net: Add Open vSwitch kernel components.

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.

Signed-off-by: Jesse Gross <jesse@nicira.com>

16 files changed, 5217 insertions, 0 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 2d998735c4d8..e07272d0bb2d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -215,6 +215,7 @@ source "net/sched/Kconfig"
 source "net/dcb/Kconfig"
 source "net/dns_resolver/Kconfig"
 source "net/batman-adv/Kconfig"
+source "net/openvswitch/Kconfig"
 
 config RPS
 	boolean
diff --git a/net/Makefile b/net/Makefile
index acdde4950de4..ad432fa4d934 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -69,3 +69,4 @@ obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
 obj-$(CONFIG_CEPH_LIB)		+= ceph/
 obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
 obj-$(CONFIG_NFC)		+= nfc/
+obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
new file mode 100644
index 000000000000..d9ea33c361be
--- /dev/null
+++ b/net/openvswitch/Kconfig
@@ -0,0 +1,28 @@
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+	tristate "Open vSwitch"
+	---help---
+	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
+	  environments.  In addition to supporting a variety of features
+	  expected in a traditional hardware switch, it enables fine-grained
+	  programmatic extension and flow-based control of the network.  This
+	  control is useful in a wide variety of applications but is
+	  particularly important in multi-server virtualization deployments,
+	  which are often characterized by highly dynamic endpoints and the
+	  need to maintain logical abstractions for multiple tenants.
+
+	  The Open vSwitch datapath provides an in-kernel fast path for packet
+	  forwarding.  It is complemented by a userspace daemon, ovs-vswitchd,
+	  which is able to accept configuration from a variety of sources and
+	  translate it into packet processing rules.
+
+	  See http://openvswitch.org for more information and userspace
+	  utilities.
+
+	  To compile this code as a module, choose M here: the module will be
+	  called openvswitch.
+
+	  If unsure, say N.
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
new file mode 100644
index 000000000000..15e7384745c1
--- /dev/null
+++ b/net/openvswitch/Makefile
@@ -0,0 +1,14 @@
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+	actions.o \
+	datapath.o \
+	dp_notify.o \
+	flow.o \
+	vport.o \
+	vport-internal_dev.o \
+	vport-netdev.o \
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
new file mode 100644
index 000000000000..2725d1bdf291
--- /dev/null
+++ b/net/openvswitch/actions.c
@@ -0,0 +1,415 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * 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/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/openvswitch.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/in6.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct nlattr *attr, int len, bool keep_skb);
+
+static int make_writable(struct sk_buff *skb, int write_len)
+{
+	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+		return 0;
+
+	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
+/* remove VLAN header from packet and update csum accrodingly. */
+static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
+{
+	struct vlan_hdr *vhdr;
+	int err;
+
+	err = make_writable(skb, VLAN_ETH_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+					+ ETH_HLEN, VLAN_HLEN, 0));
+
+	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+	*current_tci = vhdr->h_vlan_TCI;
+
+	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+	__skb_pull(skb, VLAN_HLEN);
+
+	vlan_set_encap_proto(skb, vhdr);
+	skb->mac_header += VLAN_HLEN;
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+
+static int pop_vlan(struct sk_buff *skb)
+{
+	__be16 tci;
+	int err;
+
+	if (likely(vlan_tx_tag_present(skb))) {
+		skb->vlan_tci = 0;
+	} else {
+		if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
+			     skb->len < VLAN_ETH_HLEN))
+			return 0;
+
+		err = __pop_vlan_tci(skb, &tci);
+		if (err)
+			return err;
+	}
+	/* move next vlan tag to hw accel tag */
+	if (likely(skb->protocol != htons(ETH_P_8021Q) ||
+		   skb->len < VLAN_ETH_HLEN))
+		return 0;
+
+	err = __pop_vlan_tci(skb, &tci);
+	if (unlikely(err))
