Merge branch 'next' into for-linus

Prepare input updates for 6.6 merge window.

42 files changed, 548 insertions, 266 deletions

diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 880277c9fd07..b18ba8ef93ad 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -26,7 +26,7 @@ obj-$(CONFIG_IP_MROUTE) += ipmr.o
 obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o
 obj-$(CONFIG_NET_IPIP) += ipip.o
 gre-y := gre_demux.o
-fou-y := fou_core.o fou_nl.o
+fou-y := fou_core.o fou_nl.o fou_bpf.o
 obj-$(CONFIG_NET_FOU) += fou.o
 obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
 obj-$(CONFIG_NET_IPGRE) += ip_gre.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8db6747f892f..4a76ebf793b8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending += writebias;
+	sk->sk_wait_pending++;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
 	 * change state of the socket from TCP_SYN_*.
@@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 	}
 	remove_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending -= writebias;
+	sk->sk_wait_pending--;
 	return timeo;
 }
 
@@ -894,7 +896,7 @@ int inet_shutdown(struct socket *sock, int how)
 		   EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
 		fallthrough;
 	default:
-		sk->sk_shutdown |= how;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
 		if (sk->sk_prot->shutdown)
 			sk->sk_prot->shutdown(sk, how);
 		break;
@@ -1322,7 +1324,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 		    sk->sk_state != TCP_SYN_SENT ||
 		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
 		    (err = inet_sk_reselect_saddr(sk)) != 0)
-			sk->sk_err_soft = -err;
+			WRITE_ONCE(sk->sk_err_soft, -err);
 	}
 
 	return err;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 4f7237661afb..9456f5bb35e5 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -375,7 +375,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 
 	probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
 	if (probes < 0) {
-		if (!(neigh->nud_state & NUD_VALID))
+		if (!(READ_ONCE(neigh->nud_state) & NUD_VALID))
 			pr_debug("trying to ucast probe in NUD_INVALID\n");
 		neigh_ha_snapshot(dst_ha, neigh, dev);
 		dst_hw = dst_ha;
@@ -1123,7 +1123,7 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 
 	neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	if (neigh) {
-		if (!(neigh->nud_state & NUD_NOARP)) {
+		if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) {
 			read_lock_bh(&neigh->lock);
 			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
 			r->arp_flags = arp_state_to_flags(neigh);
@@ -1144,12 +1144,12 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force)
 	struct neigh_table *tbl = &arp_tbl;
 
 	if (neigh) {
-		if ((neigh->nud_state & NUD_VALID) && !force) {
+		if ((READ_ONCE(neigh->nud_state) & NUD_VALID) && !force) {
 			neigh_release(neigh);
 			return 0;
 		}
 
-		if (neigh->nud_state & ~NUD_NOARP)
+		if (READ_ONCE(neigh->nud_state) & ~NUD_NOARP)
 			err = neigh_update(neigh, NULL, NUD_FAILED,
 					   NEIGH_UPDATE_F_OVERRIDE|
 					   NEIGH_UPDATE_F_ADMIN, 0);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 13fc0c185cd9..4406d796cc2f 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -72,15 +72,11 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size,
 
 static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 					const struct bpf_reg_state *reg,
-					int off, int size, enum bpf_access_type atype,
-					u32 *next_btf_id, enum bpf_type_flag *flag)
+					int off, int size)
 {
 	const struct btf_type *t;
 	size_t end;
 
-	if (atype == BPF_READ)
-		return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
-
 	t = btf_type_by_id(reg->btf, reg->btf_id);
 	if (t != tcp_sock_type) {
 		bpf_log(log, "only read is supported\n");
@@ -113,6 +109,9 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 	case offsetof(struct tcp_sock, ecn_flags):
 		end = offsetofend(struct tcp_sock, ecn_flags);
 		break;
+	case offsetof(struct tcp_sock, app_limited):
+		end = offsetofend(struct tcp_sock, app_limited);
+		break;
 	default:
 		bpf_log(log, "no write support to tcp_sock at off %d\n", off);
 		return -EACCES;
@@ -239,8 +238,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 		if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name,
 				     sizeof(tcp_ca->name)) <= 0)
 			return -EINVAL;
-		if (tcp_ca_find(utcp_ca->name))
-			return -EEXIST;
 		return 1;
 	}
 
