Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "Hopefully the last pull request for this release. Fingers crossed:

   1) Only refcount ESP stats on full sockets, from Martin Willi.

   2) Missing barriers in AF_UNIX, from Al Viro.

   3) RCU protection fixes in ipv6 route code, from Paolo Abeni.

   4) Avoid false positives in untrusted GSO validation, from Willem de
      Bruijn.

   5) Forwarded mesh packets in mac80211 need more tailroom allocated,
      from Felix Fietkau.

   6) Use operstate consistently for linkup in team driver, from George
      Wilkie.

   7) ThunderX bug fixes from Vadim Lomovtsev. Mostly races between VF
      and PF code paths.

   8) Purge ipv6 exceptions during netdevice removal, from Paolo Abeni.

   9) nfp eBPF code gen fixes from Jiong Wang.

  10) bnxt_en firmware timeout fix from Michael Chan.

  11) Use after free in udp/udpv6 error handlers, from Paolo Abeni.

  12) Fix a race in x25_bind triggerable by syzbot, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (65 commits)
  net: phy: realtek: Dummy IRQ calls for RTL8366RB
  tcp: repaired skbs must init their tso_segs
  net/x25: fix a race in x25_bind()
  net: dsa: Remove documentation for port_fdb_prepare
  Revert "bridge: do not add port to router list when receives query with source 0.0.0.0"
  selftests: fib_tests: sleep after changing carrier. again.
  net: set static variable an initial value in atl2_probe()
  net: phy: marvell10g: Fix Multi-G advertisement to only advertise 10G
  bpf, doc: add bpf list as secondary entry to maintainers file
  udp: fix possible user after free in error handler
  udpv6: fix possible user after free in error handler
  fou6: fix proto error handler argument type
  udpv6: add the required annotation to mib type
  mdio_bus: Fix use-after-free on device_register fails
  net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255
  bnxt_en: Wait longer for the firmware message response to complete.
  bnxt_en: Fix typo in firmware message timeout logic.
  nfp: bpf: fix ALU32 high bits clearance bug
  nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K
  Documentation: networking: switchdev: Update port parent ID section
  ...

29 files changed, 246 insertions, 186 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fa2644d276ef..e31e1b20f7f4 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -13,27 +13,13 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 
-static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
-		struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
-{
-	u32 ret;
-
-	preempt_disable();
-	rcu_read_lock();
-	bpf_cgroup_storage_set(storage);
-	ret = BPF_PROG_RUN(prog, ctx);
-	rcu_read_unlock();
-	preempt_enable();
-
-	return ret;
-}
-
-static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret,
-			u32 *time)
+static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
+			u32 *retval, u32 *time)
 {
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 };
 	enum bpf_cgroup_storage_type stype;
 	u64 time_start, time_spent = 0;
+	int ret = 0;
 	u32 i;
 
 	for_each_cgroup_storage_type(stype) {
@@ -48,25 +34,42 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret,
 
 	if (!repeat)
 		repeat = 1;
+
+	rcu_read_lock();
+	preempt_disable();
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
-		*ret = bpf_test_run_one(prog, ctx, storage);
+		bpf_cgroup_storage_set(storage);
+		*retval = BPF_PROG_RUN(prog, ctx);
+
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
 		if (need_resched()) {
-			if (signal_pending(current))
-				break;
 			time_spent += ktime_get_ns() - time_start;
+			preempt_enable();
+			rcu_read_unlock();
+
 			cond_resched();
+
+			rcu_read_lock();
+			preempt_disable();
 			time_start = ktime_get_ns();
 		}
 	}
 	time_spent += ktime_get_ns() - time_start;
+	preempt_enable();
+	rcu_read_unlock();
+
 	do_div(time_spent, repeat);
 	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
 
 	for_each_cgroup_storage_type(stype)
 		bpf_cgroup_storage_free(storage[stype]);
 