+		return err;
+
+	__vlan_hwaccel_put_tag(skb, ntohs(tci));
+	return 0;
+}
+
+static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+{
+	if (unlikely(vlan_tx_tag_present(skb))) {
+		u16 current_tag;
+
+		/* push down current VLAN tag */
+		current_tag = vlan_tx_tag_get(skb);
+
+		if (!__vlan_put_tag(skb, current_tag))
+			return -ENOMEM;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_add(skb->csum, csum_partial(skb->data
+					+ ETH_HLEN, VLAN_HLEN, 0));
+
+	}
+	__vlan_hwaccel_put_tag(skb, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+	return 0;
+}
+
+static int set_eth_addr(struct sk_buff *skb,
+			const struct ovs_key_ethernet *eth_key)
+{
+	int err;
+	err = make_writable(skb, ETH_HLEN);
+	if (unlikely(err))
+		return err;
+
+	memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
+	memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+
+	return 0;
+}
+
+static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
+				__be32 *addr, __be32 new_addr)
+{
+	int transport_len = skb->len - skb_transport_offset(skb);
+
+	if (nh->protocol == IPPROTO_TCP) {
+		if (likely(transport_len >= sizeof(struct tcphdr)))
+			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
+						 *addr, new_addr, 1);
+	} else if (nh->protocol == IPPROTO_UDP) {
+		if (likely(transport_len >= sizeof(struct udphdr)))
+			inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
+						 *addr, new_addr, 1);
+	}
+
+	csum_replace4(&nh->check, *addr, new_addr);
+	skb->rxhash = 0;
+	*addr = new_addr;
+}
+
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
+{
+	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
+	nh->ttl = new_ttl;
+}
+
+static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+{
+	struct iphdr *nh;
+	int err;
+
+	err = make_writable(skb, skb_network_offset(skb) +
+				 sizeof(struct iphdr));
+	if (unlikely(err))
+		return err;
+
+	nh = ip_hdr(skb);
+
+	if (ipv4_key->ipv4_src != nh->saddr)
+		set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
+
+	if (ipv4_key->ipv4_dst != nh->daddr)
+		set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+
+	if (ipv4_key->ipv4_tos != nh->tos)
+		ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+
+	if (ipv4_key->ipv4_ttl != nh->ttl)
+		set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+
+	return 0;
+}
+
+/* Must follow make_writable() since that can move the skb data. */
+static void set_tp_port(struct sk_buff *skb, __be16 *port,
+			 __be16 new_port, __sum16 *check)
+{
+	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
+	*port = new_port;
+	skb->rxhash = 0;
+}
+
+static int set_udp_port(struct sk_buff *skb,
+			const struct ovs_key_udp *udp_port_key)
+{
+	struct udphdr *uh;
+	int err;
+
+	err = make_writable(skb, skb_transport_offset(skb) +
+				 sizeof(struct udphdr));
+	if (unlikely(err))
+		return err;
+
+	uh = udp_hdr(skb);
+	if (udp_port_key->udp_src != uh->source)
+		set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+
+	if (udp_port_key->udp_dst != uh->dest)
+		set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+
+	return 0;
+}
+
+static int set_tcp_port(struct sk_buff *skb,
+			const struct ovs_key_tcp *tcp_port_key)
+{
+	struct tcphdr *th;
+	int err;
+
+	err = make_writable(skb, skb_transport_offset(skb) +
+				 sizeof(struct tcphdr));
+	if (unlikely(err))
+		return err;
+
+	th = tcp_hdr(skb);
+	if (tcp_port_key->tcp_src != th->source)
+		set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
+
+	if (tcp_port_key->tcp_dst != th->dest)
+		set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+
+	return 0;
+}
+
+static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+{
+	struct vport *vport;
+
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	vport = rcu_dereference(dp->ports[out_port]);
+	if (unlikely(!vport)) {
+		kfree_skb(skb);
+		return -ENODEV;
+	}
+
+	ovs_vport_send(vport, skb);
+	return 0;
+}
+
+static int output_userspace(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{
+	struct dp_upcall_info upcall;
+	const struct nlattr *a;
+	int rem;
+
+	upcall.cmd = OVS_PACKET_CMD_ACTION;
+	upcall.key = &OVS_CB(skb)->flow->key;
+	upcall.userdata = NULL;
+	upcall.pid = 0;
+
+	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+		 a = nla_next(a, &rem)) {
