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

Pull networking fixes from David Miller:

 1) Fix RCU locking in xfrm_local_error(), from Taehee Yoo.

 2) Fix return value assignments and thus error checking in
    iwl_mvm_start_ap_ibss(), from Johannes Berg.

 3) Don't count header length twice in vti4, from Stefano Brivio.

 4) Fix deadlock in rt6_age_examine_exception, from Eric Dumazet.

 5) Fix out-of-bounds access in nf_sk_lookup_slow{v4,v6}() from Subash
    Abhinov.

 6) Check nladdr size in netlink_connect(), from Alexander Potapenko.

 7) VF representor SQ numbers are 32 not 16 bits, in mlx5 driver, from
    Or Gerlitz.

 8) Out of bounds read in skb_network_protocol(), from Eric Dumazet.

 9) r8169 driver sets driver data pointer after register_netdev() which
    is too late. Fix from Heiner Kallweit.

10) Fix memory leak in mlx4 driver, from Moshe Shemesh.

11) The multi-VLAN decap fix added a regression when dealing with device
    that lack a MAC header, such as tun. Fix from Toshiaki Makita.

12) Fix integer overflow in dynamic interrupt coalescing code. From Tal
    Gilboa.

13) Use after free in vrf code, from David Ahern.

14) IPV6 route leak between VRFs fix, also from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (81 commits)
  net: mvneta: fix enable of all initialized RXQs
  net/ipv6: Fix route leaking between VRFs
  vrf: Fix use after free and double free in vrf_finish_output
  ipv6: sr: fix seg6 encap performances with TSO enabled
  net/dim: Fix int overflow
  vlan: Fix vlan insertion for packets without ethernet header
  net: Fix untag for vlan packets without ethernet header
  atm: iphase: fix spelling mistake: "Receiverd" -> "Received"
  vhost: validate log when IOTLB is enabled
  qede: Do not drop rx-checksum invalidated packets.
  hv_netvsc: enable multicast if necessary
  ip_tunnel: Resolve ipsec merge conflict properly.
  lan78xx: Crash in lan78xx_writ_reg (Workqueue: events lan78xx_deferred_multicast_write)
  qede: Fix barrier usage after tx doorbell write.
  vhost: correctly remove wait queue during poll failure
  net/mlx4_core: Fix memory leak while delete slave's resources
  net/mlx4_en: Fix mixed PFC and Global pause user control requests
  net/smc: use announced length in sock_recvmsg()
  llc: properly handle dev_queue_xmit() return value
  strparser: Fix sign of err codes
  ...

27 files changed, 261 insertions, 99 deletions

diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 37fe9a644f22..808d2dd4a839 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -746,7 +746,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 {
 	struct batadv_neigh_node *neigh_curr = NULL;
 	struct batadv_neigh_node *neigh_old = NULL;
-	struct batadv_orig_node *orig_dst_node;
+	struct batadv_orig_node *orig_dst_node = NULL;
 	struct batadv_gw_node *gw_node = NULL;
 	struct batadv_gw_node *curr_gw = NULL;
 	struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo;
@@ -757,6 +757,9 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 
 	vid = batadv_get_vid(skb, 0);
 
+	if (is_multicast_ether_addr(ethhdr->h_dest))
+		goto out;
+
 	orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source,
 						 ethhdr->h_dest, vid);
 	if (!orig_dst_node)
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d70640135e3a..ee56af5c43e0 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -814,8 +814,8 @@ static struct batadv_orig_node *
 batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv,
 			      struct ethhdr *ethhdr)
 {
-	return batadv_transtable_search(bat_priv, ethhdr->h_source,
-					ethhdr->h_dest, BATADV_NO_FLAGS);
+	return batadv_transtable_search(bat_priv, NULL, ethhdr->h_dest,
+					BATADV_NO_FLAGS);
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index 12be20535714..ef0cc6ea5f8d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2735,7 +2735,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
 			return 0;
 
-		eth = (struct ethhdr *)skb_mac_header(skb);
+		eth = (struct ethhdr *)skb->data;
 		type = eth->h_proto;
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1e7acdc30732..857e4e6f751a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5028,8 +5028,10 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 	}
 
 	mac_len = skb->data - skb_mac_header(skb);
-	memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
-		mac_len - VLAN_HLEN - ETH_TLEN);
+	if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) {
+		memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
+			mac_len - VLAN_HLEN - ETH_TLEN);
+	}
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6d21068f9b55..a7fd1c5a2a14 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -362,13 +362,18 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	struct ip_tunnel *nt;
 	struct net_device *dev;
 	int t_hlen;
+	int mtu;
+	int err;
 
