1 files changed, 366 insertions, 304 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e47ebbbe71b8..792ca44a461d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2007-2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -22,7 +9,6 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/openvswitch.h>
-#include <linux/netfilter_ipv6.h>
 #include <linux/sctp.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
@@ -31,70 +17,38 @@
 #include <linux/if_vlan.h>
 
 #include <net/dst.h>
+#include <net/gso.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
 #include <net/mpls.h>
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+#include <net/psample.h>
+#endif
+
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
+#include "drop.h"
 #include "flow.h"
 #include "conntrack.h"
 #include "vport.h"
 #include "flow_netlink.h"
+#include "openvswitch_trace.h"
 
-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 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];
-};
-
-static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
-
-#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];
-};
-
-static struct action_fifo __percpu *action_fifos;
-static struct action_flow_keys __percpu *flow_keys;
-static DEFINE_PER_CPU(int, exec_actions_level);
+struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
 
 /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
  * space. Return NULL if out of key spaces.
  */
 static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
 {
-	struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
-	int level = this_cpu_read(exec_actions_level);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
+	struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
+	int level = ovs_pcpu->exec_level;
 	struct sw_flow_key *key = NULL;
 
 	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
@@ -138,10 +92,9 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 				    const struct nlattr *actions,
 				    const int actions_len)
 {
-	struct action_fifo *fifo;
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 	struct deferred_action *da;
 
-	fifo = this_cpu_ptr(action_fifos);
 	da = action_fifo_put(fifo);
 	if (da) {
 		da->skb = skb;
@@ -169,50 +122,21 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 			 const struct nlattr *actions, int len,
 			 bool last, bool clone_flow_key);
 
-static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
-			     __be16 ethertype)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be16 diff[] = { ~(hdr->h_proto), ethertype };
-
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					~skb->csum);
-	}
-
-	hdr->h_proto = ethertype;
-}
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			      struct sw_flow_key *key,
+			      const struct nlattr *attr, int len);
 
 static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
-		     const struct ovs_action_push_mpls *mpls)
+		     __be32 mpls_lse, __be16 mpls_ethertype, __u16 mac_len)
 {
-	struct mpls_shim_hdr *new_mpls_lse;
-
-	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
-	if (skb->encapsulation)
-		return -ENOTSUPP;
-
-	if (skb_cow_head(skb, MPLS_HLEN) < 0)
-		return -ENOMEM;
-
-	if (!skb->inner_protocol) {
-		skb_set_inner_network_header(skb, skb->mac_len);
-		skb_set_inner_protocol(skb, skb->protocol);
-	}
-
-	skb_push(skb, MPLS_HLEN);
-	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
-	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
-
-	new_mpls_lse = mpls_hdr(skb);
-	new_mpls_lse->label_stack_entry = mpls->mpls_lse;
+	int err;
 
-	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
+	err = skb_mpls_push(skb, mpls_lse, mpls_ethertype, mac_len, !!mac_len);
+	if (err)
+		return err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
-		update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
-	skb->protocol = mpls->mpls_ethertype;
+	if (!mac_len)
+		key->mac_proto = MAC_PROTO_NONE;
 
 	invalidate_flow_key(key);
 	return 0;
@@ -223,30 +147,13 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
-	if (unlikely(err))
+	err = skb_mpls_pop(skb, ethertype, skb->mac_len,
+			   ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
+	if (err)
 		return err;
 
-	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
-
-	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
-
-	__skb_pull(skb, MPLS_HLEN);
-	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
-
-	if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
-		struct ethhdr *hdr;
-
-		/* mpls_hdr() is used to locate the ethertype field correctly in the
-		 * presence of VLAN tags.
-		 */
-		hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
-		update_ethertype(skb, hdr, ethertype);
-	}
-	if (eth_p_mpls(skb->protocol))
-		skb->protocol = ethertype;
+	if (ethertype == htons(ETH_P_TEB))
+		key->mac_proto = MAC_PROTO_ETHERNET;
 
 	invalidate_flow_key(key);
 	return 0;
@@ -259,21 +166,16 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	__be32 lse;
 	int err;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
-	if (unlikely(err))
-		return err;
+	if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+		return -ENOMEM;
 
 	stack = mpls_hdr(skb);
 	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be32 diff[] = { ~(stack->label_stack_entry), lse };
-
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					  ~skb->csum);
-	}
+	err = skb_mpls_update_lse(skb, lse);
+	if (err)
+		return err;
 