@@ -266,13 +263,25 @@ static void bpf_tcp_ca_unreg(void *kdata)
 	tcp_unregister_congestion_control(kdata);
 }
 
+static int bpf_tcp_ca_update(void *kdata, void *old_kdata)
+{
+	return tcp_update_congestion_control(kdata, old_kdata);
+}
+
+static int bpf_tcp_ca_validate(void *kdata)
+{
+	return tcp_validate_congestion_control(kdata);
+}
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
 	.unreg = bpf_tcp_ca_unreg,
+	.update = bpf_tcp_ca_update,
 	.check_member = bpf_tcp_ca_check_member,
 	.init_member = bpf_tcp_ca_init_member,
 	.init = bpf_tcp_ca_init,
+	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
 };
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index b0acf6e19aed..5deac0517ef7 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -962,6 +962,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 					 extack);
 	} else {
 		u32 new_metric = ifa->ifa_rt_priority;
+		u8 new_proto = ifa->ifa_proto;
 
 		inet_free_ifa(ifa);
 
@@ -975,6 +976,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			ifa->ifa_rt_priority = new_metric;
 		}
 
+		ifa->ifa_proto = new_proto;
+
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		cancel_delayed_work(&check_lifetime_work);
 		queue_delayed_work(system_power_efficient_wq,
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 3969fa805679..ee848be59e65 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -340,6 +340,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 
 	secpath_reset(skb);
 
+	if (skb_needs_linearize(skb, skb->dev->features) &&
+	    __skb_linearize(skb))
+		return -ENOMEM;
 	return 0;
 }
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b5736ef16ed2..390f4be7f7be 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -576,6 +576,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 			cfg->fc_scope = RT_SCOPE_UNIVERSE;
 	}
 
+	if (!cfg->fc_table)
+		cfg->fc_table = RT_TABLE_MAIN;
+
 	if (cmd == SIOCDELRT)
 		return 0;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3bb890a40ed7..65ba18a91865 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -563,7 +563,7 @@ static int fib_detect_death(struct fib_info *fi, int order,
 		n = NULL;
 
 	if (n) {
-		state = n->nud_state;
+		state = READ_ONCE(n->nud_state);
 		neigh_release(n);
 	} else {
 		return 0;
@@ -2191,7 +2191,7 @@ static bool fib_good_nh(const struct fib_nh *nh)
 	if (nh->fib_nh_scope == RT_SCOPE_LINK) {
 		struct neighbour *n;
 
-		rcu_read_lock_bh();
+		rcu_read_lock();
 
 		if (likely(nh->fib_nh_gw_family == AF_INET))
 			n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
@@ -2202,9 +2202,9 @@ static bool fib_good_nh(const struct fib_nh *nh)
 		else
 			n = NULL;
 		if (n)
-			state = n->nud_state;
+			state = READ_ONCE(n->nud_state);
 
