Merge tag 'net-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Cross-tree/merge window issues:

   - rtl8150: don't incorrectly assign random MAC addresses; fix late in
     the 5.9 cycle started depending on a return code from a function
     which changed with the 5.10 PR from the usb subsystem

  Current release regressions:

   - Revert "virtio-net: ethtool configurable RXCSUM", it was causing
     crashes at probe when control vq was not negotiated/available

  Previous release regressions:

   - ixgbe: fix probing of multi-port 10 Gigabit Intel NICs with an MDIO
     bus, only first device would be probed correctly

   - nexthop: Fix performance regression in nexthop deletion by
     effectively switching from recently added synchronize_rcu() to
     synchronize_rcu_expedited()

   - netsec: ignore 'phy-mode' device property on ACPI systems; the
     property is not populated correctly by the firmware, but firmware
     configures the PHY so just keep boot settings

  Previous releases - always broken:

   - tcp: fix to update snd_wl1 in bulk receiver fast path, addressing
     bulk transfers getting "stuck"

   - icmp: randomize the global rate limiter to prevent attackers from
     getting useful signal

   - r8169: fix operation under forced interrupt threading, make the
     driver always use hard irqs, even on RT, given the handler is light
     and only wants to schedule napi (and do so through a _irqoff()
     variant, preferably)

   - bpf: Enforce pointer id generation for all may-be-null register
     type to avoid pointers erroneously getting marked as null-checked

   - tipc: re-configure queue limit for broadcast link

   - net/sched: act_tunnel_key: fix OOB write in case of IPv6 ERSPAN
     tunnels

   - fix various issues in chelsio inline tls driver

  Misc:

   - bpf: improve just-added bpf_redirect_neigh() helper api to support
     supplying nexthop by the caller - in case BPF program has already
     done a lookup we can avoid doing another one

   - remove unnecessary break statements

   - make MCTCP not select IPV6, but rather depend on it"

* tag 'net-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (62 commits)
  tcp: fix to update snd_wl1 in bulk receiver fast path
  net: Properly typecast int values to set sk_max_pacing_rate
  netfilter: nf_fwd_netdev: clear timestamp in forwarding path
  ibmvnic: save changed mac address to adapter->mac_addr
  selftests: mptcp: depends on built-in IPv6
  Revert "virtio-net: ethtool configurable RXCSUM"
  rtnetlink: fix data overflow in rtnl_calcit()
  net: ethernet: mtk-star-emac: select REGMAP_MMIO
  net: hdlc_raw_eth: Clear the IFF_TX_SKB_SHARING flag after calling ether_setup
  net: hdlc: In hdlc_rcv, check to make sure dev is an HDLC device
  bpf, libbpf: Guard bpf inline asm from bpf_tail_call_static
  bpf, selftests: Extend test_tc_redirect to use modified bpf_redirect_neigh()
  bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop
  mptcp: depends on IPV6 but not as a module
  sfc: move initialisation of efx->filter_sem to efx_init_struct()
  mpls: load mpls_gso after mpls_iptunnel
  net/sched: act_tunnel_key: fix OOB write in case of IPv6 ERSPAN tunnels
  net/sched: act_gate: Unlock ->tcfa_lock in tc_setup_flow_action()
  net: dsa: bcm_sf2: make const array static, makes object smaller
  mptcp: MPTCP_IPV6 should depend on IPV6 instead of selecting it
  ...