-	return 0;
+	return ret;
 }
 
 static int bpf_test_finish(const union bpf_attr *kattr,
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 3aeff0895669..ac92b2eb32b1 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1204,14 +1204,7 @@ static void br_multicast_query_received(struct net_bridge *br,
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-
-	/* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
-	 * the arrival port for IGMP Queries where the source address
-	 * is 0.0.0.0 should not be added to router port list.
-	 */
-	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
-	    saddr->proto == htons(ETH_P_IPV6))
-		br_multicast_mark_router(br, port);
+	br_multicast_mark_router(br, port);
 }
 
 static void br_ip4_multicast_query(struct net_bridge *br,
diff --git a/net/compat.c b/net/compat.c
index 959d1c51826d..3d348198004f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname,
 				   char __user *optval, unsigned int optlen)
 {
 	int err;
-	struct socket *sock = sockfd_lookup(fd, &err);
+	struct socket *sock;
+
+	if (optlen > INT_MAX)
+		return -EINVAL;
 
+	sock = sockfd_lookup(fd, &err);
 	if (sock) {
 		err = security_socket_setsockopt(sock, level, optname);
 		if (err) {
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 2d7e01b23572..2a2a878b5ce3 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
 
 int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
 {
-	u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
 	int err;
@@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
 			return err;
 	}
 
-	dsa_port_set_state_now(dp, stp_state);
+	if (!dp->bridge_dev)
+		dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 
 	return 0;
 }
@@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy)
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
 
-	dsa_port_set_state_now(dp, BR_STATE_DISABLED);
+	if (!dp->bridge_dev)
+		dsa_port_set_state_now(dp, BR_STATE_DISABLED);
 
 	if (ds->ops->port_disable)
 		ds->ops->port_disable(ds, port, phy);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 5459f41fc26f..10e809b296ec 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			skb->len += tailen;
 			skb->data_len += tailen;
 			skb->truesize += tailen;
-			if (sk)
+			if (sk && sk_fullsock(sk))
 				refcount_add(tailen, &sk->sk_wmem_alloc);
 
 			goto out;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 3978f807fa8b..6ae89f2b541b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1457,9 +1457,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_parm *p = &t->parms;
 	__be16 o_flags = p->o_flags;
 
-	if ((t->erspan_ver == 1 || t->erspan_ver == 2) &&
-	    !t->collect_md)
-		o_flags |= TUNNEL_KEY;
+	if (t->erspan_ver == 1 || t->erspan_ver == 2) {
+		if (!t->collect_md)
+			o_flags |= TUNNEL_KEY;
+
+		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
+			goto nla_put_failure;
+
+		if (t->erspan_ver == 1) {
+			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
+				goto nla_put_failure;
+		} else {
+			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
+				goto nla_put_failure;
+		}
+	}
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -1495,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 
-	if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
-		goto nla_put_failure;
-
-	if (t->erspan_ver == 1) {
-		if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
-			goto nla_put_failure;
-	} else if (t->erspan_ver == 2) {
-		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
-			goto nla_put_failure;
-		if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
-			goto nla_put_failure;
-	}
-
 	return 0;
 
 nla_put_failure:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 730bc44dbad9..ccc78f3a4b60 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2347,6 +2347,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
 			skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
 			list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+			tcp_init_tso_segs(skb, mss_now);
 			goto repair; /* Skip network transmission */
 		}
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5c3cd5d84a6f..372fdc5381a9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
 
 	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
 		int (*handler)(struct sk_buff *skb, u32 info);
+		const struct ip_tunnel_encap_ops *encap;
 
-		if (!iptun_encaps[i])
+		encap = rcu_dereference(iptun_encaps[i]);
+		if (!encap)
 			continue;
-		handler = rcu_dereference(iptun_encaps[i]->err_handler);
+		handler = encap->err_handler;
 		if (handler && !handler(skb, info))
 			return 0;
 	}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 5afe9f83374d..239d4a65ad6e 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			skb->len += tailen;
 			skb->data_len += tailen;
 			skb->truesize += tailen;
-			if (sk)
+			if (sk && sk_fullsock(sk))
 				refcount_add(tailen, &sk->sk_wmem_alloc);
 
 			goto out;
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index b858bd5280bf..867474abe269 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 
 static int gue6_err_proto_handler(int proto, struct sk_buff *skb,
 				  struct inet6_skb_parm *opt,
-				  u8 type, u8 code, int offset, u32 info)
+				  u8 type, u8 code, int offset, __be32 info)
 {
 	const struct inet6_protocol *ipprot;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 43890898b0b5..26f25b6e2833 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1722,6 +1722,9 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[],
 static void ip6erspan_set_version(struct nlattr *data[],
 				  struct __ip6_tnl_parm *parms)
 {
+	if (!data)
+		return;
+
 	parms->erspan_ver = 1;
 	if (data[IFLA_GRE_ERSPAN_VER])
 		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
@@ -2104,9 +2107,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct __ip6_tnl_parm *p = &t->parms;
 	__be16 o_flags = p->o_flags;
 
