizeof(struct ovs_flow_stats), &meter->stats) ||
+	    nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
+			      OVS_METER_ATTR_PAD))
+		goto error;
+
+	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto error;
+
+	band = meter->bands;
+
+	for (i = 0; i < meter->n_bands; ++i, ++band) {
+		struct nlattr *band_nla;
+
+		band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+		if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS,
+					 sizeof(struct ovs_flow_stats),
+					 &band->stats))
+			goto error;
+		nla_nest_end(reply, band_nla);
+	}
+	nla_nest_end(reply, nla);
+
+	return 0;
+error:
+	return -EMSGSIZE;
+}
+
+static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *reply;
+	struct ovs_header *ovs_reply_header;
+	struct nlattr *nla, *band_nla;
+	int err;
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) ||
+	    nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
+		goto nla_put_failure;
+
+	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto nla_put_failure;
+
+	band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+	if (!band_nla)
+		goto nla_put_failure;
+	/* Currently only DROP band type is supported. */
+	if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP))
+		goto nla_put_failure;
+	nla_nest_end(reply, band_nla);
+	nla_nest_end(reply, nla);
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+nla_put_failure:
+	nlmsg_free(reply);
+	err = -EMSGSIZE;
+	return err;
+}
+
+static struct dp_meter *dp_meter_create(struct nlattr **a)
+{
+	struct nlattr *nla;
+	int rem;
+	u16 n_bands = 0;
+	struct dp_meter *meter;
+	struct dp_meter_band *band;
+	int err;
+
+	/* Validate attributes, count the bands. */
+	if (!a[OVS_METER_ATTR_BANDS])
+		return ERR_PTR(-EINVAL);
+
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem)
+		if (++n_bands > DP_MAX_BANDS)
+			return ERR_PTR(-EINVAL);
+
+	/* Allocate and set up the meter before locking anything. */
+	meter = kzalloc(n_bands * sizeof(struct dp_meter_band) +
+			sizeof(*meter), GFP_KERNEL);
+	if (!meter)
+		return ERR_PTR(-ENOMEM);
+
+	meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+	meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
+	meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
+	meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
+	spin_lock_init(&meter->lock);
+	if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) {
+		meter->stats = *(struct ovs_flow_stats *)
+			nla_data(a[OVS_METER_ATTR_STATS]);
+	}
+	meter->n_bands = n_bands;
+
+	/* Set up meter bands. */
+	band = meter->bands;
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) {
+		struct nlattr *attr[OVS_BAND_ATTR_MAX + 1];
+		u32 band_max_delta_t;
+
+		err = nla_parse((struct nlattr **)&attr, OVS_BAND_ATTR_MAX,
+				nla_data(nla), nla_len(nla), band_policy,
+				NULL);
+		if (err)
+			goto exit_free_meter;
+
+		if (!attr[OVS_BAND_ATTR_TYPE] ||
+		    !attr[OVS_BAND_ATTR_RATE] ||
+		    !attr[OVS_BAND_ATTR_BURST]) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
+		band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]);
+		band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]);
+		if (band->rate == 0) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
+		band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]);
+		/* Figure out max delta_t that is enough to fill any bucket.
+		 * Keep max_delta_t size to the bucket units:
+		 * pkts => 1/1000 packets, kilobits => bits.
+		 *
+		 * Start with a full bucket.
+		 */
+		band->bucket = (band->burst_size + band->rate) * 1000ULL;
+		band_max_delta_t = div_u64(band->bucket, band->rate);
+		if (band_max_delta_t > meter->max_delta_t)
+			meter->max_delta_t = band_max_delta_t;
+		band++;
+	}
+
+	return meter;
+
+exit_free_meter:
+	kfree(meter);
+	return ERR_PTR(err);
+}
+
+static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct dp_meter *meter, *old_meter;
+	struct sk_buff *reply;
+	struct ovs_header *ovs_reply_header;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct datapath *dp;
+	int err;
+	u32 meter_id;
+	bool failed;
+
+	if (!a[OVS_METER_ATTR_ID]) {
+		return -ENODEV;
+	}
+
+	meter = dp_meter_create(a);
+	if (IS_ERR_OR_NULL(meter))
+		return PTR_ERR(meter);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		goto exit_free_meter;
+	}
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	/* Cannot fail after this. */
+	old_meter = lookup_meter(dp, meter_id);
+	detach_meter(old_meter);
+	attach_meter(dp, meter);
+	ovs_unlock();
+
+	/* Build response with the meter_id and stats from
+	 * the old meter, if any.
+	 */
+	failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id);
+	WARN_ON(failed);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		if (old_meter->keep_stats) {
+			err = ovs_meter_cmd_reply_stats(reply, meter_id,
+							old_meter);
+			WARN_ON(err);
+		}
+		spin_unlock_bh(&old_meter->lock);
+		ovs_meter_free(old_meter);
+	}
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+exit_free_meter:
+	kfree(meter);
+	return err;
+}
+
+static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	u32 meter_id;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_reply_header;
+	struct datapath *dp;
+	int err;
+	struct sk_buff *reply;
+	struct dp_meter *meter;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	/* Locate meter, copy stats. */
+	meter = lookup_meter(dp, meter_id);
+	if (!meter) {
+		err = -ENOENT;
+		goto exit_unlock;
+	}
+
+	spin_lock_bh(&meter->lock);
+	err = ovs_meter_cmd_reply_stats(reply, meter_id, meter);
+	spin_unlock_bh(&meter->lock);
+	if (err)
+		goto exit_unlock;
+
+	ovs_unlock();
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	u32 meter_id;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_reply_header;
+	struct datapath *dp;
+	int err;
+	struct sk_buff *reply;
+	struct dp_meter *old_meter;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	old_meter = lookup_meter(dp, meter_id);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter);
+		WARN_ON(err);
+		spin_unlock_bh(&old_meter->lock);
+		detach_meter(old_meter);
+	}
+	ovs_unlock();
+	ovs_meter_free(old_meter);
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+/* Meter action execution.
+ *
+ * Return true 'meter_id' drop band is triggered. The 'skb' should be
+ * dropped by the caller'.
+ */
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id)
+{
+	struct dp_meter *meter;
+	struct dp_meter_band *band;
+	long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000);
+	long long int long_delta_ms;
+	u32 delta_ms;
+	u32 cost;
+	int i, band_exceeded_max = -1;
+	u32 band_exceeded_rate = 0;
+
+	meter = lookup_meter(dp, meter_id);
+	/* Do not drop the packet when there is no meter. */
+	if (!meter)
+		return false;
+
+	/* Lock the meter while using it. */
+	spin_lock(&meter->lock);
+
+	long_delta_ms = (now_ms - meter->used); /* ms */
+
+	/* Make sure delta_ms will not be too large, so that bucket will not
+	 * wrap around below.
+	 */
+	delta_ms = (long_delta_ms > (long long int)meter->max_delta_t)
+		   ? meter->max_delta_t : (u32)long_delta_ms;
+
+	/* Update meter statistics.
+	 */
+	meter->used = now_ms;
+	meter->stats.n_packets += 1;
+	meter->stats.n_bytes += skb->len;
+
+	/* Bucket rate is either in kilobits per second, or in packets per
+	 * second.  We maintain the bucket in the units of either bits or
+	 * 1/1000th of a packet, correspondingly.
+	 * Then, when rate is multiplied with milliseconds, we get the
+	 * bucket units:
+	 * msec * kbps = bits, and
+	 * msec * packets/sec = 1/1000 packets.
+	 *
+	 * 'cost' is the number of bucket units in this packet.
+	 */
+	cost = (meter->kbps) ? skb->len * 8 : 1000;
+
+	/* Update all bands and find the one hit with the highest rate. */
+	for (i = 0; i < meter->n_bands; ++i) {
+		long long int max_bucket_size;
+
+		band = &meter->bands[i];
+		max_bucket_size = (band->burst_size + band->rate) * 1000LL;
+
+		band->bucket += delta_ms * band->rate;
+		if (band->bucket > max_bucket_size)
+			band->bucket = max_bucket_size;
+
+		if (band->bucket >= cost) {
+			band->bucket -= cost;
+		} else if (band->rate > band_exceeded_rate) {
+			band_exceeded_rate = band->rate;
+			band_exceeded_max = i;
+		}
+	}
+
+	if (band_exceeded_max >= 0) {
+		/* Update band statistics. */
+		band = &meter->bands[band_exceeded_max];
+		band->stats.n_packets += 1;
+		band->stats.n_bytes += skb->len;
+
+		/* Drop band triggered, let the caller drop the 'skb'.  */
+		if (band->type == OVS_METER_BAND_TYPE_DROP) {
+			spin_unlock(&meter->lock);
+			return true;
+		}
+	}
+
+	spin_unlock(&meter->lock);
+	return false;
+}
+
+static struct genl_ops dp_meter_genl_ops[] = {
+	{ .cmd = OVS_METER_CMD_FEATURES,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_features
+	},
+	{ .cmd = OVS_METER_CMD_SET,
+		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					   *  privilege.
+					   */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_set,
+	},
+	{ .cmd = OVS_METER_CMD_GET,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_get,
+	},
+	{ .cmd = OVS_METER_CMD_DEL,
+		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					   *  privilege.
+					   */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_del
+	},
+};
+
+static const struct genl_multicast_group ovs_meter_multicast_group = {
+	.name = OVS_METER_MCGROUP,
+};
+
+struct genl_family dp_meter_genl_family __ro_after_init = {
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_METER_FAMILY,
+	.version = OVS_METER_VERSION,
+	.maxattr = OVS_METER_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_meter_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_meter_genl_ops),
+	.mcgrps = &ovs_meter_multicast_group,
+	.n_mcgrps = 1,
+	.module = THIS_MODULE,
+};
+
+int ovs_meters_init(struct datapath *dp)
+{
+	int i;
+
+	dp->meters = kmalloc_array(METER_HASH_BUCKETS,
+				   sizeof(struct hlist_head), GFP_KERNEL);
+
+	if (!dp->meters)
+		return -ENOMEM;
+
+	for (i = 0; i < METER_HASH_BUCKETS; i++)
+		INIT_HLIST_HEAD(&dp->meters[i]);
+
+	return 0;
+}
+
+void ovs_meters_exit(struct datapath *dp)
+{
+	int i;
+
+	for (i = 0; i < METER_HASH_BUCKETS; i++) {
+		struct hlist_head *head = &dp->meters[i];
+		struct dp_meter *meter;
+		struct hlist_node *n;
+
+		hlist_for_each_entry_safe(meter, n, head, dp_hash_node)
+			kfree(meter);
+	}
+
+	kfree(dp->meters);
+}