-		rcu_read_unlock_bh();
+		rcu_read_unlock();
 	}
 
 	return !!(state & NUD_VALID);
diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c
new file mode 100644
index 000000000000..3760a14b6b57
--- /dev/null
+++ b/net/ipv4/fou_bpf.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable Fou Helpers for TC-BPF hook
+ *
+ * These are called from SCHED_CLS BPF programs. Note that it is
+ * allowed to break compatibility for these functions since the interface they
+ * are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+
+#include <net/dst_metadata.h>
+#include <net/fou.h>
+
+struct bpf_fou_encap {
+	__be16 sport;
+	__be16 dport;
+};
+
+enum bpf_fou_encap_type {
+	FOU_BPF_ENCAP_FOU,
+	FOU_BPF_ENCAP_GUE,
+};
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in BTF");
+
+/* bpf_skb_set_fou_encap - Set FOU encap parameters
+ *
+ * This function allows for using GUE or FOU encapsulation together with an
+ * ipip device in collect-metadata mode.
+ *
+ * It is meant to be used in BPF tc-hooks and after a call to the
+ * bpf_skb_set_tunnel_key helper, responsible for setting IP addresses.
+ *
+ * Parameters:
+ * @skb_ctx	Pointer to ctx (__sk_buff) in TC program. Cannot be NULL
+ * @encap	Pointer to a `struct bpf_fou_encap` storing UDP src and
+ * 		dst ports. If sport is set to 0 the kernel will auto-assign a
+ * 		port. This is similar to using `encap-sport auto`.
+ * 		Cannot be NULL
+ * @type	Encapsulation type for the packet. Their definitions are
+ * 		specified in `enum bpf_fou_encap_type`
+ */
+__bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
+				      struct bpf_fou_encap *encap, int type)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
+
+	if (unlikely(!encap))
+		return -EINVAL;
+
+	if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX)))
+		return -EINVAL;
+
+	switch (type) {
+	case FOU_BPF_ENCAP_FOU:
+		info->encap.type = TUNNEL_ENCAP_FOU;
+		break;
+	case FOU_BPF_ENCAP_GUE:
+		info->encap.type = TUNNEL_ENCAP_GUE;
+		break;
+	default:
+		info->encap.type = TUNNEL_ENCAP_NONE;
+	}
+
+	if (info->key.tun_flags & TUNNEL_CSUM)
+		info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM;
+
+	info->encap.sport = encap->sport;
+	info->encap.dport = encap->dport;
+
+	return 0;
+}
+
+/* bpf_skb_get_fou_encap - Get FOU encap parameters
+ *
+ * This function allows for reading encap metadata from a packet received
+ * on an ipip device in collect-metadata mode.
+ *
+ * Parameters:
+ * @skb_ctx	Pointer to ctx (__sk_buff) in TC program. Cannot be NULL
+ * @encap	Pointer to a struct bpf_fou_encap storing UDP source and
+ * 		destination port. Cannot be NULL
+ */
+__bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
+				      struct bpf_fou_encap *encap)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
+
+	if (unlikely(!info))
+		return -EINVAL;
+
+	encap->sport = info->encap.sport;
+	encap->dport = info->encap.dport;
+
+	return 0;
+}
+
+__diag_pop()
+
+BTF_SET8_START(fou_kfunc_set)
+BTF_ID_FLAGS(func, bpf_skb_set_fou_encap)
+BTF_ID_FLAGS(func, bpf_skb_get_fou_encap)
+BTF_SET8_END(fou_kfunc_set)
+
+static const struct btf_kfunc_id_set fou_bpf_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &fou_kfunc_set,
+};
+
+int register_fou_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
+					 &fou_bpf_kfunc_set);
+}
diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
index cafec9b4eee0..0c41076e31ed 100644
--- a/net/ipv4/fou_core.c
+++ b/net/ipv4/fou_core.c
@@ -1236,10 +1236,15 @@ static int __init fou_init(void)
 	if (ret < 0)
 		goto unregister;
 
+	ret = register_fou_bpf();
+	if (ret < 0)
+		goto kfunc_failed;
+
 	ret = ip_tunnel_encap_add_fou_ops();
 	if (ret == 0)
 		return 0;
 
+kfunc_failed:
 	genl_unregister_family(&fou_nl_family);
 unregister:
 	unregister_pernet_device(&fou_net_ops);
diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c
index 5c14fe030eda..6c37c4f98cca 100644
--- a/net/ipv4/fou_nl.c
+++ b/net/ipv4/fou_nl.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/fou.yaml */
 /* YNL-GEN kernel source */
diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h
index 58b1e1ed4b3b..dbd0780a5d34 100644
--- a/net/ipv4/fou_nl.h
+++ b/net/ipv4/fou_nl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/fou.yaml */
 /* YNL-GEN kernel header */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8cebb476b3ab..b8607763d113 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -749,6 +749,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		room = 576;
 	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
 	room -= sizeof(struct icmphdr);
+	/* Guard against tiny mtu. We need to include at least one
+	 * IP network header for this message to make any sense.
+	 */
+	if (room <= (int)sizeof(struct iphdr))
+		goto ende;
 
 	icmp_param.data_len = skb_in->len - icmp_param.offset;
 	if (icmp_param.data_len > room)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c920aa9a62a9..48ff5f13e797 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2638,10 +2638,10 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 /*
  * check if a multicast source filter allows delivery for a given <src,dst,intf>
  */
-int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
+int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
 		   int dif, int sdif)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
 	struct ip_mc_socklist *pmc;
 	struct ip_sf_socklist *psl;
 	int i;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 65ad4251f6fd..1386787eaf1a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
+		newsk->sk_wait_pending = 0;
 		inet_sk_set_state(newsk, TCP_SYN_RECV);
 		newicsk->icsk_bind_hash = NULL;
 		newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e41fdc38ce19..e7391bf310a7 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -826,15 +826,19 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const
 				      unsigned short port, int l3mdev, const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	struct in6_addr addr_any = {};
+	if (sk->sk_family != tb->family) {
+		if (sk->sk_family == AF_INET)
+			return net_eq(ib2_net(tb), net) && tb->port == port &&
+				tb->l3mdev == l3mdev &&
+				ipv6_addr_any(&tb->v6_rcv_saddr);
 