+		switch (nla_type(a)) {
+		case OVS_USERSPACE_ATTR_USERDATA:
+			upcall.userdata = a;
+			break;
+
+		case OVS_USERSPACE_ATTR_PID:
+			upcall.pid = nla_get_u32(a);
+			break;
+		}
+	}
+
+	return ovs_dp_upcall(dp, skb, &upcall);
+}
+
+static int sample(struct datapath *dp, struct sk_buff *skb,
+		  const struct nlattr *attr)
+{
+	const struct nlattr *acts_list = NULL;
+	const struct nlattr *a;
+	int rem;
+
+	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+		 a = nla_next(a, &rem)) {
+		switch (nla_type(a)) {
+		case OVS_SAMPLE_ATTR_PROBABILITY:
+			if (net_random() >= nla_get_u32(a))
+				return 0;
+			break;
+
+		case OVS_SAMPLE_ATTR_ACTIONS:
+			acts_list = a;
+			break;
+		}
+	}
+
+	return do_execute_actions(dp, skb, nla_data(acts_list),
+						 nla_len(acts_list), true);
+}
+
+static int execute_set_action(struct sk_buff *skb,
+				 const struct nlattr *nested_attr)
+{
+	int err = 0;
+
+	switch (nla_type(nested_attr)) {
+	case OVS_KEY_ATTR_PRIORITY:
+		skb->priority = nla_get_u32(nested_attr);
+		break;
+
+	case OVS_KEY_ATTR_ETHERNET:
+		err = set_eth_addr(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_IPV4:
+		err = set_ipv4(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_TCP:
+		err = set_tcp_port(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_UDP:
+		err = set_udp_port(skb, nla_data(nested_attr));
+		break;
+	}
+
+	return err;
+}
+
+/* Execute a list of actions against 'skb'. */
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct nlattr *attr, int len, bool keep_skb)
+{
+	/* Every output action needs a separate clone of 'skb', but the common
+	 * case is just a single output action, so that doing a clone and
+	 * then freeing the original skbuff is wasteful.  So the following code
+	 * is slightly obscure just to avoid that. */
+	int prev_port = -1;
+	const struct nlattr *a;
+	int rem;
+
+	for (a = attr, rem = len; rem > 0;
+	     a = nla_next(a, &rem)) {
+		int err = 0;
+
+		if (prev_port != -1) {
+			do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+			prev_port = -1;
+		}
+
+		switch (nla_type(a)) {
+		case OVS_ACTION_ATTR_OUTPUT:
+			prev_port = nla_get_u32(a);
+			break;
+
+		case OVS_ACTION_ATTR_USERSPACE:
+			output_userspace(dp, skb, a);
+			break;
+
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+			err = push_vlan(skb, nla_data(a));
+			if (unlikely(err)) /* skb already freed. */
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_POP_VLAN:
+			err = pop_vlan(skb);
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			err = execute_set_action(skb, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			err = sample(dp, skb, a);
+			break;
+		}
+
+		if (unlikely(err)) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
+	if (prev_port != -1) {
+		if (keep_skb)
+			skb = skb_clone(skb, GFP_ATOMIC);
+
+		do_output(dp, skb, prev_port);
+	} else if (!keep_skb)
+		consume_skb(skb);
+
+	return 0;
+}
+
+/* Execute a list of actions against 'skb'. */
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
+{
+	struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+	return do_execute_actions(dp, skb, acts->actions,
+					 acts->actions_len, false);
+}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
new file mode 100644
index 000000000000..9a2725114e99
--- /dev/null
+++ b/net/openvswitch/datapath.c
@@ -0,0 +1,1912 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * 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/init.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/jhash.h>
+#include <linux/delay.h>
+#include <linux/time.h>
+#include <linux/etherdevice.h>
+#include <linux/genetlink.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/version.h>
+#include <linux/ethtool.h>
+#include <linux/wait.h>
+#include <asm/system.h>
+#include <asm/div64.h>
+#include <linux/highmem.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/inetdevice.h>
+#include <linux/list.h>
+#include <linux/openvswitch.h>
+#include <linux/rculist.h>
+#include <linux/dmi.h>
+#include <linux/workqueue.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "flow.h"
+#include "vport-internal_dev.h"
+
+/**
+ * DOC: Locking:
+ *
+ * Writes to device state (add/remove datapath, port, set operations on vports,
+ * etc.) are protected by RTNL.