28 files changed, 208 insertions, 127 deletions

diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index 12a4f4d93681..3fda71a8579d 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -21,7 +21,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 0cad62a4052b..307790562b49 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_redirect_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	if (xt_hooknum(par) != NF_BR_BROUTING)
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index 27443bf229a3..7dfbcdfc30e5 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN * 2))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_source, info->mac);
diff --git a/net/core/dev.c b/net/core/dev.c
index 751e5264fd49..9499a414d67e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10213,7 +10213,7 @@ void netdev_run_todo(void)
 		struct net_device *dev = list_first_entry(&unlink_list,
 							  struct net_device,
 							  unlink_list);
-		list_del(&dev->unlink_list);
+		list_del_init(&dev->unlink_list);
 		dev->nested_level = dev->lower_level - 1;
 	}
 #endif
diff --git a/net/core/filter.c b/net/core/filter.c
index c5e2a1c5fd8d..2ca5eecebacf 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2165,12 +2165,12 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	const struct in6_addr *nexthop;
+	struct dst_entry *dst = NULL;
 	struct neighbour *neigh;
 
 	if (dev_xmit_recursion()) {
@@ -2196,8 +2196,13 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
-			      &ipv6_hdr(skb)->daddr);
+	if (!nh) {
+		dst = skb_dst(skb);
+		nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+				      &ipv6_hdr(skb)->daddr);
+	} else {
+		nexthop = &nh->ipv6_nh;
+	}
 	neigh = ip_neigh_gw6(dev, nexthop);
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
@@ -2210,36 +2215,43 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 		return ret;
 	}
 	rcu_read_unlock_bh();
-	IP6_INC_STATS(dev_net(dst->dev),
-		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	if (dst)
+		IP6_INC_STATS(dev_net(dst->dev),
+			      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 out_drop:
 	kfree_skb(skb);
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct dst_entry *dst;
-	struct flowi6 fl6 = {
-		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi6_mark	= skb->mark,
-		.flowlabel	= ip6_flowinfo(ip6h),
-		.flowi6_oif	= dev->ifindex,
-		.flowi6_proto	= ip6h->nexthdr,
-		.daddr		= ip6h->daddr,
-		.saddr		= ip6h->saddr,
-	};
 
-	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
-	if (IS_ERR(dst))
-		goto out_drop;
+	if (!nh) {
+		struct dst_entry *dst;
+		struct flowi6 fl6 = {
+			.flowi6_flags = FLOWI_FLAG_ANYSRC,
+			.flowi6_mark  = skb->mark,
+			.flowlabel    = ip6_flowinfo(ip6h),
+			.flowi6_oif   = dev->ifindex,
+			.flowi6_proto = ip6h->nexthdr,
+			.daddr	      = ip6h->daddr,
+			.saddr	      = ip6h->saddr,
+		};
+
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+		if (IS_ERR(dst))
+			goto out_drop;
 
-	skb_dst_set(skb, dst);
+		skb_dst_set(skb, dst);
+	} else if (nh->nh_family != AF_INET6) {
+		goto out_drop;
+	}
 
-	err = bpf_out_neigh_v6(net, skb);
+	err = bpf_out_neigh_v6(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2252,7 +2264,8 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
@@ -2260,11 +2273,9 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
 #endif /* CONFIG_IPV6 */
 
 #if IS_ENABLED(CONFIG_INET)
-static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	bool is_v6gw = false;
@@ -2292,7 +2303,21 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (!nh) {
+		struct dst_entry *dst = skb_dst(skb);
+		struct rtable *rt = container_of(dst, struct rtable, dst);
+
+		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	} else if (nh->nh_family == AF_INET6) {
+		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
+		is_v6gw = true;
+	} else if (nh->nh_family == AF_INET) {
+		neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
+	} else {
+		rcu_read_unlock_bh();
+		goto out_drop;
+	}
+
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
 
@@ -2309,33 +2334,37 @@ out_drop:
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct rtable *rt;
-	struct flowi4 fl4 = {
-		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi4_mark	= skb->mark,
-		.flowi4_tos	= RT_TOS(ip4h->tos),
-		.flowi4_oif	= dev->ifindex,
-		.flowi4_proto	= ip4h->protocol,
-		.daddr		= ip4h->daddr,
-		.saddr		= ip4h->saddr,
-	};
 