-	if ((p->erspan_ver == 1 || p->erspan_ver == 2) &&
-	    !p->collect_md)
-		o_flags |= TUNNEL_KEY;
+	if (p->erspan_ver == 1 || p->erspan_ver == 2) {
+		if (!p->collect_md)
+			o_flags |= TUNNEL_KEY;
+
+		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
+			goto nla_put_failure;
+
+		if (p->erspan_ver == 1) {
+			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+				goto nla_put_failure;
+		} else {
+			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
+				goto nla_put_failure;
+		}
+	}
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -2121,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
 	    nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
 	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) ||
-	    nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) ||
-	    nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+	    nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -2140,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 
-	if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
-		goto nla_put_failure;
-
-	if (p->erspan_ver == 1) {
-		if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
-			goto nla_put_failure;
-	} else if (p->erspan_ver == 2) {
-		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
-			goto nla_put_failure;
-		if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
-			goto nla_put_failure;
-	}
-
 	return 0;
 
 nla_put_failure:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 964491cf3672..ce15dc4ccbfa 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
 static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 				 struct rt6_exception *rt6_ex)
 {
+	struct fib6_info *from;
 	struct net *net;
 
 	if (!bucket || !rt6_ex)
 		return;
 
 	net = dev_net(rt6_ex->rt6i->dst.dev);
+	net->ipv6.rt6_stats->fib_rt_cache--;
+
+	/* purge completely the exception to allow releasing the held resources:
+	 * some [sk] cache may keep the dst around for unlimited time
+	 */
+	from = rcu_dereference_protected(rt6_ex->rt6i->from,
+					 lockdep_is_held(&rt6_exception_lock));
+	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	fib6_info_release(from);
+	dst_dev_put(&rt6_ex->rt6i->dst);
+
 	hlist_del_rcu(&rt6_ex->hlist);
 	dst_release(&rt6_ex->rt6i->dst);
 	kfree_rcu(rt6_ex, rcu);
 	WARN_ON_ONCE(!bucket->depth);
 	bucket->depth--;
-	net->ipv6.rt6_stats->fib_rt_cache--;
 }
 
 /* Remove oldest rt6_ex in bucket and free the memory
@@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
 static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 {
 	struct rt6_exception_bucket *bucket;
-	struct fib6_info *from = rt->from;
 	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
-
-	if (!from ||
-	    !(rt->rt6i_flags & RTF_CACHE))
-		return;
+	struct fib6_info *from;
 
 	rcu_read_lock();
+	from = rcu_dereference(rt->from);
+	if (!from || !(rt->rt6i_flags & RTF_CACHE))
+		goto unlock;
+
 	bucket = rcu_dereference(from->rt6i_exception_bucket);
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 	if (rt6_ex)
 		rt6_ex->stamp = jiffies;
 
+unlock:
 	rcu_read_unlock();
 }
 
@@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	const struct in6_addr *gw_addr = &cfg->fc_gateway;
 	u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT;
+	struct fib6_info *from;
 	struct rt6_info *grt;
 	int err;
 
 	err = 0;
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
+		rcu_read_lock();
+		from = rcu_dereference(grt->from);
 		if (!grt->dst.error &&
 		    /* ignore match if it is the default route */
-		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
+		    from && !ipv6_addr_any(&from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
 			err = -EINVAL;
 		}
+		rcu_read_unlock();
 
 		ip6_rt_put(grt);
 	}
@@ -4649,7 +4665,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		table = rt->fib6_table->tb6_id;
 	else
 		table = RT6_TABLE_UNSPEC;
-	rtm->rtm_table = table;
+	rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table))
 		goto nla_put_failure;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2596ffdeebea..b444483cdb2b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int peeked, peeking, off;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	struct udp_mib __percpu *mib;
 	bool checksum_valid = false;
-	struct udp_mib *mib;
 	int is_udp4;
 
 	if (flags & MSG_ERRQUEUE)
@@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable);
  */
 static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
 				      struct inet6_skb_parm *opt,
-				      u8 type, u8 code, int offset, u32 info)
+				      u8 type, u8 code, int offset, __be32 info)
 {
 	int i;
 
