Resguardo inicial

linux-7.2.3/net/openvswitch/Kconfig

@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+	tristate "Open vSwitch"
+	depends on INET
+	depends on !NF_CONNTRACK || \
+		   (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \
+				     (!NF_NAT || NF_NAT) && \
+				     (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
+	depends on PSAMPLE || !PSAMPLE
+	select MPLS
+	select NET_CRC32C
+	select NET_MPLS_GSO
+	select DST_CACHE
+	select NET_NSH
+	select NF_CONNTRACK_OVS if NF_CONNTRACK
+	select NF_NAT_OVS if NF_NAT
+	help
+	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
+	  environments.  In addition to supporting a variety of features
+	  expected in a traditional hardware switch, it enables fine-grained
+	  programmatic extension and flow-based control of the network.  This
+	  control is useful in a wide variety of applications but is
+	  particularly important in multi-server virtualization deployments,
+	  which are often characterized by highly dynamic endpoints and the
+	  need to maintain logical abstractions for multiple tenants.
+
+	  The Open vSwitch datapath provides an in-kernel fast path for packet
+	  forwarding.  It is complemented by a userspace daemon, ovs-vswitchd,
+	  which is able to accept configuration from a variety of sources and
+	  translate it into packet processing rules.
+
+	  See http://openvswitch.org for more information and userspace
+	  utilities.
+
+	  To compile this code as a module, choose M here: the module will be
+	  called openvswitch.
+
+	  If unsure, say N.
+
+config OPENVSWITCH_GRE
+	tristate "Open vSwitch GRE tunneling support"
+	depends on OPENVSWITCH
+	depends on NET_IPGRE
+	default OPENVSWITCH
+	help
+	  If you say Y here, then the Open vSwitch will be able create GRE
+	  vport.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.
+
+config OPENVSWITCH_VXLAN
+	tristate "Open vSwitch VXLAN tunneling support"
+	depends on OPENVSWITCH
+	depends on VXLAN
+	default OPENVSWITCH
+	help
+	  If you say Y here, then the Open vSwitch will be able create vxlan vport.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+	tristate "Open vSwitch Geneve tunneling support"
+	depends on OPENVSWITCH
+	depends on GENEVE
+	default OPENVSWITCH
+	help
+	  If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+	  Say N to exclude this support and reduce the binary size.

linux-7.2.3/net/openvswitch/Makefile

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+	actions.o \
+	datapath.o \
+	dp_notify.o \
+	flow.o \
+	flow_netlink.o \
+	flow_table.o \
+	meter.o \
+	openvswitch_trace.o \
+	vport.o \
+	vport-internal_dev.o \
+	vport-netdev.o
+
+ifneq ($(CONFIG_NF_CONNTRACK),)
+openvswitch-y += conntrack.o
+endif
+
+obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o
+obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o
+obj-$(CONFIG_OPENVSWITCH_GRE)	+= vport-gre.o
+
+CFLAGS_openvswitch_trace.o = -I$(src)

linux-7.2.3/net/openvswitch/conntrack.h

@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015 Nicira, Inc.
+ */
+
+#ifndef OVS_CONNTRACK_H
+#define OVS_CONNTRACK_H 1
+
+#include "flow.h"
+
+struct ovs_conntrack_info;
+struct ovs_ct_limit_info;
+enum ovs_key_attr;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+int ovs_ct_init(struct net *);
+void ovs_ct_exit(struct net *);
+bool ovs_ct_verify(struct net *, enum ovs_key_attr attr);
+int ovs_ct_copy_action(struct net *, const struct nlattr *,
+		       const struct sw_flow_key *, struct sw_flow_actions **,
+		       bool log);
+int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
+
+int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
+		   const struct ovs_conntrack_info *);
+int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
+
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key,
+		     bool post_ct);
+int ovs_ct_put_key(const struct sw_flow_key *swkey,
+		   const struct sw_flow_key *output, struct sk_buff *skb);
+void ovs_ct_free_action(const struct nlattr *a);
+
+#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \
+			   OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \
+			   OVS_CS_F_INVALID | OVS_CS_F_TRACKED | \
+			   OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT)
+#else
+#include <linux/errno.h>
+
+static inline int ovs_ct_init(struct net *net) { return 0; }
+
+static inline void ovs_ct_exit(struct net *net) { }
+
+static inline bool ovs_ct_verify(struct net *net, int attr)
+{
+	return false;
+}
+
+static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla,
+				     const struct sw_flow_key *key,
+				     struct sw_flow_actions **acts, bool log)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info,
+					struct sk_buff *skb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
+				 struct sw_flow_key *key,
+				 const struct ovs_conntrack_info *info)
+{
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_clear(struct sk_buff *skb,
+			       struct sw_flow_key *key)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ovs_ct_fill_key(const struct sk_buff *skb,
+				   struct sw_flow_key *key,
+				   bool post_ct)
+{
+	key->ct_state = 0;
+	key->ct_zone = 0;
+	key->ct.mark = 0;
+	memset(&key->ct.labels, 0, sizeof(key->ct.labels));
+	/* Clear 'ct_orig_proto' to mark the non-existence of original
+	 * direction key fields.
+	 */
+	key->ct_orig_proto = 0;
+}
+
+static inline int ovs_ct_put_key(const struct sw_flow_key *swkey,
+				 const struct sw_flow_key *output,
+				 struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline void ovs_ct_free_action(const struct nlattr *a) { }
+
+#define CT_SUPPORTED_MASK 0
+#endif /* CONFIG_NF_CONNTRACK */
+
+#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+extern struct genl_family dp_ct_limit_genl_family;
+#endif
+#endif /* ovs_conntrack.h */

linux-7.2.3/net/openvswitch/datapath.h

@@ -0,0 +1,346 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ */
+
+#ifndef DATAPATH_H
+#define DATAPATH_H 1
+
+#include <asm/page.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+#include <net/ip_tunnels.h>
+#include <net/mpls.h>
+
+#include "conntrack.h"
+#include "flow.h"
+#include "flow_table.h"
+#include "meter.h"
+#include "vport-internal_dev.h"
+
+#define DP_MAX_PORTS                USHRT_MAX
+#define DP_VPORT_HASH_BUCKETS       1024
+#define DP_MASKS_REBALANCE_INTERVAL 4000
+
+/**
+ * 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_missed: Number of received packets that had no matching flow in the flow
+ * table.  The sum of @n_hit and @n_missed 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.
+ * @n_cache_hit: The number of received packets that had their mask found using
+ * the mask cache.
+ * @syncp: Synchronization point for 64bit counters.
+ */
+struct dp_stats_percpu {
+	u64 n_hit;
+	u64 n_missed;
+	u64 n_lost;
+	u64 n_mask_hit;
+	u64 n_cache_hit;
+	struct u64_stats_sync syncp;
+};
+
+/**
+ * struct dp_nlsk_pids - array of netlink portids of for a datapath.
+ *                       This is used when OVS_DP_F_DISPATCH_UPCALL_PER_CPU
+ *                       is enabled and must be protected by rcu.
+ * @rcu: RCU callback head for deferred destruction.
+ * @n_pids: Size of @pids array.
+ * @pids: Array storing the Netlink socket PIDs indexed by CPU ID for packets
+ *       that miss the flow table.
+ */
+struct dp_nlsk_pids {
+	struct rcu_head rcu;
+	u32 n_pids;
+	u32 pids[];
+};
+
+/**
+ * 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.
+ * @user_features: Bitmap of enabled %OVS_DP_F_* features.
+ * @max_headroom: The maximum headroom of all vports in this datapath; it will
+ * be used by all the internal vports in this dp.
+ * @meter_tbl: Meter table.
+ * @upcall_portids: RCU protected 'struct dp_nlsk_pids'.
+ *
+ * Context: See the comment on locking at the top of datapath.c for additional
+ * locking information.
+ */
+struct datapath {
+	struct rcu_head rcu;
+	struct list_head list_node;
+
+	/* Flow table. */
+	struct flow_table table;
+
+	/* Switch ports. */
+	struct hlist_head *ports;
+
+	/* Stats. */
+	struct dp_stats_percpu __percpu *stats_percpu;
+
+	/* Network namespace ref. */
+	possible_net_t net;
+
+	u32 user_features;
+
+	u32 max_headroom;
+
+	/* Switch meters. */
+	struct dp_meter_table meter_tbl;
+
+	struct dp_nlsk_pids __rcu *upcall_portids;
+};
+
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @input_vport: The original vport packet came in on. This value is cached
+ * when a packet is received by OVS.
+ * @mru: The maximum received fragement size; 0 if the packet is not
+ * fragmented.
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
+ * @cutlen: The number of bytes in the packet to preserve on output.
+ * @probability: The sampling probability that was applied to this skb; 0 means
+ * no sampling has occurred; U32_MAX means 100% probability.
+ * @upcall_pid: Netlink socket PID to use for sending this packet to userspace;
+ * 0 means "not set" and default per-CPU or per-vport dispatch should be used.
+ */
+struct ovs_skb_cb {
+	struct vport		*input_vport;
+	u16			mru;
+	u16			acts_origlen;
+	u32			cutlen;
+	u32			probability;
+	u32			upcall_pid;
+};
+#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
+
+/**
+ * struct dp_upcall_info - metadata to include with a packet sent to userspace
+ * @cmd: One of %OVS_PACKET_CMD_*.
+ * @userdata: If nonnull, its variable-length value is passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @actions: If nonnull, its variable-length value is passed to userspace as
+ * %OVS_PACKET_ATTR_ACTIONS.
+ * @actions_len: The length of the @actions.
+ * @portid: Netlink portid to which packet should be sent.  If @portid is 0
+ * then no packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
+ * @mru: If not zero, Maximum received IP fragment size.
+ */
+struct dp_upcall_info {
+	struct ip_tunnel_info *egress_tun_info;
+	const struct nlattr *userdata;
+	const struct nlattr *actions;
+	int actions_len;
+	u32 portid;
+	u8 cmd;
+	u16 mru;
+};
+
+/**
+ * struct ovs_net - Per net-namespace data for ovs.
+ * @dps: List of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ * @dp_notify_work: A work notifier to handle port unregistering.
+ * @masks_rebalance: A work to periodically optimize flow table caches.
+ * @ct_limit_info: A hash table of conntrack zone connection limits.
+ * @xt_label: Whether connlables are configured for the network or not.
+ */
+struct ovs_net {
+	struct list_head dps;
+	struct work_struct dp_notify_work;
+	struct delayed_work masks_rebalance;
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+	struct ovs_ct_limit_info *ct_limit_info;
+#endif
+	bool xt_label;
+};
+
+#define MAX_L2_LEN	(VLAN_ETH_HLEN + 3 * MPLS_HLEN)
+struct ovs_frag_data {
+	unsigned long dst;
+	struct vport *vport;
+	struct ovs_skb_cb cb;
+	__be16 inner_protocol;
+	u16 network_offset;	/* valid only for MPLS */
+	u16 vlan_tci;
+	__be16 vlan_proto;
+	unsigned int l2_len;
+	u8 mac_proto;
+	u8 l2_data[MAX_L2_LEN];
+};
+
+struct deferred_action {
+	struct sk_buff *skb;
+	const struct nlattr *actions;
+	int actions_len;
+
+	/* Store pkt_key clone when creating deferred action. */
+	struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+#define OVS_RECURSION_LIMIT 5
+#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
+
+struct action_fifo {
+	int head;
+	int tail;
+	/* Deferred action fifo queue storage. */
+	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+struct action_flow_keys {
+	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
+};
+
+struct ovs_pcpu_storage {
+	struct action_fifo action_fifos;
+	struct action_flow_keys flow_keys;
+	struct ovs_frag_data frag_data;
+	int exec_level;
+	struct task_struct *owner;
+	local_lock_t bh_lock;
+};
+
+extern struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
+
+/**
+ * enum ovs_pkt_hash_types - hash info to include with a packet
+ * to send to userspace.
+ * @OVS_PACKET_HASH_SW_BIT: indicates hash was computed in software stack.
+ * @OVS_PACKET_HASH_L4_BIT: indicates hash is a canonical 4-tuple hash
+ * over transport ports.
+ */
+enum ovs_pkt_hash_types {
+	OVS_PACKET_HASH_SW_BIT = (1ULL << 32),
+	OVS_PACKET_HASH_L4_BIT = (1ULL << 33),
+};
+
+extern unsigned int ovs_net_id;
+void ovs_lock(void);
+void ovs_unlock(void);
+
+#ifdef CONFIG_LOCKDEP
+int lockdep_ovsl_is_held(void);
+#else
+#define lockdep_ovsl_is_held()	1
+#endif
+
+#define ASSERT_OVSL()		WARN_ON(!lockdep_ovsl_is_held())
+#define ovsl_dereference(p)					\
+	rcu_dereference_protected(p, lockdep_ovsl_is_held())
+#define rcu_dereference_ovsl(p)					\
+	rcu_dereference_check(p, lockdep_ovsl_is_held())
+
+static inline struct net *ovs_dp_get_net(const struct datapath *dp)
+{
+	return read_pnet(&dp->net);
+}
+
+static inline void ovs_dp_set_net(struct datapath *dp, struct net *net)
+{
+	write_pnet(&dp->net, net);
+}
+
+struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no);
+
+static inline struct vport *ovs_vport_rcu(const struct datapath *dp, int port_no)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_ovsl_rcu(const struct datapath *dp, int port_no)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_no)
+{
+	ASSERT_OVSL();
+	return ovs_lookup_vport(dp, port_no);
+}
+
+/* Must be called with rcu_read_lock. */
+static inline struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
+{
+	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
+
+	if (dev) {
+		struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+		if (vport)
+			return vport->dp;
+	}
+
+	return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+	struct datapath *dp;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	rcu_read_lock();
+	dp = get_dp_rcu(net, dp_ifindex);
+	rcu_read_unlock();
+
+	return dp;
+}
+
+extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_family dp_vport_genl_family;
+
+void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
+void ovs_dp_detach_port(struct vport *);
+int ovs_dp_upcall(struct datapath *, struct sk_buff *,
+		  const struct sw_flow_key *, const struct dp_upcall_info *,
+		  uint32_t cutlen);
+
+u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+					 u32 portid, u32 seq, u8 cmd);
+
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct sw_flow_actions *, struct sw_flow_key *);
+
+void ovs_dp_notify_wq(struct work_struct *work);
+
+/* 'KEY' must not have any bits set outside of the 'MASK' */
+#define OVS_MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
+#define OVS_SET_MASKED(OLD, KEY, MASK) ((OLD) = OVS_MASKED(OLD, KEY, MASK))
+
+#define OVS_NLERR(logging_allowed, fmt, ...)			\
+do {								\
+	if (logging_allowed && net_ratelimit())			\
+		pr_info("netlink: " fmt "\n", ##__VA_ARGS__);	\
+} while (0)
+#endif /* datapath.h */