-	rt = ip_route_output_flow(net, &fl4, NULL);
-	if (IS_ERR(rt))
-		goto out_drop;
-	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
-		ip_rt_put(rt);
-		goto out_drop;
-	}
+	if (!nh) {
+		struct flowi4 fl4 = {
+			.flowi4_flags = FLOWI_FLAG_ANYSRC,
+			.flowi4_mark  = skb->mark,
+			.flowi4_tos   = RT_TOS(ip4h->tos),
+			.flowi4_oif   = dev->ifindex,
+			.flowi4_proto = ip4h->protocol,
+			.daddr	      = ip4h->daddr,
+			.saddr	      = ip4h->saddr,
+		};
+		struct rtable *rt;
+
+		rt = ip_route_output_flow(net, &fl4, NULL);
+		if (IS_ERR(rt))
+			goto out_drop;
+		if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+			ip_rt_put(rt);
+			goto out_drop;
+		}
 
-	skb_dst_set(skb, &rt->dst);
+		skb_dst_set(skb, &rt->dst);
+	}
 
-	err = bpf_out_neigh_v4(net, skb);
+	err = bpf_out_neigh_v4(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2348,14 +2377,16 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
 }
 #endif /* CONFIG_INET */
 
-static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
+				struct bpf_nh_params *nh)
 {
 	struct ethhdr *ethh = eth_hdr(skb);
 
@@ -2370,9 +2401,9 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
 	skb_reset_network_header(skb);
 
 	if (skb->protocol == htons(ETH_P_IP))
-		return __bpf_redirect_neigh_v4(skb, dev);
+		return __bpf_redirect_neigh_v4(skb, dev, nh);
 	else if (skb->protocol == htons(ETH_P_IPV6))
-		return __bpf_redirect_neigh_v6(skb, dev);
+		return __bpf_redirect_neigh_v6(skb, dev, nh);
 out:
 	kfree_skb(skb);
 	return -ENOTSUPP;
@@ -2382,7 +2413,8 @@ out:
 enum {
 	BPF_F_NEIGH	= (1ULL << 1),
 	BPF_F_PEER	= (1ULL << 2),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
+	BPF_F_NEXTHOP	= (1ULL << 3),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2455,7 +2487,8 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
-	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
+				    &ri->nh : NULL) :
 	       __bpf_redirect(skb, dev, flags);
 out_drop:
 	kfree_skb(skb);
@@ -2504,16 +2537,21 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
+	   int, plen, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
-	if (unlikely(flags))
+	if (unlikely((plen && plen < sizeof(*params)) || flags))
 		return TC_ACT_SHOT;
 
-	ri->flags = BPF_F_NEIGH;
+	ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
 	ri->tgt_index = ifindex;
 
+	BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
+	if (plen)
+		memcpy(&ri->nh, params, sizeof(ri->nh));
+
 	return TC_ACT_REDIRECT;
 }
 
@@ -2522,7 +2560,9 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_ANYTHING,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
 };
 
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
@@ -4693,7 +4733,8 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				cmpxchg(&sk->sk_pacing_status,
 					SK_PACING_NONE,
 					SK_PACING_NEEDED);
-			sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val;
+			sk->sk_max_pacing_rate = (val == ~0U) ?
+						 ~0UL : (unsigned int)val;
 			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
 						 sk->sk_max_pacing_rate);
 			break;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 68e0682450c6..7d7223691783 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3709,13 +3709,13 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
 }
 
-static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
+	size_t min_ifinfo_dump_size = 0;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
-	u16 min_ifinfo_dump_size = 0;
+	struct net_device *dev;
 	int hdrlen;
 
 	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
@@ -3735,9 +3735,8 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	 */
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
-					     if_nlmsg_size(dev,
-						           ext_filter_mask));
+		min_ifinfo_dump_size = max(min_ifinfo_dump_size,
+					   if_nlmsg_size(dev, ext_filter_mask));
 	}
 	rcu_read_unlock();
 