-	stack->label_stack_entry = lse;
-	flow_key->mpls.top_lse = lse;
+	flow_key->mpls.lse[0] = lse;
 	return 0;
 }
 
@@ -294,14 +196,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_vlan *vlan)
 {
+	int err;
+
 	if (skb_vlan_tag_present(skb)) {
 		invalidate_flow_key(key);
 	} else {
 		key->eth.vlan.tci = vlan->vlan_tci;
 		key->eth.vlan.tpid = vlan->vlan_tpid;
 	}
-	return skb_vlan_push(skb, vlan->vlan_tpid,
-			     ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
+	err = skb_vlan_push(skb, vlan->vlan_tpid,
+			    ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
+	skb_reset_mac_len(skb);
+	return err;
 }
 
 /* 'src' is already properly masked. */
@@ -345,9 +251,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -358,22 +266,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
@@ -381,11 +279,18 @@ static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 	return 0;
 }
 
-static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
-		    const struct nshhdr *nh)
+static noinline_for_stack int push_nsh(struct sk_buff *skb,
+				       struct sw_flow_key *key,
+				       const struct nlattr *a)
 {
+	u8 buffer[NSH_HDR_MAX_LEN];
+	struct nshhdr *nh = (struct nshhdr *)buffer;
 	int err;
 
+	err = nsh_hdr_from_nlattr(a, nh, NSH_HDR_MAX_LEN);
+	if (err)
+		return err;
+
 	err = nsh_push(skb, nh);
 	if (err)
 		return err;
@@ -445,6 +350,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
 	update_ip_l4_checksum(skb, nh, *addr, new_addr);
 	csum_replace4(&nh->check, *addr, new_addr);
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
 	*addr = new_addr;
 }
 
@@ -492,15 +398,47 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 		update_ipv6_checksum(skb, l4_proto, addr, new_addr);
 
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
+static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask)
+{
+	u8 old_ipv6_tclass = ipv6_get_dsfield(nh);
+
+	ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12),
+			     (__force __wsum)(ipv6_tclass << 12));
+
+	ipv6_change_dsfield(nh, ~mask, ipv6_tclass);
+}
+
+static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask)
 {
+	u32 ofl;
+
+	ofl = nh->flow_lbl[0] << 16 |  nh->flow_lbl[1] << 8 |  nh->flow_lbl[2];
+	fl = OVS_MASKED(ofl, fl, mask);
+
 	/* Bits 21-24 are always unmasked, so this retains their values. */
-	OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
-	OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
-	OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
+	nh->flow_lbl[0] = (u8)(fl >> 16);
+	nh->flow_lbl[1] = (u8)(fl >> 8);
+	nh->flow_lbl[2] = (u8)fl;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl));
+}
+
+static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask)
+{
+	new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8),
+			     (__force __wsum)(new_ttl << 8));
+	nh->hop_limit = new_ttl;
 }
 
 static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
@@ -618,90 +556,27 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		}
 	}
 	if (mask->ipv6_tclass) {
-		ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+		set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass);
 		flow_key->ip.tos = ipv6_get_dsfield(nh);
 	}
 	if (mask->ipv6_label) {
-		set_ipv6_fl(nh, ntohl(key->ipv6_label),
+		set_ipv6_fl(skb, nh, ntohl(key->ipv6_label),
 			    ntohl(mask->ipv6_label));
 		flow_key->ipv6.label =
 		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
 	}
 	if (mask->ipv6_hlimit) {
-		OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
-			       mask->ipv6_hlimit);
+		set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit);
 		flow_key->ip.ttl = nh->hop_limit;
 	}
 	return 0;
 }
 