 	BUG_ON(!itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
 
-	dev->mtu = ip_tunnel_bind_dev(dev);
+	mtu = ip_tunnel_bind_dev(dev);
+	err = dev_set_mtu(dev, mtu);
+	if (err)
+		goto err_dev_set_mtu;
 
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
@@ -376,6 +381,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+	return ERR_PTR(err);
 }
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
@@ -1102,17 +1111,29 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 	nt->fwmark = fwmark;
 	err = register_netdevice(dev);
 	if (err)
-		goto out;
+		goto err_register_netdevice;
 
 	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 
 	mtu = ip_tunnel_bind_dev(dev);
-	if (!tb[IFLA_MTU])
-		dev->mtu = mtu;
+	if (tb[IFLA_MTU]) {
+		unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+
+		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
+			    (unsigned int)(max - sizeof(struct iphdr)));
+	}
+
+	err = dev_set_mtu(dev, mtu);
+	if (err)
+		goto err_dev_set_mtu;
 
 	ip_tunnel_add(itn, nt);
-out:
+	return 0;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+err_register_netdevice:
 	return err;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 51b1669334fe..3f091ccad9af 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -387,8 +387,6 @@ static int vti_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
-	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index b50721d9d30e..9db988f9a4d7 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -154,8 +154,20 @@ static unsigned int ipv4_conntrack_local(void *priv,
 					 struct sk_buff *skb,
 					 const struct nf_hook_state *state)
 {
-	if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
+		enum ip_conntrack_info ctinfo;
+		struct nf_conn *tmpl;
+
+		tmpl = nf_ct_get(skb, &ctinfo);
+		if (tmpl && nf_ct_is_template(tmpl)) {
+			/* when skipping ct, clear templates to avoid fooling
+			 * later targets/matches
+			 */
+			skb->_nfct = 0;
+			nf_ct_put(tmpl);
+		}
 		return NF_ACCEPT;
+	}
 
 	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
 }
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index e9293bdebba0..4824b1e183a1 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -108,10 +108,12 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
 	int doff = 0;
 
 	if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
-		struct udphdr _hdr, *hp;
+		struct tcphdr _hdr;
+		struct udphdr *hp;
 
 		hp = skb_header_pointer(skb, ip_hdrlen(skb),
-					sizeof(_hdr), &_hdr);
+					iph->protocol == IPPROTO_UDP ?
+					sizeof(*hp) : sizeof(_hdr), &_hdr);
 		if (hp == NULL)
 			return NULL;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index fda37f2862c9..c3387dfd725b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -349,6 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= 0;
 	treq->tfo_listener	= false;
+	if (IS_ENABLED(CONFIG_SMC))
+		ireq->smc_ok = 0;
 
 	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9a1b3c1c1c14..ff6cd98ce8d5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6256,6 +6256,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
 
+	if (IS_ENABLED(CONFIG_SMC) && want_cookie)
+		tmp_opt.smc_ok = 0;
+
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
 	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a8a919520090..5cb18c8ba9b2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1246,7 +1246,7 @@ static int __ip6_append_data(struct sock *sk,
 			     const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
 	int exthdrlen = 0;
 	int dst_exthdrlen = 0;
 	int hh_len;
@@ -1282,6 +1282,12 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
+	 * the first fragment
+	 */
+	if (headersize + transhdrlen > mtu)
+		goto emsgsize;
+
 	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
@@ -1297,9 +1303,8 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-		ipv6_local_error(sk, EMSGSIZE, fl6,
-				 mtu - headersize +
-				 sizeof(struct ipv6hdr));
+		pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0);
+		ipv6_local_error(sk, EMSGSIZE, fl6, pmtu);
 		return -EMSGSIZE;
 	}
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index fa3ae1cb50d3..ce18cd20389d 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -622,11 +622,12 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	return 0;
 }
 
-static void vti6_link_config(struct ip6_tnl *t)
+static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu)
 {
 	struct net_device *dev = t->dev;
 	struct __ip6_tnl_parm *p = &t->parms;
 	struct net_device *tdev = NULL;
+	int mtu;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
 	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -640,6 +641,11 @@ static void vti6_link_config(struct ip6_tnl *t)
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
 