@@ -5494,7 +5493,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
-		u16 min_dump_alloc = 0;
+		u32 min_dump_alloc = 0;
 
 		link = rtnl_get_link(family, type);
 		if (!link || !link->dumpit) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 4e8729357122..727ea1cc633c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1163,7 +1163,7 @@ set_sndbuf:
 
 	case SO_MAX_PACING_RATE:
 		{
-		unsigned long ulval = (val == ~0U) ? ~0UL : val;
+		unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val;
 
 		if (sizeof(ulval) != sizeof(val) &&
 		    optlen >= sizeof(ulval) &&
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 945a9bd5ba35..0a5aa982c60d 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -123,6 +123,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = {
 	.xmit	= ksz8795_xmit,
 	.rcv	= ksz8795_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz8795_netdev_ops);
@@ -199,6 +200,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = {
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz9477_netdev_ops);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 07f67ced962a..005faea415a4 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -239,7 +239,7 @@ static struct {
 /**
  * icmp_global_allow - Are we allowed to send one more ICMP message ?
  *
- * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
+ * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
  * Returns false if we reached the limit and can not send another packet.
  * Note: called with BH disabled
  */
@@ -267,7 +267,10 @@ bool icmp_global_allow(void)
 	}
 	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
 	if (credit) {
-		credit--;
+		/* We want to use a credit of one in average, but need to randomize
+		 * it for security reasons.
+		 */
+		credit = max_t(int, credit - prandom_u32_max(3), 0);
 		rc = true;
 	}
 	WRITE_ONCE(icmp_global.credit, credit);
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 8c0f17c6863c..0dc43ad28eb9 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -845,7 +845,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 		remove_nh_grp_entry(net, nhge, nlinfo);
 
 	/* make sure all see the newly published array before releasing rtnl */
-	synchronize_rcu();
+	synchronize_net();
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 67f10d3ec240..fc445833b5e5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5827,6 +5827,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				tcp_data_snd_check(sk);
 				if (!inet_csk_ack_scheduled(sk))
 					goto no_ack;
+			} else {
+				tcp_update_wl(tp, TCP_SKB_CB(skb)->seq);
 			}
 
 			__tcp_ack_snd_check(sk, 0);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index fed9666a2f7d..054d287eb13d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -355,6 +355,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	ipv6_hdr(skb)->payload_len = htons(payload_len);
 	ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
 	IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+	IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2def85718d94..ef59e25dc482 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -300,5 +300,6 @@ static void __exit mpls_iptunnel_exit(void)
 module_exit(mpls_iptunnel_exit);
 
 MODULE_ALIAS_RTNL_LWT(MPLS);
+MODULE_SOFTDEP("post: mpls_gso");
 MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels");
 MODULE_LICENSE("GPL v2");
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
index 698bc3525160..a014149aa323 100644
--- a/net/mptcp/Kconfig
+++ b/net/mptcp/Kconfig
@@ -19,14 +19,11 @@ config INET_MPTCP_DIAG
 
 config MPTCP_IPV6
 	bool "MPTCP: IPv6 support for Multipath TCP"
-	select IPV6
+	depends on IPV6=y
 	default y
 
-endif
-
 config MPTCP_KUNIT_TESTS
 	tristate "This builds the MPTCP KUnit tests" if !KUNIT_ALL_TESTS
-	select MPTCP
 	depends on KUNIT
 	default KUNIT_ALL_TESTS
 	help
@@ -39,3 +36,4 @@ config MPTCP_KUNIT_TESTS
 
 	  If unsure, say N.
 
