Fixed MTP to work with TWRP

net/openvswitch/Kconfig

@@ -0,0 +1,67 @@
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+	tristate "Open vSwitch"
+	select LIBCRC32C
+	---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
+	bool "Open vSwitch GRE tunneling support"
+	depends on INET
+	depends on OPENVSWITCH
+	depends on NET_IPGRE_DEMUX && !(OPENVSWITCH=y && NET_IPGRE_DEMUX=m)
+	default y
+	---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
+	bool "Open vSwitch VXLAN tunneling support"
+	depends on INET
+	depends on OPENVSWITCH
+	depends on VXLAN && !(OPENVSWITCH=y && VXLAN=m)
+	default y
+	---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
+	bool "Open vSwitch Geneve tunneling support"
+	depends on INET
+	depends on OPENVSWITCH
+	depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
+	default y
+	---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 +1,28 @@
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+	actions.o \
+	datapath.o \
+	dp_notify.o \
+	flow.o \
+	flow_netlink.o \
+	flow_table.o \
+	vport.o \
+	vport-internal_dev.o \
+	vport-netdev.o
+
+ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
+openvswitch-y += vport-geneve.o
+endif
+
+ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
+openvswitch-y += vport-vxlan.o
+endif
+
+ifneq ($(CONFIG_OPENVSWITCH_GRE),)
+openvswitch-y += vport-gre.o
+endif