+	if (keep_mtu && dev->mtu) {
+		dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu);
+		return;
+	}
+
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
@@ -656,20 +662,25 @@ static void vti6_link_config(struct ip6_tnl *t)
 		tdev = __dev_get_by_index(t->net, p->link);
 
 	if (tdev)
-		dev->mtu = max_t(int, tdev->mtu - dev->hard_header_len,
-				 IPV6_MIN_MTU);
+		mtu = tdev->mtu - sizeof(struct ipv6hdr);
+	else
+		mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
+
+	dev->mtu = max_t(int, mtu, IPV6_MIN_MTU);
 }
 
 /**
  * vti6_tnl_change - update the tunnel parameters
  *   @t: tunnel to be changed
  *   @p: tunnel configuration parameters
+ *   @keep_mtu: MTU was set from userspace, don't re-compute it
  *
  * Description:
  *   vti6_tnl_change() updates the tunnel parameters
  **/
 static int
-vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
+vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
+		bool keep_mtu)
 {
 	t->parms.laddr = p->laddr;
 	t->parms.raddr = p->raddr;
@@ -679,11 +690,12 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 	t->parms.proto = p->proto;
 	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
-	vti6_link_config(t);
+	vti6_link_config(t, keep_mtu);
 	return 0;
 }
 
-static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
+static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p,
+		       bool keep_mtu)
 {
 	struct net *net = dev_net(t->dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
@@ -691,7 +703,7 @@ static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 
 	vti6_tnl_unlink(ip6n, t);
 	synchronize_net();
-	err = vti6_tnl_change(t, p);
+	err = vti6_tnl_change(t, p, keep_mtu);
 	vti6_tnl_link(ip6n, t);
 	netdev_state_change(t->dev);
 	return err;
@@ -804,7 +816,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			} else
 				t = netdev_priv(dev);
 
-			err = vti6_update(t, &p1);
+			err = vti6_update(t, &p1, false);
 		}
 		if (t) {
 			err = 0;
@@ -866,10 +878,8 @@ static void vti6_dev_setup(struct net_device *dev)
 	dev->priv_destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
-	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
-	dev->mtu = ETH_DATA_LEN;
 	dev->min_mtu = IPV6_MIN_MTU;
-	dev->max_mtu = IP_MAX_MTU;
+	dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
 	netif_keep_dst(dev);
@@ -905,7 +915,7 @@ static int vti6_dev_init(struct net_device *dev)
 
 	if (err)
 		return err;
-	vti6_link_config(t);
+	vti6_link_config(t, true);
 	return 0;
 }
 
@@ -1010,7 +1020,7 @@ static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
 	} else
 		t = netdev_priv(dev);
 
-	return vti6_update(t, &p);
+	return vti6_update(t, &p, tb && tb[IFLA_MTU]);
 }
 
 static size_t vti6_get_size(const struct net_device *dev)
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index ebb2bf84232a..f14de4b6d639 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -116,9 +116,11 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
 	}
 
 	if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
-		struct udphdr _hdr, *hp;
+		struct tcphdr _hdr;
+		struct udphdr *hp;
 
-		hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+		hp = skb_header_pointer(skb, thoff, tproto == IPPROTO_UDP ?
+					sizeof(*hp) : sizeof(_hdr), &_hdr);
 		if (hp == NULL)
 			return NULL;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b0d5c64e1978..fc74352fac12 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -919,6 +919,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
 
+	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+		flags &= ~RT6_LOOKUP_F_IFACE;
+
 	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
@@ -1626,11 +1629,10 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
 		struct neighbour *neigh;
 		__u8 neigh_flags = 0;
 
-		neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
-		if (neigh) {
+		neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+		if (neigh)
 			neigh_flags = neigh->flags;
-			neigh_release(neigh);
-		}
+
 		if (!(neigh_flags & NTF_ROUTER)) {
 			RT6_TRACE("purging route %p via non-router but gateway\n",
 				  rt);
@@ -1654,7 +1656,8 @@ void rt6_age_exceptions(struct rt6_info *rt,
 	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
 		return;
 
-	spin_lock_bh(&rt6_exception_lock);
+	rcu_read_lock_bh();
+	spin_lock(&rt6_exception_lock);
 	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
 				    lockdep_is_held(&rt6_exception_lock));
 