+endif
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 092a2d48bfd3..a044dd43411d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -241,7 +241,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		}
 
 		mp_opt->add_addr = 1;
-		mp_opt->port = 0;
 		mp_opt->addr_id = *ptr++;
 		pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
@@ -297,6 +296,8 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->mp_capable = 0;
 	mp_opt->mp_join = 0;
 	mp_opt->add_addr = 0;
+	mp_opt->ahmac = 0;
+	mp_opt->port = 0;
 	mp_opt->rm_addr = 0;
 	mp_opt->dss = 0;
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index dc2e7da2742a..7da51390cea6 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -539,8 +539,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 	if (new_state != cp->state) {
 		struct ip_vs_dest *dest = cp->dest;
 
-		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->"
-			      "%s:%d state: %s->%s conn->refcnt:%d\n",
+		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d "
+			      "d:%s:%d state: %s->%s conn->refcnt:%d\n",
 			      pd->pp->name,
 			      ((state_off == TCP_DIR_OUTPUT) ?
 			       "output " : "input "),
@@ -548,10 +548,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 			      th->fin ? 'F' : '.',
 			      th->ack ? 'A' : '.',
 			      th->rst ? 'R' : '.',
-			      IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
-			      ntohs(cp->dport),
 			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
 			      ntohs(cp->cport),
+			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
+			      ntohs(cp->vport),
+			      IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
+			      ntohs(cp->dport),
 			      tcp_state_name(cp->state),
 			      tcp_state_name(new_state),
 			      refcount_read(&cp->refcnt));
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e8c86ee4c1c4..c8fb2187ad4b 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -541,13 +541,20 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			swin = win << sender->td_scale;
 			sender->td_maxwin = (swin == 0 ? 1 : swin);
 			sender->td_maxend = end + sender->td_maxwin;
-			/*
-			 * We haven't seen traffic in the other direction yet
-			 * but we have to tweak window tracking to pass III
-			 * and IV until that happens.
-			 */
-			if (receiver->td_maxwin == 0)
+			if (receiver->td_maxwin == 0) {
+				/* We haven't seen traffic in the other
+				 * direction yet but we have to tweak window
+				 * tracking to pass III and IV until that
+				 * happens.
+				 */
 				receiver->td_end = receiver->td_maxend = sack;
+			} else if (sack == receiver->td_end + 1) {
+				/* Likely a reply to a keepalive.
+				 * Needed for III.
+				 */
+				receiver->td_end++;
+			}
+
 		}
 	} else if (((state->state == TCP_CONNTRACK_SYN_SENT
 		     && dir == IP_CT_DIR_ORIGINAL)
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 2b01a151eaa8..a579e59ee5c5 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -19,6 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev)
 		skb_push(skb, skb->mac_len);
 
 	skb->dev = dev;
+	skb->tstamp = 0;
 	dev_queue_xmit(skb);
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9957e0ed8658..65cb8e3c13d9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -302,7 +302,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->activate)
 			expr->ops->activate(ctx, expr);
 
@@ -317,7 +317,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->deactivate)
 			expr->ops->deactivate(ctx, expr, phase);
 
@@ -3080,7 +3080,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 * is called on error from nf_tables_newrule().
 	 */
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
 		expr = next;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 7c7e06624dc3..9f625724a20f 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -37,7 +37,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION)
 			num_actions++;
 
@@ -61,7 +61,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	ctx->net = net;
 	ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC;
 
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (!expr->ops->offload) {
 			err = -EOPNOTSUPP;
 			goto err_out;
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index 3087e23297db..b77985986b24 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -138,6 +138,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		return;
 
 	skb->dev = dev;
+	skb->tstamp = 0;
 	neigh_xmit(neigh_table, dev, addr, skb);
 out:
 	regs->verdict.code = verdict;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index e894254c17d4..8709f3d4e7c4 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1217,7 +1217,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info)
 	u32 idx;
 	char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1];
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME])
 		return -EINVAL;
 
 	idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 87c286ad660e..f3486a37361a 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -175,7 +175,7 @@ static struct table_instance *table_instance_alloc(int new_size)
 
 static void __mask_array_destroy(struct mask_array *ma)
 {
-	free_percpu(ma->masks_usage_cntr);
+	free_percpu(ma->masks_usage_stats);
 	kfree(ma);
 }
 