linux-7.2.3/net/openvswitch/dp_notify.c

@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static void dp_detach_port_notify(struct vport *vport)
+{
+	struct sk_buff *notify;
+	struct datapath *dp;
+
+	dp = vport->dp;
+	notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp),
+					  0, 0, OVS_VPORT_CMD_DEL);
+	ovs_dp_detach_port(vport);
+	if (IS_ERR(notify)) {
+		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
+			     0, PTR_ERR(notify));
+		return;
+	}
+
+	genlmsg_multicast_netns(&dp_vport_genl_family,
+				ovs_dp_get_net(dp), notify, 0,
+				0, GFP_KERNEL);
+}
+
+void ovs_dp_notify_wq(struct work_struct *work)
+{
+	struct ovs_net *ovs_net = container_of(work, struct ovs_net, dp_notify_work);
+	struct datapath *dp;
+
+	ovs_lock();
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
+		int i;
+
+		for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+			struct vport *vport;
+			struct hlist_node *n;
+
+			hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
+				if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
+					continue;
+
+				if (!(netif_is_ovs_port(vport->dev)))
+					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_percpu_wq, &ovs_net->dp_notify_work);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ovs_dp_device_notifier = {
+	.notifier_call = dp_device_event
+};

linux-7.2.3/net/openvswitch/drop.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * OpenvSwitch drop reason list.
+ */
+
+#ifndef OPENVSWITCH_DROP_H
+#define OPENVSWITCH_DROP_H
+#include <linux/skbuff.h>
+#include <net/dropreason.h>
+
+#define OVS_DROP_REASONS(R)			\
+	R(OVS_DROP_LAST_ACTION)		        \
+	R(OVS_DROP_ACTION_ERROR)		\
+	R(OVS_DROP_EXPLICIT)			\
+	R(OVS_DROP_EXPLICIT_WITH_ERROR)		\
+	R(OVS_DROP_METER)			\
+	R(OVS_DROP_RECURSION_LIMIT)		\
+	R(OVS_DROP_DEFERRED_LIMIT)		\
+	R(OVS_DROP_FRAG_L2_TOO_LONG)		\
+	R(OVS_DROP_FRAG_INVALID_PROTO)		\
+	R(OVS_DROP_CONNTRACK)			\
+	R(OVS_DROP_IP_TTL)			\
+	/* deliberate comment for trailing \ */
+
+enum ovs_drop_reason {
+	__OVS_DROP_REASON = SKB_DROP_REASON_SUBSYS_OPENVSWITCH <<
+				SKB_DROP_REASON_SUBSYS_SHIFT,
+#define ENUM(x) x,
+	OVS_DROP_REASONS(ENUM)
+#undef ENUM
+
+	OVS_DROP_MAX,
+};
+
+static inline void
+ovs_kfree_skb_reason(struct sk_buff *skb, enum ovs_drop_reason reason)
+{
+	kfree_skb_reason(skb, (u32)reason);
+}
+
+#endif /* OPENVSWITCH_DROP_H */

linux-7.2.3/net/openvswitch/flow.h

@@ -0,0 +1,298 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2017 Nicira, Inc.
+ */
+
+#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/cpumask.h>
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+#include <net/dst_metadata.h>
+#include <net/nsh.h>
+
+struct sk_buff;
+
+enum sw_flow_mac_proto {
+	MAC_PROTO_NONE = 0,
+	MAC_PROTO_ETHERNET,
+};
+#define SW_FLOW_KEY_INVALID	0x80
+#define MPLS_LABEL_DEPTH       3
+
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+	OFPIEH12_NONEXT = 1 << 0,   /* "No next header" encountered. */
+	OFPIEH12_ESP    = 1 << 1,   /* Encrypted Sec Payload header present. */
+	OFPIEH12_AUTH   = 1 << 2,   /* Authentication header present. */
+	OFPIEH12_DEST   = 1 << 3,   /* 1 or 2 dest headers present. */
+	OFPIEH12_FRAG   = 1 << 4,   /* Fragment header present. */
+	OFPIEH12_ROUTER = 1 << 5,   /* Router header present. */
+	OFPIEH12_HOP    = 1 << 6,   /* Hop-by-hop header present. */
+	OFPIEH12_UNREP  = 1 << 7,   /* Unexpected repeats encountered. */
+	OFPIEH12_UNSEQ  = 1 << 8    /* Unexpected sequencing encountered. */
+};
+
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define TUN_METADATA_OFFSET(opt_len) \
+	(sizeof_field(struct sw_flow_key, tun_opts) - opt_len)
+#define TUN_METADATA_OPTS(flow_key, opt_len) \
+	((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
+
+struct ovs_tunnel_info {
+	struct metadata_dst	*tun_dst;
+};
+
+struct vlan_head {
+	__be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/
+	__be16 tci;  /* 0 if no VLAN, VLAN_CFI_MASK set otherwise. */
+};
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
+	(offsetof(struct sw_flow_key, recirc_id) +	\
+	sizeof_field(struct sw_flow_key, recirc_id))
+
+struct ovs_key_nsh {
+	struct ovs_nsh_key_base base;
+	__be32 context[NSH_MD1_CONTEXT_SIZE];
+};
+
+struct sw_flow_key {
+	u8 tun_opts[IP_TUNNEL_OPTS_MAX];
+	u8 tun_opts_len;
+	struct ip_tunnel_key tun_key;	/* Encapsulating tunnel key. */
+	struct {
+		u32	priority;	/* Packet QoS priority. */
+		u32	skb_mark;	/* SKB mark. */
+		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
+	} __packed phy; /* Safe when right after 'tun_key'. */
+	u8 mac_proto;			/* MAC layer protocol (e.g. Ethernet). */
+	u8 tun_proto;			/* Protocol of encapsulating tunnel. */
+	u32 ovs_flow_hash;		/* Datapath computed hash value.  */
+	u32 recirc_id;			/* Recirculation ID.  */
+	struct {
+		u8     src[ETH_ALEN];	/* Ethernet source address. */
+		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
+		struct vlan_head vlan;
+		struct vlan_head cvlan;
+		__be16 type;		/* Ethernet frame type. */
+	} eth;
+	/* Filling a hole of two bytes. */
+	u8 ct_state;
+	u8 ct_orig_proto;		/* CT original direction tuple IP
+					 * protocol.
+					 */
+	union {
+		struct {
+			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
+			u8     tos;	    /* IP ToS. */
+			u8     ttl;	    /* IP TTL/hop limit. */
+			u8     frag;	/* One of OVS_FRAG_TYPE_*. */
+		} ip;
+	};
+	u16 ct_zone;			/* Conntrack zone. */
+	struct {
+		__be16 src;		/* TCP/UDP/SCTP source port. */
+		__be16 dst;		/* TCP/UDP/SCTP destination port. */
+		__be16 flags;		/* TCP flags. */
+	} tp;
+	union {
+		struct {
+			struct {
+				__be32 src;	/* IP source address. */
+				__be32 dst;	/* IP destination address. */
+			} addr;
+			union {
+				struct {
+					__be32 src;
+					__be32 dst;
+				} ct_orig;	/* Conntrack original direction fields. */
+				struct {
+					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
+					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
+				} arp;
+			};
+		} ipv4;
+		struct {
+			struct {
+				struct in6_addr src;	/* IPv6 source address. */
+				struct in6_addr dst;	/* IPv6 destination address. */
+			} addr;
+			__be32 label;			/* IPv6 flow label. */
+			u16 exthdrs;	/* IPv6 extension header flags */
+			union {
+				struct {
+					struct in6_addr src;
+					struct in6_addr dst;
+				} ct_orig;	/* Conntrack original direction fields. */
+				struct {
+					struct in6_addr target;	/* ND target address. */
+					u8 sll[ETH_ALEN];	/* ND source link layer address. */
+					u8 tll[ETH_ALEN];	/* ND target link layer address. */
+				} nd;
+			};
+		} ipv6;
+		struct {
+			u32 num_labels_mask;    /* labels present bitmap of effective length MPLS_LABEL_DEPTH */
+			__be32 lse[MPLS_LABEL_DEPTH];     /* label stack entry  */
+		} mpls;
+
+		struct ovs_key_nsh nsh;         /* network service header */
+	};
+	struct {
+		/* Connection tracking fields not packed above. */
+		struct {
+			__be16 src;	/* CT orig tuple tp src port. */
+			__be16 dst;	/* CT orig tuple tp dst port. */
+		} orig_tp;
+		u32 mark;
+		struct ovs_key_ct_labels labels;
+	} ct;
+
+} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
+
+static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key)
+{
+	return key->eth.type == htons(ETH_P_IPV6) &&
+		key->ip.proto == NEXTHDR_ICMP &&
+		key->tp.dst == 0 &&
+		(key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+		 key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT));
+}
+
+struct sw_flow_key_range {
+	unsigned short int start;
+	unsigned short int end;
+};
+
+struct sw_flow_mask {
+	int ref_count;
+	struct rcu_head rcu;
+	struct sw_flow_key_range range;
+	struct sw_flow_key key;
+};
+
+struct sw_flow_match {
+	struct sw_flow_key *key;
+	struct sw_flow_key_range range;
+	struct sw_flow_mask *mask;
+};
+
+#define MAX_UFID_LENGTH 16 /* 128 bits */
+
+struct sw_flow_id {
+	u32 ufid_len;
+	union {
+		u32 ufid[MAX_UFID_LENGTH / 4];
+		struct sw_flow_key *unmasked_key;
+	};
+};
+
+struct sw_flow_actions {
+	struct rcu_head rcu;
+	size_t orig_len;	/* From flow_cmd_new netlink actions size */
+	u32 actions_len;
+	struct nlattr actions[];
+};
+
+struct sw_flow_stats {
+	u64 packet_count;		/* Number of packets matched. */
+	u64 byte_count;			/* Number of bytes matched. */
+	unsigned long used;		/* Last used time (in jiffies). */
+	spinlock_t lock;		/* Lock for atomic stats update. */
+	__be16 tcp_flags;		/* Union of seen TCP flags. */
+};
+
+struct sw_flow {
+	struct rcu_head rcu;
+	struct {
+		struct hlist_node node[2];
+		u32 hash;
+	} flow_table, ufid_table;
+	int stats_last_writer;		/* CPU id of the last writer on
+					 * 'stats[0]'.
+					 */
+	struct sw_flow_key key;
+	struct sw_flow_id id;
+	struct cpumask *cpu_used_mask;
+	struct sw_flow_mask *mask;
+	struct sw_flow_actions __rcu *sf_acts;
+	struct sw_flow_stats __rcu *stats[]; /* One for each CPU.  First one
+					   * is allocated at flow creation time,
+					   * the rest are allocated on demand
+					   * while holding the 'stats[0].lock'.
+					   */
+};
+
+struct arp_eth_header {
+	__be16      ar_hrd;	/* format of hardware address   */
+	__be16      ar_pro;	/* format of protocol address   */
+	unsigned char   ar_hln;	/* length of hardware address   */
+	unsigned char   ar_pln;	/* length of protocol address   */
+	__be16      ar_op;	/* ARP opcode (command)     */
+
+	/* Ethernet+IPv4 specific members. */
+	unsigned char       ar_sha[ETH_ALEN];	/* sender hardware address  */
+	unsigned char       ar_sip[4];		/* sender IP address        */
+	unsigned char       ar_tha[ETH_ALEN];	/* target hardware address  */
+	unsigned char       ar_tip[4];		/* target IP address        */
+} __packed;
+
+static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key)
+{
+	return key->mac_proto & ~SW_FLOW_KEY_INVALID;
+}
+
+static inline u16 __ovs_mac_header_len(u8 mac_proto)
+{
+	return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0;
+}
+
+static inline u16 ovs_mac_header_len(const struct sw_flow_key *key)
+{
+	return __ovs_mac_header_len(ovs_key_mac_proto(key));
+}
+
+static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
+{
+	return sfid->ufid_len;
+}
+
+static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid)
+{
+	return !ovs_identifier_is_ufid(sfid);
+}
+
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+			   const struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
+			unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *);
+u64 ovs_flow_used_time(unsigned long flow_jiffies);
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
+			 struct sk_buff *skb,
+			 struct sw_flow_key *key);
+/* Extract key from packet coming from userspace. */
+int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key, bool log);
+
+#endif /* flow.h */