-static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
-		   const struct nlattr *a)
-{
-	struct nshhdr *nh;
-	size_t length;
-	int err;
-	u8 flags;
-	u8 ttl;
-	int i;
-
-	struct ovs_key_nsh key;
-	struct ovs_key_nsh mask;
-
-	err = nsh_key_from_nlattr(a, &key, &mask);
-	if (err)
-		return err;
-
-	/* Make sure the NSH base header is there */
-	if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
-		return -ENOMEM;
-
-	nh = nsh_hdr(skb);
-	length = nsh_hdr_len(nh);
-
-	/* Make sure the whole NSH header is there */
-	err = skb_ensure_writable(skb, skb_network_offset(skb) +
-				       length);
-	if (unlikely(err))
-		return err;
-
-	nh = nsh_hdr(skb);
-	skb_postpull_rcsum(skb, nh, length);
-	flags = nsh_get_flags(nh);
-	flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
-	flow_key->nsh.base.flags = flags;
-	ttl = nsh_get_ttl(nh);
-	ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
-	flow_key->nsh.base.ttl = ttl;
-	nsh_set_flags_and_ttl(nh, flags, ttl);
-	nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
-				  mask.base.path_hdr);
-	flow_key->nsh.base.path_hdr = nh->path_hdr;
-	switch (nh->mdtype) {
-	case NSH_M_TYPE1:
-		for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
-			nh->md1.context[i] =
-			    OVS_MASKED(nh->md1.context[i], key.context[i],
-				       mask.context[i]);
-		}
-		memcpy(flow_key->nsh.context, nh->md1.context,
-		       sizeof(nh->md1.context));
-		break;
-	case NSH_M_TYPE2:
-		memset(flow_key->nsh.context, 0,
-		       sizeof(flow_key->nsh.context));
-		break;
-	default:
-		return -EINVAL;
-	}
-	skb_postpush_rcsum(skb, nh, length);
-	return 0;
-}
-
 /* Must follow skb_ensure_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
 			__be16 new_port, __sum16 *check)
 {
+	ovs_ct_clear(skb, NULL);
 	inet_proto_csum_replace2(check, skb, *port, new_port, false);
 	*port = new_port;
 }
@@ -741,6 +616,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		uh->dest = dst;
 		flow_key->tp.src = src;
 		flow_key->tp.dst = dst;
+		ovs_ct_clear(skb, NULL);
 	}
 
 	skb_clear_hash(skb);
@@ -803,19 +679,22 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
+
 	flow_key->tp.src = sh->source;
 	flow_key->tp.dst = sh->dest;
 
 	return 0;
 }
 
-static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
 {
-	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
+	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	struct vport *vport = data->vport;
 
 	if (skb_cow_head(skb, data->l2_len) < 0) {
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM);
 		return -ENOMEM;
 	}
 
@@ -863,7 +742,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
 	unsigned int hlen = skb_network_offset(skb);
 	struct ovs_frag_data *data;
 
-	data = this_cpu_ptr(&ovs_frag_data_storage);
+	data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	data->dst = skb->_skb_refdst;
 	data->vport = vport;
 	data->cb = *OVS_CB(skb);
@@ -886,6 +765,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 			 struct sk_buff *skb, u16 mru,
 			 struct sw_flow_key *key)
 {
+	enum ovs_drop_reason reason;
 	u16 orig_network_offset = 0;
 
 	if (eth_p_mpls(skb->protocol)) {
@@ -895,37 +775,34 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 
 	if (skb_network_offset(skb) > MAX_L2_LEN) {
 		OVS_NLERR(1, "L2 header too long to fragment");
+		reason = OVS_DROP_FRAG_L2_TOO_LONG;
 		goto err;
 	}
 
 	if (key->eth.type == htons(ETH_P_IP)) {
-		struct dst_entry ovs_dst;
+		struct rtable ovs_rt = { 0 };
 		unsigned long orig_dst;
 
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
-		dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
+		dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
 			 DST_OBSOLETE_NONE, DST_NOCOUNT);
-		ovs_dst.dev = vport->dev;
+		ovs_rt.dst.dev = vport->dev;
 
 		orig_dst = skb->_skb_refdst;
-		skb_dst_set_noref(skb, &ovs_dst);
+		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IPCB(skb)->frag_max_size = mru;
 