@@ -199,15 +199,15 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma)
 		ma->masks_usage_zero_cntr[i] = 0;
 
 		for_each_possible_cpu(cpu) {
-			u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr,
-							  cpu);
+			struct mask_array_stats *stats;
 			unsigned int start;
 			u64 counter;
 
+			stats = per_cpu_ptr(ma->masks_usage_stats, cpu);
 			do {
-				start = u64_stats_fetch_begin_irq(&ma->syncp);
-				counter = usage_counters[i];
-			} while (u64_stats_fetch_retry_irq(&ma->syncp, start));
+				start = u64_stats_fetch_begin_irq(&stats->syncp);
+				counter = stats->usage_cntrs[i];
+			} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
 
 			ma->masks_usage_zero_cntr[i] += counter;
 		}
@@ -230,9 +230,10 @@ static struct mask_array *tbl_mask_array_alloc(int size)
 					     sizeof(struct sw_flow_mask *) *
 					     size);
 
-	new->masks_usage_cntr = __alloc_percpu(sizeof(u64) * size,
-					       __alignof__(u64));
-	if (!new->masks_usage_cntr) {
+	new->masks_usage_stats = __alloc_percpu(sizeof(struct mask_array_stats) +
+						sizeof(u64) * size,
+						__alignof__(u64));
+	if (!new->masks_usage_stats) {
 		kfree(new);
 		return NULL;
 	}
@@ -722,6 +723,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 
 /* Flow lookup does full lookup on flow table. It starts with
  * mask from index passed in *index.
+ * This function MUST be called with BH disabled due to the use
+ * of CPU specific variables.
  */
 static struct sw_flow *flow_lookup(struct flow_table *tbl,
 				   struct table_instance *ti,
@@ -731,7 +734,7 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 				   u32 *n_cache_hit,
 				   u32 *index)
 {
-	u64 *usage_counters = this_cpu_ptr(ma->masks_usage_cntr);
+	struct mask_array_stats *stats = this_cpu_ptr(ma->masks_usage_stats);
 	struct sw_flow *flow;
 	struct sw_flow_mask *mask;
 	int i;
@@ -741,9 +744,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 		if (mask) {
 			flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
 			if (flow) {
-				u64_stats_update_begin(&ma->syncp);
-				usage_counters[*index]++;
-				u64_stats_update_end(&ma->syncp);
+				u64_stats_update_begin(&stats->syncp);
+				stats->usage_cntrs[*index]++;
+				u64_stats_update_end(&stats->syncp);
 				(*n_cache_hit)++;
 				return flow;
 			}
@@ -762,9 +765,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 		flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
 		if (flow) { /* Found */
 			*index = i;
-			u64_stats_update_begin(&ma->syncp);
-			usage_counters[*index]++;
-			u64_stats_update_end(&ma->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			stats->usage_cntrs[*index]++;
+			u64_stats_update_end(&stats->syncp);
 			return flow;
 		}
 	}
@@ -850,9 +853,17 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array);
 	u32 __always_unused n_mask_hit;
 	u32 __always_unused n_cache_hit;
+	struct sw_flow *flow;
 	u32 index = 0;
 
-	return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index);
+	/* This function gets called trough the netlink interface and therefore
+	 * is preemptible. However, flow_lookup() function needs to be called
+	 * with BH disabled due to CPU specific variables.
+	 */
+	local_bh_disable();
+	flow = flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index);
+	local_bh_enable();
+	return flow;
 }
 
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
@@ -1109,7 +1120,6 @@ void ovs_flow_masks_rebalance(struct flow_table *table)
 
 	for (i = 0; i < ma->max; i++) {
 		struct sw_flow_mask *mask;
-		unsigned int start;
 		int cpu;
 
 		mask = rcu_dereference_ovsl(ma->masks[i]);
@@ -1120,14 +1130,16 @@ void ovs_flow_masks_rebalance(struct flow_table *table)
 		masks_and_count[i].counter = 0;
 
 		for_each_possible_cpu(cpu) {
-			u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr,
-							  cpu);
+			struct mask_array_stats *stats;
+			unsigned int start;
 			u64 counter;
 