linux-7.2.3/net/openvswitch/flow_netlink.h

@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2013 Nicira, Inc.
+ */
+
+
+#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 <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+size_t ovs_tun_key_attr_size(void);
+size_t ovs_key_attr_size(void);
+
+void ovs_match_init(struct sw_flow_match *match,
+		    struct sw_flow_key *key, bool reset_key,
+		    struct sw_flow_mask *mask);
+
+int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *,
+		    int attr, bool is_mask, struct sk_buff *);
+int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[],
+		       u64 *attrsp, bool log);
+int ovs_nla_get_flow_metadata(struct net *net,
+			      const struct nlattr *a[OVS_KEY_ATTR_MAX + 1],
+			      u64 attrs, struct sw_flow_key *key, bool log);
+
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
+
+int ovs_nla_get_match(struct net *, struct sw_flow_match *,
+		      const struct nlattr *key, const struct nlattr *mask,
+		      bool log);
+
+int ovs_nla_put_tunnel_info(struct sk_buff *skb,
+			    struct ip_tunnel_info *tun_info);
+
+bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log);
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr);
+
+int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa, bool log);
+int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype,
+		       void *data, int len, bool log);
+int ovs_nla_put_actions(const struct nlattr *attr,
+			int len, struct sk_buff *skb);
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
+
+int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh,
+			size_t size);
+
+#endif /* flow_netlink.h */

linux-7.2.3/net/openvswitch/flow_table.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2013 Nicira, Inc.
+ */
+
+#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 <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+struct mask_cache_entry {
+	u32 skb_hash;
+	u32 mask_index;
+};
+
+struct mask_cache {
+	struct rcu_head rcu;
+	u32 cache_size;  /* Must be ^2 value. */
+	struct mask_cache_entry __percpu *mask_cache;
+};
+
+struct mask_count {
+	int index;
+	u64 counter;
+};
+
+struct mask_array_stats {
+	struct u64_stats_sync syncp;
+	u64 usage_cntrs[];
+};
+
+struct mask_array {
+	struct rcu_head rcu;
+	int count, max;
+	struct mask_array_stats __percpu *masks_usage_stats;
+	u64 *masks_usage_zero_cntr;
+	struct sw_flow_mask __rcu *masks[] __counted_by(max);
+};
+
+struct table_instance {
+	struct hlist_head *buckets;
+	unsigned int n_buckets;
+	struct rcu_head rcu;
+	int node_ver;
+	u32 hash_seed;
+};
+
+struct flow_table {
+	struct table_instance __rcu *ti;
+	struct table_instance __rcu *ufid_ti;
+	struct mask_cache __rcu *mask_cache;
+	struct mask_array __rcu *mask_array;
+	unsigned long last_rehash;
+	unsigned int count;
+	unsigned int ufid_count;
+};
+
+extern struct kmem_cache *flow_stats_cache;
+
+int ovs_flow_init(void);
+void ovs_flow_exit(void);
+
+struct sw_flow *ovs_flow_alloc(void);
+void ovs_flow_free(struct sw_flow *, bool deferred);
+
+int ovs_flow_tbl_init(struct flow_table *);
+int ovs_flow_tbl_count(const struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table);
+int ovs_flow_tbl_flush(struct flow_table *flow_table);
+
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			const struct sw_flow_mask *mask);
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+int  ovs_flow_tbl_num_masks(const struct flow_table *table);
+u32  ovs_flow_tbl_masks_cache_size(const struct flow_table *table);
+int  ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size);
+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 skb_hash,
+					  u32 *n_mask_hit,
+					  u32 *n_cache_hit);
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+				    const struct sw_flow_key *);
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  const struct sw_flow_match *match);
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
+					 const struct sw_flow_id *);
+
+bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+		       bool full, const struct sw_flow_mask *mask);
+
+void ovs_flow_masks_rebalance(struct flow_table *table);
+void table_instance_flow_flush(struct flow_table *table,
+			       struct table_instance *ti,
+			       struct table_instance *ufid_ti);
+
+#endif /* flow_table.h */

