Merge branch 'net_next_ovs' of git://git.kernel.org/pub/scm/linux/kernel/git/pshelar/openvswitch

Pravin B Shelar says:

====================
Open vSwitch

Following batch of patches brings feature parity between upstream
ovs and out of tree ovs module.

Two features are added, first adds support to export egress
tunnel information for a packet. This is used to improve
visibility in network traffic. Second feature allows userspace
vswitchd process to probe ovs module features. Other patches
are optimization and code cleanup.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/uapi/linux/openvswitch.h

@@ -157,6 +157,11 @@ enum ovs_packet_cmd {
  * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
  * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content
  * specified there.
+ * @OVS_PACKET_ATTR_EGRESS_TUN_KEY: Present for an %OVS_PACKET_CMD_ACTION
+ * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
+ * %OVS_USERSPACE_ATTR_EGRESS_TUN_PORT attribute, which is sent only if the
+ * output port is actually a tunnel port. Contains the output tunnel key
+ * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_PACKET_* commands.
@@ -167,6 +172,8 @@ enum ovs_packet_attr {
 	OVS_PACKET_ATTR_KEY,         /* Nested OVS_KEY_ATTR_* attributes. */
 	OVS_PACKET_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
 	OVS_PACKET_ATTR_USERDATA,    /* OVS_ACTION_ATTR_USERSPACE arg. */
+	OVS_PACKET_ATTR_EGRESS_TUN_KEY,  /* Nested OVS_TUNNEL_KEY_ATTR_*
+					    attributes. */
 	__OVS_PACKET_ATTR_MAX
 };
 
@@ -315,6 +322,8 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */
 	OVS_TUNNEL_KEY_ATTR_OAM,                /* No argument. OAM frame.  */
 	OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,        /* Array of Geneve options. */
+	OVS_TUNNEL_KEY_ATTR_TP_SRC,		/* be16 src Transport Port. */
+	OVS_TUNNEL_KEY_ATTR_TP_DST,		/* be16 dst Transport Port. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
@@ -448,6 +457,8 @@ enum ovs_flow_attr {
 	OVS_FLOW_ATTR_USED,      /* u64 msecs last used in monotonic time. */
 	OVS_FLOW_ATTR_CLEAR,     /* Flag to clear stats, tcp_flags, used. */
 	OVS_FLOW_ATTR_MASK,      /* Sequence of OVS_KEY_ATTR_* attributes. */
+	OVS_FLOW_ATTR_PROBE,     /* Flow operation is a feature probe, error
+				  * logging should be suppressed. */
 	__OVS_FLOW_ATTR_MAX
 };
 
@@ -480,11 +491,15 @@ enum ovs_sample_attr {
  * message should be sent.  Required.
  * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is
  * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA.
+ * @OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: If present, u32 output port to get
+ * tunnel info.
  */
 enum ovs_userspace_attr {
 	OVS_USERSPACE_ATTR_UNSPEC,
 	OVS_USERSPACE_ATTR_PID,	      /* u32 Netlink PID to receive upcalls. */
 	OVS_USERSPACE_ATTR_USERDATA,  /* Optional user-specified cookie. */
+	OVS_USERSPACE_ATTR_EGRESS_TUN_PORT,  /* Optional, u32 output port
+					      * to get tunnel info. */
 	__OVS_USERSPACE_ATTR_MAX
 };
 

net/openvswitch/actions.c

@@ -69,7 +69,7 @@ static void action_fifo_init(struct action_fifo *fifo)
 	fifo->tail = 0;
 }
 
-static bool action_fifo_is_empty(struct action_fifo *fifo)
+static bool action_fifo_is_empty(const struct action_fifo *fifo)
 {
 	return (fifo->head == fifo->tail);
 }
@@ -92,7 +92,7 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
 
 /* Return true if fifo is not full */
 static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
-						    struct sw_flow_key *key,
+						    const struct sw_flow_key *key,
 						    const struct nlattr *attr)
 {
 	struct action_fifo *fifo;
@@ -109,6 +109,16 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 	return da;
 }
 
+static void invalidate_flow_key(struct sw_flow_key *key)
+{
+	key->eth.type = htons(0);
+}
+
+static bool is_flow_key_valid(const struct sw_flow_key *key)
+{
+	return !!key->eth.type;
+}
+
 static int make_writable(struct sk_buff *skb, int write_len)
 {
 	if (!pskb_may_pull(skb, write_len))
@@ -120,7 +130,7 @@ static int make_writable(struct sk_buff *skb, int write_len)
 	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 }
 
-static int push_mpls(struct sk_buff *skb,
+static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_mpls *mpls)
 {
 	__be32 *new_mpls_lse;
@@ -151,10 +161,12 @@ static int push_mpls(struct sk_buff *skb,
 	skb_set_inner_protocol(skb, skb->protocol);
 	skb->protocol = mpls->mpls_ethertype;
 
+	invalidate_flow_key(key);
 	return 0;
 }
 
-static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
+static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
+		    const __be16 ethertype)
 {
 	struct ethhdr *hdr;
 	int err;
@@ -181,10 +193,13 @@ static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
 	hdr->h_proto = ethertype;
 	if (eth_p_mpls(skb->protocol))
 		skb->protocol = ethertype;
+
+	invalidate_flow_key(key);
 	return 0;
 }
 
-static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
+static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
+		    const __be32 *mpls_lse)
 {
 	__be32 *stack;
 	int err;
@@ -196,13 +211,12 @@ static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
 	stack = (__be32 *)skb_mpls_header(skb);
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be32 diff[] = { ~(*stack), *mpls_lse };
-
 		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
 					  ~skb->csum);
 	}
 