net/openvswitch/meter.h

@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#ifndef METER_H
+#define METER_H 1
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/genetlink.h>
+#include <linux/skbuff.h>
+
+#include "flow.h"
+struct datapath;
+
+#define DP_MAX_BANDS		1
+
+struct dp_meter_band {
+	u32 type;
+	u32 rate;
+	u32 burst_size;
+	u64 bucket; /* 1/1000 packets, or in bits */
+	struct ovs_flow_stats stats;
+};
+
+struct dp_meter {
+	spinlock_t lock;    /* Per meter lock */
+	struct rcu_head rcu;
+	struct hlist_node dp_hash_node; /*Element in datapath->meters
+					 * hash table.
+					 */
+	u32 id;
+	u16 kbps:1, keep_stats:1;
+	u16 n_bands;
+	u32 max_delta_t;
+	u64 used;
+	struct ovs_flow_stats stats;
+	struct dp_meter_band bands[];
+};
+
+extern struct genl_family dp_meter_genl_family;
+int ovs_meters_init(struct datapath *dp);
+void ovs_meters_exit(struct datapath *dp);
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id);
+
+#endif /* meter.h */

net/openvswitch/vport-geneve.c

@@ -0,0 +1,144 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/rculist.h>
+#include <linux/udp.h>
+#include <linux/if_vlan.h>
+#include <linux/module.h>
+
+#include <net/geneve.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_geneve_vport_ops;
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @dst_port: destination port.
+ */
+struct geneve_port {
+	u16 dst_port;
+};
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+static int geneve_get_options(const struct vport *vport,
+			      struct sk_buff *skb)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, geneve_port->dst_port))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static struct vport *geneve_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct nlattr *options = parms->options;
+	struct geneve_port *geneve_port;
+	struct net_device *dev;
+	struct vport *vport;
+	struct nlattr *a;
+	u16 dst_port;
+	int err;
+
+	if (!options) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+	if (a && nla_len(a) == sizeof(u16)) {
+		dst_port = nla_get_u16(a);
+	} else {
+		/* Require destination port from userspace. */
+		err = -EINVAL;
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(sizeof(struct geneve_port),
+				&ovs_geneve_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	geneve_port = geneve_vport(vport);
+	geneve_port->dst_port = dst_port;
+
+	rtnl_lock();
+	dev = geneve_dev_create_fb(net, parms->name, NET_NAME_USER, dst_port);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	if (err < 0) {
+		rtnl_delete_link(dev);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		goto error;
+	}
+
+	rtnl_unlock();
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static struct vport *geneve_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = geneve_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, parms->name);
+}
+
+static struct vport_ops ovs_geneve_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GENEVE,
+	.create		= geneve_create,
+	.destroy	= ovs_netdev_tunnel_destroy,
+	.get_options	= geneve_get_options,
+	.send		= dev_queue_xmit,
+};
+
+static int __init ovs_geneve_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_geneve_vport_ops);
+}
+
+static void __exit ovs_geneve_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_geneve_vport_ops);
+}
+
+module_init(ovs_geneve_tnl_init);
+module_exit(ovs_geneve_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: Geneve switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-5");

net/openvswitch/vport-gre.c

@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/in_route.h>
+#include <linux/inetdevice.h>
+#include <linux/jhash.h>
+#include <linux/list.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/rculist.h>
+#include <net/route.h>
+#include <net/xfrm.h>
+
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ip_tunnels.h>
+#include <net/gre.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/protocol.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_gre_vport_ops;
+
+static struct vport *gre_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct net_device *dev;
+	struct vport *vport;
+	int err;
+
+	vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	rtnl_lock();
+	dev = gretap_fb_dev_create(net, parms->name, NET_NAME_USER);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	if (err < 0) {
+		rtnl_delete_link(dev);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_PTR(err);
+	}
+
+	rtnl_unlock();
+	return vport;
+}
+
+static struct vport *gre_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = gre_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, parms->name);
+}
+
+static struct vport_ops ovs_gre_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GRE,
+	.create		= gre_create,
+	.send		= dev_queue_xmit,
+	.destroy	= ovs_netdev_tunnel_destroy,
+};
+
+static int __init ovs_gre_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_gre_vport_ops);
+}
+
+static void __exit ovs_gre_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_gre_vport_ops);
+}
+
+module_init(ovs_gre_tnl_init);
+module_exit(ovs_gre_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: GRE switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-3");

net/openvswitch/vport-internal_dev.c

@@ -0,0 +1,306 @@
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/skbuff.h>
+
+#include <net/dst.h>
+#include <net/xfrm.h>
+#include <net/rtnetlink.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+struct internal_dev {
+	struct vport *vport;
+};
+
+static struct vport_ops ovs_internal_vport_ops;
+
+static struct internal_dev *internal_dev_priv(struct net_device *netdev)
+{
+	return netdev_priv(netdev);
+}
+
+/* Called with rcu_read_lock_bh. */
+static netdev_tx_t
+internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	int len, err;
+
+	len = skb->len;
+	rcu_read_lock();
+	err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
+	rcu_read_unlock();
+
+	if (likely(!err)) {