 	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
 		int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
-			       u8 type, u8 code, int offset, u32 info);
+			       u8 type, u8 code, int offset, __be32 info);
+		const struct ip6_tnl_encap_ops *encap;
 
-		if (!ip6tun_encaps[i])
+		encap = rcu_dereference(ip6tun_encaps[i]);
+		if (!encap)
 			continue;
-		handler = rcu_dereference(ip6tun_encaps[i]->err_handler);
+		handler = encap->err_handler;
 		if (handler && !handler(skb, opt, type, code, offset, info))
 			return 0;
 	}
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index f5b4febeaa25..bc65db782bfb 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
 	struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
 	unsigned int i;
 
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
 	xfrm_flush_gc();
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
 
 	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
 		WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 655c787f9d54..5651c29cb5bd 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock)
 	return 0;
 }
 
-static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
-			       gfp_t allocation, struct sock *sk)
+static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation,
+			       struct sock *sk)
 {
 	int err = -ENOBUFS;
 
-	sock_hold(sk);
-	if (*skb2 == NULL) {
-		if (refcount_read(&skb->users) != 1) {
-			*skb2 = skb_clone(skb, allocation);
-		} else {
-			*skb2 = skb;
-			refcount_inc(&skb->users);
-		}
-	}
-	if (*skb2 != NULL) {
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
-			skb_set_owner_r(*skb2, sk);
-			skb_queue_tail(&sk->sk_receive_queue, *skb2);
-			sk->sk_data_ready(sk);
-			*skb2 = NULL;
-			err = 0;
-		}
+	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+		return err;
+
+	skb = skb_clone(skb, allocation);
+
+	if (skb) {
+		skb_set_owner_r(skb, sk);
+		skb_queue_tail(&sk->sk_receive_queue, skb);
+		sk->sk_data_ready(sk);
+		err = 0;
 	}
-	sock_put(sk);
 	return err;
 }
 
@@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 {
 	struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
 	struct sock *sk;
-	struct sk_buff *skb2 = NULL;
 	int err = -ESRCH;
 
 	/* XXX Do we need something like netlink_overrun?  I think
@@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 		 * socket.
 		 */
 		if (pfk->promisc)
-			pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk);
+			pfkey_broadcast_one(skb, GFP_ATOMIC, sk);
 
 		/* the exact target will be processed later */
 		if (sk == one_sk)
@@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 				continue;
 		}
 
-		err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk);
+		err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk);
 
 		/* Error is cleared after successful sending to at least one
 		 * registered KM */
@@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 	rcu_read_unlock();
 
 	if (one_sk != NULL)
-		err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
+		err = pfkey_broadcast_one(skb, allocation, one_sk);
 
-	kfree_skb(skb2);
 	kfree_skb(skb);
 	return err;
 }
@@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m
 	if (proto == 0)
 		return -EINVAL;
 
-	err = xfrm_state_flush(net, proto, true);
+	err = xfrm_state_flush(net, proto, true, false);
 	err2 = unicast_flush_resp(sk, hdr);
 	if (err || err2) {
 		if (err == -ESRCH) /* empty table - go quietly */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 87a729926734..977dea436ee8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 	 * We need a bit of data queued to build aggregates properly, so
 	 * instruct the TCP stack to allow more than a single ms of data
 	 * to be queued in the stack. The value is a bit-shift of 1
-	 * second, so 8 is ~4ms of queued data. Only affects local TCP
+	 * second, so 7 is ~8ms of queued data. Only affects local TCP
 	 * sockets.
 	 * This is the default, anyhow - drivers may need to override it
 	 * for local reasons (longer buffers, longer completion time, or
 	 * similar).
 	 */
-	local->hw.tx_sk_pacing_shift = 8;
+	local->hw.tx_sk_pacing_shift = 7;
 