 	*stack = *mpls_lse;
-
+	key->mpls.top_lse = *mpls_lse;
 	return 0;
 }
 
@@ -237,7 +251,7 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 	return 0;
 }
 
-static int pop_vlan(struct sk_buff *skb)
+static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	__be16 tci;
 	int err;
@@ -255,9 +269,12 @@ static int pop_vlan(struct sk_buff *skb)
 	}
 	/* move next vlan tag to hw accel tag */
 	if (likely(skb->protocol != htons(ETH_P_8021Q) ||
-		   skb->len < VLAN_ETH_HLEN))
+		   skb->len < VLAN_ETH_HLEN)) {
+		key->eth.tci = 0;
 		return 0;
+	}
 
+	invalidate_flow_key(key);
 	err = __pop_vlan_tci(skb, &tci);
 	if (unlikely(err))
 		return err;
@@ -266,7 +283,8 @@ static int pop_vlan(struct sk_buff *skb)
 	return 0;
 }
 
-static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
+		     const struct ovs_action_push_vlan *vlan)
 {
 	if (unlikely(vlan_tx_tag_present(skb))) {
 		u16 current_tag;
@@ -283,12 +301,15 @@ static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vla
 			skb->csum = csum_add(skb->csum, csum_partial(skb->data
 					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
 
+		invalidate_flow_key(key);
+	} else {
+		key->eth.tci = vlan->vlan_tci;
 	}
 	__vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
 	return 0;
 }
 
-static int set_eth_addr(struct sk_buff *skb,
+static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key,
 			const struct ovs_key_ethernet *eth_key)
 {
 	int err;
@@ -303,11 +324,13 @@ static int set_eth_addr(struct sk_buff *skb,
 
 	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
+	ether_addr_copy(key->eth.src, eth_key->eth_src);
+	ether_addr_copy(key->eth.dst, eth_key->eth_dst);
 	return 0;
 }
 
 static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
-				__be32 *addr, __be32 new_addr)
+			__be32 *addr, __be32 new_addr)
 {
 	int transport_len = skb->len - skb_transport_offset(skb);
 
@@ -386,7 +409,8 @@ static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
 	nh->ttl = new_ttl;
 }
 
-static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *key,
+		    const struct ovs_key_ipv4 *ipv4_key)
 {
 	struct iphdr *nh;
 	int err;
@@ -398,22 +422,31 @@ static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
 
 	nh = ip_hdr(skb);
 
-	if (ipv4_key->ipv4_src != nh->saddr)
+	if (ipv4_key->ipv4_src != nh->saddr) {
 		set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
+		key->ipv4.addr.src = ipv4_key->ipv4_src;
+	}
 
-	if (ipv4_key->ipv4_dst != nh->daddr)
+	if (ipv4_key->ipv4_dst != nh->daddr) {
 		set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+		key->ipv4.addr.dst = ipv4_key->ipv4_dst;
+	}
 
-	if (ipv4_key->ipv4_tos != nh->tos)
+	if (ipv4_key->ipv4_tos != nh->tos) {
 		ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+		key->ip.tos = nh->tos;
+	}
 
-	if (ipv4_key->ipv4_ttl != nh->ttl)
+	if (ipv4_key->ipv4_ttl != nh->ttl) {
 		set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+		key->ip.ttl = ipv4_key->ipv4_ttl;
+	}
 
 	return 0;
 }
 
-static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
+static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key,
+		    const struct ovs_key_ipv6 *ipv6_key)
 {
 	struct ipv6hdr *nh;
 	int err;
@@ -429,9 +462,12 @@ static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
 	saddr = (__be32 *)&nh->saddr;
 	daddr = (__be32 *)&nh->daddr;
 
-	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src)))
+	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src))) {
 		set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
 			      ipv6_key->ipv6_src, true);
+		memcpy(&key->ipv6.addr.src, ipv6_key->ipv6_src,
+		       sizeof(ipv6_key->ipv6_src));
+	}
 
 	if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
 		unsigned int offset = 0;
@@ -445,12 +481,18 @@ static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
 
 		set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
 			      ipv6_key->ipv6_dst, recalc_csum);
+		memcpy(&key->ipv6.addr.dst, ipv6_key->ipv6_dst,
+		       sizeof(ipv6_key->ipv6_dst));
 	}
 
 	set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
+	key->ip.tos = ipv6_get_dsfield(nh);
+
 	set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
-	nh->hop_limit = ipv6_key->ipv6_hlimit;
+	key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
 
+	nh->hop_limit = ipv6_key->ipv6_hlimit;
+	key->ip.ttl = ipv6_key->ipv6_hlimit;
 	return 0;
 }
 
@@ -478,7 +520,8 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
 	}
 }
 
-static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
+static int set_udp(struct sk_buff *skb, struct sw_flow_key *key,
+		   const struct ovs_key_udp *udp_port_key)
 {
 	struct udphdr *uh;
 	int err;
@@ -489,16 +532,21 @@ static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
 		return err;
 
 	uh = udp_hdr(skb);
-	if (udp_port_key->udp_src != uh->source)
+	if (udp_port_key->udp_src != uh->source) {
 		set_udp_port(skb, &uh->source, udp_port_key->udp_src);
+		key->tp.src = udp_port_key->udp_src;
+	}
 
-	if (udp_port_key->udp_dst != uh->dest)
+	if (udp_port_key->udp_dst != uh->dest) {
 		set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
+		key->tp.dst = udp_port_key->udp_dst;
+	}
 
 	return 0;
 }
 
-static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key,
+		   const struct ovs_key_tcp *tcp_port_key)
 {
 	struct tcphdr *th;
 	int err;
@@ -509,17 +557,21 @@ static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
 		return err;
 
 	th = tcp_hdr(skb);
-	if (tcp_port_key->tcp_src != th->source)
+	if (tcp_port_key->tcp_src != th->source) {
 		set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
+		key->tp.src = tcp_port_key->tcp_src;
+	}
 