linux-7.2.3/net/openvswitch/meter.c

@@ -0,0 +1,771 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/openvswitch.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "meter.h"
+
+static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = {
+	[OVS_METER_ATTR_ID] = { .type = NLA_U32, },
+	[OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+	[OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED },
+	[OVS_METER_ATTR_USED] = { .type = NLA_U64 },
+	[OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 },
+	[OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = {
+	[OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_RATE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_BURST] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+};
+
+static u32 meter_hash(struct dp_meter_instance *ti, u32 id)
+{
+	return id % ti->n_meters;
+}
+
+static void ovs_meter_free(struct dp_meter *meter)
+{
+	if (!meter)
+		return;
+
+	kfree_rcu(meter, rcu);
+}
+
+/* Call with ovs_mutex or RCU read lock. */
+static struct dp_meter *lookup_meter(const struct dp_meter_table *tbl,
+				     u32 meter_id)
+{
+	struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	u32 hash = meter_hash(ti, meter_id);
+	struct dp_meter *meter;
+
+	meter = rcu_dereference_ovsl(ti->dp_meters[hash]);
+	if (meter && likely(meter->id == meter_id))
+		return meter;
+
+	return NULL;
+}
+
+static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size)
+{
+	struct dp_meter_instance *ti;
+
+	ti = kvzalloc_flex(*ti, dp_meters, size);
+	if (!ti)
+		return NULL;
+
+	ti->n_meters = size;
+
+	return ti;
+}
+
+static void dp_meter_instance_free(struct dp_meter_instance *ti)
+{
+	kvfree(ti);
+}
+
+static void dp_meter_instance_free_rcu(struct rcu_head *rcu)
+{
+	struct dp_meter_instance *ti;
+
+	ti = container_of(rcu, struct dp_meter_instance, rcu);
+	kvfree(ti);
+}
+
+static int
+dp_meter_instance_realloc(struct dp_meter_table *tbl, u32 size)
+{
+	struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	int n_meters = min(size, ti->n_meters);
+	struct dp_meter_instance *new_ti;
+	int i;
+
+	new_ti = dp_meter_instance_alloc(size);
+	if (!new_ti)
+		return -ENOMEM;
+
+	for (i = 0; i < n_meters; i++)
+		if (rcu_dereference_ovsl(ti->dp_meters[i]))
+			new_ti->dp_meters[i] = ti->dp_meters[i];
+
+	rcu_assign_pointer(tbl->ti, new_ti);
+	call_rcu(&ti->rcu, dp_meter_instance_free_rcu);
+
+	return 0;
+}
+
+static void dp_meter_instance_insert(struct dp_meter_instance *ti,
+				     struct dp_meter *meter)
+{
+	u32 hash;
+
+	hash = meter_hash(ti, meter->id);
+	rcu_assign_pointer(ti->dp_meters[hash], meter);
+}
+
+static void dp_meter_instance_remove(struct dp_meter_instance *ti,
+				     struct dp_meter *meter)
+{
+	u32 hash;
+
+	hash = meter_hash(ti, meter->id);
+	RCU_INIT_POINTER(ti->dp_meters[hash], NULL);
+}
+
+static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter)
+{
+	struct dp_meter_instance *ti;
+	u32 hash;
+	int err;
+
+	/* That function is thread-safe. */
+	tbl->count++;
+	if (tbl->count >= tbl->max_meters_allowed) {
+		err = -EFBIG;
+		goto attach_err;
+	}
+
+	ti = rcu_dereference_ovsl(tbl->ti);
+	if (tbl->count >= ti->n_meters) {
+		err = dp_meter_instance_realloc(tbl, ti->n_meters * 2);
+		if (err)
+			goto attach_err;
+
+		ti = rcu_dereference_ovsl(tbl->ti);
+	}
+
+	hash = meter_hash(ti, meter->id);
+
+	/* In general, selected slots should be empty, because
+	 * OvS uses id-pool to fetch available ids.
+	 */
+	if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) {
+		err = -EBUSY;
+		goto attach_err;
+	}
+
+	dp_meter_instance_insert(ti, meter);
+	return 0;
+
+attach_err:
+	tbl->count--;
+	return err;
+}
+
+static int detach_meter(struct dp_meter_table *tbl, struct dp_meter *meter)
+{
+	struct dp_meter_instance *ti;
+
+	ASSERT_OVSL();
+	if (!meter)
+		return 0;
+
+	ti = rcu_dereference_ovsl(tbl->ti);
+	dp_meter_instance_remove(ti, meter);
+
+	tbl->count--;
+
+	/* Shrink the meter array if necessary. */
+	if (ti->n_meters > DP_METER_ARRAY_SIZE_MIN &&
+	    tbl->count <= (ti->n_meters / 4)) {
+		int half_size = ti->n_meters / 2;
+		int i;
+
+		/* Avoid hash collision, don't move slots to other place.
+		 * Make sure there are no references of meters in array
+		 * which will be released.
+		 */
+		for (i = half_size; i < ti->n_meters; i++)
+			if (rcu_dereference_ovsl(ti->dp_meters[i]))
+				goto out;
+
+		if (dp_meter_instance_realloc(tbl, half_size))
+			goto shrink_err;
+	}
+
+out:
+	return 0;
+
+shrink_err:
+	dp_meter_instance_insert(ti, meter);
+	tbl->count++;
+	return -ENOMEM;
+}
+
+static struct sk_buff *
+ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd,
+			  struct ovs_header **ovs_reply_header)
+{
+	struct sk_buff *skb;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	*ovs_reply_header = genlmsg_put(skb, info->snd_portid,
+					info->snd_seq,
+					&dp_meter_genl_family, 0, cmd);
+	if (!*ovs_reply_header) {
+		nlmsg_free(skb);
+		return ERR_PTR(-EMSGSIZE);
+	}
+	(*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex;
+
+	return skb;
+}
+
+static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
+				     struct dp_meter *meter)
+{
+	struct nlattr *nla;
+	struct dp_meter_band *band;
+	u16 i;
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id))
+		goto error;
+
+	if (nla_put(reply, OVS_METER_ATTR_STATS,
+		    sizeof(struct ovs_flow_stats), &meter->stats))
+		goto error;
+
+	if (nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
+			      OVS_METER_ATTR_PAD))
+		goto error;
+
+	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto error;
+
+	band = meter->bands;
+
+	for (i = 0; i < meter->n_bands; ++i, ++band) {
+		struct nlattr *band_nla;
+
+		band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
+		if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS,
+					 sizeof(struct ovs_flow_stats),
+					 &band->stats))
+			goto error;
+		nla_nest_end(reply, band_nla);
+	}
+	nla_nest_end(reply, nla);
+
+	return 0;
+error:
+	return -EMSGSIZE;
+}
+
+static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
+	struct ovs_header *ovs_reply_header;
+	struct nlattr *nla, *band_nla;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	int err = -EMSGSIZE;
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS,
+			dp->meter_tbl.max_meters_allowed))
+		goto exit_unlock;
+
+	ovs_unlock();
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
+		goto nla_put_failure;
+
+	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto nla_put_failure;
+
+	band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
+	if (!band_nla)
+		goto nla_put_failure;
+	/* Currently only DROP band type is supported. */
+	if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP))
+		goto nla_put_failure;
+	nla_nest_end(reply, band_nla);
+	nla_nest_end(reply, nla);
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+nla_put_failure:
+	nlmsg_free(reply);
+	return err;
+}
+
+static struct dp_meter *dp_meter_create(struct nlattr **a)
+{
+	struct nlattr *nla;
+	int rem;
+	u16 n_bands = 0;
+	struct dp_meter *meter;
+	struct dp_meter_band *band;
+	int err;
+
+	/* Validate attributes, count the bands. */
+	if (!a[OVS_METER_ATTR_BANDS])
+		return ERR_PTR(-EINVAL);
+
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem)
+		if (++n_bands > DP_MAX_BANDS)
+			return ERR_PTR(-EINVAL);
+
+	/* Allocate and set up the meter before locking anything. */
+	meter = kzalloc_flex(*meter, bands, n_bands, GFP_KERNEL_ACCOUNT);
+	if (!meter)
+		return ERR_PTR(-ENOMEM);
+
+	meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+	meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
+	meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
+	meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
+	spin_lock_init(&meter->lock);
+	if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) {
+		meter->stats = *(struct ovs_flow_stats *)
+			nla_data(a[OVS_METER_ATTR_STATS]);
+	}
+	meter->n_bands = n_bands;
+
+	/* Set up meter bands. */
+	band = meter->bands;
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) {
+		struct nlattr *attr[OVS_BAND_ATTR_MAX + 1];
+		u32 band_max_delta_t;
+
+		err = nla_parse_deprecated((struct nlattr **)&attr,
+					   OVS_BAND_ATTR_MAX, nla_data(nla),
+					   nla_len(nla), band_policy, NULL);
+		if (err)
+			goto exit_free_meter;
+
+		if (!attr[OVS_BAND_ATTR_TYPE] ||
+		    !attr[OVS_BAND_ATTR_RATE] ||
+		    !attr[OVS_BAND_ATTR_BURST]) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
+		band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]);
+		band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]);
+		if (band->rate == 0) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
+		band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]);
+		/* Figure out max delta_t that is enough to fill any bucket.
+		 * Keep max_delta_t size to the bucket units:
+		 * pkts => 1/1000 packets, kilobits => bits.
+		 *
+		 * Start with a full bucket.
+		 */
+		band->bucket = band->burst_size * 1000ULL;
+		band_max_delta_t = div_u64(band->bucket, band->rate);
+		if (band_max_delta_t > meter->max_delta_t)
+			meter->max_delta_t = band_max_delta_t;
+		band++;
+	}
+
+	return meter;
+
+exit_free_meter:
+	kfree(meter);
+	return ERR_PTR(err);
+}
+
+static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct dp_meter *meter, *old_meter;
+	struct sk_buff *reply;
+	struct ovs_header *ovs_reply_header;
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
+	struct dp_meter_table *meter_tbl;
+	struct datapath *dp;
+	int err;
+	u32 meter_id;
+	bool failed;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+
+	meter = dp_meter_create(a);
+	if (IS_ERR(meter))
+		return PTR_ERR(meter);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		goto exit_free_meter;
+	}
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	meter_tbl = &dp->meter_tbl;
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	old_meter = lookup_meter(meter_tbl, meter_id);
+	err = detach_meter(meter_tbl, old_meter);
+	if (err)
+		goto exit_unlock;
+
+	err = attach_meter(meter_tbl, meter);
+	if (err)
+		goto exit_free_old_meter;
+
+	ovs_unlock();
+
+	/* Build response with the meter_id and stats from
+	 * the old meter, if any.
+	 */
+	failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id);
+	WARN_ON(failed);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		if (old_meter->keep_stats) {
+			err = ovs_meter_cmd_reply_stats(reply, meter_id,
+							old_meter);
+			WARN_ON(err);
+		}
+		spin_unlock_bh(&old_meter->lock);
+		ovs_meter_free(old_meter);
+	}
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_free_old_meter:
+	ovs_meter_free(old_meter);
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+exit_free_meter:
+	kfree(meter);
+	return err;
+}
+
+static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
+	struct ovs_header *ovs_reply_header;
+	struct nlattr **a = info->attrs;
+	struct dp_meter *meter;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	u32 meter_id;
+	int err;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	/* Locate meter, copy stats. */
+	meter = lookup_meter(&dp->meter_tbl, meter_id);
+	if (!meter) {
+		err = -ENOENT;
+		goto exit_unlock;
+	}
+
+	spin_lock_bh(&meter->lock);
+	err = ovs_meter_cmd_reply_stats(reply, meter_id, meter);
+	spin_unlock_bh(&meter->lock);
+	if (err)
+		goto exit_unlock;
+
+	ovs_unlock();
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovs_header *ovs_header = genl_info_userhdr(info);
+	struct ovs_header *ovs_reply_header;
+	struct nlattr **a = info->attrs;
+	struct dp_meter *old_meter;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	u32 meter_id;
+	int err;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+	old_meter = lookup_meter(&dp->meter_tbl, meter_id);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter);
+		WARN_ON(err);
+		spin_unlock_bh(&old_meter->lock);
+
+		err = detach_meter(&dp->meter_tbl, old_meter);
+		if (err)
+			goto exit_unlock;
+	}
+
+	ovs_unlock();
+	ovs_meter_free(old_meter);
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+/* Meter action execution.
+ *
+ * Return true 'meter_id' drop band is triggered. The 'skb' should be
+ * dropped by the caller'.
+ */
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id)
+{
+	long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000);
+	long long int long_delta_ms;
+	struct dp_meter_band *band;
+	struct dp_meter *meter;
+	int i, band_exceeded_max = -1;
+	u32 band_exceeded_rate = 0;
+	u32 delta_ms;
+	u32 cost;
+
+	meter = lookup_meter(&dp->meter_tbl, meter_id);
+	/* Do not drop the packet when there is no meter. */
+	if (!meter)
+		return false;
+
+	/* Lock the meter while using it. */
+	spin_lock(&meter->lock);
+
+	long_delta_ms = (now_ms - meter->used); /* ms */
+	if (long_delta_ms < 0) {
+		/* This condition means that we have several threads fighting
+		 * for a meter lock, and the one who received the packets a
+		 * bit later wins. Assuming that all racing threads received
+		 * packets at the same time to avoid overflow.
+		 */
+		long_delta_ms = 0;
+	}
+
+	/* Make sure delta_ms will not be too large, so that bucket will not
+	 * wrap around below.
+	 */
+	delta_ms = (long_delta_ms > (long long int)meter->max_delta_t)
+		   ? meter->max_delta_t : (u32)long_delta_ms;
+
+	/* Update meter statistics.
+	 */
+	meter->used = now_ms;
+	meter->stats.n_packets += 1;
+	meter->stats.n_bytes += skb->len;
+
+	/* Bucket rate is either in kilobits per second, or in packets per
+	 * second.  We maintain the bucket in the units of either bits or
+	 * 1/1000th of a packet, correspondingly.
+	 * Then, when rate is multiplied with milliseconds, we get the
+	 * bucket units:
+	 * msec * kbps = bits, and
+	 * msec * packets/sec = 1/1000 packets.
+	 *
+	 * 'cost' is the number of bucket units in this packet.
+	 */
+	cost = (meter->kbps) ? skb->len * 8 : 1000;
+
+	/* Update all bands and find the one hit with the highest rate. */
+	for (i = 0; i < meter->n_bands; ++i) {
+		long long int max_bucket_size;
+
+		band = &meter->bands[i];
+		max_bucket_size = band->burst_size * 1000LL;
+
+		band->bucket += delta_ms * band->rate;
+		if (band->bucket > max_bucket_size)
+			band->bucket = max_bucket_size;
+
+		if (band->bucket >= cost) {
+			band->bucket -= cost;
+		} else if (band->rate > band_exceeded_rate) {
+			band_exceeded_rate = band->rate;
+			band_exceeded_max = i;
+		}
+	}
+
+	if (band_exceeded_max >= 0) {
+		/* Update band statistics. */
+		band = &meter->bands[band_exceeded_max];
+		band->stats.n_packets += 1;
+		band->stats.n_bytes += skb->len;
+
+		/* Drop band triggered, let the caller drop the 'skb'.  */
+		if (band->type == OVS_METER_BAND_TYPE_DROP) {
+			spin_unlock(&meter->lock);
+			return true;
+		}
+	}
+
+	spin_unlock(&meter->lock);
+	return false;
+}
+
+static const struct genl_small_ops dp_meter_genl_ops[] = {
+	{ .cmd = OVS_METER_CMD_FEATURES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.doit = ovs_meter_cmd_features
+	},
+	{ .cmd = OVS_METER_CMD_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       *  privilege.
+					       */
+		.doit = ovs_meter_cmd_set,
+	},
+	{ .cmd = OVS_METER_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.doit = ovs_meter_cmd_get,
+	},
+	{ .cmd = OVS_METER_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       *  privilege.
+					       */
+		.doit = ovs_meter_cmd_del
+	},
+};
+
+static const struct genl_multicast_group ovs_meter_multicast_group = {
+	.name = OVS_METER_MCGROUP,
+};
+
+struct genl_family dp_meter_genl_family __ro_after_init = {
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_METER_FAMILY,
+	.version = OVS_METER_VERSION,
+	.maxattr = OVS_METER_ATTR_MAX,
+	.policy = meter_policy,
+	.netnsok = true,
+	.parallel_ops = true,
+	.small_ops = dp_meter_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_meter_genl_ops),
+	.resv_start_op = OVS_METER_CMD_GET + 1,
+	.mcgrps = &ovs_meter_multicast_group,
+	.n_mcgrps = 1,
+	.module = THIS_MODULE,
+};
+
+int ovs_meters_init(struct datapath *dp)
+{
+	struct dp_meter_table *tbl = &dp->meter_tbl;
+	struct dp_meter_instance *ti;
+	unsigned long free_mem_bytes;
+
+	ti = dp_meter_instance_alloc(DP_METER_ARRAY_SIZE_MIN);
+	if (!ti)
+		return -ENOMEM;
+
+	/* Allow meters in a datapath to use ~3.12% of physical memory. */
+	free_mem_bytes = nr_free_buffer_pages() * (PAGE_SIZE >> 5);
+	tbl->max_meters_allowed = min(free_mem_bytes / sizeof(struct dp_meter),
+				      DP_METER_NUM_MAX);
+	if (!tbl->max_meters_allowed)
+		goto out_err;
+
+	rcu_assign_pointer(tbl->ti, ti);
+	tbl->count = 0;
+
+	return 0;
+
+out_err:
+	dp_meter_instance_free(ti);
+	return -ENOMEM;
+}
+
+void ovs_meters_exit(struct datapath *dp)
+{
+	struct dp_meter_table *tbl = &dp->meter_tbl;
+	struct dp_meter_instance *ti = rcu_dereference_raw(tbl->ti);
+	int i;
+
+	for (i = 0; i < ti->n_meters; i++)
+		ovs_meter_free(rcu_dereference_raw(ti->dp_meters[i]));
+
+	dp_meter_instance_free(ti);
+}