 	/* set up some defaults */
 	local->hw.queues = 1;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index bb4d71efb6fb..c2a6da5d80da 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	u16 ac, q, hdrlen;
+	int tailroom = 0;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -2732,8 +2733,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	if (!ifmsh->mshcfg.dot11MeshForwarding)
 		goto out;
 
+	if (sdata->crypto_tx_tailroom_needed_cnt)
+		tailroom = IEEE80211_ENCRYPT_TAILROOM;
+
 	fwd_skb = skb_copy_expand(skb, local->tx_headroom +
-				       sdata->encrypt_headroom, 0, GFP_ATOMIC);
+				       sdata->encrypt_headroom,
+				  tailroom, GFP_ATOMIC);
 	if (!fwd_skb)
 		goto out;
 
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9fc76b19cd3c..db3473540303 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code,
 	ph->utid = 0;
 	ph->message_id = id;
 	ph->pipe_handle = pn->pipe_handle;
-	ph->data[0] = code;
+	ph->error_code = code;
 	return pn_skb_send(sk, skb, NULL);
 }
 
@@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code,
 	ph->utid = id; /* whatever */
 	ph->message_id = id;
 	ph->pipe_handle = pn->pipe_handle;
-	ph->data[0] = code;
+	ph->error_code = code;
 	return pn_skb_send(sk, skb, NULL);
 }
 
@@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code,
 	struct pnpipehdr *ph;
 	struct sockaddr_pn dst;
 	u8 data[4] = {
-		oph->data[0], /* PEP type */
+		oph->pep_type, /* PEP type */
 		code, /* error code, at an unusual offset */
 		PAD, PAD,
 	};
@@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code,
 	ph->utid = oph->utid;
 	ph->message_id = PNS_PEP_CTRL_RESP;
 	ph->pipe_handle = oph->pipe_handle;
-	ph->data[0] = oph->data[1]; /* CTRL id */
+	ph->data0 = oph->data[0]; /* CTRL id */
 
 	pn_skb_get_src_sockaddr(oskb, &dst);
 	return pn_skb_send(sk, skb, &dst);
@@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 		return -EINVAL;
 
 	hdr = pnp_hdr(skb);
-	if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
+	if (hdr->pep_type != PN_PEP_TYPE_COMMON) {
 		net_dbg_ratelimited("Phonet unknown PEP type: %u\n",
-				    (unsigned int)hdr->data[0]);
+				    (unsigned int)hdr->pep_type);
 		return -EOPNOTSUPP;
 	}
 
-	switch (hdr->data[1]) {
+	switch (hdr->data[0]) {
 	case PN_PEP_IND_FLOW_CONTROL:
 		switch (pn->tx_fc) {
 		case PN_LEGACY_FLOW_CONTROL:
-			switch (hdr->data[4]) {
+			switch (hdr->data[3]) {
 			case PEP_IND_BUSY:
 				atomic_set(&pn->tx_credits, 0);
 				break;
@@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 			}
 			break;
 		case PN_ONE_CREDIT_FLOW_CONTROL:
-			if (hdr->data[4] == PEP_IND_READY)
+			if (hdr->data[3] == PEP_IND_READY)
 				atomic_set(&pn->tx_credits, wake = 1);
 			break;
 		}
@@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 	case PN_PEP_IND_ID_MCFC_GRANT_CREDITS:
 		if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL)
 			break;
-		atomic_add(wake = hdr->data[4], &pn->tx_credits);
+		atomic_add(wake = hdr->data[3], &pn->tx_credits);
 		break;
 
 	default:
 		net_dbg_ratelimited("Phonet unknown PEP indication: %u\n",
-				    (unsigned int)hdr->data[1]);
+				    (unsigned int)hdr->data[0]);
 		return -EOPNOTSUPP;
 	}
 	if (wake)
@@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb)
 {
 	struct pep_sock *pn = pep_sk(sk);
 	struct pnpipehdr *hdr = pnp_hdr(skb);
-	u8 n_sb = hdr->data[0];
+	u8 n_sb = hdr->data0;
 
 	pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL;
 	__skb_pull(skb, sizeof(*hdr));
@@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 		return -ECONNREFUSED;
 