-	if (tcp_port_key->tcp_dst != th->dest)
+	if (tcp_port_key->tcp_dst != th->dest) {
 		set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+		key->tp.dst = tcp_port_key->tcp_dst;
+	}
 
 	return 0;
 }
 
-static int set_sctp(struct sk_buff *skb,
-		     const struct ovs_key_sctp *sctp_port_key)
+static int set_sctp(struct sk_buff *skb, struct sw_flow_key *key,
+		    const struct ovs_key_sctp *sctp_port_key)
 {
 	struct sctphdr *sh;
 	int err;
@@ -546,6 +598,8 @@ static int set_sctp(struct sk_buff *skb,
 		sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
 		skb_clear_hash(skb);
+		key->tp.src = sctp_port_key->sctp_src;
+		key->tp.dst = sctp_port_key->sctp_dst;
 	}
 
 	return 0;
@@ -564,14 +618,15 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr)
 {
+	struct ovs_tunnel_info info;
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
 	int rem;
 
 	upcall.cmd = OVS_PACKET_CMD_ACTION;
-	upcall.key = key;
 	upcall.userdata = NULL;
 	upcall.portid = 0;
+	upcall.egress_tun_info = NULL;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -583,10 +638,27 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 		case OVS_USERSPACE_ATTR_PID:
 			upcall.portid = nla_get_u32(a);
 			break;
+
+		case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
+			/* Get out tunnel info. */
+			struct vport *vport;
+
+			vport = ovs_vport_rcu(dp, nla_get_u32(a));
+			if (vport) {
+				int err;
+
+				err = ovs_vport_get_egress_tun_info(vport, skb,
+								    &info);
+				if (!err)
+					upcall.egress_tun_info = &info;
+			}
+			break;
 		}
+
+		} /* End of switch. */
 	}
 
-	return ovs_dp_upcall(dp, skb, &upcall);
+	return ovs_dp_upcall(dp, skb, key, &upcall);
 }
 
 static int sample(struct datapath *dp, struct sk_buff *skb,
@@ -656,18 +728,20 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
 	key->ovs_flow_hash = hash;
 }
 
-static int execute_set_action(struct sk_buff *skb,
-				 const struct nlattr *nested_attr)
+static int execute_set_action(struct sk_buff *skb, struct sw_flow_key *key,
+			      const struct nlattr *nested_attr)
 {
 	int err = 0;
 
 	switch (nla_type(nested_attr)) {
 	case OVS_KEY_ATTR_PRIORITY:
 		skb->priority = nla_get_u32(nested_attr);
+		key->phy.priority = skb->priority;
 		break;
 
 	case OVS_KEY_ATTR_SKB_MARK:
 		skb->mark = nla_get_u32(nested_attr);
+		key->phy.skb_mark = skb->mark;
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL_INFO:
@@ -675,31 +749,31 @@ static int execute_set_action(struct sk_buff *skb,
 		break;
 
 	case OVS_KEY_ATTR_ETHERNET:
-		err = set_eth_addr(skb, nla_data(nested_attr));
+		err = set_eth_addr(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		err = set_ipv4(skb, nla_data(nested_attr));
+		err = set_ipv4(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		err = set_ipv6(skb, nla_data(nested_attr));
+		err = set_ipv6(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		err = set_tcp(skb, nla_data(nested_attr));
+		err = set_tcp(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_UDP:
-		err = set_udp(skb, nla_data(nested_attr));
+		err = set_udp(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_SCTP:
-		err = set_sctp(skb, nla_data(nested_attr));
+		err = set_sctp(skb, key, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_MPLS:
-		err = set_mpls(skb, nla_data(nested_attr));
+		err = set_mpls(skb, key, nla_data(nested_attr));
 		break;
 	}
 
@@ -711,11 +785,15 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			  const struct nlattr *a, int rem)
 {
 	struct deferred_action *da;
-	int err;
 
-	err = ovs_flow_key_update(skb, key);
-	if (err)
-		return err;
+	if (!is_flow_key_valid(key)) {
+		int err;
+
+		err = ovs_flow_key_update(skb, key);
+		if (err)
+			return err;
+	}
+	BUG_ON(!is_flow_key_valid(key));
 
 	if (!nla_is_last(a, rem)) {
 		/* Recirc action is the not the last action
@@ -752,7 +830,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	/* Every output action needs a separate clone of 'skb', but the common
 	 * case is just a single output action, so that doing a clone and
 	 * then freeing the original skbuff is wasteful.  So the following code
-	 * is slightly obscure just to avoid that. */
+	 * is slightly obscure just to avoid that.
+	 */
 	int prev_port = -1;
 	const struct nlattr *a;
 	int rem;
@@ -784,21 +863,21 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_MPLS:
-			err = push_mpls(skb, nla_data(a));
+			err = push_mpls(skb, key, nla_data(a));
 			break;
 
 		case OVS_ACTION_ATTR_POP_MPLS:
-			err = pop_mpls(skb, nla_get_be16(a));
+			err = pop_mpls(skb, key, nla_get_be16(a));
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_VLAN:
-			err = push_vlan(skb, nla_data(a));
+			err = push_vlan(skb, key, nla_data(a));
 			if (unlikely(err)) /* skb already freed. */
 				return err;
 			break;
 
 		case OVS_ACTION_ATTR_POP_VLAN:
-			err = pop_vlan(skb);
+			err = pop_vlan(skb, key);
 			break;
 
 		case OVS_ACTION_ATTR_RECIRC:
@@ -813,7 +892,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			break;
 
 		case OVS_ACTION_ATTR_SET:
-			err = execute_set_action(skb, nla_data(a));
+			err = execute_set_action(skb, key, nla_data(a));
 			break;
 
 		case OVS_ACTION_ATTR_SAMPLE:
@@ -865,7 +944,8 @@ static void process_deferred_actions(struct datapath *dp)
 