+		struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);
+
+		u64_stats_update_begin(&tstats->syncp);
+		tstats->tx_bytes += len;
+		tstats->tx_packets++;
+		u64_stats_update_end(&tstats->syncp);
+	} else {
+		netdev->stats.tx_errors++;
+	}
+	return NETDEV_TX_OK;
+}
+
+static int internal_dev_open(struct net_device *netdev)
+{
+	netif_start_queue(netdev);
+	return 0;
+}
+
+static int internal_dev_stop(struct net_device *netdev)
+{
+	netif_stop_queue(netdev);
+	return 0;
+}
+
+static void internal_dev_getinfo(struct net_device *netdev,
+				 struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, "openvswitch", sizeof(info->driver));
+}
+
+static const struct ethtool_ops internal_dev_ethtool_ops = {
+	.get_drvinfo	= internal_dev_getinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+static void internal_dev_destructor(struct net_device *dev)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+	ovs_vport_free(vport);
+}
+
+static void
+internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	int i;
+
+	memset(stats, 0, sizeof(*stats));
+	stats->rx_errors  = dev->stats.rx_errors;
+	stats->tx_errors  = dev->stats.tx_errors;
+	stats->tx_dropped = dev->stats.tx_dropped;
+	stats->rx_dropped = dev->stats.rx_dropped;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_sw_netstats *percpu_stats;
+		struct pcpu_sw_netstats local_stats;
+		unsigned int start;
+
+		percpu_stats = per_cpu_ptr(dev->tstats, i);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
+			local_stats = *percpu_stats;
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
+
+		stats->rx_bytes         += local_stats.rx_bytes;
+		stats->rx_packets       += local_stats.rx_packets;
+		stats->tx_bytes         += local_stats.tx_bytes;
+		stats->tx_packets       += local_stats.tx_packets;
+	}
+}
+
+static const struct net_device_ops internal_dev_netdev_ops = {
+	.ndo_open = internal_dev_open,
+	.ndo_stop = internal_dev_stop,
+	.ndo_start_xmit = internal_dev_xmit,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_get_stats64 = internal_get_stats,
+};
+
+static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
+	.kind = "openvswitch",
+};
+
+static void do_setup(struct net_device *netdev)
+{
+	ether_setup(netdev);
+
+	netdev->max_mtu = ETH_MAX_MTU;
+
+	netdev->netdev_ops = &internal_dev_netdev_ops;
+
+	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
+			      IFF_NO_QUEUE;
+	netdev->needs_free_netdev = true;
+	netdev->priv_destructor = NULL;
+	netdev->ethtool_ops = &internal_dev_ethtool_ops;
+	netdev->rtnl_link_ops = &internal_dev_link_ops;
+
+	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
+			   NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+			   NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;
+
+	netdev->vlan_features = netdev->features;
+	netdev->hw_enc_features = netdev->features;
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
+
+	eth_hw_addr_random(netdev);
+}
+
+static struct vport *internal_dev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	struct internal_dev *internal_dev;
+	struct net_device *dev;
+	int err;
+
+	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	dev = alloc_netdev(sizeof(struct internal_dev),
+			   parms->name, NET_NAME_USER, do_setup);
+	vport->dev = dev;
+	if (!vport->dev) {
+		err = -ENOMEM;
+		goto error_free_vport;
+	}
+	vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!vport->dev->tstats) {
+		err = -ENOMEM;
+		goto error_free_netdev;
+	}
+
+	dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
+	internal_dev = internal_dev_priv(vport->dev);
+	internal_dev->vport = vport;
+
+	/* Restrict bridge port to current netns. */
+	if (vport->port_no == OVSP_LOCAL)
+		vport->dev->features |= NETIF_F_NETNS_LOCAL;
+
+	rtnl_lock();
+	err = register_netdevice(vport->dev);
+	if (err)
+		goto error_unlock;
+	vport->dev->priv_destructor = internal_dev_destructor;
+
+	dev_set_promiscuity(vport->dev, 1);
+	rtnl_unlock();
+	netif_start_queue(vport->dev);
+
+	return vport;
+
+error_unlock:
+	rtnl_unlock();
+	free_percpu(dev->tstats);
+error_free_netdev:
+	free_netdev(dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void internal_dev_destroy(struct vport *vport)
+{
+	netif_stop_queue(vport->dev);
+	rtnl_lock();
+	dev_set_promiscuity(vport->dev, -1);
+
+	/* unregister_netdevice() waits for an RCU grace period. */
+	unregister_netdevice(vport->dev);
+	free_percpu(vport->dev->tstats);
+	rtnl_unlock();
+}
+
+static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
+{
+	struct net_device *netdev = skb->dev;
+	struct pcpu_sw_netstats *stats;
+
+	if (unlikely(!(netdev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		netdev->stats.rx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	skb_dst_drop(skb);
+	nf_reset(skb);
+	secpath_reset(skb);
+
+	skb->pkt_type = PACKET_HOST;
+	skb->protocol = eth_type_trans(skb, netdev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+
+	stats = this_cpu_ptr(netdev->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 NETDEV_TX_OK;
+}
+
+static struct vport_ops ovs_internal_vport_ops = {
+	.type		= OVS_VPORT_TYPE_INTERNAL,
+	.create		= internal_dev_create,
+	.destroy	= internal_dev_destroy,
+	.send		= internal_dev_recv,
+};
+
+int ovs_is_internal_dev(const struct net_device *netdev)
+{
+	return netdev->netdev_ops == &internal_dev_netdev_ops;
+}
+
+struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
+{
+	if (!ovs_is_internal_dev(netdev))
+		return NULL;
+
+	return internal_dev_priv(netdev)->vport;
+}
+
+int ovs_internal_dev_rtnl_link_register(void)
+{
+	int err;
+
+	err = rtnl_link_register(&internal_dev_link_ops);
+	if (err < 0)
+		return err;
+
+	err = ovs_vport_ops_register(&ovs_internal_vport_ops);
+	if (err < 0)
+		rtnl_link_unregister(&internal_dev_link_ops);
+
+	return err;
+}
+
+void ovs_internal_dev_rtnl_link_unregister(void)
+{
+	ovs_vport_ops_unregister(&ovs_internal_vport_ops);
+	rtnl_link_unregister(&internal_dev_link_ops);
+}