 	/* Parse sub-blocks */
-	n_sb = hdr->data[4];
+	n_sb = hdr->data[3];
 	while (n_sb > 0) {
 		u8 type, buf[6], len = sizeof(buf);
 		const u8 *data = pep_get_sb(skb, &type, &len, buf);
@@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk)
 	ph->utid = 0;
 	ph->message_id = PNS_PIPE_REMOVE_REQ;
 	ph->pipe_handle = pn->pipe_handle;
-	ph->data[0] = PAD;
+	ph->data0 = PAD;
 	return pn_skb_send(sk, skb, NULL);
 }
 
@@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
 	peer_type = hdr->other_pep_type << 8;
 
 	/* Parse sub-blocks (options) */
-	n_sb = hdr->data[4];
+	n_sb = hdr->data[3];
 	while (n_sb > 0) {
 		u8 type, buf[1], len = sizeof(buf);
 		const u8 *data = pep_get_sb(skb, &type, &len, buf);
@@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb)
 	ph->utid = 0;
 	if (pn->aligned) {
 		ph->message_id = PNS_PIPE_ALIGNED_DATA;
-		ph->data[0] = 0; /* padding */
+		ph->data0 = 0; /* padding */
 	} else
 		ph->message_id = PNS_PIPE_DATA;
 	ph->pipe_handle = pn->pipe_handle;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 033696e6f74f..ad158d311ffa 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport)
 
 	/* When a data chunk is sent, reset the heartbeat interval.  */
 	expires = jiffies + sctp_transport_timeout(transport);
-	if (time_before(transport->hb_timer.expires, expires) &&
+	if ((time_before(transport->hb_timer.expires, expires) ||
+	     !timer_pending(&transport->hb_timer)) &&
 	    !mod_timer(&transport->hb_timer,
 		       expires + prandom_u32_max(transport->rto)))
 		sctp_transport_hold(transport);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 5721416d0605..adbdf195eb08 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -113,9 +113,9 @@ struct smc_host_cdc_msg {		/* Connection Data Control message */
 } __aligned(8);
 
 enum smc_urg_state {
-	SMC_URG_VALID,			/* data present */
-	SMC_URG_NOTYET,			/* data pending */
-	SMC_URG_READ			/* data was already read */
+	SMC_URG_VALID	= 1,			/* data present */
+	SMC_URG_NOTYET	= 2,			/* data pending */
+	SMC_URG_READ	= 3,			/* data was already read */
 };
 
 struct smc_connection {
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1217c90a363b..684f2125fc6b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -388,7 +388,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
 		rc_ = tipc_sk_sock_err((sock_), timeo_);		       \
 		if (rc_)						       \
 			break;						       \
-		prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE);    \
+		add_wait_queue(sk_sleep(sk_), &wait_);                         \
 		release_sock(sk_);					       \
 		*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
 		sched_annotate_sleep();				               \
@@ -1677,7 +1677,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk)
 static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 {
 	struct sock *sk = sock->sk;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	long timeo = *timeop;
 	int err = sock_error(sk);
 
@@ -1685,15 +1685,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 		return err;
 
 	for (;;) {
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
 			if (sk->sk_shutdown & RCV_SHUTDOWN) {
 				err = -ENOTCONN;
 				break;
 			}
+			add_wait_queue(sk_sleep(sk), &wait);
 			release_sock(sk);
-			timeo = schedule_timeout(timeo);
+			timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+			sched_annotate_sleep();
 			lock_sock(sk);
+			remove_wait_queue(sk_sleep(sk), &wait);
 		}
 		err = 0;
 		if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -1709,7 +1711,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 		if (err)
 			break;
 	}
-	finish_wait(sk_sleep(sk), &wait);
 	*timeop = timeo;
 	return err;
 }
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 74d1eed7cbd4..a95d479caeea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -890,7 +890,7 @@ retry:
 	addr->hash ^= sk->sk_type;
 