 /* Execute a list of actions against 'skb'. */
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			struct sw_flow_actions *acts, struct sw_flow_key *key)
+			const struct sw_flow_actions *acts,
+			struct sw_flow_key *key)
 {
 	int level = this_cpu_read(exec_actions_level);
 	int err;

net/openvswitch/datapath.c

@@ -59,7 +59,7 @@
 #include "vport-netdev.h"
 
 int ovs_net_id __read_mostly;
-EXPORT_SYMBOL(ovs_net_id);
+EXPORT_SYMBOL_GPL(ovs_net_id);
 
 static struct genl_family dp_packet_genl_family;
 static struct genl_family dp_flow_genl_family;
@@ -131,13 +131,15 @@ int lockdep_ovsl_is_held(void)
 	else
 		return 1;
 }
-EXPORT_SYMBOL(lockdep_ovsl_is_held);
+EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
 #endif
 
 static struct vport *new_vport(const struct vport_parms *);
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
+			     const struct sw_flow_key *,
 			     const struct dp_upcall_info *);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
+				  const struct sw_flow_key *,
 				  const struct dp_upcall_info *);
 
 /* Must be called with rcu_read_lock. */
@@ -176,7 +178,7 @@ const char *ovs_dp_name(const struct datapath *dp)
 	return vport->ops->get_name(vport);
 }
 
-static int get_dpifindex(struct datapath *dp)
+static int get_dpifindex(const struct datapath *dp)
 {
 	struct vport *local;
 	int ifindex;
@@ -271,10 +273,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		int error;
 
 		upcall.cmd = OVS_PACKET_CMD_MISS;
-		upcall.key = key;
 		upcall.userdata = NULL;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
-		error = ovs_dp_upcall(dp, skb, &upcall);
+		upcall.egress_tun_info = NULL;
+		error = ovs_dp_upcall(dp, skb, key, &upcall);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -298,6 +300,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 }
 
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
+		  const struct sw_flow_key *key,
 		  const struct dp_upcall_info *upcall_info)
 {
 	struct dp_stats_percpu *stats;
@@ -309,9 +312,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 	else
-		err = queue_gso_packets(dp, skb, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info);
 	if (err)
 		goto err;
 
@@ -328,39 +331,43 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 }
 
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
+			     const struct sw_flow_key *key,
 			     const struct dp_upcall_info *upcall_info)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
-	struct dp_upcall_info later_info;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
+	struct ovs_skb_cb ovs_cb;
 	int err;
 
+	ovs_cb = *OVS_CB(skb);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		*OVS_CB(skb) = ovs_cb;
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 		if (err)
 			break;
 
-		if (skb == segs && gso_type & SKB_GSO_UDP) {
-			/* The initial flow key extracted by ovs_flow_extract()
-			 * in this case is for a first fragment, so we need to
-			 * properly mark later fragments.
-			 */
-			later_key = *upcall_info->key;
-			later_key.ip.frag = OVS_FRAG_TYPE_LATER;
-
-			later_info = *upcall_info;
-			later_info.key = &later_key;
-			upcall_info = &later_info;
-		}
 	} while ((skb = skb->next));
 
 	/* Free all of the segments. */
@@ -375,7 +382,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	return err;
 }
 
-static size_t upcall_msg_size(const struct nlattr *userdata,
+static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 			      unsigned int hdrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
@@ -383,13 +390,18 @@ static size_t upcall_msg_size(const struct nlattr *userdata,
 		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
 
 	/* OVS_PACKET_ATTR_USERDATA */
-	if (userdata)
-		size += NLA_ALIGN(userdata->nla_len);
+	if (upcall_info->userdata)
+		size += NLA_ALIGN(upcall_info->userdata->nla_len);
+
+	/* OVS_PACKET_ATTR_EGRESS_TUN_KEY */
+	if (upcall_info->egress_tun_info)
+		size += nla_total_size(ovs_tun_key_attr_size());
 
 	return size;
 }
 
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
+				  const struct sw_flow_key *key,
 				  const struct dp_upcall_info *upcall_info)
 {
 	struct ovs_header *upcall;
@@ -440,7 +452,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info->userdata, hlen);
+	len = upcall_msg_size(upcall_info, hlen);
 	user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -452,7 +464,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	upcall->dp_ifindex = dp_ifindex;
 
 	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
-	err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+	err = ovs_nla_put_flow(key, key, user_skb);
 	BUG_ON(err);
 	nla_nest_end(user_skb, nla);
 
@@ -461,6 +473,14 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 			  nla_len(upcall_info->userdata),
 			  nla_data(upcall_info->userdata));
 
+	if (upcall_info->egress_tun_info) {
+		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		err = ovs_nla_put_egress_tunnel_key(user_skb,
+						    upcall_info->egress_tun_info);
+		BUG_ON(err);
+		nla_nest_end(user_skb, nla);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
@@ -506,6 +526,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct vport *input_vport;
 	int len;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	err = -EINVAL;
 	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
@@ -539,12 +560,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_skb;
 
 	err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet,
-					     &flow->key);
+					     &flow->key, log);
 	if (err)
 		goto err_flow_free;
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, &acts);
+				   &flow->key, &acts, log);
 	if (err)
 		goto err_flow_free;
 
@@ -613,7 +634,7 @@ static struct genl_family dp_packet_genl_family = {
 	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
 };
 