net/openvswitch/vport-internal_dev.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (c) 2007-2011 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_INTERNAL_DEV_H
+#define VPORT_INTERNAL_DEV_H 1
+
+#include "datapath.h"
+#include "vport.h"
+
+int ovs_is_internal_dev(const struct net_device *);
+struct vport *ovs_internal_dev_get_vport(struct net_device *);
+int ovs_internal_dev_rtnl_link_register(void);
+void ovs_internal_dev_rtnl_link_unregister(void);
+
+#endif /* vport-internal_dev.h */

net/openvswitch/vport-netdev.c

@@ -0,0 +1,225 @@
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if_arp.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/llc.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <linux/openvswitch.h>
+#include <linux/export.h>
+
+#include <net/ip_tunnels.h>
+#include <net/rtnetlink.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_netdev_vport_ops;
+
+/* Must be called with rcu_read_lock. */
+static void netdev_port_receive(struct sk_buff *skb)
+{
+	struct vport *vport;
+
+	vport = ovs_netdev_get_vport(skb->dev);
+	if (unlikely(!vport))
+		goto error;
+
+	if (unlikely(skb_warn_if_lro(skb)))
+		goto error;
+
+	/* Make our own copy of the packet.  Otherwise we will mangle the
+	 * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
+	 */
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return;
+
+	if (skb->dev->type == ARPHRD_ETHER) {
+		skb_push(skb, ETH_HLEN);
+		skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+	}
+	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
+	return;
+error:
+	kfree_skb(skb);
+}
+
+/* Called with rcu_read_lock and bottom-halves disabled. */
+static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	netdev_port_receive(skb);
+	return RX_HANDLER_CONSUMED;
+}
+
+static struct net_device *get_dpdev(const struct datapath *dp)
+{
+	struct vport *local;
+
+	local = ovs_vport_ovsl(dp, OVSP_LOCAL);
+	BUG_ON(!local);
+	return local->dev;
+}
+
+struct vport *ovs_netdev_link(struct vport *vport, const char *name)
+{
+	int err;
+
+	vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name);
+	if (!vport->dev) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+
+	if (vport->dev->flags & IFF_LOOPBACK ||
+	    (vport->dev->type != ARPHRD_ETHER &&
+	     vport->dev->type != ARPHRD_NONE) ||
+	    ovs_is_internal_dev(vport->dev)) {
+		err = -EINVAL;
+		goto error_put;
+	}
+
+	rtnl_lock();
+	err = netdev_master_upper_dev_link(vport->dev,
+					   get_dpdev(vport->dp),
+					   NULL, NULL, NULL);
+	if (err)
+		goto error_unlock;
+
+	err = netdev_rx_handler_register(vport->dev, netdev_frame_hook,
+					 vport);
+	if (err)
+		goto error_master_upper_dev_unlink;
+
+	dev_disable_lro(vport->dev);
+	dev_set_promiscuity(vport->dev, 1);
+	vport->dev->priv_flags |= IFF_OVS_DATAPATH;
+	rtnl_unlock();
+
+	return vport;
+
+error_master_upper_dev_unlink:
+	netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp));
+error_unlock:
+	rtnl_unlock();
+error_put:
+	dev_put(vport->dev);
+error_free_vport:
+	ovs_vport_free(vport);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(ovs_netdev_link);
+
+static struct vport *netdev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, parms->name);
+}
+
+static void vport_netdev_free(struct rcu_head *rcu)
+{
+	struct vport *vport = container_of(rcu, struct vport, rcu);
+
+	if (vport->dev)
+		dev_put(vport->dev);
+	ovs_vport_free(vport);
+}
+
+void ovs_netdev_detach_dev(struct vport *vport)
+{
+	ASSERT_RTNL();
+	vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
+	netdev_rx_handler_unregister(vport->dev);
+	netdev_upper_dev_unlink(vport->dev,
+				netdev_master_upper_dev_get(vport->dev));
+	dev_set_promiscuity(vport->dev, -1);
+}
+
+static void netdev_destroy(struct vport *vport)
+{
+	rtnl_lock();
+	if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
+		ovs_netdev_detach_dev(vport);
+	rtnl_unlock();
+
+	call_rcu(&vport->rcu, vport_netdev_free);
+}
+
+void ovs_netdev_tunnel_destroy(struct vport *vport)
+{
+	rtnl_lock();
+	if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
+		ovs_netdev_detach_dev(vport);
+
+	/* We can be invoked by both explicit vport deletion and
+	 * underlying netdev deregistration; delete the link only
+	 * if it's not already shutting down.
+	 */
+	if (vport->dev->reg_state == NETREG_REGISTERED)
+		rtnl_delete_link(vport->dev);
+	dev_put(vport->dev);
+	vport->dev = NULL;
+	rtnl_unlock();
+
+	call_rcu(&vport->rcu, vport_netdev_free);
+}
+EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);
+
+/* Returns null if this device is not attached to a datapath. */
+struct vport *ovs_netdev_get_vport(struct net_device *dev)
+{
+	if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
+		return (struct vport *)
+			rcu_dereference_rtnl(dev->rx_handler_data);
+	else
+		return NULL;
+}
+
+static struct vport_ops ovs_netdev_vport_ops = {
+	.type		= OVS_VPORT_TYPE_NETDEV,
+	.create		= netdev_create,
+	.destroy	= netdev_destroy,
+	.send		= dev_queue_xmit,
+};
+
+int __init ovs_netdev_init(void)
+{
+	return ovs_vport_ops_register(&ovs_netdev_vport_ops);
+}
+
+void ovs_netdev_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_netdev_vport_ops);
+}