net/openvswitch/actions.c

@@ -0,0 +1,808 @@
+/*
+ * 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/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/openvswitch.h>
+#include <linux/sctp.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/ipv6.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/sctp/checksum.h>
+
+#include "datapath.h"
+#include "flow.h"
+#include "vport.h"
+
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			      struct sw_flow_key *key,
+			      const struct nlattr *attr, int len);
+
+struct deferred_action {
+	struct sk_buff *skb;
+	const struct nlattr *actions;
+
+	/* Store pkt_key clone when creating deferred action. */
+	struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+struct action_fifo {
+	int head;
+	int tail;
+	/* Deferred action fifo queue storage. */
+	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+static struct action_fifo __percpu *action_fifos;
+static DEFINE_PER_CPU(int, exec_actions_level);
+
+static void action_fifo_init(struct action_fifo *fifo)
+{
+	fifo->head = 0;
+	fifo->tail = 0;
+}
+
+static bool action_fifo_is_empty(struct action_fifo *fifo)
+{
+	return (fifo->head == fifo->tail);
+}
+
+static struct deferred_action *action_fifo_get(struct action_fifo *fifo)
+{
+	if (action_fifo_is_empty(fifo))
+		return NULL;
+
+	return &fifo->fifo[fifo->tail++];
+}
+
+static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
+{
+	if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)
+		return NULL;
+
+	return &fifo->fifo[fifo->head++];
+}
+
+/* Return true if fifo is not full */
+static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
+						    struct sw_flow_key *key,
+						    const struct nlattr *attr)
+{
+	struct action_fifo *fifo;
+	struct deferred_action *da;
+
+	fifo = this_cpu_ptr(action_fifos);
+	da = action_fifo_put(fifo);
+	if (da) {
+		da->skb = skb;
+		da->actions = attr;
+		da->pkt_key = *key;
+	}
+
+	return da;
+}
+
+static int make_writable(struct sk_buff *skb, int write_len)
+{
+	if (!pskb_may_pull(skb, write_len))
+		return -ENOMEM;
+
+	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 accordingly. */
+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
+					+ (2 * ETH_ALEN), 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;
+	if (skb_network_offset(skb) < ETH_HLEN)
+		skb_set_network_header(skb, ETH_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, htons(ETH_P_8021Q), 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);
+
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						current_tag);
+		if (!skb)
+			return -ENOMEM;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_add(skb->csum, csum_partial(skb->data
+					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+
+	}
+	__vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, 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;
+
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+
+	ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+	ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
+
+	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+
+	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))) {
+			struct udphdr *uh = udp_hdr(skb);
+
+			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+				inet_proto_csum_replace4(&uh->check, skb,
+							 *addr, new_addr, 1);
+				if (!uh->check)
+					uh->check = CSUM_MANGLED_0;
+			}
+		}
+	}
+
+	csum_replace4(&nh->check, *addr, new_addr);
+	skb_clear_hash(skb);
+	*addr = new_addr;
+}
+
+static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
+				 __be32 addr[4], const __be32 new_addr[4])
+{
+	int transport_len = skb->len - skb_transport_offset(skb);
+
+	if (l4_proto == NEXTHDR_TCP) {
+		if (likely(transport_len >= sizeof(struct tcphdr)))
+			inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
+						  addr, new_addr, 1);
+	} else if (l4_proto == NEXTHDR_UDP) {
+		if (likely(transport_len >= sizeof(struct udphdr))) {
+			struct udphdr *uh = udp_hdr(skb);
+
+			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+				inet_proto_csum_replace16(&uh->check, skb,
+							  addr, new_addr, 1);
+				if (!uh->check)
+					uh->check = CSUM_MANGLED_0;
+			}
+		}
+	} else if (l4_proto == NEXTHDR_ICMP) {
+		if (likely(transport_len >= sizeof(struct icmp6hdr)))
+			inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,
+						  skb, addr, new_addr, 1);
+	}
+}
+
+static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
+			  __be32 addr[4], const __be32 new_addr[4],
+			  bool recalculate_csum)
+{
+	if (recalculate_csum)
+		update_ipv6_checksum(skb, l4_proto, addr, new_addr);
+
+	skb_clear_hash(skb);
+	memcpy(addr, new_addr, sizeof(__be32[4]));
+}
+
+static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc)
+{
+	nh->priority = tc >> 4;
+	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4);
+}
+
+static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl)
+{
+	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16;
+	nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8;
+	nh->flow_lbl[2] = fl & 0x000000FF;
+}
+
+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;
+}
+
+static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
+{
+	struct ipv6hdr *nh;
+	int err;
+	__be32 *saddr;
+	__be32 *daddr;
+
+	err = make_writable(skb, skb_network_offset(skb) +
+			    sizeof(struct ipv6hdr));
+	if (unlikely(err))
+		return err;
+
+	nh = ipv6_hdr(skb);
+	saddr = (__be32 *)&nh->saddr;
+	daddr = (__be32 *)&nh->daddr;
+
+	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src)))
+		set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
+			      ipv6_key->ipv6_src, true);
+
+	if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+		unsigned int offset = 0;
+		int flags = IP6_FH_F_SKIP_RH;
+		bool recalc_csum = true;
+
+		if (ipv6_ext_hdr(nh->nexthdr))
+			recalc_csum = ipv6_find_hdr(skb, &offset,
+						    NEXTHDR_ROUTING, NULL,
+						    &flags) != NEXTHDR_ROUTING;
+
+		set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
+			      ipv6_key->ipv6_dst, recalc_csum);
+	}
+
+	set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
+	set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
+	nh->hop_limit = ipv6_key->ipv6_hlimit;
+
+	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_clear_hash(skb);
+}
+
+static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+		set_tp_port(skb, port, new_port, &uh->check);
+
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	} else {
+		*port = new_port;
+		skb_clear_hash(skb);
+	}
+}
+
+static int set_udp(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_udp_port(skb, &uh->source, udp_port_key->udp_src);
+
+	if (udp_port_key->udp_dst != uh->dest)
+		set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
+
+	return 0;
+}
+
+static int set_tcp(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 set_sctp(struct sk_buff *skb,
+		     const struct ovs_key_sctp *sctp_port_key)
+{
+	struct sctphdr *sh;
+	int err;
+	unsigned int sctphoff = skb_transport_offset(skb);
+
+	err = make_writable(skb, sctphoff + sizeof(struct sctphdr));
+	if (unlikely(err))
+		return err;
+
+	sh = sctp_hdr(skb);
+	if (sctp_port_key->sctp_src != sh->source ||
+	    sctp_port_key->sctp_dst != sh->dest) {
+		__le32 old_correct_csum, new_csum, old_csum;
+
+		old_csum = sh->checksum;
+		old_correct_csum = sctp_compute_cksum(skb, sctphoff);
+
+		sh->source = sctp_port_key->sctp_src;
+		sh->dest = sctp_port_key->sctp_dst;
+
+		new_csum = sctp_compute_cksum(skb, sctphoff);
+
+		/* Carry any checksum errors through. */
+		sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
+
+		skb_clear_hash(skb);
+	}
+
+	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 = ovs_vport_rcu(dp, 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,
+			    struct sw_flow_key *key, const struct nlattr *attr)
+{
+	struct dp_upcall_info upcall;
+	const struct nlattr *a;
+	int rem;
+
+	upcall.cmd = OVS_PACKET_CMD_ACTION;
+	upcall.key = key;
+	upcall.userdata = NULL;
+	upcall.portid = 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.portid = nla_get_u32(a);
+			break;
+		}
+	}
+
+	return ovs_dp_upcall(dp, skb, &upcall);
+}
+
+static bool last_action(const struct nlattr *a, int rem)
+{
+	return a->nla_len == rem;
+}
+
+static int sample(struct datapath *dp, struct sk_buff *skb,
+		  struct sw_flow_key *key, 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 (prandom_u32() >= nla_get_u32(a))
+				return 0;
+			break;
+
+		case OVS_SAMPLE_ATTR_ACTIONS:
+			acts_list = a;
+			break;
+		}
+	}
+
+	rem = nla_len(acts_list);
+	a = nla_data(acts_list);
+
+	/* Actions list is empty, do nothing */
+	if (unlikely(!rem))
+		return 0;
+
+	/* The only known usage of sample action is having a single user-space
+	 * action. Treat this usage as a special case.
+	 * The output_userspace() should clone the skb to be sent to the
+	 * user space. This skb will be consumed by its caller.
+	 */
+	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
+		   last_action(a, rem)))
+		return output_userspace(dp, skb, key, a);
+
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb)
+		/* Skip the sample action when out of memory. */
+		return 0;
+
+	if (!add_deferred_actions(skb, key, a)) {
+		if (net_ratelimit())
+			pr_warn("%s: deferred actions limit reached, dropping sample action\n",
+				ovs_dp_name(dp));
+
+		kfree_skb(skb);
+	}
+	return 0;
+}
+
+static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
+			 const struct nlattr *attr)
+{
+	struct ovs_action_hash *hash_act = nla_data(attr);
+	u32 hash = 0;
+
+	/* OVS_HASH_ALG_L4 is the only possible hash algorithm.  */
+	hash = skb_get_hash(skb);
+	hash = jhash_1word(hash, hash_act->hash_basis);
+	if (!hash)
+		hash = 0x1;
+
+	key->ovs_flow_hash = hash;
+}
+
+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_SKB_MARK:
+		skb->mark = nla_get_u32(nested_attr);
+		break;
+
+	case OVS_KEY_ATTR_TUNNEL_INFO:
+		OVS_CB(skb)->egress_tun_info = nla_data(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_IPV6:
+		err = set_ipv6(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_TCP:
+		err = set_tcp(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_UDP:
+		err = set_udp(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_SCTP:
+		err = set_sctp(skb, nla_data(nested_attr));
+		break;
+	}
+
+	return err;
+}
+
+static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
+			  struct sw_flow_key *key,
+			  const struct nlattr *a, int rem)
+{
+	struct deferred_action *da;
+	int err;
+
+	err = ovs_flow_key_update(skb, key);
+	if (err)
+		return err;
+
+	if (!last_action(a, rem)) {
+		/* Recirc action is the not the last action
+		 * of the action list, need to clone the skb.
+		 */
+		skb = skb_clone(skb, GFP_ATOMIC);
+
+		/* Skip the recirc action when out of memory, but
+		 * continue on with the rest of the action list.
+		 */
+		if (!skb)
+			return 0;
+	}
+
+	da = add_deferred_actions(skb, key, NULL);
+	if (da) {
+		da->pkt_key.recirc_id = nla_get_u32(a);
+	} else {
+		kfree_skb(skb);
+
+		if (net_ratelimit())
+			pr_warn("%s: deferred action limit reached, drop recirc action\n",
+				ovs_dp_name(dp));
+	}
+
+	return 0;
+}
+
+/* Execute a list of actions against 'skb'. */
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			      struct sw_flow_key *key,
+			      const struct nlattr *attr, int len)
+{
+	/* 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, key, a);
+			break;
+
+		case OVS_ACTION_ATTR_HASH:
+			execute_hash(skb, key, 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_RECIRC:
+			err = execute_recirc(dp, skb, key, a, rem);
+			if (last_action(a, rem)) {
+				/* If this is the last action, the skb has
+				 * been consumed or freed.
+				 * Return immediately.
+				 */
+				return err;
+			}
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			err = execute_set_action(skb, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			err = sample(dp, skb, key, a);
+			break;
+		}
+
+		if (unlikely(err)) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
+	if (prev_port != -1)
+		do_output(dp, skb, prev_port);
+	else
+		consume_skb(skb);
+
+	return 0;
+}
+
+static void process_deferred_actions(struct datapath *dp)
+{
+	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+
+	/* Do not touch the FIFO in case there is no deferred actions. */
+	if (action_fifo_is_empty(fifo))
+		return;
+
+	/* Finishing executing all deferred actions. */
+	do {
+		struct deferred_action *da = action_fifo_get(fifo);
+		struct sk_buff *skb = da->skb;
+		struct sw_flow_key *key = &da->pkt_key;
+		const struct nlattr *actions = da->actions;
+
+		if (actions)
+			do_execute_actions(dp, skb, key, actions,
+					   nla_len(actions));
+		else
+			ovs_dp_process_packet(skb, key);
+	} while (!action_fifo_is_empty(fifo));
+
+	/* Reset FIFO for the next packet.  */
+	action_fifo_init(fifo);
+}
+
+/* Execute a list of actions against 'skb'. */
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			struct sw_flow_key *key)
+{
+	int level = this_cpu_read(exec_actions_level);
+	struct sw_flow_actions *acts;
+	int err;
+
+	acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+	this_cpu_inc(exec_actions_level);
+	OVS_CB(skb)->egress_tun_info = NULL;
+	err = do_execute_actions(dp, skb, key,
+				 acts->actions, acts->actions_len);
+
+	if (!level)
+		process_deferred_actions(dp);
+
+	this_cpu_dec(exec_actions_level);
+	return err;
+}
+
+int action_fifos_init(void)
+{
+	action_fifos = alloc_percpu(struct action_fifo);
+	if (!action_fifos)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void action_fifos_exit(void)
+{
+	free_percpu(action_fifos);
+}