-	if (sk->sk_family != tb->family)
 		return false;
+	}
 
 	if (sk->sk_family == AF_INET6)
 		return net_eq(ib2_net(tb), net) && tb->port == port &&
 			tb->l3mdev == l3mdev &&
-			ipv6_addr_equal(&tb->v6_rcv_saddr, &addr_any);
+			ipv6_addr_any(&tb->v6_rcv_saddr);
 	else
 #endif
 		return net_eq(ib2_net(tb), net) && tb->port == port &&
@@ -860,11 +864,10 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
 {
 	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	u32 hash;
-#if IS_ENABLED(CONFIG_IPV6)
-	struct in6_addr addr_any = {};
 
+#if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
-		hash = ipv6_portaddr_hash(net, &addr_any, port);
+		hash = ipv6_portaddr_hash(net, &in6addr_any, port);
 	else
 #endif
 		hash = ipv4_portaddr_hash(net, 0, port);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index ffff46cdcb58..e55a20264960 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -552,7 +552,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		truncate = true;
 	}
 
-	nhoff = skb_network_header(skb) - skb_mac_header(skb);
+	nhoff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
 		truncate = true;
@@ -561,7 +561,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		int thoff;
 
 		if (skb_transport_header_was_set(skb))
-			thoff = skb_transport_header(skb) - skb_mac_header(skb);
+			thoff = skb_transport_offset(skb);
 		else
 			thoff = nhoff + sizeof(struct ipv6hdr);
 		if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4e4e308c3230..61892268e8a6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -129,7 +129,8 @@ int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ip_local_out);
 
-static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
+static inline int ip_select_ttl(const struct inet_sock *inet,
+				const struct dst_entry *dst)
 {
 	int ttl = inet->uc_ttl;
 
@@ -146,7 +147,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt,
 			  u8 tos)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = sock_net(sk);
 	struct iphdr *iph;
@@ -218,7 +219,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 			return res;
 	}
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	if (!IS_ERR(neigh)) {
 		int res;
@@ -226,10 +227,10 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 		sock_confirm_neigh(skb, neigh);
 		/* if crossing protocols, can not use the cached header */
 		res = neigh_output(neigh, skb, is_v6gw);
-		rcu_read_unlock_bh();
+		rcu_read_unlock();
 		return res;
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
 			    __func__);
@@ -990,7 +991,7 @@ static int __ip_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
 	paged = !!cork->gso_size;
 
-	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
+	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
 	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
 		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
@@ -1570,9 +1571,19 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	cork->dst = NULL;
 	skb_dst_set(skb, &rt->dst);
 
-	if (iph->protocol == IPPROTO_ICMP)
-		icmp_out_count(net, ((struct icmphdr *)
-			skb_transport_header(skb))->type);
+	if (iph->protocol == IPPROTO_ICMP) {
+		u8 icmp_type;
+
+		/* For such sockets, transhdrlen is zero when do ip_append_data(),
+		 * so icmphdr does not in skb linear region and can not get icmp_type
+		 * by icmp_hdr(skb)->type.
+		 */
+		if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+			icmp_type = fl4->fl4_icmp_type;
+		else
+			icmp_type = icmp_hdr(skb)->type;
+		icmp_out_count(net, icmp_type);
+	}
 
 	ip_cork_release(cork);
 out:
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			ipc->tos = val;
 			ipc->priority = rt_tos2priority(ipc->tos);
 			break;
-
+		case IP_PROTOCOL:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 1 || val > 255)
+				return -EINVAL;
+			ipc->protocol = val;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_LOCAL_PORT_RANGE:
 		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
 		break;
+	case IP_PROTOCOL:
+		val = inet_sk(sk)->inet_num;
+		break;
 	default:
 		sockopt_release_sock(sk);
 		return -ENOPROTOOPT;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index de90b09dfe78..beeae624c412 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -359,6 +359,20 @@ err_dev_set_mtu:
 	return ERR_PTR(err);
 }
 