-static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
+static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats,
 			 struct ovs_dp_megaflow_stats *mega_stats)
 {
 	int i;
@@ -835,15 +856,16 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Must have key and actions. */
 	error = -EINVAL;
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow key attribute not present in new flow.\n");
+		OVS_NLERR(log, "Flow key attr not present in new flow.");
 		goto error;
 	}
 	if (!a[OVS_FLOW_ATTR_ACTIONS]) {
-		OVS_NLERR("Flow actions attribute not present in new flow.\n");
+		OVS_NLERR(log, "Flow actions attr not present in new flow.");
 		goto error;
 	}
 
@@ -858,8 +880,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	/* Extract key. */
 	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto err_kfree_flow;
 
@@ -867,9 +889,9 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	/* Validate actions. */
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     &acts);
+				     &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+		OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
 		goto err_kfree_flow;
 	}
 
@@ -922,6 +944,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		}
 		/* The unmasked key has to be the same for flow updates. */
 		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+			/* Look for any overlapping flow. */
 			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 			if (!flow) {
 				error = -ENOENT;
@@ -964,16 +987,18 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
 static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 						const struct sw_flow_key *key,
-						const struct sw_flow_mask *mask)
+						const struct sw_flow_mask *mask,
+						bool log)
 {
 	struct sw_flow_actions *acts;
 	struct sw_flow_key masked_key;
 	int error;
 
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
-		OVS_NLERR("Actions may not be safe on all matching packets.\n");
+		OVS_NLERR(log,
+			  "Actions may not be safe on all matching packets");
 		return ERR_PTR(error);
 	}
 
@@ -992,23 +1017,25 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Extract key. */
 	error = -EINVAL;
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow key attribute not present in set flow.\n");
+		OVS_NLERR(log, "Flow key attribute not present in set flow.");
 		goto error;
 	}
 
 	ovs_match_init(&match, &key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto error;
 
 	/* Validate actions. */
 	if (a[OVS_FLOW_ATTR_ACTIONS]) {
-		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask,
+					log);
 		if (IS_ERR(acts)) {
 			error = PTR_ERR(acts);
 			goto error;
@@ -1089,14 +1116,16 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow get message rejected, Key attribute missing.\n");
+		OVS_NLERR(log,
+			  "Flow get message rejected, Key attribute missing.");
 		return -EINVAL;
 	}
 
 	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log);
 	if (err)
 		return err;
 
@@ -1137,10 +1166,12 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (likely(a[OVS_FLOW_ATTR_KEY])) {
 		ovs_match_init(&match, &key, NULL);
-		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
 		if (unlikely(err))
 			return err;
 	}
@@ -1230,8 +1261,10 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_MASK] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG },
 };
 
 static const struct genl_ops dp_flow_genl_ops[] = {
@@ -1332,7 +1365,7 @@ static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
 
 /* Called with rcu_read_lock or ovs_mutex. */
 static struct datapath *lookup_datapath(struct net *net,
-					struct ovs_header *ovs_header,
+					const struct ovs_header *ovs_header,
 					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
 {
 	struct datapath *dp;
@@ -1360,7 +1393,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in
 	dp->user_features = 0;
 }
 
-static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+static void ovs_dp_change(struct datapath *dp, struct nlattr *a[])
 {
 	if (a[OVS_DP_ATTR_USER_FEATURES])
 		dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
@@ -1724,7 +1757,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 
 /* Called with ovs_mutex or RCU read lock. */
 static struct vport *lookup_vport(struct net *net,
-				  struct ovs_header *ovs_header,
+				  const struct ovs_header *ovs_header,
 				  struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
 {
 	struct datapath *dp;

net/openvswitch/datapath.h

@@ -108,18 +108,18 @@ struct ovs_skb_cb {
 /**
  * struct dp_upcall - metadata to include with a packet to send to userspace
  * @cmd: One of %OVS_PACKET_CMD_*.
- * @key: Becomes %OVS_PACKET_ATTR_KEY.  Must be nonnull.
  * @userdata: If nonnull, its variable-length value is passed to userspace as
  * %OVS_PACKET_ATTR_USERDATA.
- * @pid: Netlink PID to which packet should be sent.  If @pid is 0 then no
- * packet is sent and the packet is accounted in the datapath's @n_lost
+ * @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.
  */
 struct dp_upcall_info {
-	u8 cmd;
-	const struct sw_flow_key *key;
+	const struct ovs_tunnel_info *egress_tun_info;
 	const struct nlattr *userdata;
 	u32 portid;
+	u8 cmd;
 };
 
 /**
@@ -149,7 +149,7 @@ int lockdep_ovsl_is_held(void);
 #define rcu_dereference_ovsl(p)					\
 	rcu_dereference_check(p, lockdep_ovsl_is_held())
 
-static inline struct net *ovs_dp_get_net(struct datapath *dp)
+static inline struct net *ovs_dp_get_net(const struct datapath *dp)
 {
 	return read_pnet(&dp->net);
 }
@@ -185,23 +185,23 @@ extern struct genl_family dp_vport_genl_family;
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
-		  const struct dp_upcall_info *);
+		  const struct sw_flow_key *, const struct dp_upcall_info *);
 
 const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
 					 u8 cmd);
 
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			struct sw_flow_actions *acts, struct sw_flow_key *);
+			const struct sw_flow_actions *, struct sw_flow_key *);
 
 void ovs_dp_notify_wq(struct work_struct *work);
 
 int action_fifos_init(void);
 void action_fifos_exit(void);
 
-#define OVS_NLERR(fmt, ...)					\
+#define OVS_NLERR(logging_allowed, fmt, ...)			\
 do {								\
-	if (net_ratelimit())					\
-		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+	if (logging_allowed && net_ratelimit())			\
+		pr_info("netlink: " fmt "\n", ##__VA_ARGS__);	\
 } while (0)
 #endif /* datapath.h */

net/openvswitch/flow.c

@@ -66,7 +66,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
 
 void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
-			   struct sk_buff *skb)
+			   const struct sk_buff *skb)
 {
 	struct flow_stats *stats;
 	int node = numa_node_id();
@@ -679,7 +679,7 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 	return key_extract(skb, key);
 }
 