net/openvswitch/vport-netdev.h

@@ -0,0 +1,36 @@
+/*
+ * Copyright (c) 2007-2011 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_NETDEV_H
+#define VPORT_NETDEV_H 1
+
+#include <linux/netdevice.h>
+#include <linux/rcupdate.h>
+
+#include "vport.h"
+
+struct vport *ovs_netdev_get_vport(struct net_device *dev);
+
+struct vport *ovs_netdev_link(struct vport *vport, const char *name);
+void ovs_netdev_detach_dev(struct vport *);
+
+int __init ovs_netdev_init(void);
+void ovs_netdev_exit(void);
+
+void ovs_netdev_tunnel_destroy(struct vport *vport);
+#endif /* vport_netdev.h */

net/openvswitch/vport-vxlan.c

@@ -0,0 +1,182 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ * Copyright (c) 2013 Cisco Systems, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/openvswitch.h>
+#include <linux/module.h>
+#include <net/udp.h>
+#include <net/ip_tunnels.h>
+#include <net/rtnetlink.h>
+#include <net/vxlan.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_vxlan_netdev_vport_ops;
+
+static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vport->dev);
+	__be16 dst_port = vxlan->cfg.dst_port;
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
+		return -EMSGSIZE;
+
+	if (vxlan->cfg.flags & VXLAN_F_GBP) {
+		struct nlattr *exts;
+
+		exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION);
+		if (!exts)
+			return -EMSGSIZE;
+
+		if (vxlan->cfg.flags & VXLAN_F_GBP &&
+		    nla_put_flag(skb, OVS_VXLAN_EXT_GBP))
+			return -EMSGSIZE;
+
+		nla_nest_end(skb, exts);
+	}
+
+	return 0;
+}
+
+static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_FLAG, },
+};
+
+static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr,
+				struct vxlan_config *conf)
+{
+	struct nlattr *exts[OVS_VXLAN_EXT_MAX + 1];
+	int err;
+
+	if (nla_len(attr) < sizeof(struct nlattr))
+		return -EINVAL;
+
+	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy,
+			       NULL);
+	if (err < 0)
+		return err;
+
+	if (exts[OVS_VXLAN_EXT_GBP])
+		conf->flags |= VXLAN_F_GBP;
+
+	return 0;
+}
+
+static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct nlattr *options = parms->options;
+	struct net_device *dev;
+	struct vport *vport;
+	struct nlattr *a;
+	int err;
+	struct vxlan_config conf = {
+		.no_share = true,
+		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
+	};
+
+	if (!options) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+	if (a && nla_len(a) == sizeof(u16)) {
+		conf.dst_port = htons(nla_get_u16(a));
+	} else {
+		/* Require destination port from userspace. */
+		err = -EINVAL;
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
+	if (a) {
+		err = vxlan_configure_exts(vport, a, &conf);
+		if (err) {
+			ovs_vport_free(vport);
+			goto error;
+		}
+	}
+
+	rtnl_lock();
+	dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	if (err < 0) {
+		rtnl_delete_link(dev);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		goto error;
+	}
+
+	rtnl_unlock();
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static struct vport *vxlan_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = vxlan_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, parms->name);
+}
+
+static struct vport_ops ovs_vxlan_netdev_vport_ops = {
+	.type			= OVS_VPORT_TYPE_VXLAN,
+	.create			= vxlan_create,
+	.destroy		= ovs_netdev_tunnel_destroy,
+	.get_options		= vxlan_get_options,
+	.send			= dev_queue_xmit,
+};
+
+static int __init ovs_vxlan_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops);
+}
+
+static void __exit ovs_vxlan_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops);
+}
+
+module_init(ovs_vxlan_tnl_init);
+module_exit(ovs_vxlan_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: VXLAN switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-4");