 		ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
-		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 		unsigned long orig_dst;
 		struct rt6_info ovs_rt;
 
-		if (!v6ops)
-			goto err;
-
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
 		memset(&ovs_rt, 0, sizeof(ovs_rt));
-		dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+		dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
 			 DST_OBSOLETE_NONE, DST_NOCOUNT);
 		ovs_rt.dst.dev = vport->dev;
 
@@ -933,18 +810,19 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IP6CB(skb)->frag_max_size = mru;
 
-		v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
+		ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else {
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
 			  ovs_vport_name(vport), ntohs(key->eth.type), mru,
 			  vport->dev->mtu);
+		reason = OVS_DROP_FRAG_INVALID_PROTO;
 		goto err;
 	}
 
 	return;
 err:
-	kfree_skb(skb);
+	ovs_kfree_skb_reason(skb, reason);
 }
 
 static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
@@ -952,7 +830,9 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 {
 	struct vport *vport = ovs_vport_rcu(dp, out_port);
 
-	if (likely(vport)) {
+	if (likely(vport &&
+		   netif_running(vport->dev) &&
+		   netif_carrier_ok(vport->dev))) {
 		u16 mru = OVS_CB(skb)->mru;
 		u32 cutlen = OVS_CB(skb)->cutlen;
 
@@ -971,10 +851,10 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 			ovs_fragment(net, vport, skb, mru, key);
 		} else {
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
 		}
 	} else {
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY);
 	}
 }
 
@@ -991,15 +871,22 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	upcall.cmd = OVS_PACKET_CMD_ACTION;
 	upcall.mru = OVS_CB(skb)->mru;
 
-	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-		 a = nla_next(a, &rem)) {
+	nla_for_each_nested(a, attr, rem) {
 		switch (nla_type(a)) {
 		case OVS_USERSPACE_ATTR_USERDATA:
 			upcall.userdata = a;
 			break;
 
 		case OVS_USERSPACE_ATTR_PID:
-			upcall.portid = nla_get_u32(a);
+			if (OVS_CB(skb)->upcall_pid)
+				upcall.portid = OVS_CB(skb)->upcall_pid;
+			else if (dp->user_features &
+				 OVS_DP_F_DISPATCH_UPCALL_PER_CPU)
+				upcall.portid =
+				  ovs_dp_get_upcall_portid(dp,
+							   smp_processor_id());
+			else
+				upcall.portid = nla_get_u32(a);
 			break;
 
 		case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
@@ -1031,6 +918,21 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
+static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
+				     struct sw_flow_key *key,
+				     const struct nlattr *attr)
+{
+	/* The first attribute is always 'OVS_DEC_TTL_ATTR_ACTION'. */
+	struct nlattr *actions = nla_data(attr);
+
+	if (nla_len(actions))
+		return clone_execute(dp, skb, key, 0, nla_data(actions),
+				     nla_len(actions), true, false);
+
+	ovs_kfree_skb_reason(skb, OVS_DROP_IP_TTL);
+	return 0;
+}
+
 /* When 'last' is true, sample() should always consume the 'skb'.
  * Otherwise, sample() should keep 'skb' intact regardless what
  * actions are executed within sample().
@@ -1043,23 +945,33 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	struct nlattr *sample_arg;
 	int rem = nla_len(attr);
 	const struct sample_arg *arg;
+	u32 init_probability;
 	bool clone_flow_key;
+	int err;
 
 	/* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
 	sample_arg = nla_data(attr);
 	arg = nla_data(sample_arg);
 	actions = nla_next(sample_arg, &rem);
+	init_probability = OVS_CB(skb)->probability;
 
 	if ((arg->probability != U32_MAX) &&
-	    (!arg->probability || prandom_u32() > arg->probability)) {
+	    (!arg->probability || get_random_u32() > arg->probability)) {
 		if (last)
-			consume_skb(skb);
+			ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
 		return 0;
 	}
 