net/openvswitch/datapath.h

@@ -0,0 +1,209 @@
+/*
+ * 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 "flow.h"
+#include "flow_table.h"
+#include "vport.h"
+
+#define DP_MAX_PORTS           USHRT_MAX
+#define DP_VPORT_HASH_BUCKETS  1024
+
+#define SAMPLE_ACTION_DEPTH 3
+
+/**
+ * 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.
+ *
+ * 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;
+
+#ifdef CONFIG_NET_NS
+	/* Network namespace ref. */
+	struct net *net;
+#endif
+
+	u32 user_features;
+};
+
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @flow: The flow associated with this packet.  May be %NULL if no flow.
+ * @egress_tun_key: Tunnel information about this packet on egress path.
+ * NULL if the packet is not being tunneled.
+ * @input_vport: The original vport packet came in on. This value is cached
+ * when a packet is received by OVS.
+ */
+struct ovs_skb_cb {
+	struct sw_flow		*flow;
+	struct ovs_tunnel_info  *egress_tun_info;
+	struct vport		*input_vport;
+};
+#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_*.
+ * @key: Becomes %OVS_PACKET_ATTR_KEY.  Must be nonnull.
+ * @userdata: If nonnull, its variable-length value is passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @pid: Netlink PID to which packet should be sent.  If @pid is 0 then no
+ * packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ */
+struct dp_upcall_info {
+	u8 cmd;
+	const struct sw_flow_key *key;
+	const struct nlattr *userdata;
+	u32 portid;
+};
+
+/**
+ * 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;
+	struct vport_net vport_net;
+};
+
+extern 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(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);
+}
+
+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 dp_upcall_info *);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
+					 u8 cmd);
+
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			struct sw_flow_key *);
+
+void ovs_dp_notify_wq(struct work_struct *work);
+
+int action_fifos_init(void);
+void action_fifos_exit(void);
+
+#define OVS_NLERR(fmt, ...)					\
+do {								\
+	if (net_ratelimit())					\
+		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+} while (0)
+#endif /* datapath.h */

net/openvswitch/dp_notify.c

@@ -0,0 +1,102 @@
+/*
+ * 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, 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) {
+				struct netdev_vport *netdev_vport;
+
+				if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+					continue;
+
+				netdev_vport = netdev_vport_priv(vport);
+				if (!(netdev_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 +1,695 @@
+/*
+ * 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/if_arp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.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/ndisc.h>
+
+#include "datapath.h"
+#include "flow.h"
+#include "flow_netlink.h"
+
+u64 ovs_flow_used_time(unsigned long flow_jiffies)
+{
+	struct timespec cur_ts;
+	u64 cur_ms, idle_ms;
+
+	ktime_get_ts(&cur_ts);
+	idle_ms = jiffies_to_msecs(jiffies - flow_jiffies);
+	cur_ms = (u64)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,
+			   struct sk_buff *skb)
+{
+	struct flow_stats *stats;
+	int node = numa_node_id();
+
+	stats = rcu_dereference(flow->stats[node]);
+
+	/* Check if already have node-specific stats. */
+	if (likely(stats)) {
+		spin_lock(&stats->lock);
+		/* Mark if we write on the pre-allocated stats. */
+		if (node == 0 && unlikely(flow->stats_last_writer != node))
+			flow->stats_last_writer = node;
+	} else {
+		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+		spin_lock(&stats->lock);
+
+		/* If the current NUMA-node is the only writer on the
+		 * pre-allocated stats keep using them.
+		 */
+		if (unlikely(flow->stats_last_writer != node)) {
+			/* A previous locker may have already allocated the
+			 * stats, so we need to check again.  If node-specific
+			 * stats were already allocated, we update the pre-
+			 * allocated stats as we have already locked them.
+			 */
+			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
+			    && likely(!rcu_access_pointer(flow->stats[node]))) {
+				/* Try to allocate node-specific stats. */
+				struct flow_stats *new_stats;
+
+				new_stats =
+					kmem_cache_alloc_node(flow_stats_cache,
+							      GFP_THISNODE |
+							      __GFP_NOMEMALLOC,
+							      node);
+				if (likely(new_stats)) {
+					new_stats->used = jiffies;
+					new_stats->packet_count = 1;
+					new_stats->byte_count = skb->len;
+					new_stats->tcp_flags = tcp_flags;
+					spin_lock_init(&new_stats->lock);
+
+					rcu_assign_pointer(flow->stats[node],
+							   new_stats);
+					goto unlock;
+				}
+			}
+			flow->stats_last_writer = node;
+		}
+	}
+
+	stats->used = jiffies;
+	stats->packet_count++;
+	stats->byte_count += skb->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 node;
+
+	*used = 0;
+	*tcp_flags = 0;
+	memset(ovs_stats, 0, sizeof(*ovs_stats));
+
+	for_each_node(node) {
+		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
+
+		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 node;
+
+	for_each_node(node) {
+		struct flow_stats *stats = ovsl_dereference(flow->stats[node]);
+
+		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 (unlikely(payload_ofs < 0))
+		return -EINVAL;
+
+	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;
+	}
+
+	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));
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct qtag_prefix {
+		__be16 eth_type; /* ETH_P_8021Q */
+		__be16 tci;
+	};
+	struct qtag_prefix *qp;
+
+	if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16)))
+		return 0;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
+					 sizeof(__be16))))
+		return -ENOMEM;
+
+	qp = (struct qtag_prefix *) skb->data;
+	key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT);
+	__skb_pull(skb, sizeof(struct qtag_prefix));
+
+	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 (ntohs(proto) >= ETH_P_802_3_MIN)
+		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 (ntohs(llc->ethertype) >= ETH_P_802_3_MIN)
+		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;
+}
+
+/**
+ * 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 pointers as follows:
+ *
+ *    - skb->mac_header: the Ethernet header.
+ *
+ *    - skb->network_header: just past the Ethernet header, or just past the
+ *      VLAN header, to the first byte of the Ethernet 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.
+ */
+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.  We are guaranteed to have at least the 14 byte Ethernet
+	 * header in the linear data area.
+	 */
+	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.
+	 */
+
+	key->eth.tci = 0;
+	if (vlan_tx_tag_present(skb))
+		key->eth.tci = htons(skb->vlan_tci);
+	else if (eth->h_proto == htons(ETH_P_8021Q))
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+	key->eth.type = parse_ethertype(skb);
+	if (unlikely(key->eth.type == htons(0)))
+		return -ENOMEM;
+
+	skb_reset_network_header(skb);
+	__skb_push(skb, skb->data - skb_mac_header(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 (key->eth.type == htons(ETH_P_IPV6)) {
+		int nh_len;             /* IPv6 Header + Extensions */
+
+		nh_len = parse_ipv6hdr(skb, key);
+		if (unlikely(nh_len < 0)) {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
+			if (nh_len == -EINVAL) {
+				skb->transport_header = skb->network_header;
+				error = 0;
+			} else {
+				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));
+			}
+		}
+	}
+	return 0;
+}
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
+			 struct sk_buff *skb, struct sw_flow_key *key)
+{
+	/* Extract metadata from packet. */
+	if (tun_info) {
+		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
+
+		if (tun_info->options) {
+			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+						   8)) - 1
+					> sizeof(key->tun_opts));
+			memcpy(GENEVE_OPTS(key, tun_info->options_len),
+			       tun_info->options, tun_info->options_len);
+			key->tun_opts_len = tun_info->options_len;
+		} else {
+			key->tun_opts_len = 0;
+		}
+	} else  {
+		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;
+	key->recirc_id = 0;
+
+	return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract_userspace(const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key)
+{
+	int err;
+
+	/* Extract metadata from netlink attributes. */
+	err = ovs_nla_get_flow_metadata(attr, key);
+	if (err)
+		return err;
+
+	return key_extract(skb, key);
+}