-int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
+int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
@@ -712,12 +712,12 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key)
+				   struct sw_flow_key *key, bool log)
 {
 	int err;
 
 	/* Extract metadata from netlink attributes. */
-	err = ovs_nla_get_flow_metadata(attr, key);
+	err = ovs_nla_get_flow_metadata(attr, key, log);
 	if (err)
 		return err;
 

net/openvswitch/flow.h

@@ -37,8 +37,8 @@ struct sk_buff;
 
 /* Used to memset ovs_key_ipv4_tunnel padding. */
 #define OVS_TUNNEL_KEY_SIZE					\
-	(offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) +	\
-	FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl))
+	(offsetof(struct ovs_key_ipv4_tunnel, tp_dst) +		\
+	 FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst))
 
 struct ovs_key_ipv4_tunnel {
 	__be64 tun_id;
@@ -47,11 +47,13 @@ struct ovs_key_ipv4_tunnel {
 	__be16 tun_flags;
 	u8   ipv4_tos;
 	u8   ipv4_ttl;
+	__be16 tp_src;
+	__be16 tp_dst;
 } __packed __aligned(4); /* Minimize padding. */
 
 struct ovs_tunnel_info {
 	struct ovs_key_ipv4_tunnel tunnel;
-	struct geneve_opt *options;
+	const struct geneve_opt *options;
 	u8 options_len;
 };
 
@@ -64,27 +66,59 @@ struct ovs_tunnel_info {
 			       FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
 			       opt_len))
 
-static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
-					  const struct iphdr *iph,
-					  __be64 tun_id, __be16 tun_flags,
-					  struct geneve_opt *opts,
-					  u8 opts_len)
+static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					    __be32 saddr, __be32 daddr,
+					    u8 tos, u8 ttl,
+					    __be16 tp_src,
+					    __be16 tp_dst,
+					    __be64 tun_id,
+					    __be16 tun_flags,
+					    const struct geneve_opt *opts,
+					    u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
-	tun_info->tunnel.ipv4_src = iph->saddr;
-	tun_info->tunnel.ipv4_dst = iph->daddr;
-	tun_info->tunnel.ipv4_tos = iph->tos;
-	tun_info->tunnel.ipv4_ttl = iph->ttl;
+	tun_info->tunnel.ipv4_src = saddr;
+	tun_info->tunnel.ipv4_dst = daddr;
+	tun_info->tunnel.ipv4_tos = tos;
+	tun_info->tunnel.ipv4_ttl = ttl;
 	tun_info->tunnel.tun_flags = tun_flags;
 
-	/* clear struct padding. */
-	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
-	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+	 * the upper tunnel are used.
+	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+	 */
+	tun_info->tunnel.tp_src = tp_src;
+	tun_info->tunnel.tp_dst = tp_dst;
+
+	/* Clear struct padding. */
+	if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE)
+		memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE,
+		       0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
 
 	tun_info->options = opts;
 	tun_info->options_len = opts_len;
 }
 
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					  const struct iphdr *iph,
+					  __be16 tp_src,
+					  __be16 tp_dst,
+					  __be64 tun_id,
+					  __be16 tun_flags,
+					  const struct geneve_opt *opts,
+					  u8 opts_len)
+{
+	__ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr,
+				 iph->tos, iph->ttl,
+				 tp_src, tp_dst,
+				 tun_id, tun_flags,
+				 opts, opts_len);
+}
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
+	(offsetof(struct sw_flow_key, recirc_id) +	\
+	FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
 struct sw_flow_key {
 	u8 tun_opts[255];
 	u8 tun_opts_len;
@@ -210,18 +244,19 @@ struct arp_eth_header {
 } __packed;
 
 void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
-			   struct sk_buff *);
+			   const struct sk_buff *);
 void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
 			unsigned long *used, __be16 *tcp_flags);
 void ovs_flow_stats_clear(struct sw_flow *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
-int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb,
+int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
+			 struct sk_buff *skb,
 			 struct sw_flow_key *key);
 /* Extract key from packet coming from userspace. */
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key);
+				   struct sw_flow_key *key, bool log);
 
 #endif /* flow.h */

net/openvswitch/flow_netlink.h

@@ -37,6 +37,7 @@
 
 #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,
@@ -44,15 +45,17 @@ void ovs_match_init(struct sw_flow_match *match,
 
 int ovs_nla_put_flow(const struct sw_flow_key *,
 		     const struct sw_flow_key *, struct sk_buff *);
-int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
+int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *,
+			      bool log);
 
-int ovs_nla_get_match(struct sw_flow_match *match,
-		      const struct nlattr *,
-		      const struct nlattr *);
+int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
+		      const struct nlattr *mask, bool log);
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
+				  const struct ovs_tunnel_info *);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
-			 struct sw_flow_actions **sfa);
+			 struct sw_flow_actions **sfa, bool log);
 int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
 

net/openvswitch/flow_table.c

@@ -107,7 +107,7 @@ struct sw_flow *ovs_flow_alloc(void)
 	return ERR_PTR(-ENOMEM);
 }
 
-int ovs_flow_tbl_count(struct flow_table *table)
+int ovs_flow_tbl_count(const struct flow_table *table)
 {
 	return table->count;
 }
@@ -401,7 +401,7 @@ static bool flow_cmp_masked_key(const struct sw_flow *flow,
 }
 