+void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	const struct udphdr *udph;
+
+	if (iph->protocol != IPPROTO_UDP)
+		return;
+
+	udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2));
+	info->encap.sport = udph->source;
+	info->encap.dport = udph->dest;
+}
+EXPORT_SYMBOL(ip_tunnel_md_udp_encap);
+
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error)
@@ -572,7 +586,11 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
 			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
 			    key->flow_flags);
-	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
+
+	if (!tunnel_hlen)
+		tunnel_hlen = ip_encap_hlen(&tun_info->encap);
+
+	if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0)
 		goto tx_error;
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);
@@ -614,10 +632,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
-	if (headroom > dev->needed_headroom)
-		dev->needed_headroom = headroom;
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
 
-	if (skb_cow_head(skb, dev->needed_headroom)) {
+	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
@@ -732,7 +750,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			    dev_net(dev), tunnel->parms.link,
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
-	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
+	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)
 		goto tx_error;
 
 	if (connected && md) {
@@ -800,10 +818,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
-	if (max_headroom > dev->needed_headroom)
-		dev->needed_headroom = max_headroom;
+	if (max_headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, max_headroom);
 
-	if (skb_cow_head(skb, dev->needed_headroom)) {
+	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
 		ip_rt_put(rt);
 		DEV_STATS_INC(dev, tx_dropped);
 		kfree_skb(skb);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index abea77759b7e..27b8f83c6ea2 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -241,6 +241,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 			tun_dst = ip_tun_rx_dst(skb, 0, 0, 0);
 			if (!tun_dst)
 				return 0;
+			ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info);
 		}
 		skb_reset_mac_header(skb);
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index da5998011ab9..7da1df4997d0 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -14,7 +14,6 @@
 #include <linux/vmalloc.h>
 #include <linux/netdevice.h>
 #include <linux/module.h>
-#include <linux/icmp.h>
 #include <net/ip.h>
 #include <net/compat.h>
 #include <linux/uaccess.h>
@@ -31,7 +30,6 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("IPv4 packet filter");
-MODULE_ALIAS("ipt_icmp");
 
 void *ipt_alloc_initial_table(const struct xt_table *info)
 {
@@ -1799,52 +1797,6 @@ void ipt_unregister_table_exit(struct net *net, const char *name)
 		__ipt_unregister_table(net, table);
 }
 
-/* Returns 1 if the type and code is matched by the range, 0 otherwise */
-static inline bool
-icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,
-		     u_int8_t type, u_int8_t code,
-		     bool invert)
-{
-	return ((test_type == 0xFF) ||
-		(type == test_type && code >= min_code && code <= max_code))
-		^ invert;
-}
-
-static bool
-icmp_match(const struct sk_buff *skb, struct xt_action_param *par)
-{
-	const struct icmphdr *ic;
-	struct icmphdr _icmph;
-	const struct ipt_icmp *icmpinfo = par->matchinfo;
-
-	/* Must not be a fragment. */
-	if (par->fragoff != 0)
-		return false;
-
-	ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph);
-	if (ic == NULL) {
-		/* We've been asked to examine this packet, and we
-		 * can't.  Hence, no choice but to drop.
-		 */
-		par->hotdrop = true;
-		return false;
-	}
-
-	return icmp_type_code_match(icmpinfo->type,
-				    icmpinfo->code[0],
-				    icmpinfo->code[1],
-				    ic->type, ic->code,
-				    !!(icmpinfo->invflags&IPT_ICMP_INV));
-}
-
-static int icmp_checkentry(const struct xt_mtchk_param *par)
-{
-	const struct ipt_icmp *icmpinfo = par->matchinfo;
-
-	/* Must specify no unknown invflags */
-	return (icmpinfo->invflags & ~IPT_ICMP_INV) ? -EINVAL : 0;
-}
-
 static struct xt_target ipt_builtin_tg[] __read_mostly = {
 	{
 		.name             = XT_STANDARD_TARGET,
@@ -1875,18 +1827,6 @@ static struct nf_sockopt_ops ipt_sockopts = {
 	.owner		= THIS_MODULE,
 };
 