net/openvswitch/flow.h

@@ -0,0 +1,222 @@
+/*
+ * 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 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 <net/inet_ecn.h>
+
+struct sk_buff;
+
+/* Used to memset ovs_key_ipv4_tunnel padding. */
+#define OVS_TUNNEL_KEY_SIZE					\
+	(offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) +	\
+	FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl))
+
+struct ovs_key_ipv4_tunnel {
+	__be64 tun_id;
+	__be32 ipv4_src;
+	__be32 ipv4_dst;
+	__be16 tun_flags;
+	u8   ipv4_tos;
+	u8   ipv4_ttl;
+} __packed __aligned(4); /* Minimize padding. */
+
+struct ovs_tunnel_info {
+	struct ovs_key_ipv4_tunnel tunnel;
+	struct geneve_opt *options;
+	u8 options_len;
+};
+
+/* 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 GENEVE_OPTS(flow_key, opt_len)	\
+	((struct geneve_opt *)((flow_key)->tun_opts + \
+			       FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
+			       opt_len))
+
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					  const struct iphdr *iph,
+					  __be64 tun_id, __be16 tun_flags,
+					  struct geneve_opt *opts,
+					  u8 opts_len)
+{
+	tun_info->tunnel.tun_id = tun_id;
+	tun_info->tunnel.ipv4_src = iph->saddr;
+	tun_info->tunnel.ipv4_dst = iph->daddr;
+	tun_info->tunnel.ipv4_tos = iph->tos;
+	tun_info->tunnel.ipv4_ttl = iph->ttl;
+	tun_info->tunnel.tun_flags = tun_flags;
+
+	/* clear struct padding. */
+	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
+	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+	tun_info->options = opts;
+	tun_info->options_len = opts_len;
+}
+
+struct sw_flow_key {
+	u8 tun_opts[255];
+	u8 tun_opts_len;
+	struct ovs_key_ipv4_tunnel 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'. */
+	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. */
+		__be16 tci;		/* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
+		__be16 type;		/* Ethernet frame type. */
+	} eth;
+	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;
+	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;
+			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. */
+			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;
+	};
+} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
+
+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;
+};
+
+struct sw_flow_actions {
+	struct rcu_head rcu;
+	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 hlist_node hash_node[2];
+	u32 hash;
+	int stats_last_writer;		/* NUMA-node id of the last writer on
+					 * 'stats[0]'.
+					 */
+	struct sw_flow_key key;
+	struct sw_flow_key unmasked_key;
+	struct sw_flow_mask *mask;
+	struct sw_flow_actions __rcu *sf_acts;
+	struct flow_stats __rcu *stats[]; /* One for each NUMA node.  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;
+
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+			   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(struct ovs_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(const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key);
+
+#endif /* flow.h */

net/openvswitch/flow_netlink.h

@@ -0,0 +1,60 @@
+/*
+ * 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"
+
+void ovs_match_init(struct sw_flow_match *match,
+		    struct sw_flow_key *key, struct sw_flow_mask *mask);
+
+int ovs_nla_put_flow(const struct sw_flow_key *,
+		     const struct sw_flow_key *, struct sk_buff *);
+int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
+
+int ovs_nla_get_match(struct sw_flow_match *match,
+		      const struct nlattr *,
+		      const struct nlattr *);
+
+int ovs_nla_copy_actions(const struct nlattr *attr,
+			 const struct sw_flow_key *key, int depth,
+			 struct sw_flow_actions **sfa);
+int ovs_nla_put_actions(const struct nlattr *attr,
+			int len, struct sk_buff *skb);
+
+struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
+void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+
+#endif /* flow_netlink.h */

net/openvswitch/flow_table.c

@@ -0,0 +1,647 @@
+/*
+ * 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
+ */
+
+#include "flow.h"
+#include "datapath.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/hash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.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,
+		       const struct sw_flow_mask *mask)
+{
+	const long *m = (const long *)((const u8 *)&mask->key +
+				mask->range.start);
+	const long *s = (const long *)((const u8 *)src +
+				mask->range.start);
+	long *d = (long *)((u8 *)dst + mask->range.start);
+	int i;
+
+	/* The memory outside of the 'mask->range' are not set since
+	 * further operations on 'dst' only uses contents within
+	 * 'mask->range'.
+	 */
+	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+		*d++ = *s++ & *m++;
+}
+
+struct sw_flow *ovs_flow_alloc(void)
+{
+	struct sw_flow *flow;
+	struct flow_stats *stats;
+	int node;
+
+	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	flow->sf_acts = NULL;
+	flow->mask = NULL;
+	flow->stats_last_writer = NUMA_NO_NODE;
+
+	/* Initialize the default stat node. */
+	stats = kmem_cache_alloc_node(flow_stats_cache,
+				      GFP_KERNEL | __GFP_ZERO, 0);
+	if (!stats)
+		goto err;
+
+	spin_lock_init(&stats->lock);
+
+	RCU_INIT_POINTER(flow->stats[0], stats);
+
+	for_each_node(node)
+		if (node != 0)
+			RCU_INIT_POINTER(flow->stats[node], NULL);
+
+	return flow;
+err:
+	kmem_cache_free(flow_cache, flow);
+	return ERR_PTR(-ENOMEM);
+}
+
+int ovs_flow_tbl_count(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 node;
+
+	kfree((struct sw_flow_actions __force *)flow->sf_acts);
+	for_each_node(node)
+		if (flow->stats[node])
+			kmem_cache_free(flow_stats_cache,
+					(struct flow_stats __force *)flow->stats[node]);
+	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;
+
+	ti = table_instance_alloc(TBL_MIN_BUCKETS);
+
+	if (!ti)
+		return -ENOMEM;
+
+	rcu_assign_pointer(table->ti, ti);
+	INIT_LIST_HEAD(&table->mask_list);
+	table->last_rehash = jiffies;
+	table->count = 0;
+	return 0;
+}
+
+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, bool deferred)
+{
+	int i;
+
+	if (!ti)
+		return;
+
+	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;
+
+		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+			hlist_del_rcu(&flow->hash_node[ver]);
+			ovs_flow_free(flow, deferred);
+		}
+	}
+
+skip_flows:
+	if (deferred)
+		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+	else
+		__table_instance_destroy(ti);
+}
+
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
+{
+	struct table_instance *ti = ovsl_dereference(table->ti);
+
+	table_instance_destroy(ti, deferred);
+}
+
+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, hash_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->hash);
+	hlist_add_head_rcu(&flow->hash_node[ti->node_ver], head);
+}
+
+static void flow_table_copy_flows(struct table_instance *old,
+				  struct table_instance *new)
+{
+	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);
+
+		hlist_for_each_entry(flow, head, hash_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)
+{
+	struct table_instance *new_ti;
+
+	new_ti = table_instance_alloc(n_buckets);
+	if (!new_ti)
+		return NULL;
+
+	flow_table_copy_flows(ti, new_ti);
+
+	return new_ti;
+}
+
+int ovs_flow_tbl_flush(struct flow_table *flow_table)
+{
+	struct table_instance *old_ti;
+	struct table_instance *new_ti;
+
+	old_ti = ovsl_dereference(flow_table->ti);
+	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!new_ti)
+		return -ENOMEM;
+
+	rcu_assign_pointer(flow_table->ti, new_ti);
+	flow_table->last_rehash = jiffies;
+	flow_table->count = 0;
+
+	table_instance_destroy(old_ti, true);
+	return 0;
+}
+
+static u32 flow_hash(const struct sw_flow_key *key, int key_start,
+		     int key_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 arch_fast_hash2(hash_key, hash_u32s, 0);
+}
+
+static int flow_key_start(const struct sw_flow_key *key)
+{
+	if (key->tun_key.ipv4_dst)
+		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,
+				int key_start, int key_end)
+{
+	return cmp_key(&flow->key, key, key_start, key_end);
+}
+
+bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+			       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;
+
+	return cmp_key(&flow->unmasked_key, key, key_start, key_end);
+}
+
+static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
+					  const struct sw_flow_key *unmasked,
+					  struct sw_flow_mask *mask)
+{
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	int key_start = mask->range.start;
+	int key_end = mask->range.end;
+	u32 hash;
+	struct sw_flow_key masked_key;
+
+	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	hash = flow_hash(&masked_key, key_start, key_end);
+	head = find_bucket(ti, hash);
+	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
+		if (flow->mask == mask && flow->hash == hash &&
+		    flow_cmp_masked_key(flow, &masked_key,
+					  key_start, key_end))
+			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,
+					  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_flow_cmp_unmasked_key(flow, match))  /* Found */
+			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)
+{
+	return table_instance_rehash(ti, ti->n_buckets * 2);
+}
+
+/* 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);
+
+	BUG_ON(table->count == 0);
+	hlist_del_rcu(&flow->hash_node[ti->node_ver]);
+	table->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,
+			    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. */
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			struct sw_flow_mask *mask)
+{
+	struct table_instance *new_ti = NULL;
+	struct table_instance *ti;
+	int err;
+
+	err = flow_mask_insert(table, flow, mask);
+	if (err)
+		return err;
+
+	flow->hash = flow_hash(&flow->key, flow->mask->range.start,
+			flow->mask->range.end);
+	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);
+	else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
+		new_ti = table_instance_rehash(ti, ti->n_buckets);
+
+	if (new_ti) {
+		rcu_assign_pointer(table->ti, new_ti);
+		table_instance_destroy(ti, true);
+		table->last_rehash = jiffies;
+	}
+	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)
+				       + (num_possible_nodes()
+					  * 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 +1,86 @@
+/*
+ * 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 list_head mask_list;
+	unsigned long last_rehash;
+	unsigned int 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(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
+int ovs_flow_tbl_flush(struct flow_table *flow_table);
+
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			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,
+					  struct sw_flow_match *match);
+bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+			       struct sw_flow_match *match);
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+		       const struct sw_flow_mask *mask);
+#endif /* flow_table.h */