linux-7.2.3/net/openvswitch/meter.h

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ */
+
+#ifndef METER_H
+#define METER_H 1
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/skbuff.h>
+#include <linux/bits.h>
+
+#include "flow.h"
+struct datapath;
+
+#define DP_MAX_BANDS		1
+#define DP_METER_ARRAY_SIZE_MIN	BIT_ULL(10)
+#define DP_METER_NUM_MAX	(200000UL)
+
+struct dp_meter_band {
+	u32 type;
+	u32 rate;
+	u32 burst_size;
+	u64 bucket; /* 1/1000 packets, or in bits */
+	struct ovs_flow_stats stats;
+};
+
+struct dp_meter {
+	spinlock_t lock;    /* Per meter lock */
+	struct rcu_head rcu;
+	u32 id;
+	u16 kbps:1, keep_stats:1;
+	u16 n_bands;
+	u32 max_delta_t;
+	u64 used;
+	struct ovs_flow_stats stats;
+	struct dp_meter_band bands[] __counted_by(n_bands);
+};
+
+struct dp_meter_instance {
+	struct rcu_head rcu;
+	u32 n_meters;
+	struct dp_meter __rcu *dp_meters[] __counted_by(n_meters);
+};
+
+struct dp_meter_table {
+	struct dp_meter_instance __rcu *ti;
+	u32 count;
+	u32 max_meters_allowed;
+};
+
+extern struct genl_family dp_meter_genl_family;
+int ovs_meters_init(struct datapath *dp);
+void ovs_meters_exit(struct datapath *dp);
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id);
+
+#endif /* meter.h */

linux-7.2.3/net/openvswitch/openvswitch_trace.c

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/* bug in tracepoint.h, it should include this */
+#include <linux/module.h>
+
+/* sparse isn't too happy with all macros... */
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "openvswitch_trace.h"
+
+#endif

linux-7.2.3/net/openvswitch/openvswitch_trace.h

@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM openvswitch
+
+#if !defined(_TRACE_OPENVSWITCH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_OPENVSWITCH_H
+
+#include <linux/tracepoint.h>
+
+#include "datapath.h"
+
+TRACE_EVENT(ovs_do_execute_action,
+
+	TP_PROTO(struct datapath *dp, struct sk_buff *skb,
+		 struct sw_flow_key *key, const struct nlattr *a, int rem),
+
+	TP_ARGS(dp, skb, key, a, rem),
+
+	TP_STRUCT__entry(
+		__field(	void *,		dpaddr			)
+		__string(	dp_name,	ovs_dp_name(dp)		)
+		__string(	dev_name,	skb->dev->name		)
+		__field(	void *,		skbaddr			)
+		__field(	unsigned int,	len			)
+		__field(	unsigned int,	data_len		)
+		__field(	unsigned int,	truesize		)
+		__field(	u8,		nr_frags		)
+		__field(	u16,		gso_size		)
+		__field(	u16,		gso_type		)
+		__field(	u32,		ovs_flow_hash		)
+		__field(	u32,		recirc_id		)
+		__field(	void *,		keyaddr			)
+		__field(	u16,		key_eth_type		)
+		__field(	u8,		key_ct_state		)
+		__field(	u8,		key_ct_orig_proto	)
+		__field(	u16,		key_ct_zone		)
+		__field(	unsigned int,	flow_key_valid		)
+		__field(	u8,		action_type		)
+		__field(	unsigned int,	action_len		)
+		__field(	void *,		action_data		)
+		__field(	u8,		is_last			)
+	),
+
+	TP_fast_assign(
+		__entry->dpaddr = dp;
+		__assign_str(dp_name);
+		__assign_str(dev_name);
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->data_len = skb->data_len;
+		__entry->truesize = skb->truesize;
+		__entry->nr_frags = skb_shinfo(skb)->nr_frags;
+		__entry->gso_size = skb_shinfo(skb)->gso_size;
+		__entry->gso_type = skb_shinfo(skb)->gso_type;
+		__entry->ovs_flow_hash = key->ovs_flow_hash;
+		__entry->recirc_id = key->recirc_id;
+		__entry->keyaddr = key;
+		__entry->key_eth_type = key->eth.type;
+		__entry->key_ct_state = key->ct_state;
+		__entry->key_ct_orig_proto = key->ct_orig_proto;
+		__entry->key_ct_zone = key->ct_zone;
+		__entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID);
+		__entry->action_type = nla_type(a);
+		__entry->action_len = nla_len(a);
+		__entry->action_data = nla_data(a);
+		__entry->is_last = nla_is_last(a, rem);
+	),
+
+	TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_Zone=%04x flow_key_valid=%d action_type=%u action_len=%u action_data=%p is_last=%d",
+		  __entry->dpaddr, __get_str(dp_name), __get_str(dev_name),
+		  __entry->skbaddr, __entry->len, __entry->data_len,
+		  __entry->truesize, __entry->nr_frags, __entry->gso_size,
+		  __entry->gso_type, __entry->ovs_flow_hash,
+		  __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type,
+		  __entry->key_ct_state, __entry->key_ct_orig_proto,
+		  __entry->key_ct_zone,
+		  __entry->flow_key_valid,
+		  __entry->action_type, __entry->action_len,
+		  __entry->action_data, __entry->is_last)
+);
+
+TRACE_EVENT(ovs_dp_upcall,
+
+	TP_PROTO(struct datapath *dp, struct sk_buff *skb,
+		 const struct sw_flow_key *key,
+		 const struct dp_upcall_info *upcall_info),
+
+	TP_ARGS(dp, skb, key, upcall_info),
+
+	TP_STRUCT__entry(
+		__field(	void *,		dpaddr			)
+		__string(	dp_name,	ovs_dp_name(dp)		)
+		__string(	dev_name,	skb->dev->name		)
+		__field(	void *,		skbaddr			)
+		__field(	unsigned int,	len			)
+		__field(	unsigned int,	data_len		)
+		__field(	unsigned int,	truesize		)
+		__field(	u8,		nr_frags		)
+		__field(	u16,		gso_size		)
+		__field(	u16,		gso_type		)
+		__field(	u32,		ovs_flow_hash		)
+		__field(	u32,		recirc_id		)
+		__field(	const void *,	keyaddr			)
+		__field(	u16,		key_eth_type		)
+		__field(	u8,		key_ct_state		)
+		__field(	u8,		key_ct_orig_proto	)
+		__field(	u16,		key_ct_zone		)
+		__field(	unsigned int,	flow_key_valid		)
+		__field(	u8,		upcall_cmd		)
+		__field(	u32,		upcall_port		)
+		__field(	u16,		upcall_mru		)
+	),
+
+	TP_fast_assign(
+		__entry->dpaddr = dp;
+		__assign_str(dp_name);
+		__assign_str(dev_name);
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->data_len = skb->data_len;
+		__entry->truesize = skb->truesize;
+		__entry->nr_frags = skb_shinfo(skb)->nr_frags;
+		__entry->gso_size = skb_shinfo(skb)->gso_size;
+		__entry->gso_type = skb_shinfo(skb)->gso_type;
+		__entry->ovs_flow_hash = key->ovs_flow_hash;
+		__entry->recirc_id = key->recirc_id;
+		__entry->keyaddr = key;
+		__entry->key_eth_type = key->eth.type;
+		__entry->key_ct_state = key->ct_state;
+		__entry->key_ct_orig_proto = key->ct_orig_proto;
+		__entry->key_ct_zone = key->ct_zone;
+		__entry->flow_key_valid =  !(key->mac_proto & SW_FLOW_KEY_INVALID);
+		__entry->upcall_cmd = upcall_info->cmd;
+		__entry->upcall_port = upcall_info->portid;
+		__entry->upcall_mru = upcall_info->mru;
+	),
+
+	TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_zone=%04x flow_key_valid=%d upcall_cmd=%u upcall_port=%u upcall_mru=%u",
+		  __entry->dpaddr, __get_str(dp_name), __get_str(dev_name),
+		  __entry->skbaddr, __entry->len, __entry->data_len,
+		  __entry->truesize, __entry->nr_frags, __entry->gso_size,
+		  __entry->gso_type, __entry->ovs_flow_hash,
+		  __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type,
+		  __entry->key_ct_state, __entry->key_ct_orig_proto,
+		  __entry->key_ct_zone,
+		  __entry->flow_key_valid,
+		  __entry->upcall_cmd, __entry->upcall_port,
+		  __entry->upcall_mru)
+);
+
+#endif /* _TRACE_OPENVSWITCH_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE openvswitch_trace
+#include <trace/define_trace.h>

linux-7.2.3/net/openvswitch/vport-geneve.c

@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/rculist.h>
+#include <linux/udp.h>
+#include <linux/if_vlan.h>
+#include <linux/module.h>
+
+#include <net/geneve.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_geneve_vport_ops;
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @dst_port: destination port.
+ */
+struct geneve_port {
+	u16 dst_port;
+};
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+static int geneve_get_options(const struct vport *vport,
+			      struct sk_buff *skb)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, geneve_port->dst_port))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static struct vport *geneve_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct nlattr *options = parms->options;
+	struct geneve_port *geneve_port;
+	struct net_device *dev;
+	struct vport *vport;
+	struct nlattr *a;
+	u16 dst_port;
+	int err;
+
+	if (!options) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+	if (a && nla_len(a) == sizeof(u16)) {
+		dst_port = nla_get_u16(a);
+	} else {
+		/* Require destination port from userspace. */
+		err = -EINVAL;
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(sizeof(struct geneve_port),
+				&ovs_geneve_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	geneve_port = geneve_vport(vport);
+	geneve_port->dst_port = dst_port;
+
+	rtnl_lock();
+	dev = geneve_dev_create_fb(net, parms->name, NET_NAME_USER, dst_port);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+	if (err < 0) {
+		rtnl_delete_link(dev, 0, NULL);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		goto error;
+	}
+
+	vport->dev = dev;
+	netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL);
+
+	rtnl_unlock();
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static struct vport *geneve_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = geneve_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, true);
+}
+
+static struct vport_ops ovs_geneve_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GENEVE,
+	.create		= geneve_create,
+	.destroy	= ovs_netdev_tunnel_destroy,
+	.get_options	= geneve_get_options,
+	.send		= dev_queue_xmit,
+};
+
+static int __init ovs_geneve_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_geneve_vport_ops);
+}
+
+static void __exit ovs_geneve_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_geneve_vport_ops);
+}
+
+module_init(ovs_geneve_tnl_init);
+module_exit(ovs_geneve_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: Geneve switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-5");