net/openvswitch/vport.c

@@ -0,0 +1,522 @@
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/if.h>
+#include <linux/if_vlan.h>
+#include <linux/jhash.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+#include <linux/compat.h>
+#include <net/net_namespace.h>
+#include <linux/module.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-internal_dev.h"
+
+static LIST_HEAD(vport_ops_list);
+
+/* Protected by RCU read lock for reading, ovs_mutex for writing. */
+static struct hlist_head *dev_table;
+#define VPORT_HASH_BUCKETS 1024
+
+/**
+ *	ovs_vport_init - initialize vport subsystem
+ *
+ * Called at module load time to initialize the vport subsystem.
+ */
+int ovs_vport_init(void)
+{
+	dev_table = kcalloc(VPORT_HASH_BUCKETS, sizeof(struct hlist_head),
+			    GFP_KERNEL);
+	if (!dev_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ *	ovs_vport_exit - shutdown vport subsystem
+ *
+ * Called at module exit time to shutdown the vport subsystem.
+ */
+void ovs_vport_exit(void)
+{
+	kfree(dev_table);
+}
+
+static struct hlist_head *hash_bucket(const struct net *net, const char *name)
+{
+	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
+	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
+}
+
+int __ovs_vport_ops_register(struct vport_ops *ops)
+{
+	int err = -EEXIST;
+	struct vport_ops *o;
+
+	ovs_lock();
+	list_for_each_entry(o, &vport_ops_list, list)
+		if (ops->type == o->type)
+			goto errout;
+
+	list_add_tail(&ops->list, &vport_ops_list);
+	err = 0;
+errout:
+	ovs_unlock();
+	return err;
+}
+EXPORT_SYMBOL_GPL(__ovs_vport_ops_register);
+
+void ovs_vport_ops_unregister(struct vport_ops *ops)
+{
+	ovs_lock();
+	list_del(&ops->list);
+	ovs_unlock();
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
+
+/**
+ *	ovs_vport_locate - find a port that has already been created
+ *
+ * @name: name of port to find
+ *
+ * Must be called with ovs or RCU read lock.
+ */
+struct vport *ovs_vport_locate(const struct net *net, const char *name)
+{
+	struct hlist_head *bucket = hash_bucket(net, name);
+	struct vport *vport;
+
+	hlist_for_each_entry_rcu(vport, bucket, hash_node)
+		if (!strcmp(name, ovs_vport_name(vport)) &&
+		    net_eq(ovs_dp_get_net(vport->dp), net))
+			return vport;
+
+	return NULL;
+}
+
+/**
+ *	ovs_vport_alloc - allocate and initialize new vport
+ *
+ * @priv_size: Size of private data area to allocate.
+ * @ops: vport device ops
+ *
+ * Allocate and initialize a new vport defined by @ops.  The vport will contain
+ * a private data area of size @priv_size that can be accessed using
+ * vport_priv().  vports that are no longer needed should be released with
+ * vport_free().
+ */
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
+			  const struct vport_parms *parms)
+{
+	struct vport *vport;
+	size_t alloc_size;
+
+	alloc_size = sizeof(struct vport);
+	if (priv_size) {
+		alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
+		alloc_size += priv_size;
+	}
+
+	vport = kzalloc(alloc_size, GFP_KERNEL);
+	if (!vport)
+		return ERR_PTR(-ENOMEM);
+
+	vport->dp = parms->dp;
+	vport->port_no = parms->port_no;
+	vport->ops = ops;
+	INIT_HLIST_NODE(&vport->dp_hash_node);
+
+	if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
+		kfree(vport);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return vport;
+}
+EXPORT_SYMBOL_GPL(ovs_vport_alloc);
+
+/**
+ *	ovs_vport_free - uninitialize and free vport
+ *
+ * @vport: vport to free
+ *
+ * Frees a vport allocated with vport_alloc() when it is no longer needed.
+ *
+ * The caller must ensure that an RCU grace period has passed since the last
+ * time @vport was in a datapath.
+ */
+void ovs_vport_free(struct vport *vport)
+{
+	/* vport is freed from RCU callback or error path, Therefore
+	 * it is safe to use raw dereference.
+	 */
+	kfree(rcu_dereference_raw(vport->upcall_portids));
+	kfree(vport);
+}
+EXPORT_SYMBOL_GPL(ovs_vport_free);
+
+static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+
+	list_for_each_entry(ops, &vport_ops_list, list)
+		if (ops->type == parms->type)
+			return ops;
+
+	return NULL;
+}
+
+/**
+ *	ovs_vport_add - add vport device (for kernel callers)
+ *
+ * @parms: Information about new vport.
+ *
+ * Creates a new vport with the specified configuration (which is dependent on
+ * device type).  ovs_mutex must be held.
+ */
+struct vport *ovs_vport_add(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+	struct vport *vport;
+
+	ops = ovs_vport_lookup(parms);
+	if (ops) {
+		struct hlist_head *bucket;
+
+		if (!try_module_get(ops->owner))
+			return ERR_PTR(-EAFNOSUPPORT);
+
+		vport = ops->create(parms);
+		if (IS_ERR(vport)) {
+			module_put(ops->owner);
+			return vport;
+		}
+
+		bucket = hash_bucket(ovs_dp_get_net(vport->dp),
+				     ovs_vport_name(vport));
+		hlist_add_head_rcu(&vport->hash_node, bucket);
+		return vport;
+	}
+
+	/* Unlock to attempt module load and return -EAGAIN if load
+	 * was successful as we need to restart the port addition
+	 * workflow.
+	 */
+	ovs_unlock();
+	request_module("vport-type-%d", parms->type);
+	ovs_lock();
+
+	if (!ovs_vport_lookup(parms))
+		return ERR_PTR(-EAFNOSUPPORT);
+	else
+		return ERR_PTR(-EAGAIN);
+}
+
+/**
+ *	ovs_vport_set_options - modify existing vport device (for kernel callers)
+ *
+ * @vport: vport to modify.
+ * @options: New configuration.
+ *
+ * Modifies an existing device with the specified configuration (which is
+ * dependent on device type).  ovs_mutex must be held.
+ */
+int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
+{
+	if (!vport->ops->set_options)
+		return -EOPNOTSUPP;
+	return vport->ops->set_options(vport, options);
+}
+
+/**
+ *	ovs_vport_del - delete existing vport device
+ *
+ * @vport: vport to delete.
+ *
+ * Detaches @vport from its datapath and destroys it.  ovs_mutex must
+ * be held.
+ */
+void ovs_vport_del(struct vport *vport)
+{
+	ASSERT_OVSL();
+
+	hlist_del_rcu(&vport->hash_node);
+	module_put(vport->ops->owner);
+	vport->ops->destroy(vport);
+}
+
+/**
+ *	ovs_vport_get_stats - retrieve device stats
+ *
+ * @vport: vport from which to retrieve the stats
+ * @stats: location to store stats
+ *
+ * Retrieves transmit, receive, and error stats for the given device.
+ *
+ * Must be called with ovs_mutex or rcu_read_lock.
+ */
+void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