+	OVS_CB(skb)->probability = arg->probability;
+
 	clone_flow_key = !arg->exec;
-	return clone_execute(dp, skb, key, 0, actions, rem, last,
-			     clone_flow_key);
+	err = clone_execute(dp, skb, key, 0, actions, rem, last,
+			    clone_flow_key);
+
+	if (!last)
+		OVS_CB(skb)->probability = init_probability;
+
+	return err;
 }
 
 /* When 'last' is true, clone() should always consume the 'skb'.
@@ -1075,7 +987,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
 	int rem = nla_len(attr);
 	bool dont_clone_flow_key;
 
-	/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+	/* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
 	clone_arg = nla_data(attr);
 	dont_clone_flow_key = nla_get_u32(clone_arg);
 	actions = nla_next(clone_arg, &rem);
@@ -1090,8 +1002,16 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
 	struct ovs_action_hash *hash_act = nla_data(attr);
 	u32 hash = 0;
 
-	/* OVS_HASH_ALG_L4 is the only possible hash algorithm.  */
-	hash = skb_get_hash(skb);
+	if (hash_act->hash_alg == OVS_HASH_ALG_L4) {
+		/* OVS_HASH_ALG_L4 hasing type. */
+		hash = skb_get_hash(skb);
+	} else if (hash_act->hash_alg == OVS_HASH_ALG_SYM_L4) {
+		/* OVS_HASH_ALG_SYM_L4 hashing type.  NOTE: this doesn't
+		 * extend past an encapsulated header.
+		 */
+		hash = __skb_get_hash_symmetric(skb);
+	}
+
 	hash = jhash_1word(hash, hash_act->hash_basis);
 	if (!hash)
 		hash = 0x1;
@@ -1147,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb,
 				   get_mask(a, struct ovs_key_ethernet *));
 		break;
 
-	case OVS_KEY_ATTR_NSH:
-		err = set_nsh(skb, flow_key, a);
-		break;
-
 	case OVS_KEY_ATTR_IPV4:
 		err = set_ipv4(skb, flow_key, nla_data(a),
 			       get_mask(a, struct ovs_key_ipv4 *));
@@ -1187,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb,
 	case OVS_KEY_ATTR_CT_LABELS:
 	case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4:
 	case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6:
+	case OVS_KEY_ATTR_NSH:
 		err = -EINVAL;
 		break;
 	}
@@ -1213,6 +1130,122 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 	return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
 }
 
+static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
+				 struct sw_flow_key *key,
+				 const struct nlattr *attr, bool last)
+{
+	struct ovs_skb_cb *ovs_cb = OVS_CB(skb);
+	const struct nlattr *actions, *cpl_arg;
+	int len, max_len, rem = nla_len(attr);
+	const struct check_pkt_len_arg *arg;
+	bool clone_flow_key;
+
+	/* The first netlink attribute in 'attr' is always
+	 * 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
+	 */
+	cpl_arg = nla_data(attr);
+	arg = nla_data(cpl_arg);
+
+	len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len;
+	max_len = arg->pkt_len;
+
+	if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) ||
+	    len <= max_len) {
+		/* Second netlink attribute in 'attr' is always
+		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
+		 */
+		actions = nla_next(cpl_arg, &rem);
+		clone_flow_key = !arg->exec_for_lesser_equal;
+	} else {
+		/* Third netlink attribute in 'attr' is always
+		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER'.
+		 */
+		actions = nla_next(cpl_arg, &rem);
+		actions = nla_next(actions, &rem);
+		clone_flow_key = !arg->exec_for_greater;
+	}
+
+	return clone_execute(dp, skb, key, 0, nla_data(actions),
+			     nla_len(actions), last, clone_flow_key);
+}
+
+static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int err;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *nh;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ipv6_hdr(skb);
+
+		if (nh->hop_limit <= 1)
+			return -EHOSTUNREACH;
+
+		key->ip.ttl = --nh->hop_limit;
+	} else if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *nh;
+		u8 old_ttl;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ip_hdr(skb);
+		if (nh->ttl <= 1)
+			return -EHOSTUNREACH;
+
+		old_ttl = nh->ttl--;
+		csum_replace2(&nh->check, htons(old_ttl << 8),
+			      htons(nh->ttl << 8));
+		key->ip.ttl = nh->ttl;
+	}
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{
+	struct psample_group psample_group = {};
+	struct psample_metadata md = {};
+	const struct nlattr *a;
+	u32 rate;
+	int rem;
+
+	nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) {
+		switch (nla_type(a)) {
+		case OVS_PSAMPLE_ATTR_GROUP:
+			psample_group.group_num = nla_get_u32(a);
+			break;
+
+		case OVS_PSAMPLE_ATTR_COOKIE:
+			md.user_cookie = nla_data(a);
+			md.user_cookie_len = nla_len(a);
+			break;
+		}
+	}
+
+	psample_group.net = ovs_dp_get_net(dp);
+	md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex;
+	md.trunc_size = skb->len - OVS_CB(skb)->cutlen;
+	md.rate_as_probability = 1;
+
+	rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX;
+
+	psample_sample_packet(&psample_group, skb, rate, &md);
+}
+#else
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{}
+#endif
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -1225,6 +1258,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	     a = nla_next(a, &rem)) {
 		int err = 0;
 