+ *
+ * Writes to other state (flow table modifications, set miscellaneous datapath
+ * parameters, etc.) are protected by genl_mutex.  The RTNL lock nests inside
+ * genl_mutex.
+ *
+ * Reads are protected by RCU.
+ *
+ * There are a few special cases (mostly stats) that have their own
+ * synchronization but they nest under all of above and don't interact with
+ * each other.
+ */
+
+/* Global list of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ */
+static LIST_HEAD(dps);
+
+#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
+static void rehash_flow_table(struct work_struct *work);
+static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);
+
+static struct vport *new_vport(const struct vport_parms *);
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *,
+			     const struct dp_upcall_info *);
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *,
+				  const struct dp_upcall_info *);
+
+/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */
+static struct datapath *get_dp(int dp_ifindex)
+{
+	struct datapath *dp = NULL;
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(&init_net, dp_ifindex);
+	if (dev) {
+		struct vport *vport = ovs_internal_dev_get_vport(dev);
+		if (vport)
+			dp = vport->dp;
+	}
+	rcu_read_unlock();
+
+	return dp;
+}
+
+/* Must be called with rcu_read_lock or RTNL lock. */
+const char *ovs_dp_name(const struct datapath *dp)
+{
+	struct vport *vport = rcu_dereference_rtnl(dp->ports[OVSP_LOCAL]);
+	return vport->ops->get_name(vport);
+}
+
+static int get_dpifindex(struct datapath *dp)
+{
+	struct vport *local;
+	int ifindex;
+
+	rcu_read_lock();
+
+	local = rcu_dereference(dp->ports[OVSP_LOCAL]);
+	if (local)
+		ifindex = local->ops->get_ifindex(local);
+	else
+		ifindex = 0;
+
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
+static void destroy_dp_rcu(struct rcu_head *rcu)
+{
+	struct datapath *dp = container_of(rcu, struct datapath, rcu);
+
+	ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
+	free_percpu(dp->stats_percpu);
+	kfree(dp);
+}
+
+/* Called with RTNL lock and genl_lock. */
+static struct vport *new_vport(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = ovs_vport_add(parms);
+	if (!IS_ERR(vport)) {
+		struct datapath *dp = parms->dp;
+
+		rcu_assign_pointer(dp->ports[parms->port_no], vport);
+		list_add(&vport->node, &dp->port_list);
+	}
+
+	return vport;
+}
+
+/* Called with RTNL lock. */
+void ovs_dp_detach_port(struct vport *p)
+{
+	ASSERT_RTNL();
+
+	/* First drop references to device. */
+	list_del(&p->node);
+	rcu_assign_pointer(p->dp->ports[p->port_no], NULL);
+
+	/* Then destroy it. */
+	ovs_vport_del(p);
+}
+
+/* Must be called with rcu_read_lock. */
+void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
+{
+	struct datapath *dp = p->dp;
+	struct sw_flow *flow;
+	struct dp_stats_percpu *stats;
+	struct sw_flow_key key;
+	u64 *stats_counter;
+	int error;
+	int key_len;
+
+	stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+	/* Extract flow from 'skb' into 'key'. */
+	error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
+	if (unlikely(error)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	/* Look up flow. */
+	flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table), &key, key_len);
+	if (unlikely(!flow)) {
+		struct dp_upcall_info upcall;
+
+		upcall.cmd = OVS_PACKET_CMD_MISS;
+		upcall.key = &key;
+		upcall.userdata = NULL;
+		upcall.pid = p->upcall_pid;
+		ovs_dp_upcall(dp, skb, &upcall);
+		consume_skb(skb);
+		stats_counter = &stats->n_missed;
+		goto out;
+	}
+
+	OVS_CB(skb)->flow = flow;
+
+	stats_counter = &stats->n_hit;
+	ovs_flow_used(OVS_CB(skb)->flow, skb);
+	ovs_execute_actions(dp, skb);
+
+out:
+	/* Update datapath statistics. */
+	u64_stats_update_begin(&stats->sync);
+	(*stats_counter)++;
+	u64_stats_update_end(&stats->sync);
+}
+
+static struct genl_family dp_packet_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_PACKET_FAMILY,
+	.version = OVS_PACKET_VERSION,
+	.maxattr = OVS_PACKET_ATTR_MAX
+};
+
+int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