net/openvswitch/vport-geneve.c

@@ -0,0 +1,235 @@
+/*
+ * 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/version.h>
+
+#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 <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"
+
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @gs: The socket created for this port number.
+ * @name: vport name.
+ */
+struct geneve_port {
+	struct geneve_sock *gs;
+	char name[IFNAMSIZ];
+};
+
+static LIST_HEAD(geneve_ports);
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
+/* Convert 64 bit tunnel ID to 24 bit VNI. */
+static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	vni[0] = (__force __u8)(tun_id >> 16);
+	vni[1] = (__force __u8)(tun_id >> 8);
+	vni[2] = (__force __u8)tun_id;
+#else
+	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+/* Convert 24 bit VNI to 64 bit tunnel ID. */
+static __be64 vni_to_tunnel_id(__u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
+#else
+	return (__force __be64)(((__force u64)vni[0] << 40) |
+				((__force u64)vni[1] << 48) |
+				((__force u64)vni[2] << 56));
+#endif
+}
+
+static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
+{
+	struct vport *vport = gs->rcv_data;
+	struct genevehdr *geneveh = geneve_hdr(skb);
+	int opts_len;
+	struct ovs_tunnel_info tun_info;
+	__be64 key;
+	__be16 flags;
+
+	opts_len = geneveh->opt_len * 4;
+
+	flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+		(udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
+		(geneveh->oam ? TUNNEL_OAM : 0) |
+		(geneveh->critical ? TUNNEL_CRIT_OPT : 0);
+
+	key = vni_to_tunnel_id(geneveh->vni);
+
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+			       geneveh->options, opts_len);
+
+	ovs_vport_receive(vport, skb, &tun_info);
+}
+
+static int geneve_get_options(const struct vport *vport,
+			      struct sk_buff *skb)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	struct inet_sock *sk = inet_sk(geneve_port->gs->sock->sk);
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(sk->inet_sport)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static void geneve_tnl_destroy(struct vport *vport)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	geneve_sock_release(geneve_port->gs);
+
+	ovs_vport_deferred_free(vport);
+}
+
+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 geneve_sock *gs;
+	struct vport *vport;
+	struct nlattr *a;
+	int err;
+	u16 dst_port;
+
+	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);
+	strncpy(geneve_port->name, parms->name, IFNAMSIZ);
+
+	gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0);
+	if (IS_ERR(gs)) {
+		ovs_vport_free(vport);
+		return (void *)gs;
+	}
+	geneve_port->gs = gs;
+
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct ovs_key_ipv4_tunnel *tun_key;
+	struct ovs_tunnel_info *tun_info;
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+	__be16 sport;
+	struct rtable *rt;
+	struct flowi4 fl;
+	u8 vni[3];
+	__be16 df;
+	int err;
+
+	tun_info = OVS_CB(skb)->egress_tun_info;
+	if (unlikely(!tun_info)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb->mark;
+	fl.flowi4_proto = IPPROTO_UDP;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		goto error;
+	}
+
+	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+	sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+	tunnel_id_to_vni(tun_key->tun_id, vni);
+	skb->ignore_df = 1;
+
+	err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
+			      tun_key->ipv4_dst, tun_key->ipv4_tos,
+			      tun_key->ipv4_ttl, df, sport, dport,
+			      tun_key->tun_flags, vni,
+			      tun_info->options_len, (u8 *)tun_info->options,
+			      false);
+	if (err < 0)
+		ip_rt_put(rt);
+error:
+	return err;
+}
+
+static const char *geneve_get_name(const struct vport *vport)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	return geneve_port->name;
+}
+
+const struct vport_ops ovs_geneve_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GENEVE,
+	.create		= geneve_tnl_create,
+	.destroy	= geneve_tnl_destroy,
+	.get_name	= geneve_get_name,
+	.get_options	= geneve_get_options,
+	.send		= geneve_tnl_send,
+};