+{
+	const struct rtnl_link_stats64 *dev_stats;
+	struct rtnl_link_stats64 temp;
+
+	dev_stats = dev_get_stats(vport->dev, &temp);
+	stats->rx_errors  = dev_stats->rx_errors;
+	stats->tx_errors  = dev_stats->tx_errors;
+	stats->tx_dropped = dev_stats->tx_dropped;
+	stats->rx_dropped = dev_stats->rx_dropped;
+
+	stats->rx_bytes	  = dev_stats->rx_bytes;
+	stats->rx_packets = dev_stats->rx_packets;
+	stats->tx_bytes	  = dev_stats->tx_bytes;
+	stats->tx_packets = dev_stats->tx_packets;
+}
+
+/**
+ *	ovs_vport_get_options - retrieve device options
+ *
+ * @vport: vport from which to retrieve the options.
+ * @skb: sk_buff where options should be appended.
+ *
+ * Retrieves the configuration of the given device, appending an
+ * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
+ * vport-specific attributes to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
+ * negative error code if a real error occurred.  If an error occurs, @skb is
+ * left unmodified.
+ *
+ * Must be called with ovs_mutex or rcu_read_lock.
+ */
+int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+	struct nlattr *nla;
+	int err;
+
+	if (!vport->ops->get_options)
+		return 0;
+
+	nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	err = vport->ops->get_options(vport, skb);
+	if (err) {
+		nla_nest_cancel(skb, nla);
+		return err;
+	}
+
+	nla_nest_end(skb, nla);
+	return 0;
+}
+
+/**
+ *	ovs_vport_set_upcall_portids - set upcall portids of @vport.
+ *
+ * @vport: vport to modify.
+ * @ids: new configuration, an array of port ids.
+ *
+ * Sets the vport's upcall_portids to @ids.
+ *
+ * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
+ * as an array of U32.
+ *
+ * Must be called with ovs_mutex.
+ */
+int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
+{
+	struct vport_portids *old, *vport_portids;
+
+	if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
+		return -EINVAL;
+
+	old = ovsl_dereference(vport->upcall_portids);
+
+	vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
+				GFP_KERNEL);
+	if (!vport_portids)
+		return -ENOMEM;
+
+	vport_portids->n_ids = nla_len(ids) / sizeof(u32);
+	vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids);
+	nla_memcpy(vport_portids->ids, ids, nla_len(ids));
+
+	rcu_assign_pointer(vport->upcall_portids, vport_portids);
+
+	if (old)
+		kfree_rcu(old, rcu);
+	return 0;
+}
+
+/**
+ *	ovs_vport_get_upcall_portids - get the upcall_portids of @vport.
+ *
+ * @vport: vport from which to retrieve the portids.
+ * @skb: sk_buff where portids should be appended.
+ *
+ * Retrieves the configuration of the given vport, appending the
+ * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall
+ * portids to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room.
+ * If an error occurs, @skb is left unmodified.  Must be called with
+ * ovs_mutex or rcu_read_lock.
+ */
+int ovs_vport_get_upcall_portids(const struct vport *vport,
+				 struct sk_buff *skb)
+{
+	struct vport_portids *ids;
+
+	ids = rcu_dereference_ovsl(vport->upcall_portids);
+
+	if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS)
+		return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID,
+			       ids->n_ids * sizeof(u32), (void *)ids->ids);
+	else
+		return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]);
+}
+
+/**
+ *	ovs_vport_find_upcall_portid - find the upcall portid to send upcall.
+ *
+ * @vport: vport from which the missed packet is received.
+ * @skb: skb that the missed packet was received.
+ *
+ * Uses the skb_get_hash() to select the upcall portid to send the
+ * upcall.
+ *
+ * Returns the portid of the target socket.  Must be called with rcu_read_lock.
+ */
+u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
+{
+	struct vport_portids *ids;
+	u32 ids_index;
+	u32 hash;
+
+	ids = rcu_dereference(vport->upcall_portids);
+
+	if (ids->n_ids == 1 && ids->ids[0] == 0)
+		return 0;
+
+	hash = skb_get_hash(skb);
+	ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids);
+	return ids->ids[ids_index];
+}
+
+/**
+ *	ovs_vport_receive - pass up received packet to the datapath for processing
+ *
+ * @vport: vport that received the packet
+ * @skb: skb that was received
+ * @tun_key: tunnel (if any) that carried packet
+ *
+ * Must be called with rcu_read_lock.  The packet cannot be shared and
+ * skb->data should point to the Ethernet header.
+ */
+int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
+		      const struct ip_tunnel_info *tun_info)
+{
+	struct sw_flow_key key;
+	int error;
+
+	OVS_CB(skb)->input_vport = vport;
+	OVS_CB(skb)->mru = 0;
+	OVS_CB(skb)->cutlen = 0;
+	if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
+		u32 mark;
+
+		mark = skb->mark;
+		skb_scrub_packet(skb, true);
+		skb->mark = mark;
+		tun_info = NULL;
+	}
+
+	/* Extract flow from 'skb' into 'key'. */
+	error = ovs_flow_key_extract(tun_info, skb, &key);
+	if (unlikely(error)) {
+		kfree_skb(skb);
+		return error;
+	}
+	ovs_dp_process_packet(skb, &key);
+	return 0;
+}
+
+static int packet_length(const struct sk_buff *skb,
+			 struct net_device *dev)
+{
+	int length = skb->len - dev->hard_header_len;
+
+	if (!skb_vlan_tag_present(skb) &&
+	    eth_type_vlan(skb->protocol))
+		length -= VLAN_HLEN;
+
+	/* Don't subtract for multiple VLAN tags. Most (all?) drivers allow
+	 * (ETH_LEN + VLAN_HLEN) in addition to the mtu value, but almost none
+	 * account for 802.1ad. e.g. is_skb_forwardable().
+	 */
+
+	return length > 0 ? length : 0;
+}
+
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
+{
+	int mtu = vport->dev->mtu;
+
+	switch (vport->dev->type) {
+	case ARPHRD_NONE:
+		if (mac_proto == MAC_PROTO_ETHERNET) {
+			skb_reset_network_header(skb);
+			skb_reset_mac_len(skb);
+			skb->protocol = htons(ETH_P_TEB);
+		} else if (mac_proto != MAC_PROTO_NONE) {
+			WARN_ON_ONCE(1);
+			goto drop;
+		}
+		break;
+	case ARPHRD_ETHER:
+		if (mac_proto != MAC_PROTO_ETHERNET)
+			goto drop;
+		break;
+	default:
+		goto drop;
+	}
+
+	if (unlikely(packet_length(skb, vport->dev) > mtu &&
+		     !skb_is_gso(skb))) {
+		net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
+				     vport->dev->name,
+				     packet_length(skb, vport->dev), mtu);
+		vport->dev->stats.tx_errors++;
+		goto drop;
+	}
+
+	skb->dev = vport->dev;
+	vport->ops->send(skb);
+	return;
+
+drop:
+	kfree_skb(skb);
+}