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
 	spin_unlock(&unix_table_lock);
 	err = 0;
@@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	err = 0;
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(list, sk);
 
 out_unlock:
@@ -1331,15 +1331,29 @@ restart:
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
-	/* copy address information from listening to new sock*/
-	if (otheru->addr) {
-		refcount_inc(&otheru->addr->refcnt);
-		newu->addr = otheru->addr;
-	}
+	/* copy address information from listening to new sock
+	 *
+	 * The contents of *(otheru->addr) and otheru->path
+	 * are seen fully set up here, since we have found
+	 * otheru in hash under unix_table_lock.  Insertion
+	 * into the hash chain we'd found it in had been done
+	 * in an earlier critical area protected by unix_table_lock,
+	 * the same one where we'd set *(otheru->addr) contents,
+	 * as well as otheru->path and otheru->addr itself.
+	 *
+	 * Using smp_store_release() here to set newu->addr
+	 * is enough to make those stores, as well as stores
+	 * to newu->path visible to anyone who gets newu->addr
+	 * by smp_load_acquire().  IOW, the same warranties
+	 * as for unix_sock instances bound in unix_bind() or
+	 * in unix_autobind().
+	 */
 	if (otheru->path.dentry) {
 		path_get(&otheru->path);
 		newu->path = otheru->path;
 	}
+	refcount_inc(&otheru->addr->refcnt);
+	smp_store_release(&newu->addr, otheru->addr);
 
 	/* Set credentials */
 	copy_peercred(sk, other);
@@ -1453,7 +1467,7 @@ out:
 static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 {
 	struct sock *sk = sock->sk;
-	struct unix_sock *u;
+	struct unix_address *addr;
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
 	int err = 0;
 
@@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 		sock_hold(sk);
 	}
 
-	u = unix_sk(sk);
-	unix_state_lock(sk);
-	if (!u->addr) {
+	addr = smp_load_acquire(&unix_sk(sk)->addr);
+	if (!addr) {
 		sunaddr->sun_family = AF_UNIX;
 		sunaddr->sun_path[0] = 0;
 		err = sizeof(short);
 	} else {
-		struct unix_address *addr = u->addr;
-
 		err = addr->len;
 		memcpy(sunaddr, addr->name, addr->len);
 	}
-	unix_state_unlock(sk);
 	sock_put(sk);
 out:
 	return err;
@@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
 
 static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 {
-	struct unix_sock *u = unix_sk(sk);
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
-	if (u->addr) {
-		msg->msg_namelen = u->addr->len;
-		memcpy(msg->msg_name, u->addr->name, u->addr->len);
+	if (addr) {
+		msg->msg_namelen = addr->len;
+		memcpy(msg->msg_name, addr->name, addr->len);
 	}
 }
 
@@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk)
 	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	unix_state_lock(sk);
+	if (!smp_load_acquire(&unix_sk(sk)->addr))
+		return -ENOENT;
+
 	path = unix_sk(sk)->path;
-	if (!path.dentry) {
-		unix_state_unlock(sk);
+	if (!path.dentry)
 		return -ENOENT;
-	}
 
 	path_get(&path);
-	unix_state_unlock(sk);
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0)
@@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
 			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
 			sock_i_ino(s));
 
-		if (u->addr) {
+		if (u->addr) {	// under unix_table_lock here
 			int i, len;
 			seq_putc(seq, ' ');
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 384c84e83462..3183d9b8ab33 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -10,7 +10,8 @@
 
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
-	struct unix_address *addr = unix_sk(sk)->addr;
+	/* might or might not have unix_table_lock */
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
 	if (!addr)
 		return 0;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index ec3a828672ef..eff31348e20b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -679,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr;
 	int len, i, rc = 0;
 
-	if (!sock_flag(sk, SOCK_ZAPPED) ||
-	    addr_len != sizeof(struct sockaddr_x25) ||
+	if (addr_len != sizeof(struct sockaddr_x25) ||
 	    addr->sx25_family != AF_X25) {
 		rc = -EINVAL;
 		goto out;
@@ -699,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	}
 
 	lock_sock(sk);
-	x25_sk(sk)->source_addr = addr->sx25_addr;
-	x25_insert_socket(sk);
-	sock_reset_flag(sk, SOCK_ZAPPED);
+	if (sock_flag(sk, SOCK_ZAPPED)) {
+		x25_sk(sk)->source_addr = addr->sx25_addr;
+		x25_insert_socket(sk);
+		sock_reset_flag(sk, SOCK_ZAPPED);
+	} else {
+		rc = -EINVAL;
+	}
 	release_sock(sk);
 	SOCK_DEBUG(sk, "x25_bind: socket is bound\n");
 out:
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 45f3b528dc09..85e4fe4f18cc 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -366,7 +366,6 @@ static int xsk_release(struct socket *sock)
 
 	xskq_destroy(xs->rx);
 	xskq_destroy(xs->tx);
-	xdp_put_umem(xs->umem);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -718,6 +717,18 @@ static const struct proto_ops xsk_proto_ops = {
 	.sendpage	= sock_no_sendpage,
 };
 