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-			       struct sw_flow_match *match)
+			       const struct sw_flow_match *match)
 {
 	struct sw_flow_key *key = match->key;
 	int key_start = flow_key_start(key);
@@ -412,7 +412,7 @@ bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 
 static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 					  const struct sw_flow_key *unmasked,
-					  struct sw_flow_mask *mask)
+					  const struct sw_flow_mask *mask)
 {
 	struct sw_flow *flow;
 	struct hlist_head *head;
@@ -460,7 +460,7 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 }
 
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
-					  struct sw_flow_match *match)
+					  const struct sw_flow_match *match)
 {
 	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
 	struct sw_flow_mask *mask;
@@ -563,7 +563,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
 
 /* Add 'mask' into the mask list, if it is not already there. */
 static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
-			    struct sw_flow_mask *new)
+			    const struct sw_flow_mask *new)
 {
 	struct sw_flow_mask *mask;
 	mask = flow_mask_find(tbl, new);
@@ -586,7 +586,7 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 
 /* Must be called with OVS mutex held. */
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
-			struct sw_flow_mask *mask)
+			const struct sw_flow_mask *mask)
 {
 	struct table_instance *new_ti = NULL;
 	struct table_instance *ti;

net/openvswitch/flow_table.h

@@ -61,12 +61,12 @@ struct sw_flow *ovs_flow_alloc(void);
 void ovs_flow_free(struct sw_flow *, bool deferred);
 
 int ovs_flow_tbl_init(struct flow_table *);
-int ovs_flow_tbl_count(struct flow_table *table);
+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,
-			struct sw_flow_mask *mask);
+			const struct sw_flow_mask *mask);
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
 int  ovs_flow_tbl_num_masks(const struct flow_table *table);
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
@@ -77,9 +77,9 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
 struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
 				    const struct sw_flow_key *);
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
-					  struct sw_flow_match *match);
+					  const struct sw_flow_match *match);
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-			       struct sw_flow_match *match);
+			       const struct sw_flow_match *match);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		       const struct sw_flow_mask *mask);

net/openvswitch/vport-geneve.c

@@ -68,7 +68,7 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
 }
 
 /* Convert 24 bit VNI to 64 bit tunnel ID. */
-static __be64 vni_to_tunnel_id(__u8 *vni)
+static __be64 vni_to_tunnel_id(const __u8 *vni)
 {
 #ifdef __BIG_ENDIAN
 	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
@@ -97,7 +97,9 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 
 	key = vni_to_tunnel_id(geneveh->vni);
 
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb),
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, flags,
 			       geneveh->options, opts_len);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -228,6 +230,22 @@ static const char *geneve_get_name(const struct vport *vport)
 	return geneve_port->name;
 }
 
+static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				      struct ovs_tunnel_info *egress_tun_info)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	struct net *net = ovs_dp_get_net(vport->dp);
+	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+	__be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+
+	/* Get tp_src and tp_dst, refert to geneve_build_header().
+	 */
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark, sport, dport);
+}
+
 static struct vport_ops ovs_geneve_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GENEVE,
 	.create		= geneve_tnl_create,
@@ -236,6 +254,7 @@ static struct vport_ops ovs_geneve_vport_ops = {
 	.get_options	= geneve_get_options,
 	.send		= geneve_tnl_send,
 	.owner          = THIS_MODULE,
+	.get_egress_tun_info	= geneve_get_egress_tun_info,
 };
 
 static int __init ovs_geneve_tnl_init(void)

net/openvswitch/vport-gre.c

@@ -108,7 +108,7 @@ static int gre_rcv(struct sk_buff *skb,
 		return PACKET_REJECT;
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
 			       filter_tnl_flags(tpi->flags), NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -284,12 +284,22 @@ static void gre_tnl_destroy(struct vport *vport)
 	gre_exit();
 }
 
+static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				   struct ovs_tunnel_info *egress_tun_info)
+{
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_GRE, skb->mark, 0, 0);
+}
+
 static struct vport_ops ovs_gre_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GRE,
 	.create		= gre_create,
 	.destroy	= gre_tnl_destroy,
 	.get_name	= gre_get_name,
 	.send		= gre_tnl_send,
+	.get_egress_tun_info	= gre_get_egress_tun_info,
 	.owner		= THIS_MODULE,
 };
 

net/openvswitch/vport-netdev.c

@@ -77,7 +77,7 @@ static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
 	return RX_HANDLER_CONSUMED;
 }
 
-static struct net_device *get_dpdev(struct datapath *dp)
+static struct net_device *get_dpdev(const struct datapath *dp)
 {
 	struct vport *local;
 

net/openvswitch/vport-vxlan.c

@@ -69,7 +69,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(vx_vni) >> 8);
-	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
+	ovs_flow_tun_info_init(&tun_info, iph,
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, TUNNEL_KEY, NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }
@@ -189,6 +191,25 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	return err;
 }
 
+static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				     struct ovs_tunnel_info *egress_tun_info)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+	__be16 src_port;
+	int port_min;
+	int port_max;
+
+	inet_get_local_port_range(net, &port_min, &port_max);
+	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+	return ovs_tunnel_get_egress_info(egress_tun_info, net,
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark,
+					  src_port, dst_port);
+}
+
 static const char *vxlan_get_name(const struct vport *vport)
 {
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
@@ -202,6 +223,7 @@ static struct vport_ops ovs_vxlan_vport_ops = {
 	.get_name	= vxlan_get_name,
 	.get_options	= vxlan_get_options,
 	.send		= vxlan_tnl_send,
+	.get_egress_tun_info	= vxlan_get_egress_tun_info,
 	.owner		= THIS_MODULE,
 };
 

net/openvswitch/vport.c

@@ -68,7 +68,7 @@ void ovs_vport_exit(void)
 	kfree(dev_table);
 }
 
-static struct hlist_head *hash_bucket(struct net *net, const char *name)
+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)];
@@ -90,7 +90,7 @@ int ovs_vport_ops_register(struct vport_ops *ops)
 	ovs_unlock();
 	return err;
 }
-EXPORT_SYMBOL(ovs_vport_ops_register);
+EXPORT_SYMBOL_GPL(ovs_vport_ops_register);
 
 void ovs_vport_ops_unregister(struct vport_ops *ops)
 {
@@ -98,7 +98,7 @@ void ovs_vport_ops_unregister(struct vport_ops *ops)
 	list_del(&ops->list);
 	ovs_unlock();
 }
-EXPORT_SYMBOL(ovs_vport_ops_unregister);
+EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
 