+	      const struct dp_upcall_info *upcall_info)
+{
+	struct dp_stats_percpu *stats;
+	int dp_ifindex;
+	int err;
+
+	if (upcall_info->pid == 0) {
+		err = -ENOTCONN;
+		goto err;
+	}
+
+	dp_ifindex = get_dpifindex(dp);
+	if (!dp_ifindex) {
+		err = -ENODEV;
+		goto err;
+	}
+
+	if (!skb_is_gso(skb))
+		err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+	else
+		err = queue_gso_packets(dp_ifindex, skb, upcall_info);
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+	u64_stats_update_begin(&stats->sync);
+	stats->n_lost++;
+	u64_stats_update_end(&stats->sync);
+
+	return err;
+}
+
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb,
+			     const struct dp_upcall_info *upcall_info)
+{
+	struct dp_upcall_info later_info;
+	struct sw_flow_key later_key;
+	struct sk_buff *segs, *nskb;
+	int err;
+
+	segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Queue all of the segments. */
+	skb = segs;
+	do {
+		err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+		if (err)
+			break;
+
+		if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) {
+			/* The initial flow key extracted by ovs_flow_extract()
+			 * in this case is for a first fragment, so we need to
+			 * properly mark later fragments.
+			 */
+			later_key = *upcall_info->key;
+			later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+
+			later_info = *upcall_info;
+			later_info.key = &later_key;
+			upcall_info = &later_info;
+		}
+	} while ((skb = skb->next));
+
+	/* Free all of the segments. */
+	skb = segs;
+	do {
+		nskb = skb->next;
+		if (err)
+			kfree_skb(skb);
+		else
+			consume_skb(skb);
+	} while ((skb = nskb));
+	return err;
+}
+
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb,
+				  const struct dp_upcall_info *upcall_info)
+{
+	struct ovs_header *upcall;
+	struct sk_buff *nskb = NULL;
+	struct sk_buff *user_skb; /* to be queued to userspace */
+	struct nlattr *nla;
+	unsigned int len;
+	int err;
+
+	if (vlan_tx_tag_present(skb)) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb));
+		if (!skb)
+			return -ENOMEM;
+
+		nskb->vlan_tci = 0;
+		skb = nskb;
+	}
+
+	if (nla_attr_size(skb->len) > USHRT_MAX) {
+		err = -EFBIG;
+		goto out;
+	}
+
+	len = sizeof(struct ovs_header);
+	len += nla_total_size(skb->len);
+	len += nla_total_size(FLOW_BUFSIZE);
+	if (upcall_info->cmd == OVS_PACKET_CMD_ACTION)
+		len += nla_total_size(8);
+
+	user_skb = genlmsg_new(len, GFP_ATOMIC);
+	if (!user_skb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family,
+			     0, upcall_info->cmd);
+	upcall->dp_ifindex = dp_ifindex;
+
+	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
+	ovs_flow_to_nlattrs(upcall_info->key, user_skb);
+	nla_nest_end(user_skb, nla);
+
+	if (upcall_info->userdata)
+		nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA,
+			    nla_get_u64(upcall_info->userdata));
+
+	nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
+
+	skb_copy_and_csum_dev(skb, nla_data(nla));
+
+	err = genlmsg_unicast(&init_net, user_skb, upcall_info->pid);
+
+out:
+	kfree_skb(nskb);
+	return err;
+}
+
+/* Called with genl_mutex. */
+static int flush_flows(int dp_ifindex)
+{
+	struct flow_table *old_table;
+	struct flow_table *new_table;
+	struct datapath *dp;
+
+	dp = get_dp(dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	old_table = genl_dereference(dp->table);
+	new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS);
+	if (!new_table)
+		return -ENOMEM;
+
+	rcu_assign_pointer(dp->table, new_table);
+
+	ovs_flow_tbl_deferred_destroy(old_table);
+	return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+				const struct sw_flow_key *key, int depth);
+
+static int validate_sample(const struct nlattr *attr,
+				const struct sw_flow_key *key, int depth)
+{
+	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
+	const struct nlattr *probability, *actions;
+	const struct nlattr *a;
+	int rem;
+
+	memset(attrs, 0, sizeof(attrs));
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
+		if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
+			return -EINVAL;
+		attrs[type] = a;
+	}
+	if (rem)
+		return -EINVAL;
+