linux-7.2.3/net/openvswitch/vport-gre.c

@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/in_route.h>
+#include <linux/inetdevice.h>
+#include <linux/jhash.h>
+#include <linux/list.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/rculist.h>
+#include <net/route.h>
+#include <net/xfrm.h>
+
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ip_tunnels.h>
+#include <net/gre.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/protocol.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_gre_vport_ops;
+
+static struct vport *gre_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct net_device *dev;
+	struct vport *vport;
+	int err;
+
+	vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	rtnl_lock();
+	dev = gretap_fb_dev_create(net, parms->name, NET_NAME_USER);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+	if (err < 0) {
+		rtnl_delete_link(dev, 0, NULL);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_PTR(err);
+	}
+
+	vport->dev = dev;
+	netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL);
+
+	rtnl_unlock();
+	return vport;
+}
+
+static struct vport *gre_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = gre_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, true);
+}
+
+static struct vport_ops ovs_gre_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GRE,
+	.create		= gre_create,
+	.send		= dev_queue_xmit,
+	.destroy	= ovs_netdev_tunnel_destroy,
+};
+
+static int __init ovs_gre_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_gre_vport_ops);
+}
+
+static void __exit ovs_gre_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_gre_vport_ops);
+}
+
+module_init(ovs_gre_tnl_init);
+module_exit(ovs_gre_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: GRE switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-3");

linux-7.2.3/net/openvswitch/vport-internal_dev.c

@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ */
+
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/skbuff.h>
+
+#include <net/dst.h>
+#include <net/xfrm.h>
+#include <net/rtnetlink.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+struct internal_dev {
+	struct vport *vport;
+};
+
+static struct vport_ops ovs_internal_vport_ops;
+
+static struct internal_dev *internal_dev_priv(struct net_device *netdev)
+{
+	return netdev_priv(netdev);
+}
+
+/* Called with rcu_read_lock_bh. */
+static netdev_tx_t
+internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	int len, err;
+
+	/* store len value because skb can be freed inside ovs_vport_receive() */
+	len = skb->len;
+
+	rcu_read_lock();
+	err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
+	rcu_read_unlock();
+
+	if (likely(!err))
+		dev_sw_netstats_tx_add(netdev, 1, len);
+	else
+		netdev->stats.tx_errors++;
+
+	return NETDEV_TX_OK;
+}
+
+static int internal_dev_open(struct net_device *netdev)
+{
+	netif_start_queue(netdev);
+	return 0;
+}
+
+static int internal_dev_stop(struct net_device *netdev)
+{
+	netif_stop_queue(netdev);
+	return 0;
+}
+
+static void internal_dev_getinfo(struct net_device *netdev,
+				 struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, "openvswitch", sizeof(info->driver));
+}
+
+static const struct ethtool_ops internal_dev_ethtool_ops = {
+	.get_drvinfo	= internal_dev_getinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+static void internal_dev_destructor(struct net_device *dev)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+	ovs_vport_free(vport);
+}
+
+static 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,
+};
+
+static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
+	.kind = "openvswitch",
+};
+
+static void do_setup(struct net_device *netdev)
+{
+	ether_setup(netdev);
+
+	netdev->max_mtu = ETH_MAX_MTU;
+
+	netdev->netdev_ops = &internal_dev_netdev_ops;
+
+	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
+			      IFF_NO_QUEUE;
+	netdev->lltx = true;
+	netdev->needs_free_netdev = true;
+	netdev->priv_destructor = NULL;
+	netdev->ethtool_ops = &internal_dev_ethtool_ops;
+	netdev->rtnl_link_ops = &internal_dev_link_ops;
+
+	netdev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+			   NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE |
+			   NETIF_F_GSO_ENCAP_ALL;
+
+	netdev->vlan_features = netdev->features;
+	netdev->hw_enc_features = netdev->features;
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	netdev->hw_features = netdev->features;
+
+	eth_hw_addr_random(netdev);
+}
+
+static struct vport *internal_dev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	struct internal_dev *internal_dev;
+	struct net_device *dev;
+	int err;
+
+	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	dev = alloc_netdev(sizeof(struct internal_dev),
+			   parms->name, NET_NAME_USER, do_setup);
+	vport->dev = dev;
+	if (!vport->dev) {
+		err = -ENOMEM;
+		goto error_free_vport;
+	}
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
+
+	dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
+	dev->ifindex = parms->desired_ifindex;
+	internal_dev = internal_dev_priv(vport->dev);
+	internal_dev->vport = vport;
+
+	/* Restrict bridge port to current netns. */
+	if (vport->port_no == OVSP_LOCAL)
+		vport->dev->netns_immutable = true;
+
+	rtnl_lock();
+	err = register_netdevice(vport->dev);
+	if (err)
+		goto error_unlock;
+	vport->dev->priv_destructor = internal_dev_destructor;
+
+	dev_set_promiscuity(vport->dev, 1);
+	rtnl_unlock();
+	netif_start_queue(vport->dev);
+
+	return vport;
+
+error_unlock:
+	rtnl_unlock();
+	free_netdev(dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void internal_dev_destroy(struct vport *vport)
+{
+	netif_stop_queue(vport->dev);
+	rtnl_lock();
+	dev_set_promiscuity(vport->dev, -1);
+
+	/* unregister_netdevice() waits for an RCU grace period. */
+	unregister_netdevice(vport->dev);
+	rtnl_unlock();
+}
+
+static int internal_dev_recv(struct sk_buff *skb)
+{
+	struct net_device *netdev = skb->dev;
+
+	if (unlikely(!(netdev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		netdev->stats.rx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	skb_dst_drop(skb);
+	nf_reset_ct(skb);
+
+	skb->pkt_type = PACKET_HOST;
+	skb->protocol = eth_type_trans(skb, netdev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+	dev_sw_netstats_rx_add(netdev, skb->len);
+
+	netif_rx(skb);
+	return NETDEV_TX_OK;
+}
+
+static struct vport_ops ovs_internal_vport_ops = {
+	.type		= OVS_VPORT_TYPE_INTERNAL,
+	.create		= internal_dev_create,
+	.destroy	= internal_dev_destroy,
+	.send		= internal_dev_recv,
+};
+
+int ovs_is_internal_dev(const struct net_device *netdev)
+{
+	return netdev->netdev_ops == &internal_dev_netdev_ops;
+}
+
+struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
+{
+	if (!ovs_is_internal_dev(netdev))
+		return NULL;
+
+	return internal_dev_priv(netdev)->vport;
+}
+
+int ovs_internal_dev_rtnl_link_register(void)
+{
+	int err;
+
+	err = rtnl_link_register(&internal_dev_link_ops);
+	if (err < 0)
+		return err;
+
+	err = ovs_vport_ops_register(&ovs_internal_vport_ops);
+	if (err < 0)
+		rtnl_link_unregister(&internal_dev_link_ops);
+
+	return err;
+}
+
+void ovs_internal_dev_rtnl_link_unregister(void)
+{
+	ovs_vport_ops_unregister(&ovs_internal_vport_ops);
+	rtnl_link_unregister(&internal_dev_link_ops);
+}

linux-7.2.3/net/openvswitch/vport-internal_dev.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2011 Nicira, Inc.
+ */
+
+#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 */

linux-7.2.3/net/openvswitch/vport-netdev.c

@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if_arp.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/llc.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <linux/openvswitch.h>
+#include <linux/export.h>
+
+#include <net/ip_tunnels.h>
+#include <net/rtnetlink.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_netdev_vport_ops;
+
+/* Must be called with rcu_read_lock. */
+static void netdev_port_receive(struct sk_buff *skb)
+{
+	struct vport *vport;
+
+	vport = ovs_netdev_get_vport(skb->dev);
+	if (unlikely(!vport))
+		goto error;
+
+	if (unlikely(skb_warn_if_lro(skb)))
+		goto error;
+
+	/* Make our own copy of the packet.  Otherwise we will mangle the
+	 * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
+	 */
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return;
+
+	if (skb->dev->type == ARPHRD_ETHER)
+		skb_push_rcsum(skb, ETH_HLEN);
+
+	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
+	return;
+error:
+	kfree_skb(skb);
+}
+
+/* Called with rcu_read_lock and bottom-halves disabled. */
+static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	netdev_port_receive(skb);
+	return RX_HANDLER_CONSUMED;
+}
+
+static struct net_device *get_dpdev(const struct datapath *dp)
+{
+	struct vport *local;
+
+	local = ovs_vport_ovsl(dp, OVSP_LOCAL);
+	return local->dev;
+}
+
+struct vport *ovs_netdev_link(struct vport *vport, bool tunnel)
+{
+	int err;
+
+	if (WARN_ON_ONCE(!vport->dev)) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+
+	rtnl_lock();
+	/* Do not link devices that are not registered to avoid a potential
+	 * race with the NETDEV_UNREGISTER notification in dp_device_event().
+	 */
+	if (vport->dev->reg_state != NETREG_REGISTERED) {
+		err = -ENODEV;
+		goto error_put_unlock;
+	}
+
+	err = netdev_master_upper_dev_link(vport->dev,
+					   get_dpdev(vport->dp),
+					   NULL, NULL, NULL);
+	if (err)
+		goto error_put_unlock;
+
+	err = netdev_rx_handler_register(vport->dev, netdev_frame_hook,
+					 vport);
+	if (err)
+		goto error_master_upper_dev_unlink;
+
+	dev_disable_lro(vport->dev);
+	dev_set_promiscuity(vport->dev, 1);
+	vport->dev->priv_flags |= IFF_OVS_DATAPATH;
+	rtnl_unlock();
+
+	return vport;
+
+error_master_upper_dev_unlink:
+	netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp));
+error_put_unlock:
+	if (tunnel && vport->dev->reg_state == NETREG_REGISTERED)
+		rtnl_delete_link(vport->dev, 0, NULL);
+	netdev_put(vport->dev, &vport->dev_tracker);
+	rtnl_unlock();
+error_free_vport:
+	ovs_vport_free(vport);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(ovs_netdev_link);
+
+static struct vport *netdev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	int err;
+
+	vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name);
+	if (!vport->dev) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+	netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL);
+
+	/* Ensure that the provided name is not an alias. */
+	if (strcmp(parms->name, ovs_vport_name(vport))) {
+		err = -ENODEV;
+		goto error_put;
+	}
+
+	if (vport->dev->flags & IFF_LOOPBACK ||
+	    (vport->dev->type != ARPHRD_ETHER &&
+	     vport->dev->type != ARPHRD_NONE) ||
+	    ovs_is_internal_dev(vport->dev)) {
+		err = -EINVAL;
+		goto error_put;
+	}
+
+	return ovs_netdev_link(vport, false);
+error_put:
+	netdev_put(vport->dev, &vport->dev_tracker);
+error_free_vport:
+	ovs_vport_free(vport);
+	return ERR_PTR(err);
+}
+
+static void vport_netdev_free(struct rcu_head *rcu)
+{
+	struct vport *vport = container_of(rcu, struct vport, rcu);
+
+	netdev_put(vport->dev, &vport->dev_tracker);
+	ovs_vport_free(vport);
+}
+
+void ovs_netdev_detach_dev(struct vport *vport)
+{
+	ASSERT_RTNL();
+	netdev_rx_handler_unregister(vport->dev);
+	netdev_upper_dev_unlink(vport->dev,
+				netdev_master_upper_dev_get(vport->dev));
+	dev_set_promiscuity(vport->dev, -1);
+
+	/* paired with smp_mb() in netdev_destroy() */
+	smp_wmb();
+
+	vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
+}
+
+static void netdev_destroy(struct vport *vport)
+{
+	/* When called from ovs_db_notify_wq() after a dp_device_event(), the
+	 * port has already been detached, so we can avoid taking the RTNL by
+	 * checking this first.
+	 */
+	if (netif_is_ovs_port(vport->dev)) {
+		rtnl_lock();
+		/* Check again while holding the lock to ensure we don't race
+		 * with the netdev notifier and detach twice.
+		 */
+		if (netif_is_ovs_port(vport->dev))
+			ovs_netdev_detach_dev(vport);
+		rtnl_unlock();
+	}
+
+	/* paired with smp_wmb() in ovs_netdev_detach_dev() */
+	smp_mb();
+
+	call_rcu(&vport->rcu, vport_netdev_free);
+}
+
+void ovs_netdev_tunnel_destroy(struct vport *vport)
+{
+	rtnl_lock();
+	if (netif_is_ovs_port(vport->dev))
+		ovs_netdev_detach_dev(vport);
+
+	/* We can be invoked by both explicit vport deletion and
+	 * underlying netdev deregistration; delete the link only
+	 * if it's not already shutting down.
+	 */
+	if (vport->dev->reg_state == NETREG_REGISTERED)
+		rtnl_delete_link(vport->dev, 0, NULL);
+
+	/* We can't put the device reference yet, since it can still be in
+	 * use, but rtnl_unlock()->netdev_run_todo() will block until all
+	 * the references are released, so the RCU call must be before it.
+	 */
+	call_rcu(&vport->rcu, vport_netdev_free);
+	rtnl_unlock();
+}
+EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);
+
+/* Returns null if this device is not attached to a datapath. */
+struct vport *ovs_netdev_get_vport(struct net_device *dev)
+{
+	if (likely(netif_is_ovs_port(dev)))
+		return (struct vport *)
+			rcu_dereference_rtnl(dev->rx_handler_data);
+	else
+		return NULL;
+}
+
+static struct vport_ops ovs_netdev_vport_ops = {
+	.type		= OVS_VPORT_TYPE_NETDEV,
+	.create		= netdev_create,
+	.destroy	= netdev_destroy,
+	.send		= dev_queue_xmit,
+};
+
+int __init ovs_netdev_init(void)
+{
+	return ovs_vport_ops_register(&ovs_netdev_vport_ops);
+}
+
+void ovs_netdev_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_netdev_vport_ops);
+}