 /**
  *	ovs_vport_locate - find a port that has already been created
@@ -107,7 +107,7 @@ EXPORT_SYMBOL(ovs_vport_ops_unregister);
  *
  * Must be called with ovs or RCU read lock.
  */
-struct vport *ovs_vport_locate(struct net *net, const char *name)
+struct vport *ovs_vport_locate(const struct net *net, const char *name)
 {
 	struct hlist_head *bucket = hash_bucket(net, name);
 	struct vport *vport;
@@ -165,7 +165,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 
 	return vport;
 }
-EXPORT_SYMBOL(ovs_vport_alloc);
+EXPORT_SYMBOL_GPL(ovs_vport_alloc);
 
 /**
  *	ovs_vport_free - uninitialize and free vport
@@ -186,7 +186,7 @@ void ovs_vport_free(struct vport *vport)
 	free_percpu(vport->percpu_stats);
 	kfree(vport);
 }
-EXPORT_SYMBOL(ovs_vport_free);
+EXPORT_SYMBOL_GPL(ovs_vport_free);
 
 static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
 {
@@ -380,7 +380,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
  *
  * Must be called with ovs_mutex.
  */
-int ovs_vport_set_upcall_portids(struct vport *vport,  struct nlattr *ids)
+int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
 {
 	struct vport_portids *old, *vport_portids;
 
@@ -471,7 +471,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       struct ovs_tunnel_info *tun_info)
+		       const struct ovs_tunnel_info *tun_info)
 {
 	struct pcpu_sw_netstats *stats;
 	struct sw_flow_key key;
@@ -493,7 +493,7 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	}
 	ovs_dp_process_packet(skb, &key);
 }
-EXPORT_SYMBOL(ovs_vport_receive);
+EXPORT_SYMBOL_GPL(ovs_vport_receive);
 
 /**
  *	ovs_vport_send - send a packet on a device
@@ -572,4 +572,65 @@ void ovs_vport_deferred_free(struct vport *vport)
 
 	call_rcu(&vport->rcu, free_vport_rcu);
 }
-EXPORT_SYMBOL(ovs_vport_deferred_free);
+EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
+
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst)
+{
+	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct rtable *rt;
+	struct flowi4 fl;
+
+	if (unlikely(!tun_info))
+		return -EINVAL;
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup to get srouce IP address.
+	 * The process may need to be changed if the corresponding process
+	 * in vports ops changed.
+	 */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb_mark;
+	fl.flowi4_proto = IPPROTO_GRE;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	ip_rt_put(rt);
+
+	/* Generate egress_tun_info based on tun_info,
+	 * saddr, tp_src and tp_dst
+	 */
+	__ovs_flow_tun_info_init(egress_tun_info,
+				 fl.saddr, tun_key->ipv4_dst,
+				 tun_key->ipv4_tos,
+				 tun_key->ipv4_ttl,
+				 tp_src, tp_dst,
+				 tun_key->tun_id,
+				 tun_key->tun_flags,
+				 tun_info->options,
+				 tun_info->options_len);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
+
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info)
+{
+	/* get_egress_tun_info() is only implemented on tunnel ports. */
+	if (unlikely(!vport->ops->get_egress_tun_info))
+		return -EINVAL;
+
+	return vport->ops->get_egress_tun_info(vport, skb, info);
+}

net/openvswitch/vport.h

@@ -45,19 +45,29 @@ void ovs_vport_exit(void);
 struct vport *ovs_vport_add(const struct vport_parms *);
 void ovs_vport_del(struct vport *);
 
-struct vport *ovs_vport_locate(struct net *net, const char *name);
+struct vport *ovs_vport_locate(const struct net *net, const char *name);
 
 void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
 
 int ovs_vport_set_options(struct vport *, struct nlattr *options);
 int ovs_vport_get_options(const struct vport *, struct sk_buff *);
 
-int ovs_vport_set_upcall_portids(struct vport *, struct nlattr *pids);
+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 *);
 
 int ovs_vport_send(struct vport *, struct sk_buff *);
 
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst);
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info);
+
 /* The following definitions are for implementers of vport devices: */
 
 struct vport_err_stats {
@@ -146,6 +156,8 @@ struct vport_parms {
  * @get_name: Get the device's name.
  * @send: Send a packet on the device.  Returns the length of the packet sent,
  * zero for dropped packets or negative for error.
+ * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for
+ * a packet.
  */
 struct vport_ops {
 	enum ovs_vport_type type;
@@ -161,6 +173,8 @@ struct vport_ops {
 	const char *(*get_name)(const struct vport *);
 
 	int (*send)(struct vport *, struct sk_buff *);
+	int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
+				   struct ovs_tunnel_info *);
 
 	struct module *owner;
 	struct list_head list;
@@ -210,7 +224,7 @@ static inline struct vport *vport_from_priv(void *priv)
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
-		       struct ovs_tunnel_info *);
+		       const struct ovs_tunnel_info *);
 
 static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
 				      const void *start, unsigned int len)