-static struct xt_match ipt_builtin_mt[] __read_mostly = {
-	{
-		.name       = "icmp",
-		.match      = icmp_match,
-		.matchsize  = sizeof(struct ipt_icmp),
-		.checkentry = icmp_checkentry,
-		.proto      = IPPROTO_ICMP,
-		.family     = NFPROTO_IPV4,
-		.me	    = THIS_MODULE,
-	},
-};
-
 static int __net_init ip_tables_net_init(struct net *net)
 {
 	return xt_proto_init(net, NFPROTO_IPV4);
@@ -1914,19 +1854,14 @@ static int __init ip_tables_init(void)
 	ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 	if (ret < 0)
 		goto err2;
-	ret = xt_register_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
-	if (ret < 0)
-		goto err4;
 
 	/* Register setsockopt */
 	ret = nf_register_sockopt(&ipt_sockopts);
 	if (ret < 0)
-		goto err5;
+		goto err4;
 
 	return 0;
 
-err5:
-	xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
 err4:
 	xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 err2:
@@ -1939,7 +1874,6 @@ static void __exit ip_tables_fini(void)
 {
 	nf_unregister_sockopt(&ipt_sockopts);
 
-	xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
 	xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 	unregister_pernet_subsys(&ip_tables_net_ops);
 }
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d8ef05347fd9..f95142e56da0 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1124,13 +1124,13 @@ static bool ipv6_good_nh(const struct fib6_nh *nh)
 	int state = NUD_REACHABLE;
 	struct neighbour *n;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 
 	n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6);
 	if (n)
-		state = n->nud_state;
+		state = READ_ONCE(n->nud_state);
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return !!(state & NUD_VALID);
 }
@@ -1140,14 +1140,14 @@ static bool ipv4_good_nh(const struct fib_nh *nh)
 	int state = NUD_REACHABLE;
 	struct neighbour *n;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 
 	n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
 				      (__force u32)nh->fib_nh_gw4);
 	if (n)
-		state = n->nud_state;
+		state = READ_ONCE(n->nud_state);
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return !!(state & NUD_VALID);
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 409ec2a1f95b..5178a3f3cb53 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -1089,13 +1089,13 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
-	__acquires(RCU)
+	__acquires(ping_table.lock)
 {
 	struct ping_iter_state *state = seq->private;
 	state->bucket = 0;
 	state->family = family;
 
-	rcu_read_lock();
+	spin_lock(&ping_table.lock);
 
 	return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
 }
@@ -1121,9 +1121,9 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 EXPORT_SYMBOL_GPL(ping_seq_next);
 
 void ping_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU)
+	__releases(ping_table.lock)
 {
-	rcu_read_unlock();
+	spin_unlock(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_seq_stop);
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 94df935ee0c5..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -91,12 +91,12 @@ EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
 int raw_hash_sk(struct sock *sk)
 {
 	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
-	struct hlist_nulls_head *hlist;
+	struct hlist_head *hlist;
 
 	hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)];
 
 	spin_lock(&h->lock);
-	__sk_nulls_add_node_rcu(sk, hlist);
+	sk_add_node_rcu(sk, hlist);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 	spin_unlock(&h->lock);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -110,16 +110,16 @@ void raw_unhash_sk(struct sock *sk)
 	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
 
 	spin_lock(&h->lock);
-	if (__sk_nulls_del_node_init_rcu(sk))
+	if (sk_del_node_init_rcu(sk))
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	spin_unlock(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_unhash_sk);
 
-bool raw_v4_match(struct net *net, struct sock *sk, unsigned short num,
+bool raw_v4_match(struct net *net, const struct sock *sk, unsigned short num,
 		  __be32 raddr, __be32 laddr, int dif, int sdif)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
 
 	if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
 	    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
@@ -163,16 +163,15 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
 static int raw_v4_input(struct net *net, struct sk_buff *skb,
 			const struct iphdr *iph, int hash)
 {
-	struct hlist_nulls_head *hlist;
-	struct hlist_nulls_node *hnode;
 	int sdif = inet_sdif(skb);
+	struct hlist_head *hlist;
 	int dif = inet_iif(skb);
 	int delivered = 0;
 	struct sock *sk;
 
 	hlist = &raw_v4_hashinfo.ht[hash];
 	rcu_read_lock();
-	sk_nulls_for_each(sk, hnode, hlist) {
+	sk_for_each_rcu(sk, hlist) {
 		if (!raw_v4_match(net, sk, iph->protocol,
 				  iph->saddr, iph->daddr, dif, sdif))
 			continue;
@@ -264,10 +263,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
-	struct hlist_nulls_head *hlist;
-	struct hlist_nulls_node *hnode;
 	int dif = skb->dev->ifindex;
 	int sdif = inet_sdif(skb);
+	struct hlist_head *hlist;
 	const struct iphdr *iph;
 	struct sock *sk;
 	int hash;
@@ -276,7 +274,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 	hlist = &raw_v4_hashinfo.ht[hash];
 