linux-7.2.3/net/openvswitch/vport-netdev.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2011 Nicira, Inc.
+ */
+
+#ifndef VPORT_NETDEV_H
+#define VPORT_NETDEV_H 1
+
+#include <linux/netdevice.h>
+#include <linux/rcupdate.h>
+
+#include "vport.h"
+
+struct vport *ovs_netdev_get_vport(struct net_device *dev);
+
+struct vport *ovs_netdev_link(struct vport *vport, bool tunnel);
+void ovs_netdev_detach_dev(struct vport *);
+
+int __init ovs_netdev_init(void);
+void ovs_netdev_exit(void);
+
+void ovs_netdev_tunnel_destroy(struct vport *vport);
+#endif /* vport_netdev.h */

linux-7.2.3/net/openvswitch/vport-vxlan.c

@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ * Copyright (c) 2013 Cisco Systems, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/openvswitch.h>
+#include <linux/module.h>
+#include <net/udp.h>
+#include <net/ip_tunnels.h>
+#include <net/rtnetlink.h>
+#include <net/vxlan.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-netdev.h"
+
+static struct vport_ops ovs_vxlan_netdev_vport_ops;
+
+static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vport->dev);
+	__be16 dst_port = vxlan->cfg.dst_port;
+
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
+		return -EMSGSIZE;
+
+	if (vxlan->cfg.flags & VXLAN_F_GBP) {
+		struct nlattr *exts;
+
+		exts = nla_nest_start_noflag(skb, OVS_TUNNEL_ATTR_EXTENSION);
+		if (!exts)
+			return -EMSGSIZE;
+
+		if (vxlan->cfg.flags & VXLAN_F_GBP &&
+		    nla_put_flag(skb, OVS_VXLAN_EXT_GBP))
+			return -EMSGSIZE;
+
+		nla_nest_end(skb, exts);
+	}
+
+	return 0;
+}
+
+static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_FLAG, },
+};
+
+static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr,
+				struct vxlan_config *conf)
+{
+	struct nlattr *exts[OVS_VXLAN_EXT_MAX + 1];
+	int err;
+
+	if (nla_len(attr) < sizeof(struct nlattr))
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(exts, OVS_VXLAN_EXT_MAX, attr,
+					  exts_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (exts[OVS_VXLAN_EXT_GBP])
+		conf->flags |= VXLAN_F_GBP;
+
+	return 0;
+}
+
+static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct nlattr *options = parms->options;
+	struct net_device *dev;
+	struct vport *vport;
+	struct nlattr *a;
+	int err;
+	struct vxlan_config conf = {
+		.no_share = true,
+		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
+	};
+
+	if (!options) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+	if (a && nla_len(a) == sizeof(u16)) {
+		conf.dst_port = htons(nla_get_u16(a));
+	} else {
+		/* Require destination port from userspace. */
+		err = -EINVAL;
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
+	if (a) {
+		err = vxlan_configure_exts(vport, a, &conf);
+		if (err) {
+			ovs_vport_free(vport);
+			goto error;
+		}
+	}
+
+	rtnl_lock();
+	dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		return ERR_CAST(dev);
+	}
+
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+	if (err < 0) {
+		rtnl_delete_link(dev, 0, NULL);
+		rtnl_unlock();
+		ovs_vport_free(vport);
+		goto error;
+	}
+
+	vport->dev = dev;
+	netdev_hold(vport->dev, &vport->dev_tracker, GFP_KERNEL);
+
+	rtnl_unlock();
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static struct vport *vxlan_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = vxlan_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	return ovs_netdev_link(vport, true);
+}
+
+static struct vport_ops ovs_vxlan_netdev_vport_ops = {
+	.type			= OVS_VPORT_TYPE_VXLAN,
+	.create			= vxlan_create,
+	.destroy		= ovs_netdev_tunnel_destroy,
+	.get_options		= vxlan_get_options,
+	.send			= dev_queue_xmit,
+};
+
+static int __init ovs_vxlan_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops);
+}
+
+static void __exit ovs_vxlan_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops);
+}
+
+module_init(ovs_vxlan_tnl_init);
+module_exit(ovs_vxlan_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: VXLAN switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-4");