+static void xsk_destruct(struct sock *sk)
+{
+	struct xdp_sock *xs = xdp_sk(sk);
+
+	if (!sock_flag(sk, SOCK_DEAD))
+		return;
+
+	xdp_put_umem(xs->umem);
+
+	sk_refcnt_debug_dec(sk);
+}
+
 static int xsk_create(struct net *net, struct socket *sock, int protocol,
 		      int kern)
 {
@@ -744,6 +755,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	sk->sk_family = PF_XDP;
 
+	sk->sk_destruct = xsk_destruct;
+	sk_refcnt_debug_inc(sk);
+
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	xs = xdp_sk(sk);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 6be8c7df15bb..dbb3c1945b5c 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
 	int ifindex;
 	struct xfrm_if *xi;
 
-	if (!skb->dev)
+	if (!secpath_exists(skb) || !skb->dev)
 		return NULL;
 
-	xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id);
+	xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
 	ifindex = skb->dev->ifindex;
 
 	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ba0a4048c846..8d1a898d0ba5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3314,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 
 	if (ifcb) {
 		xi = ifcb->decode_session(skb);
-		if (xi)
+		if (xi) {
 			if_id = xi->p.if_id;
+			net = xi->net;
+		}
 	}
 	rcu_read_unlock();
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 23c92891758a..1bb971f46fc6 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_free);
 
-static void xfrm_state_gc_destroy(struct xfrm_state *x)
+static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
 	tasklet_hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
@@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work)
 	synchronize_rcu();
 
 	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
-		xfrm_state_gc_destroy(x);
+		___xfrm_state_destroy(x);
 }
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 }
 EXPORT_SYMBOL(xfrm_state_alloc);
 
-void __xfrm_state_destroy(struct xfrm_state *x)
+void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
 {
 	WARN_ON(x->km.state != XFRM_STATE_DEAD);
 
-	spin_lock_bh(&xfrm_state_gc_lock);
-	hlist_add_head(&x->gclist, &xfrm_state_gc_list);
-	spin_unlock_bh(&xfrm_state_gc_lock);
-	schedule_work(&xfrm_state_gc_work);
+	if (sync) {
+		synchronize_rcu();
+		___xfrm_state_destroy(x);
+	} else {
+		spin_lock_bh(&xfrm_state_gc_lock);
+		hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+		spin_unlock_bh(&xfrm_state_gc_lock);
+		schedule_work(&xfrm_state_gc_work);
+	}
 }
 EXPORT_SYMBOL(__xfrm_state_destroy);
 
@@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
 }
 #endif
 
-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
 {
 	int i, err = 0, cnt = 0;
 
@@ -730,7 +735,10 @@ restart:
 				err = xfrm_state_delete(x);
 				xfrm_audit_state_delete(x, err ? 0 : 1,
 							task_valid);
-				xfrm_state_put(x);
+				if (sync)
+					xfrm_state_put_sync(x);
+				else
+					xfrm_state_put(x);
 				if (!err)
 					cnt++;
 
@@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x)
 		if (atomic_read(&t->tunnel_users) == 2)
 			xfrm_state_delete(t);
 		atomic_dec(&t->tunnel_users);
-		xfrm_state_put(t);
+		xfrm_state_put_sync(t);
 		x->tunnel = NULL;
 	}
 }
@@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net)
 	unsigned int sz;
 
 	flush_work(&net->xfrm.state_hash_work);
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
 	flush_work(&xfrm_state_gc_work);
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index c6d26afcf89d..a131f9ff979e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_usersa_flush *p = nlmsg_data(nlh);
 	int err;
 
-	err = xfrm_state_flush(net, p->proto, true);
+	err = xfrm_state_flush(net, p->proto, true, false);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;