@@ -1668,7 +1671,8 @@ void rt6_age_exceptions(struct rt6_info *rt,
 			bucket++;
 		}
 	}
-	spin_unlock_bh(&rt6_exception_lock);
+	spin_unlock(&rt6_exception_lock);
+	rcu_read_unlock_bh();
 }
 
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 7a78dcfda68a..f343e6f0fc95 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -16,6 +16,7 @@
 #include <linux/net.h>
 #include <linux/module.h>
 #include <net/ip.h>
+#include <net/ip_tunnels.h>
 #include <net/lwtunnel.h>
 #include <net/netevent.h>
 #include <net/netns/generic.h>
@@ -211,11 +212,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	tinfo = seg6_encap_lwtunnel(dst->lwtstate);
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
 	switch (tinfo->mode) {
 	case SEG6_IPTUN_MODE_INLINE:
 		if (skb->protocol != htons(ETH_P_IPV6))
@@ -224,10 +220,12 @@ static int seg6_do_srh(struct sk_buff *skb)
 		err = seg6_do_srh_inline(skb, tinfo->srh);
 		if (err)
 			return err;
-
-		skb_reset_inner_headers(skb);
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+		err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+		if (err)
+			return err;
+
 		if (skb->protocol == htons(ETH_P_IPV6))
 			proto = IPPROTO_IPV6;
 		else if (skb->protocol == htons(ETH_P_IP))
@@ -239,6 +237,8 @@ static int seg6_do_srh(struct sk_buff *skb)
 		if (err)
 			return err;
 
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+		skb_set_inner_protocol(skb, skb->protocol);
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
@@ -262,8 +262,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
-	skb_set_inner_protocol(skb, skb->protocol);
-
 	return 0;
 }
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e7a3a6b6cf56..e997141aed8c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -217,6 +217,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->snt_isn = cookie;
 	treq->ts_off = 0;
 	treq->txhash = net_tx_rndhash();
+	if (IS_ENABLED(CONFIG_SMC))
+		ireq->smc_ok = 0;
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index f59648018060..163121192aca 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -389,7 +389,7 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb)
 	llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
-		llc_conn_send_pdu(sk, skb);
+		rc = llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
 	return rc;
@@ -916,7 +916,7 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk,
 	llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
-		llc_conn_send_pdu(sk, skb);
+		rc = llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
 	return rc;
@@ -935,14 +935,17 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk,
 int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb)
 {
 	struct llc_sock *llc = llc_sk(sk);
+	int ret;
 
 	if (llc->ack_must_be_send) {
-		llc_conn_ac_send_i_rsp_f_set_ackpf(sk, skb);
+		ret = llc_conn_ac_send_i_rsp_f_set_ackpf(sk, skb);
 		llc->ack_must_be_send = 0 ;
 		llc->ack_pf = 0;
-	} else
-		llc_conn_ac_send_i_cmd_p_set_0(sk, skb);
-	return 0;
+	} else {
+		ret = llc_conn_ac_send_i_cmd_p_set_0(sk, skb);
+	}
+
+	return ret;
 }
 
 /**
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 9177dbb16dce..110e32bcb399 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -30,7 +30,7 @@
 #endif
 
 static int llc_find_offset(int state, int ev_type);
-static void llc_conn_send_pdus(struct sock *sk);
+static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb);
 static int llc_conn_service(struct sock *sk, struct sk_buff *skb);
 static int llc_exec_conn_trans_actions(struct sock *sk,
 				       struct llc_conn_state_trans *trans,
@@ -193,11 +193,11 @@ out_skb_put:
 	return rc;
 }
 
-void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
+int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
 {
 	/* queue PDU to send to MAC layer */
 	skb_queue_tail(&sk->sk_write_queue, skb);
-	llc_conn_send_pdus(sk);
+	return llc_conn_send_pdus(sk, skb);
 }
 
 /**
@@ -255,7 +255,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit)
 	if (howmany_resend > 0)
 		llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
 	/* any PDUs to re-send are queued up; start sending to MAC */
-	llc_conn_send_pdus(sk);
+	llc_conn_send_pdus(sk, NULL);
 out:;
 }
 
@@ -296,7 +296,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit)
 	if (howmany_resend > 0)
 		llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
 	/* any PDUs to re-send are queued up; start sending to MAC */
-	llc_conn_send_pdus(sk);
+	llc_conn_send_pdus(sk, NULL);
 out:;
 }
 