+	probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
+	if (!probability || nla_len(probability) != sizeof(u32))
+		return -EINVAL;
+
+	actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
+	if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
+		return -EINVAL;
+	return validate_actions(actions, key, depth + 1);
+}
+
+static int validate_set(const struct nlattr *a,
+			const struct sw_flow_key *flow_key)
+{
+	const struct nlattr *ovs_key = nla_data(a);
+	int key_type = nla_type(ovs_key);
+
+	/* There can be only one key in a action */
+	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
+		return -EINVAL;
+
+	if (key_type > OVS_KEY_ATTR_MAX ||
+	    nla_len(ovs_key) != ovs_key_lens[key_type])
+		return -EINVAL;
+
+	switch (key_type) {
+	const struct ovs_key_ipv4 *ipv4_key;
+
+	case OVS_KEY_ATTR_PRIORITY:
+	case OVS_KEY_ATTR_ETHERNET:
+		break;
+
+	case OVS_KEY_ATTR_IPV4:
+		if (flow_key->eth.type != htons(ETH_P_IP))
+			return -EINVAL;
+
+		if (!flow_key->ipv4.addr.src || !flow_key->ipv4.addr.dst)
+			return -EINVAL;
+
+		ipv4_key = nla_data(ovs_key);
+		if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+			return -EINVAL;
+
+		if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+			return -EINVAL;
+
+		break;
+
+	case OVS_KEY_ATTR_TCP:
+		if (flow_key->ip.proto != IPPROTO_TCP)
+			return -EINVAL;
+
+		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+			return -EINVAL;
+
+		break;
+
+	case OVS_KEY_ATTR_UDP:
+		if (flow_key->ip.proto != IPPROTO_UDP)
+			return -EINVAL;
+
+		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int validate_userspace(const struct nlattr *attr)
+{
+	static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] =	{
+		[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
+		[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 },
+	};
+	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
+	int error;
+
+	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
+				 attr, userspace_policy);
+	if (error)
+		return error;
+
+	if (!a[OVS_USERSPACE_ATTR_PID] ||
+	    !nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+				const struct sw_flow_key *key,  int depth)
+{
+	const struct nlattr *a;
+	int rem, err;
+
+	if (depth >= SAMPLE_ACTION_DEPTH)
+		return -EOVERFLOW;
+
+	nla_for_each_nested(a, attr, rem) {
+		/* Expected argument lengths, (u32)-1 for variable length. */
+		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
+			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
+			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
+			[OVS_ACTION_ATTR_POP_VLAN] = 0,
+			[OVS_ACTION_ATTR_SET] = (u32)-1,
+			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1
+		};
+		const struct ovs_action_push_vlan *vlan;
+		int type = nla_type(a);
+
+		if (type > OVS_ACTION_ATTR_MAX ||
+		    (action_lens[type] != nla_len(a) &&
+		     action_lens[type] != (u32)-1))
+			return -EINVAL;
+
+		switch (type) {
+		case OVS_ACTION_ATTR_UNSPEC:
+			return -EINVAL;
+
+		case OVS_ACTION_ATTR_USERSPACE:
+			err = validate_userspace(a);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_OUTPUT:
+			if (nla_get_u32(a) >= DP_MAX_PORTS)
+				return -EINVAL;
+			break;
+
+
+		case OVS_ACTION_ATTR_POP_VLAN:
+			break;
+
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+			vlan = nla_data(a);
+			if (vlan->vlan_tpid != htons(ETH_P_8021Q))
+				return -EINVAL;
+			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
+				return -EINVAL;
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			err = validate_set(a, key);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			err = validate_sample(a, key, depth);
+			if (err)
+				return err;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (rem > 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void clear_stats(struct sw_flow *flow)
+{
+	flow->used = 0;
+	flow->tcp_flags = 0;
+	flow->packet_count = 0;
+	flow->byte_count = 0;
+}
+
+static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovs_header *ovs_header = info->userhdr;
+	struct nlattr **a = info->attrs;
+	struct sw_flow_actions *acts;
+	struct sk_buff *packet;