+		if (trace_ovs_do_execute_action_enabled())
+			trace_ovs_do_execute_action(dp, skb, key, a, rem);
+
+		/* Actions that rightfully have to consume the skb should do it
+		 * and return directly.
+		 */
 		switch (nla_type(a)) {
 		case OVS_ACTION_ATTR_OUTPUT: {
 			int port = nla_get_u32(a);
@@ -1260,16 +1299,34 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			output_userspace(dp, skb, key, a, attr,
 						     len, OVS_CB(skb)->cutlen);
 			OVS_CB(skb)->cutlen = 0;
+			if (nla_is_last(a, rem)) {
+				consume_skb(skb);
+				return 0;
+			}
 			break;
 
 		case OVS_ACTION_ATTR_HASH:
 			execute_hash(skb, key, a);
 			break;
 
-		case OVS_ACTION_ATTR_PUSH_MPLS:
-			err = push_mpls(skb, key, nla_data(a));
+		case OVS_ACTION_ATTR_PUSH_MPLS: {
+			struct ovs_action_push_mpls *mpls = nla_data(a);
+
+			err = push_mpls(skb, key, mpls->mpls_lse,
+					mpls->mpls_ethertype, skb->mac_len);
 			break;
+		}
+		case OVS_ACTION_ATTR_ADD_MPLS: {
+			struct ovs_action_add_mpls *mpls = nla_data(a);
+			__u16 mac_len = 0;
+
+			if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK)
+				mac_len = skb->mac_len;
 
+			err = push_mpls(skb, key, mpls->mpls_lse,
+					mpls->mpls_ethertype, mac_len);
+			break;
+		}
 		case OVS_ACTION_ATTR_POP_MPLS:
 			err = pop_mpls(skb, key, nla_get_be16(a));
 			break;
@@ -1342,17 +1399,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = pop_eth(skb, key);
 			break;
 
-		case OVS_ACTION_ATTR_PUSH_NSH: {
-			u8 buffer[NSH_HDR_MAX_LEN];
-			struct nshhdr *nh = (struct nshhdr *)buffer;
-
-			err = nsh_hdr_from_nlattr(nla_data(a), nh,
-						  NSH_HDR_MAX_LEN);
-			if (unlikely(err))
-				break;
-			err = push_nsh(skb, key, nh);
+		case OVS_ACTION_ATTR_PUSH_NSH:
+			err = push_nsh(skb, key, nla_data(a));
 			break;
-		}
 