@@ -340,12 +340,16 @@ out:
 /**
  *	llc_conn_send_pdus - Sends queued PDUs
  *	@sk: active connection
+ *	@hold_skb: the skb held by caller, or NULL if does not care
  *
- *	Sends queued pdus to MAC layer for transmission.
+ *	Sends queued pdus to MAC layer for transmission. When @hold_skb is
+ *	NULL, always return 0. Otherwise, return 0 if @hold_skb is sent
+ *	successfully, or 1 for failure.
  */
-static void llc_conn_send_pdus(struct sock *sk)
+static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb)
 {
 	struct sk_buff *skb;
+	int ret = 0;
 
 	while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) {
 		struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb);
@@ -357,10 +361,20 @@ static void llc_conn_send_pdus(struct sock *sk)
 			skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb);
 			if (!skb2)
 				break;
-			skb = skb2;
+			dev_queue_xmit(skb2);
+		} else {
+			bool is_target = skb == hold_skb;
+			int rc;
+
+			if (is_target)
+				skb_get(skb);
+			rc = dev_queue_xmit(skb);
+			if (is_target)
+				ret = rc;
 		}
-		dev_queue_xmit(skb);
 	}
+
+	return ret;
 }
 
 /**
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c4acc7340eb1..530e12ae52d7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -74,15 +74,77 @@ static void nft_trans_destroy(struct nft_trans *trans)
 	kfree(trans);
 }
 
+/* removal requests are queued in the commit_list, but not acted upon
+ * until after all new rules are in place.
+ *
+ * Therefore, nf_register_net_hook(net, &nat_hook) runs before pending
+ * nf_unregister_net_hook().
+ *
+ * nf_register_net_hook thus fails if a nat hook is already in place
+ * even if the conflicting hook is about to be removed.
+ *
+ * If collision is detected, search commit_log for DELCHAIN matching
+ * the new nat hooknum; if we find one collision is temporary:
+ *
+ * Either transaction is aborted (new/colliding hook is removed), or
+ * transaction is committed (old hook is removed).
+ */
+static bool nf_tables_allow_nat_conflict(const struct net *net,
+					 const struct nf_hook_ops *ops)
+{
+	const struct nft_trans *trans;
+	bool ret = false;
+
+	if (!ops->nat_hook)
+		return false;
+
+	list_for_each_entry(trans, &net->nft.commit_list, list) {
+		const struct nf_hook_ops *pending_ops;
+		const struct nft_chain *pending;
+
+		if (trans->msg_type != NFT_MSG_NEWCHAIN &&
+		    trans->msg_type != NFT_MSG_DELCHAIN)
+			continue;
+
+		pending = trans->ctx.chain;
+		if (!nft_is_base_chain(pending))
+			continue;
+
+		pending_ops = &nft_base_chain(pending)->ops;
+		if (pending_ops->nat_hook &&
+		    pending_ops->pf == ops->pf &&
+		    pending_ops->hooknum == ops->hooknum) {
+			/* other hook registration already pending? */
+			if (trans->msg_type == NFT_MSG_NEWCHAIN)
+				return false;
+
+			ret = true;
+		}
+	}
+
+	return ret;
+}
+
 static int nf_tables_register_hook(struct net *net,
 				   const struct nft_table *table,
 				   struct nft_chain *chain)
 {
+	struct nf_hook_ops *ops;
+	int ret;
+
 	if (table->flags & NFT_TABLE_F_DORMANT ||
 	    !nft_is_base_chain(chain))
 		return 0;
 
-	return nf_register_net_hook(net, &nft_base_chain(chain)->ops);
+	ops = &nft_base_chain(chain)->ops;
+	ret = nf_register_net_hook(net, ops);
+	if (ret == -EBUSY && nf_tables_allow_nat_conflict(net, ops)) {
+		ops->nat_hook = false;
+		ret = nf_register_net_hook(net, ops);
+		ops->nat_hook = true;
+	}
+
+	return ret;
 }
 
 static void nf_tables_unregister_hook(struct net *net,
@@ -1226,8 +1288,6 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
 		free_percpu(basechain->stats);
 		if (basechain->stats)
 			static_branch_dec(&nft_counters_enabled);
-		if (basechain->ops.dev != NULL)
-			dev_put(basechain->ops.dev);
 		kfree(chain->name);
 		kfree(basechain);
 	} else {
@@ -1294,7 +1354,7 @@ static int nft_chain_parse_hook(struct net *net,
 		}
 