net/openvswitch/vport-gre.c

@@ -0,0 +1,286 @@
+/*
+ * 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/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"
+
+/* Returns the least-significant 32 bits of a __be64. */
+static __be32 be64_get_low32(__be64 x)
+{
+#ifdef __BIG_ENDIAN
+	return (__force __be32)x;
+#else
+	return (__force __be32)((__force u64)x >> 32);
+#endif
+}
+
+static __be16 filter_tnl_flags(__be16 flags)
+{
+	return flags & (TUNNEL_CSUM | TUNNEL_KEY);
+}
+
+static struct sk_buff *__build_header(struct sk_buff *skb,
+				      int tunnel_hlen)
+{
+	struct tnl_ptk_info tpi;
+	const struct ovs_key_ipv4_tunnel *tun_key;
+
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+
+	skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
+	if (IS_ERR(skb))
+		return NULL;
+
+	tpi.flags = filter_tnl_flags(tun_key->tun_flags);
+	tpi.proto = htons(ETH_P_TEB);
+	tpi.key = be64_get_low32(tun_key->tun_id);
+	tpi.seq = 0;
+	gre_build_header(skb, &tpi, tunnel_hlen);
+
+	return skb;
+}
+
+static __be64 key_to_tunnel_id(__be32 key, __be32 seq)
+{
+#ifdef __BIG_ENDIAN
+	return (__force __be64)((__force u64)seq << 32 | (__force u32)key);
+#else
+	return (__force __be64)((__force u64)key << 32 | (__force u32)seq);
+#endif
+}
+
+/* Called with rcu_read_lock and BH disabled. */
+static int gre_rcv(struct sk_buff *skb,
+		   const struct tnl_ptk_info *tpi)
+{
+	struct ovs_tunnel_info tun_info;
+	struct ovs_net *ovs_net;
+	struct vport *vport;
+	__be64 key;
+
+	ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
+	vport = rcu_dereference(ovs_net->vport_net.gre_vport);
+	if (unlikely(!vport))
+		return PACKET_REJECT;
+
+	key = key_to_tunnel_id(tpi->key, tpi->seq);
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+			       filter_tnl_flags(tpi->flags), NULL, 0);
+
+	ovs_vport_receive(vport, skb, &tun_info);
+	return PACKET_RCVD;
+}
+
+/* Called with rcu_read_lock and BH disabled. */
+static int gre_err(struct sk_buff *skb, u32 info,
+		   const struct tnl_ptk_info *tpi)
+{
+	struct ovs_net *ovs_net;
+	struct vport *vport;
+
+	ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
+	vport = rcu_dereference(ovs_net->vport_net.gre_vport);
+
+	if (unlikely(!vport))
+		return PACKET_REJECT;
+	else
+		return PACKET_RCVD;
+}
+
+static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct ovs_key_ipv4_tunnel *tun_key;
+	struct flowi4 fl;
+	struct rtable *rt;
+	int min_headroom;
+	int tunnel_hlen;
+	__be16 df;
+	int err;
+
+	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+	/* Route lookup */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb->mark;
+	fl.flowi4_proto = IPPROTO_GRE;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);
+
+	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+			+ tunnel_hlen + sizeof(struct iphdr)
+			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
+		int head_delta = SKB_DATA_ALIGN(min_headroom -
+						skb_headroom(skb) +
+						16);
+		err = pskb_expand_head(skb, max_t(int, head_delta, 0),
+					0, GFP_ATOMIC);
+		if (unlikely(err))
+			goto err_free_rt;
+	}
+
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb)) {
+		err = -ENOMEM;
+		goto err_free_rt;
+	}
+
+	/* Push Tunnel header. */
+	skb = __build_header(skb, tunnel_hlen);
+	if (unlikely(!skb)) {
+		err = 0;
+		goto err_free_rt;
+	}
+
+	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
+		htons(IP_DF) : 0;
+
+	skb->ignore_df = 1;
+
+	return iptunnel_xmit(skb->sk, rt, skb, fl.saddr,
+			     tun_key->ipv4_dst, IPPROTO_GRE,
+			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false);
+err_free_rt:
+	ip_rt_put(rt);
+error:
+	return err;
+}
+
+static struct gre_cisco_protocol gre_protocol = {
+	.handler        = gre_rcv,
+	.err_handler    = gre_err,
+	.priority       = 1,
+};
+
+static int gre_ports;
+static int gre_init(void)
+{
+	int err;
+
+	gre_ports++;
+	if (gre_ports > 1)
+		return 0;
+
+	err = gre_cisco_register(&gre_protocol);
+	if (err)
+		pr_warn("cannot register gre protocol handler\n");
+
+	return err;
+}
+
+static void gre_exit(void)
+{
+	gre_ports--;
+	if (gre_ports > 0)
+		return;
+
+	gre_cisco_unregister(&gre_protocol);
+}
+
+static const char *gre_get_name(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+static struct vport *gre_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct ovs_net *ovs_net;
+	struct vport *vport;
+	int err;
+
+	err = gre_init();
+	if (err)
+		return ERR_PTR(err);
+
+	ovs_net = net_generic(net, ovs_net_id);
+	if (ovsl_dereference(ovs_net->vport_net.gre_vport)) {
+		vport = ERR_PTR(-EEXIST);
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(IFNAMSIZ, &ovs_gre_vport_ops, parms);
+	if (IS_ERR(vport))
+		goto error;
+
+	strncpy(vport_priv(vport), parms->name, IFNAMSIZ);
+	rcu_assign_pointer(ovs_net->vport_net.gre_vport, vport);
+	return vport;
+
+error:
+	gre_exit();
+	return vport;
+}
+
+static void gre_tnl_destroy(struct vport *vport)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct ovs_net *ovs_net;
+
+	ovs_net = net_generic(net, ovs_net_id);
+
+	RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL);
+	ovs_vport_deferred_free(vport);
+	gre_exit();
+}
+
+const struct vport_ops ovs_gre_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GRE,
+	.create		= gre_create,
+	.destroy	= gre_tnl_destroy,
+	.get_name	= gre_get_name,
+	.send		= gre_tnl_send,
+};

net/openvswitch/vport-internal_dev.c

@@ -0,0 +1,270 @@
+/*
+ * 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/hardirq.h>
+#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 internal_dev *internal_dev_priv(struct net_device *netdev)
+{
+	return netdev_priv(netdev);
+}
+
+/* This function is only called by the kernel network layer.*/
+static struct rtnl_link_stats64 *internal_dev_get_stats(struct net_device *netdev,
+							struct rtnl_link_stats64 *stats)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(netdev);
+	struct ovs_vport_stats vport_stats;
+
+	ovs_vport_get_stats(vport, &vport_stats);
+
+	/* The tx and rx stats need to be swapped because the
+	 * switch and host OS have opposite perspectives. */
+	stats->rx_packets	= vport_stats.tx_packets;
+	stats->tx_packets	= vport_stats.rx_packets;
+	stats->rx_bytes		= vport_stats.tx_bytes;
+	stats->tx_bytes		= vport_stats.rx_bytes;
+	stats->rx_errors	= vport_stats.tx_errors;
+	stats->tx_errors	= vport_stats.rx_errors;
+	stats->rx_dropped	= vport_stats.tx_dropped;
+	stats->tx_dropped	= vport_stats.rx_dropped;
+
+	return stats;
+}
+
+/* Called with rcu_read_lock_bh. */
+static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	rcu_read_lock();
+	ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
+	rcu_read_unlock();
+	return 0;
+}
+
+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 int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	netdev->mtu = new_mtu;
+	return 0;
+}
+
+static void internal_dev_destructor(struct net_device *dev)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+	ovs_vport_free(vport);
+	free_netdev(dev);
+}
+
+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_change_mtu = internal_dev_change_mtu,
+	.ndo_get_stats64 = internal_dev_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->netdev_ops = &internal_dev_netdev_ops;
+
+	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netdev->destructor = internal_dev_destructor;
+	netdev->ethtool_ops = &internal_dev_ethtool_ops;
+	netdev->rtnl_link_ops = &internal_dev_link_ops;
+	netdev->tx_queue_len = 0;
+
+	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;
+	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 netdev_vport *netdev_vport;
+	struct internal_dev *internal_dev;
+	int err;
+
+	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+				&ovs_internal_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	netdev_vport = netdev_vport_priv(vport);
+
+	netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev),
+					 parms->name, NET_NAME_UNKNOWN,
+					 do_setup);
+	if (!netdev_vport->dev) {
+		err = -ENOMEM;
+		goto error_free_vport;
+	}
+
+	dev_net_set(netdev_vport->dev, ovs_dp_get_net(vport->dp));
+	internal_dev = internal_dev_priv(netdev_vport->dev);
+	internal_dev->vport = vport;
+
+	/* Restrict bridge port to current netns. */
+	if (vport->port_no == OVSP_LOCAL)
+		netdev_vport->dev->features |= NETIF_F_NETNS_LOCAL;
+
+	rtnl_lock();
+	err = register_netdevice(netdev_vport->dev);
+	if (err)
+		goto error_free_netdev;
+
+	dev_set_promiscuity(netdev_vport->dev, 1);
+	rtnl_unlock();
+	netif_start_queue(netdev_vport->dev);
+
+	return vport;
+
+error_free_netdev:
+	rtnl_unlock();
+	free_netdev(netdev_vport->dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void internal_dev_destroy(struct vport *vport)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+	netif_stop_queue(netdev_vport->dev);
+	rtnl_lock();
+	dev_set_promiscuity(netdev_vport->dev, -1);
+
+	/* unregister_netdevice() waits for an RCU grace period. */
+	unregister_netdevice(netdev_vport->dev);
+
+	rtnl_unlock();
+}
+
+static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
+{
+	struct net_device *netdev = netdev_vport_priv(vport)->dev;
+	int len;
+
+	len = skb->len;
+
+	skb_dst_drop(skb);
+	nf_reset(skb);
+	secpath_reset(skb);
+
+	skb->dev = netdev;
+	skb->pkt_type = PACKET_HOST;
+	skb->protocol = eth_type_trans(skb, netdev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+
+	netif_rx(skb);
+
+	return len;
+}
+
+const struct vport_ops ovs_internal_vport_ops = {
+	.type		= OVS_VPORT_TYPE_INTERNAL,
+	.create		= internal_dev_create,
+	.destroy	= internal_dev_destroy,
+	.get_name	= ovs_netdev_get_name,
+	.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)
+{
+	return rtnl_link_register(&internal_dev_link_ops);
+}
+
+void ovs_internal_dev_rtnl_link_unregister(void)
+{
+	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 +1,233 @@
+/*
+ * 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 <net/llc.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+/* Must be called with rcu_read_lock. */
+static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
+{
+	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;
+
+	skb_push(skb, ETH_HLEN);
+	ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+
+	ovs_vport_receive(vport, skb, NULL);
+	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;
+	struct vport *vport;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	vport = ovs_netdev_get_vport(skb->dev);
+
+	netdev_port_receive(vport, skb);
+
+	return RX_HANDLER_CONSUMED;
+}
+
+static struct net_device *get_dpdev(struct datapath *dp)
+{
+	struct vport *local;
+
+	local = ovs_vport_ovsl(dp, OVSP_LOCAL);
+	BUG_ON(!local);
+	return netdev_vport_priv(local)->dev;
+}
+
+static struct vport *netdev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	struct netdev_vport *netdev_vport;
+	int err;
+
+	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+				&ovs_netdev_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	netdev_vport = netdev_vport_priv(vport);
+
+	netdev_vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name);
+	if (!netdev_vport->dev) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+
+	if (netdev_vport->dev->flags & IFF_LOOPBACK ||
+	    netdev_vport->dev->type != ARPHRD_ETHER ||
+	    ovs_is_internal_dev(netdev_vport->dev)) {
+		err = -EINVAL;
+		goto error_put;
+	}
+
+	rtnl_lock();
+	err = netdev_master_upper_dev_link(netdev_vport->dev,
+					   get_dpdev(vport->dp));
+	if (err)
+		goto error_unlock;
+
+	err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook,
+					 vport);
+	if (err)
+		goto error_master_upper_dev_unlink;
+
+	dev_set_promiscuity(netdev_vport->dev, 1);
+	netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
+	rtnl_unlock();
+
+	return vport;
+
+error_master_upper_dev_unlink:
+	netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp));
+error_unlock:
+	rtnl_unlock();
+error_put:
+	dev_put(netdev_vport->dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void free_port_rcu(struct rcu_head *rcu)
+{
+	struct netdev_vport *netdev_vport = container_of(rcu,
+					struct netdev_vport, rcu);
+
+	dev_put(netdev_vport->dev);
+	ovs_vport_free(vport_from_priv(netdev_vport));
+}
+
+void ovs_netdev_detach_dev(struct vport *vport)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+	ASSERT_RTNL();
+	netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
+	netdev_rx_handler_unregister(netdev_vport->dev);
+	netdev_upper_dev_unlink(netdev_vport->dev,
+				netdev_master_upper_dev_get(netdev_vport->dev));
+	dev_set_promiscuity(netdev_vport->dev, -1);
+}
+
+static void netdev_destroy(struct vport *vport)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+	rtnl_lock();
+	if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)
+		ovs_netdev_detach_dev(vport);
+	rtnl_unlock();
+
+	call_rcu(&netdev_vport->rcu, free_port_rcu);
+}
+
+const char *ovs_netdev_get_name(const struct vport *vport)
+{
+	const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+	return netdev_vport->dev->name;
+}
+
+static unsigned int packet_length(const struct sk_buff *skb)
+{
+	unsigned int length = skb->len - ETH_HLEN;
+
+	if (skb->protocol == htons(ETH_P_8021Q))
+		length -= VLAN_HLEN;
+
+	return length;
+}
+
+static int netdev_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+	int mtu = netdev_vport->dev->mtu;
+	int len;
+
+	if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+		net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
+				     netdev_vport->dev->name,
+				     packet_length(skb), mtu);
+		goto drop;
+	}
+
+	skb->dev = netdev_vport->dev;
+	len = skb->len;
+	dev_queue_xmit(skb);
+
+	return len;
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
+/* 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;
+}
+
+const struct vport_ops ovs_netdev_vport_ops = {
+	.type		= OVS_VPORT_TYPE_NETDEV,
+	.create		= netdev_create,
+	.destroy	= netdev_destroy,
+	.get_name	= ovs_netdev_get_name,
+	.send		= netdev_send,
+};