net/openvswitch/vport.h

@@ -0,0 +1,202 @@
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_H
+#define VPORT_H 1
+
+#include <linux/if_tunnel.h>
+#include <linux/list.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/reciprocal_div.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/u64_stats_sync.h>
+
+#include "datapath.h"
+
+struct vport;
+struct vport_parms;
+
+/* The following definitions are for users of the vport subsytem: */
+
+int ovs_vport_init(void);
+void ovs_vport_exit(void);
+
+struct vport *ovs_vport_add(const struct vport_parms *);
+void ovs_vport_del(struct vport *);
+
+struct vport *ovs_vport_locate(const struct net *net, const char *name);
+
+void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
+
+int ovs_vport_set_options(struct vport *, struct nlattr *options);
+int ovs_vport_get_options(const struct vport *, struct sk_buff *);
+
+int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids);
+int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *);
+u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
+
+/**
+ * struct vport_portids - array of netlink portids of a vport.
+ *                        must be protected by rcu.
+ * @rn_ids: The reciprocal value of @n_ids.
+ * @rcu: RCU callback head for deferred destruction.
+ * @n_ids: Size of @ids array.
+ * @ids: Array storing the Netlink socket pids to be used for packets received
+ * on this port that miss the flow table.
+ */
+struct vport_portids {
+	struct reciprocal_value rn_ids;
+	struct rcu_head rcu;
+	u32 n_ids;
+	u32 ids[];
+};
+
+/**
+ * struct vport - one port within a datapath
+ * @dev: Pointer to net_device.
+ * @dp: Datapath to which this port belongs.
+ * @upcall_portids: RCU protected 'struct vport_portids'.
+ * @port_no: Index into @dp's @ports array.
+ * @hash_node: Element in @dev_table hash table in vport.c.
+ * @dp_hash_node: Element in @datapath->ports hash table in datapath.c.
+ * @ops: Class structure.
+ * @detach_list: list used for detaching vport in net-exit call.
+ * @rcu: RCU callback head for deferred destruction.
+ */
+struct vport {
+	struct net_device *dev;
+	struct datapath	*dp;
+	struct vport_portids __rcu *upcall_portids;
+	u16 port_no;
+
+	struct hlist_node hash_node;
+	struct hlist_node dp_hash_node;
+	const struct vport_ops *ops;
+
+	struct list_head detach_list;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct vport_parms - parameters for creating a new vport
+ *
+ * @name: New vport's name.
+ * @type: New vport's type.
+ * @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
+ * none was supplied.
+ * @dp: New vport's datapath.
+ * @port_no: New vport's port number.
+ */
+struct vport_parms {
+	const char *name;
+	enum ovs_vport_type type;
+	struct nlattr *options;
+
+	/* For ovs_vport_alloc(). */
+	struct datapath *dp;
+	u16 port_no;
+	struct nlattr *upcall_portids;
+};
+
+/**
+ * struct vport_ops - definition of a type of virtual port
+ *
+ * @type: %OVS_VPORT_TYPE_* value for this type of virtual port.
+ * @create: Create a new vport configured as specified.  On success returns
+ * a new vport allocated with ovs_vport_alloc(), otherwise an ERR_PTR() value.
+ * @destroy: Destroys a vport.  Must call vport_free() on the vport but not
+ * before an RCU grace period has elapsed.
+ * @set_options: Modify the configuration of an existing vport.  May be %NULL
+ * if modification is not supported.
+ * @get_options: Appends vport-specific attributes for the configuration of an
+ * existing vport to a &struct sk_buff.  May be %NULL for a vport that does not
+ * have any configuration.
+ * @send: Send a packet on the device.
+ * zero for dropped packets or negative for error.
+ */
+struct vport_ops {
+	enum ovs_vport_type type;
+
+	/* Called with ovs_mutex. */
+	struct vport *(*create)(const struct vport_parms *);
+	void (*destroy)(struct vport *);
+
+	int (*set_options)(struct vport *, struct nlattr *);
+	int (*get_options)(const struct vport *, struct sk_buff *);
+
+	netdev_tx_t (*send) (struct sk_buff *skb);
+	struct module *owner;
+	struct list_head list;
+};
+
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
+			      const struct vport_parms *);
+void ovs_vport_free(struct vport *);
+
+#define VPORT_ALIGN 8
+
+/**
+ *	vport_priv - access private data area of vport
+ *
+ * @vport: vport to access
+ *
+ * If a nonzero size was passed in priv_size of vport_alloc() a private data
+ * area was allocated on creation.  This allows that area to be accessed and
+ * used for any purpose needed by the vport implementer.
+ */
+static inline void *vport_priv(const struct vport *vport)
+{
+	return (u8 *)(uintptr_t)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+}
+
+/**
+ *	vport_from_priv - lookup vport from private data pointer
+ *
+ * @priv: Start of private data area.
+ *
+ * It is sometimes useful to translate from a pointer to the private data
+ * area to the vport, such as in the case where the private data pointer is
+ * the result of a hash table lookup.  @priv must point to the start of the
+ * private data area.
+ */
+static inline struct vport *vport_from_priv(void *priv)
+{
+	return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+}
+
+int ovs_vport_receive(struct vport *, struct sk_buff *,
+		      const struct ip_tunnel_info *);
+
+static inline const char *ovs_vport_name(struct vport *vport)
+{
+	return vport->dev->name;
+}
+
+int __ovs_vport_ops_register(struct vport_ops *ops);
+#define ovs_vport_ops_register(ops)		\
+	({					\
+		(ops)->owner = THIS_MODULE;	\
+		__ovs_vport_ops_register(ops);	\
+	})
+
+void ovs_vport_ops_unregister(struct vport_ops *ops);
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto);
+
+#endif /* vport.h */