 		nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ);
-		dev = dev_get_by_name(net, ifname);
+		dev = __dev_get_by_name(net, ifname);
 		if (!dev) {
 			module_put(type->owner);
 			return -ENOENT;
@@ -1311,8 +1371,6 @@ static int nft_chain_parse_hook(struct net *net,
 static void nft_chain_release_hook(struct nft_chain_hook *hook)
 {
 	module_put(hook->type->owner);
-	if (hook->dev != NULL)
-		dev_put(hook->dev);
 }
 
 static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
@@ -1911,6 +1969,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 	[NFTA_RULE_POSITION]	= { .type = NLA_U64 },
 	[NFTA_RULE_USERDATA]	= { .type = NLA_BINARY,
 				    .len = NFT_USERDATA_MAXLEN },
+	[NFTA_RULE_ID]		= { .type = NLA_U32 },
 };
 
 static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
@@ -2446,6 +2505,9 @@ EXPORT_SYMBOL_GPL(nft_unregister_set);
 
 static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags)
 {
+	if ((flags & NFT_SET_EVAL) && !ops->update)
+		return false;
+
 	return (flags & ops->features) == (flags & NFT_SET_FEATURES);
 }
 
@@ -2510,7 +2572,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
 				if (est.space == best.space &&
 				    est.lookup < best.lookup)
 					break;
-			} else if (est.size < best.size) {
+			} else if (est.size < best.size || !bops) {
 				break;
 			}
 			continue;
@@ -3315,6 +3377,8 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 	[NFTA_SET_ELEM_TIMEOUT]		= { .type = NLA_U64 },
 	[NFTA_SET_ELEM_USERDATA]	= { .type = NLA_BINARY,
 					    .len = NFT_USERDATA_MAXLEN },
+	[NFTA_SET_ELEM_EXPR]		= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_OBJREF]		= { .type = NLA_STRING },
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
@@ -4864,8 +4928,6 @@ nf_tables_flowtable_lookup_byhandle(const struct nft_table *table,
        return ERR_PTR(-ENOENT);
 }
 
-#define NFT_FLOWTABLE_DEVICE_MAX	8
-
 static int nf_tables_parse_devices(const struct nft_ctx *ctx,
 				   const struct nlattr *attr,
 				   struct net_device *dev_array[], int *len)
@@ -4882,7 +4944,7 @@ static int nf_tables_parse_devices(const struct nft_ctx *ctx,
 		}
 
 		nla_strlcpy(ifname, tmp, IFNAMSIZ);
-		dev = dev_get_by_name(ctx->net, ifname);
+		dev = __dev_get_by_name(ctx->net, ifname);
 		if (!dev) {
 			err = -ENOENT;
 			goto err1;
@@ -4938,13 +5000,11 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 	err = nf_tables_parse_devices(ctx, tb[NFTA_FLOWTABLE_HOOK_DEVS],
 				      dev_array, &n);
 	if (err < 0)
-		goto err1;
+		return err;
 
 	ops = kzalloc(sizeof(struct nf_hook_ops) * n, GFP_KERNEL);
-	if (!ops) {
-		err = -ENOMEM;
-		goto err1;
-	}
+	if (!ops)
+		return -ENOMEM;
 
 	flowtable->hooknum	= hooknum;
 	flowtable->priority	= priority;
@@ -4958,13 +5018,10 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 		flowtable->ops[i].priv		= &flowtable->data.rhashtable;
 		flowtable->ops[i].hook		= flowtable->data.type->hook;
 		flowtable->ops[i].dev		= dev_array[i];
+		flowtable->dev_name[i]		= kstrdup(dev_array[i]->name,
+							  GFP_KERNEL);
 	}
 
-	err = 0;
-err1:
-	for (i = 0; i < n; i++)
-		dev_put(dev_array[i]);
-
 	return err;
 }
 