net/openvswitch/vport-netdev.h

@@ -0,0 +1,44 @@
+/*
+ * 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 netdev_vport {
+	struct rcu_head rcu;
+
+	struct net_device *dev;
+};
+
+static inline struct netdev_vport *
+netdev_vport_priv(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+const char *ovs_netdev_get_name(const struct vport *);
+void ovs_netdev_detach_dev(struct vport *);
+
+#endif /* vport_netdev.h */

net/openvswitch/vport-vxlan.c

@@ -0,0 +1,202 @@
+/*
+ * 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
+ */
+
+#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 <net/icmp.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/ip_tunnels.h>
+#include <net/rtnetlink.h>
+#include <net/route.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/vxlan.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+/**
+ * struct vxlan_port - Keeps track of open UDP ports
+ * @vs: vxlan_sock created for the port.
+ * @name: vport name.
+ */
+struct vxlan_port {
+	struct vxlan_sock *vs;
+	char name[IFNAMSIZ];
+};
+
+static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+/* Called with rcu_read_lock and BH disabled. */
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
+{
+	struct ovs_tunnel_info tun_info;
+	struct vport *vport = vs->data;
+	struct iphdr *iph;
+	__be64 key;
+
+	/* Save outer tunnel values */
+	iph = ip_hdr(skb);
+	key = cpu_to_be64(ntohl(vx_vni) >> 8);
+	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
+
+	ovs_vport_receive(vport, skb, &tun_info);
+}
+
+static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static void vxlan_tnl_destroy(struct vport *vport)
+{
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+
+	vxlan_sock_release(vxlan_port->vs);
+
+	ovs_vport_deferred_free(vport);
+}
+
+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 vxlan_port *vxlan_port;
+	struct vxlan_sock *vs;
+	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 vxlan_port),
+				&ovs_vxlan_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	vxlan_port = vxlan_vport(vport);
+	strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
+
+	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
+	if (IS_ERR(vs)) {
+		ovs_vport_free(vport);
+		return (void *)vs;
+	}
+	vxlan_port->vs = vs;
+
+	return vport;
+
+error:
+	return ERR_PTR(err);
+}
+
+static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+	struct ovs_key_ipv4_tunnel *tun_key;
+	struct rtable *rt;
+	struct flowi4 fl;
+	__be16 src_port;
+	__be16 df;
+	int err;
+
+	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+	/* Route lookup */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb->mark;
+	fl.flowi4_proto = IPPROTO_UDP;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		goto error;
+	}
+
+	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
+		htons(IP_DF) : 0;
+
+	skb->ignore_df = 1;
+
+	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
+			     fl.saddr, tun_key->ipv4_dst,
+			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
+			     src_port, dst_port,
+			     htonl(be64_to_cpu(tun_key->tun_id) << 8),
+			     false);
+	if (err < 0)
+		ip_rt_put(rt);
+error:
+	return err;
+}
+
+static const char *vxlan_get_name(const struct vport *vport)
+{
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	return vxlan_port->name;
+}
+
+const struct vport_ops ovs_vxlan_vport_ops = {
+	.type		= OVS_VPORT_TYPE_VXLAN,
+	.create		= vxlan_tnl_create,
+	.destroy	= vxlan_tnl_destroy,
+	.get_name	= vxlan_get_name,
+	.get_options	= vxlan_get_options,
+	.send		= vxlan_tnl_send,
+};