+			stats = per_cpu_ptr(ma->masks_usage_stats, cpu);
 			do {
-				start = u64_stats_fetch_begin_irq(&ma->syncp);
-				counter = usage_counters[i];
-			} while (u64_stats_fetch_retry_irq(&ma->syncp, start));
+				start = u64_stats_fetch_begin_irq(&stats->syncp);
+				counter = stats->usage_cntrs[i];
+			} while (u64_stats_fetch_retry_irq(&stats->syncp,
+							   start));
 
 			masks_and_count[i].counter += counter;
 		}
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index d8fb7a3a3dfd..9e659db78c05 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -38,12 +38,16 @@ struct mask_count {
 	u64 counter;
 };
 
+struct mask_array_stats {
+	struct u64_stats_sync syncp;
+	u64 usage_cntrs[];
+};
+
 struct mask_array {
 	struct rcu_head rcu;
 	int count, max;
-	u64 __percpu *masks_usage_cntr;
+	struct mask_array_stats __percpu *masks_usage_stats;
 	u64 *masks_usage_zero_cntr;
-	struct u64_stats_sync syncp;
 	struct sw_flow_mask __rcu *masks[];
 };
 
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 9c79fb92c2da..aba3cd85f284 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -156,11 +156,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
 	__be16 target_dst = target.dst.u.udp.port;
 
 	if (target_src != tuple->src.u.udp.port)
-		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
 					 offsetof(struct udphdr, source),
 					 0xFFFF, be16_to_cpu(target_src));
 	if (target_dst != tuple->dst.u.udp.port)
-		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
 					 offsetof(struct udphdr, dest),
 					 0xFFFF, be16_to_cpu(target_dst));
 }
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index a229751ee8c4..85c0d0d5b9da 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -459,7 +459,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 			metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port,
 						      0, flags,
-						      key_id, 0);
+						      key_id, opts_len);
 		} else {
 			NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst");
 			ret = -EINVAL;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 41a55c6cbeb8..faeabff283a2 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3712,7 +3712,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->gate.num_entries = tcf_gate_num_entries(act);
 			err = tcf_gate_get_entries(entry, act);
 			if (err)
-				goto err_out;
+				goto err_out_locked;
 		} else {
 			err = -EOPNOTSUPP;
 			goto err_out_locked;
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 940d176e0e87..d4beca895992 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -108,6 +108,8 @@ static void tipc_bcbase_select_primary(struct net *net)
 {
 	struct tipc_bc_base *bb = tipc_bc_base(net);
 	int all_dests =  tipc_link_bc_peers(bb->link);
+	int max_win = tipc_link_max_win(bb->link);
+	int min_win = tipc_link_min_win(bb->link);
 	int i, mtu, prim;
 
 	bb->primary_bearer = INVALID_BEARER_ID;
@@ -121,8 +123,12 @@ static void tipc_bcbase_select_primary(struct net *net)
 			continue;
 
 		mtu = tipc_bearer_mtu(net, i);
-		if (mtu < tipc_link_mtu(bb->link))
+		if (mtu < tipc_link_mtu(bb->link)) {
 			tipc_link_set_mtu(bb->link, mtu);
+			tipc_link_set_queue_limits(bb->link,
+						   min_win,
+						   max_win);
+		}
 		bb->bcast_support &= tipc_bearer_bcast_support(net, i);
 		if (bb->dests[i] < all_dests)
 			continue;
@@ -585,7 +591,7 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win)
 	if (max_win > TIPC_MAX_LINK_WIN)
 		return -EINVAL;
 	tipc_bcast_lock(net);
-	tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win);
+	tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win);
 	tipc_bcast_unlock(net);
 	return 0;
 }