 		case OVS_ACTION_ATTR_POP_NSH:
 			err = pop_nsh(skb, key);
@@ -1360,7 +1409,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_METER:
 			if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) {
-				consume_skb(skb);
+				ovs_kfree_skb_reason(skb, OVS_DROP_METER);
 				return 0;
 			}
 			break;
@@ -1374,15 +1423,50 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 			break;
 		}
+
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
+			bool last = nla_is_last(a, rem);
+
+			err = execute_check_pkt_len(dp, skb, key, a, last);
+			if (last)
+				return err;
+
+			break;
+		}
+
+		case OVS_ACTION_ATTR_DEC_TTL:
+			err = execute_dec_ttl(skb, key);
+			if (err == -EHOSTUNREACH)
+				return dec_ttl_exception_handler(dp, skb,
+								 key, a);
+			break;
+
+		case OVS_ACTION_ATTR_DROP: {
+			enum ovs_drop_reason reason = nla_get_u32(a)
+				? OVS_DROP_EXPLICIT_WITH_ERROR
+				: OVS_DROP_EXPLICIT;
+
+			ovs_kfree_skb_reason(skb, reason);
+			return 0;
+		}
+
+		case OVS_ACTION_ATTR_PSAMPLE:
+			execute_psample(dp, skb, a);
+			OVS_CB(skb)->cutlen = 0;
+			if (nla_is_last(a, rem)) {
+				consume_skb(skb);
+				return 0;
+			}
+			break;
 		}
 
 		if (unlikely(err)) {
-			kfree_skb(skb);
+			ovs_kfree_skb_reason(skb, OVS_DROP_ACTION_ERROR);
 			return err;
 		}
 	}
 
-	consume_skb(skb);
+	ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
 	return 0;
 }
 
@@ -1416,16 +1500,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 	clone = clone_flow_key ? clone_key(key) : key;
 	if (clone) {
 		int err = 0;
-
 		if (actions) { /* Sample action */
 			if (clone_flow_key)
-				__this_cpu_inc(exec_actions_level);
+				__this_cpu_inc(ovs_pcpu_storage->exec_level);
 
 			err = do_execute_actions(dp, skb, clone,
 						 actions, len);
 
 			if (clone_flow_key)
-				__this_cpu_dec(exec_actions_level);
+				__this_cpu_dec(ovs_pcpu_storage->exec_level);
 		} else { /* Recirc action */
 			clone->recirc_id = recirc_id;
 			ovs_dp_process_packet(skb, clone);
@@ -1444,15 +1527,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 		/* Out of per CPU action FIFO space. Drop the 'skb' and
 		 * log an error.
 		 */
-		kfree_skb(skb);
+		ovs_kfree_skb_reason(skb, OVS_DROP_DEFERRED_LIMIT);
 
 		if (net_ratelimit()) {
 			if (actions) { /* Sample action */
 				pr_warn("%s: deferred action limit reached, drop sample action\n",
 					ovs_dp_name(dp));
 			} else {  /* Recirc action */
-				pr_warn("%s: deferred action limit reached, drop recirc action\n",
-					ovs_dp_name(dp));
+				pr_warn("%s: deferred action limit reached, drop recirc action (recirc_id=%#x)\n",
+					ovs_dp_name(dp), recirc_id);
 			}
 		}
 	}
@@ -1461,7 +1544,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 
 static void process_deferred_actions(struct datapath *dp)
 {
-	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 
 	/* Do not touch the FIFO in case there is no deferred actions. */
 	if (action_fifo_is_empty(fifo))
@@ -1492,11 +1575,11 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 {
 	int err, level;
 
-	level = __this_cpu_inc_return(exec_actions_level);
+	level = __this_cpu_inc_return(ovs_pcpu_storage->exec_level);
 	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
-		kfree_skb(skb);
+		ovs_kfree_skb_reason(skb, OVS_DROP_RECURSION_LIMIT);
 		err = -ENETDOWN;
 		goto out;
 	}
@@ -1509,27 +1592,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		process_deferred_actions(dp);
 
 out:
-	__this_cpu_dec(exec_actions_level);
+	__this_cpu_dec(ovs_pcpu_storage->exec_level);
 	return err;
 }
-
-int action_fifos_init(void)
-{
-	action_fifos = alloc_percpu(struct action_fifo);
-	if (!action_fifos)
-		return -ENOMEM;
-
-	flow_keys = alloc_percpu(struct action_flow_keys);
-	if (!flow_keys) {
-		free_percpu(action_fifos);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void action_fifos_exit(void)
-{
-	free_percpu(action_fifos);
-	free_percpu(flow_keys);
-}