net/openvswitch/vport.c

@@ -0,0 +1,537 @@
+/*
+ * 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 "datapath.h"
+#include "vport.h"
+#include "vport-internal_dev.h"
+
+static void ovs_vport_record_error(struct vport *,
+				   enum vport_err_type err_type);
+
+/* List of statically compiled vport implementations.  Don't forget to also
+ * add yours to the list at the bottom of vport.h. */
+static const struct vport_ops *vport_ops_list[] = {
+	&ovs_netdev_vport_ops,
+	&ovs_internal_vport_ops,
+
+#ifdef CONFIG_OPENVSWITCH_GRE
+	&ovs_gre_vport_ops,
+#endif
+#ifdef CONFIG_OPENVSWITCH_VXLAN
+	&ovs_vxlan_vport_ops,
+#endif
+#ifdef CONFIG_OPENVSWITCH_GENEVE
+	&ovs_geneve_vport_ops,
+#endif
+};
+
+/* 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 = kzalloc(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(struct net *net, const char *name)
+{
+	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
+	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
+}
+
+/**
+ *	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(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, vport->ops->get_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);
+	}
+
+	vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!vport->percpu_stats) {
+		kfree(vport);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return vport;
+}
+
+/**
+ *	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));
+	free_percpu(vport->percpu_stats);
+	kfree(vport);
+}
+
+/**
+ *	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 *vport;
+	int err = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
+		if (vport_ops_list[i]->type == parms->type) {
+			struct hlist_head *bucket;
+
+			vport = vport_ops_list[i]->create(parms);
+			if (IS_ERR(vport)) {
+				err = PTR_ERR(vport);
+				goto out;
+			}
+
+			bucket = hash_bucket(ovs_dp_get_net(vport->dp),
+					     vport->ops->get_name(vport));
+			hlist_add_head_rcu(&vport->hash_node, bucket);
+			return vport;
+		}
+	}
+
+	err = -EAFNOSUPPORT;
+
+out:
+	return ERR_PTR(err);
+}
+
+/**
+ *	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.  It is possible to fail
+ * for reasons such as lack of memory.  ovs_mutex must be held.
+ */
+void ovs_vport_del(struct vport *vport)
+{
+	ASSERT_OVSL();
+
+	hlist_del_rcu(&vport->hash_node);
+
+	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)
+{
+	int i;
+
+	memset(stats, 0, sizeof(*stats));
+
+	/* We potentially have 2 sources of stats that need to be combined:
+	 * those we have collected (split into err_stats and percpu_stats) from
+	 * set_stats() and device error stats from netdev->get_stats() (for
+	 * errors that happen  downstream and therefore aren't reported through
+	 * our vport_record_error() function).
+	 * Stats from first source are reported by ovs (OVS_VPORT_ATTR_STATS).
+	 * netdev-stats can be directly read over netlink-ioctl.
+	 */
+
+	stats->rx_errors  = atomic_long_read(&vport->err_stats.rx_errors);
+	stats->tx_errors  = atomic_long_read(&vport->err_stats.tx_errors);
+	stats->tx_dropped = atomic_long_read(&vport->err_stats.tx_dropped);
+	stats->rx_dropped = atomic_long_read(&vport->err_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(vport->percpu_stats, 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;
+	}
+}
+
+/**
+ *	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,  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.
+ */
+void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
+		       struct ovs_tunnel_info *tun_info)
+{
+	struct pcpu_sw_netstats *stats;
+	struct sw_flow_key key;
+	int error;
+
+	stats = this_cpu_ptr(vport->percpu_stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	OVS_CB(skb)->input_vport = vport;
+	OVS_CB(skb)->egress_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;
+	}
+	ovs_dp_process_packet(skb, &key);
+}
+
+/**
+ *	ovs_vport_send - send a packet on a device
+ *
+ * @vport: vport on which to send the packet
+ * @skb: skb to send
+ *
+ * Sends the given packet and returns the length of data sent.  Either ovs
+ * lock or rcu_read_lock must be held.
+ */
+int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+{
+	int sent = vport->ops->send(vport, skb);
+
+	if (likely(sent > 0)) {
+		struct pcpu_sw_netstats *stats;
+
+		stats = this_cpu_ptr(vport->percpu_stats);
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->tx_packets++;
+		stats->tx_bytes += sent;
+		u64_stats_update_end(&stats->syncp);
+	} else if (sent < 0) {
+		ovs_vport_record_error(vport, VPORT_E_TX_ERROR);
+		kfree_skb(skb);
+	} else
+		ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
+
+	return sent;
+}
+
+/**
+ *	ovs_vport_record_error - indicate device error to generic stats layer
+ *
+ * @vport: vport that encountered the error
+ * @err_type: one of enum vport_err_type types to indicate the error type
+ *
+ * If using the vport generic stats layer indicate that an error of the given
+ * type has occurred.
+ */
+static void ovs_vport_record_error(struct vport *vport,
+				   enum vport_err_type err_type)
+{
+	switch (err_type) {
+	case VPORT_E_RX_DROPPED:
+		atomic_long_inc(&vport->err_stats.rx_dropped);
+		break;
+
+	case VPORT_E_RX_ERROR:
+		atomic_long_inc(&vport->err_stats.rx_errors);
+		break;
+
+	case VPORT_E_TX_DROPPED:
+		atomic_long_inc(&vport->err_stats.tx_dropped);
+		break;
+
+	case VPORT_E_TX_ERROR:
+		atomic_long_inc(&vport->err_stats.tx_errors);
+		break;
+	}
+
+}
+
+static void free_vport_rcu(struct rcu_head *rcu)
+{
+	struct vport *vport = container_of(rcu, struct vport, rcu);
+
+	ovs_vport_free(vport);
+}
+
+void ovs_vport_deferred_free(struct vport *vport)
+{
+	if (!vport)
+		return;
+
+	call_rcu(&vport->rcu, free_vport_rcu);
+}

net/openvswitch/vport.h

@@ -0,0 +1,229 @@
+/*
+ * 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: */
+
+struct vport_net {
+	struct vport __rcu *gre_vport;
+};
+
+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(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 *, 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 *);
+
+int ovs_vport_send(struct vport *, struct sk_buff *);
+
+/* The following definitions are for implementers of vport devices: */
+
+struct vport_err_stats {
+	atomic_long_t rx_dropped;
+	atomic_long_t rx_errors;
+	atomic_long_t tx_dropped;
+	atomic_long_t tx_errors;
+};
+/**
+ * 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
+ * @rcu: RCU callback head for deferred destruction.
+ * @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.
+ * @percpu_stats: Points to per-CPU statistics used and maintained by vport
+ * @err_stats: Points to error statistics used and maintained by vport
+ * @detach_list: list used for detaching vport in net-exit call.
+ */
+struct vport {
+	struct rcu_head rcu;
+	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 pcpu_sw_netstats __percpu *percpu_stats;
+
+	struct vport_err_stats err_stats;
+	struct list_head detach_list;
+};
+
+/**
+ * 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.
+ * @get_name: Get the device's name.
+ * @send: Send a packet on the device.  Returns the length of the packet sent,
+ * 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 *);
+
+	/* Called with rcu_read_lock or ovs_mutex. */
+	const char *(*get_name)(const struct vport *);
+
+	int (*send)(struct vport *, struct sk_buff *);
+};
+
+enum vport_err_type {
+	VPORT_E_RX_DROPPED,
+	VPORT_E_RX_ERROR,
+	VPORT_E_TX_DROPPED,
+	VPORT_E_TX_ERROR,
+};
+
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
+			      const struct vport_parms *);
+void ovs_vport_free(struct vport *);
+void ovs_vport_deferred_free(struct vport *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));
+}
+
+void ovs_vport_receive(struct vport *, struct sk_buff *,
+		       struct ovs_tunnel_info *);
+
+/* List of statically compiled vport implementations.  Don't forget to also
+ * add yours to the list at the top of vport.c. */
+extern const struct vport_ops ovs_netdev_vport_ops;
+extern const struct vport_ops ovs_internal_vport_ops;
+extern const struct vport_ops ovs_gre_vport_ops;
+extern const struct vport_ops ovs_vxlan_vport_ops;
+extern const struct vport_ops ovs_geneve_vport_ops;
+
+static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
+				      const void *start, unsigned int len)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
+}
+
+#endif /* vport.h */