linux-7.2.3/net/openvswitch/vport.c

@@ -0,0 +1,585 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2007-2014 Nicira, Inc.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/if.h>
+#include <linux/if_vlan.h>
+#include <linux/jhash.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+#include <linux/compat.h>
+#include <net/net_namespace.h>
+#include <linux/module.h>
+
+#include "datapath.h"
+#include "vport.h"
+#include "vport-internal_dev.h"
+
+static LIST_HEAD(vport_ops_list);
+
+/* Protected by RCU read lock for reading, ovs_mutex for writing. */
+static struct hlist_head *dev_table;
+#define VPORT_HASH_BUCKETS 1024
+
+/**
+ *	ovs_vport_init - initialize vport subsystem
+ *
+ * Called at module load time to initialize the vport subsystem.
+ */
+int ovs_vport_init(void)
+{
+	dev_table = kzalloc_objs(struct hlist_head, VPORT_HASH_BUCKETS);
+	if (!dev_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ *	ovs_vport_exit - shutdown vport subsystem
+ *
+ * Called at module exit time to shutdown the vport subsystem.
+ */
+void ovs_vport_exit(void)
+{
+	kfree(dev_table);
+}
+
+static struct hlist_head *hash_bucket(const struct net *net, const char *name)
+{
+	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
+	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
+}
+
+int __ovs_vport_ops_register(struct vport_ops *ops)
+{
+	int err = -EEXIST;
+	struct vport_ops *o;
+
+	ovs_lock();
+	list_for_each_entry(o, &vport_ops_list, list)
+		if (ops->type == o->type)
+			goto errout;
+
+	list_add_tail(&ops->list, &vport_ops_list);
+	err = 0;
+errout:
+	ovs_unlock();
+	return err;
+}
+EXPORT_SYMBOL_GPL(__ovs_vport_ops_register);
+
+void ovs_vport_ops_unregister(struct vport_ops *ops)
+{
+	ovs_lock();
+	list_del(&ops->list);
+	ovs_unlock();
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
+
+/**
+ *	ovs_vport_locate - find a port that has already been created
+ *
+ * @net: network namespace
+ * @name: name of port to find
+ *
+ * Must be called with ovs or RCU read lock.
+ */
+struct vport *ovs_vport_locate(const struct net *net, const char *name)
+{
+	struct hlist_head *bucket = hash_bucket(net, name);
+	struct vport *vport;
+
+	hlist_for_each_entry_rcu(vport, bucket, hash_node,
+				 lockdep_ovsl_is_held())
+		if (!strcmp(name, ovs_vport_name(vport)) &&
+		    net_eq(ovs_dp_get_net(vport->dp), net))
+			return vport;
+
+	return NULL;
+}
+
+/**
+ *	ovs_vport_alloc - allocate and initialize new vport
+ *
+ * @priv_size: Size of private data area to allocate.
+ * @ops: vport device ops
+ * @parms: information about new vport.
+ *
+ * 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().  Some parameters of the vport will be initialized from @parms.
+ * @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;
+	int err;
+
+	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->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
+	if (!vport->upcall_stats) {
+		err = -ENOMEM;
+		goto err_kfree_vport;
+	}
+
+	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)) {
+		err = -EINVAL;
+		goto err_free_percpu;
+	}
+
+	return vport;
+
+err_free_percpu:
+	free_percpu(vport->upcall_stats);
+err_kfree_vport:
+	kfree(vport);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(ovs_vport_alloc);
+
+/**
+ *	ovs_vport_free - uninitialize and free vport
+ *
+ * @vport: vport to free
+ *
+ * Frees a vport allocated with vport_alloc() when it is no longer needed.
+ *
+ * The caller must ensure that an RCU grace period has passed since the last
+ * time @vport was in a datapath.
+ */
+void ovs_vport_free(struct vport *vport)
+{
+	/* vport is freed from RCU callback or error path, Therefore
+	 * it is safe to use raw dereference.
+	 */
+	kfree(rcu_dereference_raw(vport->upcall_portids));
+	free_percpu(vport->upcall_stats);
+	kfree(vport);
+}
+EXPORT_SYMBOL_GPL(ovs_vport_free);
+
+static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+
+	list_for_each_entry(ops, &vport_ops_list, list)
+		if (ops->type == parms->type)
+			return ops;
+
+	return NULL;
+}
+
+/**
+ *	ovs_vport_add - add vport device (for kernel callers)
+ *
+ * @parms: Information about new vport.
+ *
+ * Creates a new vport with the specified configuration (which is dependent on
+ * device type).  ovs_mutex must be held.
+ */
+struct vport *ovs_vport_add(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+	struct vport *vport;
+
+	ops = ovs_vport_lookup(parms);
+	if (ops) {
+		struct hlist_head *bucket;
+
+		if (!try_module_get(ops->owner))
+			return ERR_PTR(-EAFNOSUPPORT);
+
+		vport = ops->create(parms);
+		if (IS_ERR(vport)) {
+			module_put(ops->owner);
+			return vport;
+		}
+
+		bucket = hash_bucket(ovs_dp_get_net(vport->dp),
+				     ovs_vport_name(vport));
+		hlist_add_head_rcu(&vport->hash_node, bucket);
+		return vport;
+	}
+
+	/* Unlock to attempt module load and return -EAGAIN if load
+	 * was successful as we need to restart the port addition
+	 * workflow.
+	 */
+	ovs_unlock();
+	request_module("vport-type-%d", parms->type);
+	ovs_lock();
+
+	if (!ovs_vport_lookup(parms))
+		return ERR_PTR(-EAFNOSUPPORT);
+	else
+		return ERR_PTR(-EAGAIN);
+}
+
+/**
+ *	ovs_vport_set_options - modify existing vport device (for kernel callers)
+ *
+ * @vport: vport to modify.
+ * @options: New configuration.
+ *
+ * Modifies an existing device with the specified configuration (which is
+ * dependent on device type).  ovs_mutex must be held.
+ */
+int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
+{
+	if (!vport->ops->set_options)
+		return -EOPNOTSUPP;
+	return vport->ops->set_options(vport, options);
+}
+
+/**
+ *	ovs_vport_del - delete existing vport device
+ *
+ * @vport: vport to delete.
+ *
+ * Detaches @vport from its datapath and destroys it.  ovs_mutex must
+ * be held.
+ */
+void ovs_vport_del(struct vport *vport)
+{
+	hlist_del_rcu(&vport->hash_node);
+	module_put(vport->ops->owner);
+	vport->ops->destroy(vport);
+}
+
+/**
+ *	ovs_vport_get_stats - retrieve device stats
+ *
+ * @vport: vport from which to retrieve the stats
+ * @stats: location to store stats
+ *
+ * Retrieves transmit, receive, and error stats for the given device.
+ *
+ * Must be called with ovs_mutex or rcu_read_lock.
+ */
+void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
+{
+	const struct rtnl_link_stats64 *dev_stats;
+	struct rtnl_link_stats64 temp;
+
+	dev_stats = dev_get_stats(vport->dev, &temp);
+	stats->rx_errors  = dev_stats->rx_errors;
+	stats->tx_errors  = dev_stats->tx_errors;
+	stats->tx_dropped = dev_stats->tx_dropped;
+	stats->rx_dropped = dev_stats->rx_dropped;
+
+	stats->rx_bytes	  = dev_stats->rx_bytes;
+	stats->rx_packets = dev_stats->rx_packets;
+	stats->tx_bytes	  = dev_stats->tx_bytes;
+	stats->tx_packets = dev_stats->tx_packets;
+}
+
+/**
+ *	ovs_vport_get_upcall_stats - retrieve upcall stats
+ *
+ * @vport: vport from which to retrieve the stats.
+ * @skb: sk_buff where upcall stats should be appended.
+ *
+ * Retrieves upcall stats for the given device.
+ *
+ * Must be called with ovs_mutex or rcu_read_lock.
+ */
+int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb)
+{
+	u64 tx_success = 0, tx_fail = 0;
+	struct nlattr *nla;
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct vport_upcall_stats_percpu *stats;
+		u64 n_success, n_fail;
+		unsigned int start;
+
+		stats = per_cpu_ptr(vport->upcall_stats, i);
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			n_success = u64_stats_read(&stats->n_success);
+			n_fail = u64_stats_read(&stats->n_fail);
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+		tx_success += n_success;
+		tx_fail += n_fail;
+	}
+
+	nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_SUCCESS, tx_success,
+			      OVS_VPORT_ATTR_PAD)) {
+		nla_nest_cancel(skb, nla);
+		return -EMSGSIZE;
+	}
+
+	if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_FAIL, tx_fail,
+			      OVS_VPORT_ATTR_PAD)) {
+		nla_nest_cancel(skb, nla);
+		return -EMSGSIZE;
+	}
+	nla_nest_end(skb, nla);
+
+	return 0;
+}
+
+/**
+ *	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_noflag(skb, OVS_VPORT_ATTR_OPTIONS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	err = vport->ops->get_options(vport, skb);
+	if (err) {
+		nla_nest_cancel(skb, nla);
+		return err;
+	}
+
+	nla_nest_end(skb, nla);
+	return 0;
+}
+
+/**
+ *	ovs_vport_set_upcall_portids - set upcall portids of @vport.
+ *
+ * @vport: vport to modify.
+ * @ids: new configuration, an array of port ids.
+ *
+ * Sets the vport's upcall_portids to @ids.
+ *
+ * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
+ * as an array of U32.
+ *
+ * Must be called with ovs_mutex.
+ */
+int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
+{
+	struct vport_portids *old, *vport_portids;
+
+	if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
+		return -EINVAL;
+
+	if (nla_len(ids) / sizeof(u32) > nr_cpu_ids)
+		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 there is only one portid, select it in the fast-path. */
+	if (ids->n_ids == 1)
+		return ids->ids[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_info: tunnel (if any) that carried packet
+ *
+ * Must be called with rcu_read_lock.  The packet cannot be shared and
+ * skb->data should point to the Ethernet header.
+ */
+int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
+		      const struct ip_tunnel_info *tun_info)
+{
+	struct sw_flow_key key;
+	int error;
+
+	OVS_CB(skb)->input_vport = vport;
+	OVS_CB(skb)->mru = 0;
+	OVS_CB(skb)->cutlen = U32_MAX;
+	OVS_CB(skb)->probability = 0;
+	OVS_CB(skb)->upcall_pid = 0;
+	if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
+		u32 mark;
+
+		mark = skb->mark;
+		skb_scrub_packet(skb, true);
+		skb->mark = mark;
+		tun_info = NULL;
+	}
+
+	/* Extract flow from 'skb' into 'key'. */
+	error = ovs_flow_key_extract(tun_info, skb, &key);
+	if (unlikely(error)) {
+		kfree_skb(skb);
+		return error;
+	}
+	ovs_dp_process_packet(skb, &key);
+	return 0;
+}
+
+static int packet_length(const struct sk_buff *skb,
+			 struct net_device *dev)
+{
+	int length = skb->len - dev->hard_header_len;
+
+	if (!skb_vlan_tag_present(skb) &&
+	    eth_type_vlan(skb->protocol))
+		length -= VLAN_HLEN;
+
+	/* Don't subtract for multiple VLAN tags. Most (all?) drivers allow
+	 * (ETH_LEN + VLAN_HLEN) in addition to the mtu value, but almost none
+	 * account for 802.1ad. e.g. is_skb_forwardable().
+	 */
+
+	return length > 0 ? length : 0;
+}
+
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
+{
+	int mtu = vport->dev->mtu;
+
+	switch (vport->dev->type) {
+	case ARPHRD_NONE:
+		if (mac_proto == MAC_PROTO_ETHERNET) {
+			skb_reset_network_header(skb);
+			skb_reset_mac_len(skb);
+			skb->protocol = htons(ETH_P_TEB);
+		} else if (mac_proto != MAC_PROTO_NONE) {
+			WARN_ON_ONCE(1);
+			goto drop;
+		}
+		break;
+	case ARPHRD_ETHER:
+		if (mac_proto != MAC_PROTO_ETHERNET)
+			goto drop;
+		break;
+	default:
+		goto drop;
+	}
+
+	if (unlikely(packet_length(skb, vport->dev) > mtu &&
+		     !skb_is_gso(skb))) {
+		vport->dev->stats.tx_errors++;
+		if (vport->dev->flags & IFF_UP)
+			net_warn_ratelimited("%s: dropped over-mtu packet: "
+					     "%d > %d\n", vport->dev->name,
+					     packet_length(skb, vport->dev),
+					     mtu);
+		goto drop;
+	}
+
+	skb->dev = vport->dev;
+	skb_clear_tstamp(skb);
+	vport->ops->send(skb);
+	return;
+
+drop:
+	kfree_skb(skb);
+}

linux-7.2.3/net/openvswitch/vport.h

@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2007-2012 Nicira, Inc.
+ */
+
+#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 subsystem: */
+
+int ovs_vport_init(void);
+void ovs_vport_exit(void);
+
+struct vport *ovs_vport_add(const struct vport_parms *);
+void ovs_vport_del(struct vport *);
+
+struct vport *ovs_vport_locate(const struct net *net, const char *name);
+
+void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
+
+int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb);
+
+int ovs_vport_set_options(struct vport *, struct nlattr *options);
+int ovs_vport_get_options(const struct vport *, struct sk_buff *);
+
+int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids);
+int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *);
+u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
+
+/**
+ * struct vport_portids - array of netlink portids of a vport.
+ *                        must be protected by rcu.
+ * @rn_ids: The reciprocal value of @n_ids.
+ * @rcu: RCU callback head for deferred destruction.
+ * @n_ids: Size of @ids array.
+ * @ids: Array storing the Netlink socket pids to be used for packets received
+ * on this port that miss the flow table.
+ */
+struct vport_portids {
+	struct reciprocal_value rn_ids;
+	struct rcu_head rcu;
+	u32 n_ids;
+	u32 ids[];
+};
+
+/**
+ * struct vport - one port within a datapath
+ * @dev: Pointer to net_device.
+ * @dev_tracker: refcount tracker for @dev reference
+ * @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.
+ * @upcall_stats: Upcall stats of every ports.
+ * @detach_list: list used for detaching vport in net-exit call.
+ * @rcu: RCU callback head for deferred destruction.
+ */
+struct vport {
+	struct net_device *dev;
+	netdevice_tracker dev_tracker;
+	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 vport_upcall_stats_percpu __percpu *upcall_stats;
+
+	struct list_head detach_list;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct vport_parms - parameters for creating a new vport
+ *
+ * @name: New vport's name.
+ * @type: New vport's type.
+ * @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
+ * none was supplied.
+ * @desired_ifindex: New vport's ifindex.
+ * @dp: New vport's datapath.
+ * @port_no: New vport's port number.
+ * @upcall_portids: %OVS_VPORT_ATTR_UPCALL_PID attribute from Netlink message,
+ * %NULL if none was supplied.
+ */
+struct vport_parms {
+	const char *name;
+	enum ovs_vport_type type;
+	int desired_ifindex;
+	struct nlattr *options;
+
+	/* For ovs_vport_alloc(). */
+	struct datapath *dp;
+	u16 port_no;
+	struct nlattr *upcall_portids;
+};
+
+/**
+ * struct vport_ops - definition of a type of virtual port
+ *
+ * @type: %OVS_VPORT_TYPE_* value for this type of virtual port.
+ * @create: Create a new vport configured as specified.  On success returns
+ * a new vport allocated with ovs_vport_alloc(), otherwise an ERR_PTR() value.
+ * @destroy: Destroys a vport.  Must call vport_free() on the vport but not
+ * before an RCU grace period has elapsed.
+ * @set_options: Modify the configuration of an existing vport.  May be %NULL
+ * if modification is not supported.
+ * @get_options: Appends vport-specific attributes for the configuration of an
+ * existing vport to a &struct sk_buff.  May be %NULL for a vport that does not
+ * have any configuration.
+ * @send: Send a packet on the device.
+ * zero for dropped packets or negative for error.
+ * @owner: Module that implements this vport type.
+ * @list: List entry in the global list of vport types.
+ */
+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 *);
+
+	int (*send)(struct sk_buff *skb);
+	struct module *owner;
+	struct list_head list;
+};
+
+/**
+ * struct vport_upcall_stats_percpu - per-cpu packet upcall statistics for
+ * a given vport.
+ * @syncp:     Synchronization point for 64bit counters.
+ * @n_success: Number of packets that upcall to userspace succeed.
+ * @n_fail:    Number of packets that upcall to userspace failed.
+ */
+struct vport_upcall_stats_percpu {
+	struct u64_stats_sync syncp;
+	u64_stats_t n_success;
+	u64_stats_t n_fail;
+};
+
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
+			      const struct vport_parms *);
+void ovs_vport_free(struct vport *);
+
+#define VPORT_ALIGN 8
+
+/**
+ *	vport_priv - access private data area of vport
+ *
+ * @vport: vport to access
+ *
+ * Returns: A void pointer to a private data allocated in the @vport.
+ *
+ * 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.
+ *
+ * Returns: A reference to a vport structure that contains @priv.
+ *
+ * It is sometimes useful to translate from a pointer to the private data
+ * area to the vport, such as in the case where the private data pointer is
+ * the result of a hash table lookup.  @priv must point to the start of the
+ * private data area.
+ */
+static inline struct vport *vport_from_priv(void *priv)
+{
+	return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+}
+
+int ovs_vport_receive(struct vport *, struct sk_buff *,
+		      const struct ip_tunnel_info *);
+
+static inline const char *ovs_vport_name(struct vport *vport)
+{
+	return vport->dev->name;
+}
+
+int __ovs_vport_ops_register(struct vport_ops *ops);
+#define ovs_vport_ops_register(ops)		\
+	({					\
+		(ops)->owner = THIS_MODULE;	\
+		__ovs_vport_ops_register(ops);	\
+	})
+
+void ovs_vport_ops_unregister(struct vport_ops *ops);
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto);
+
+#endif /* vport.h */