@@ -5135,8 +5192,10 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 err5:
 	i = flowtable->ops_len;
 err4:
-	for (k = i - 1; k >= 0; k--)
+	for (k = i - 1; k >= 0; k--) {
+		kfree(flowtable->dev_name[k]);
 		nf_unregister_net_hook(net, &flowtable->ops[k]);
+	}
 
 	kfree(flowtable->ops);
 err3:
@@ -5226,9 +5285,9 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	for (i = 0; i < flowtable->ops_len; i++) {
-		if (flowtable->ops[i].dev &&
+		if (flowtable->dev_name[i][0] &&
 		    nla_put_string(skb, NFTA_DEVICE_NAME,
-				   flowtable->ops[i].dev->name))
+				   flowtable->dev_name[i]))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest_devs);
@@ -5470,6 +5529,7 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev,
 			continue;
 
 		nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
+		flowtable->dev_name[i][0] = '\0';
 		flowtable->ops[i].dev = NULL;
 		break;
 	}
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index d40591fe1b2f..fc9c6d5d64cd 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -674,7 +674,7 @@ static const struct nft_set_ops *
 nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc,
 		    u32 flags)
 {
-	if (desc->size && !(flags & NFT_SET_TIMEOUT)) {
+	if (desc->size && !(flags & (NFT_SET_EVAL | NFT_SET_TIMEOUT))) {
 		switch (desc->klen) {
 		case 4:
 			return &nft_hash_fast_ops;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 07e8478068f0..70c455341243 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1085,6 +1085,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
+	if (alen < sizeof(struct sockaddr_nl))
+		return -EINVAL;
+
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index eba6682727dd..efc6bfb9a4e0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -135,8 +135,10 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			continue;
 
 		nest = nla_nest_start(skb, n_i);
-		if (!nest)
+		if (!nest) {
+			index--;
 			goto nla_put_failure;
+		}
 		err = tcf_action_dump_1(skb, p, 0, 0);
 		if (err < 0) {
 			index--;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7e3fbe9cc936..39c144b6ff98 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -373,24 +373,33 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
  */
 static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 {
+	bool more, validate, nolock = q->flags & TCQ_F_NOLOCK;
 	spinlock_t *root_lock = NULL;
 	struct netdev_queue *txq;
 	struct net_device *dev;
 	struct sk_buff *skb;
-	bool validate;
 
 	/* Dequeue packet */
+	if (nolock && test_and_set_bit(__QDISC_STATE_RUNNING, &q->state))
+		return false;
+
 	skb = dequeue_skb(q, &validate, packets);
-	if (unlikely(!skb))
+	if (unlikely(!skb)) {
+		if (nolock)
+			clear_bit(__QDISC_STATE_RUNNING, &q->state);
 		return false;
+	}
 
-	if (!(q->flags & TCQ_F_NOLOCK))
+	if (!nolock)
 		root_lock = qdisc_lock(q);
 
 	dev = qdisc_dev(q);
 	txq = skb_get_tx_queue(dev, skb);
 
-	return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
+	more = sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
+	if (nolock)
+		clear_bit(__QDISC_STATE_RUNNING, &q->state);
+	return more;
 }
 
 void __qdisc_run(struct Qdisc *q)
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 8ac51583a063..15c213250606 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -133,7 +133,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 
 	/* receive the complete CLC message */
 	memset(&msg, 0, sizeof(struct msghdr));
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, buflen);
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
 	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 1fdab5c4eda8..b9283ce5cd85 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -60,7 +60,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 		struct sock *sk = strp->sk;
 
 		/* Report an error on the lower socket */
-		sk->sk_err = err;
+		sk->sk_err = -err;
 		sk->sk_error_report(sk);
 	}
 }
@@ -458,7 +458,7 @@ static void strp_msg_timeout(struct work_struct *w)
 	/* Message assembly timed out */
 	STRP_STATS_INCR(strp->stats.msg_timeouts);
 	strp->cb.lock(strp);
-	strp->cb.abort_parser(strp, ETIMEDOUT);
+	strp->cb.abort_parser(strp, -ETIMEDOUT);
 	strp->cb.unlock(strp);
 }
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 1472c0857975..81788105c164 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -26,6 +26,12 @@ struct xfrm_trans_tasklet {
 };
 
 struct xfrm_trans_cb {
+	union {
+		struct inet_skb_parm	h4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct inet6_skb_parm	h6;
+#endif
+	} header;
 	int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
 };
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 23468672a767..89b178a78dc7 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -285,8 +285,9 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 		return;
 
 	afinfo = xfrm_state_get_afinfo(proto);
-	if (afinfo)
+	if (afinfo) {
 		afinfo->local_error(skb, mtu);
-	rcu_read_unlock();
+		rcu_read_unlock();
+	}
 }
 EXPORT_SYMBOL_GPL(xfrm_local_error);