 	rcu_read_lock();
-	sk_nulls_for_each(sk, hnode, hlist) {
+	sk_for_each_rcu(sk, hlist) {
 		iph = (const struct iphdr *)skb->data;
 		if (!raw_v4_match(net, sk, iph->protocol,
 				  iph->daddr, iph->saddr, dif, sdif))
@@ -534,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipcm_init_sk(&ipc, inet);
+	/* Keep backward compat */
+	if (hdrincl)
+		ipc.protocol = IPPROTO_RAW;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -601,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
 			   RT_SCOPE_UNIVERSE,
-			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   hdrincl ? ipc.protocol : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0, sk->sk_uid);
@@ -950,14 +951,13 @@ static struct sock *raw_get_first(struct seq_file *seq, int bucket)
 {
 	struct raw_hashinfo *h = pde_data(file_inode(seq->file));
 	struct raw_iter_state *state = raw_seq_private(seq);
-	struct hlist_nulls_head *hlist;
-	struct hlist_nulls_node *hnode;
+	struct hlist_head *hlist;
 	struct sock *sk;
 
 	for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE;
 			++state->bucket) {
 		hlist = &h->ht[state->bucket];
-		sk_nulls_for_each(sk, hnode, hlist) {
+		sk_for_each(sk, hlist) {
 			if (sock_net(sk) == seq_file_net(seq))
 				return sk;
 		}
@@ -970,7 +970,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
 	struct raw_iter_state *state = raw_seq_private(seq);
 
 	do {
-		sk = sk_nulls_next(sk);
+		sk = sk_next(sk);
 	} while (sk && sock_net(sk) != seq_file_net(seq));
 
 	if (!sk)
@@ -989,9 +989,12 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 void *raw_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(RCU)
+	__acquires(&h->lock)
 {
-	rcu_read_lock();
+	struct raw_hashinfo *h = pde_data(file_inode(seq->file));
+
+	spin_lock(&h->lock);
+
 	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
 EXPORT_SYMBOL_GPL(raw_seq_start);
@@ -1010,9 +1013,11 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 EXPORT_SYMBOL_GPL(raw_seq_next);
 
 void raw_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU)
+	__releases(&h->lock)
 {
-	rcu_read_unlock();
+	struct raw_hashinfo *h = pde_data(file_inode(seq->file));
+
+	spin_unlock(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_seq_stop);
 
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index 999321834b94..63a40e4b678f 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -34,7 +34,7 @@ raw_get_hashinfo(const struct inet_diag_req_v2 *r)
  * use helper to figure it out.
  */
 
-static bool raw_lookup(struct net *net, struct sock *sk,
+static bool raw_lookup(struct net *net, const struct sock *sk,
 		       const struct inet_diag_req_v2 *req)
 {
 	struct inet_diag_req_raw *r = (void *)req;
@@ -57,8 +57,7 @@ static bool raw_lookup(struct net *net, struct sock *sk,
 static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
 {
 	struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
-	struct hlist_nulls_head *hlist;
-	struct hlist_nulls_node *hnode;
+	struct hlist_head *hlist;
 	struct sock *sk;
 	int slot;
 
@@ -68,7 +67,7 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2
 	rcu_read_lock();
 	for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
 		hlist = &hashinfo->ht[slot];
-		sk_nulls_for_each(sk, hnode, hlist) {
+		sk_for_each_rcu(sk, hlist) {
 			if (raw_lookup(net, sk, r)) {
 				/*
 				 * Grab it and keep until we fill
@@ -142,9 +141,8 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
 	struct net *net = sock_net(skb->sk);
 	struct inet_diag_dump_data *cb_data;
-	struct hlist_nulls_head *hlist;
-	struct hlist_nulls_node *hnode;
 	int num, s_num, slot, s_slot;
+	struct hlist_head *hlist;
 	struct sock *sk = NULL;
 	struct nlattr *bc;
 
@@ -161,7 +159,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		num = 0;
 
 		hlist = &hashinfo->ht[slot];
-		sk_nulls_for_each(sk, hnode, hlist) {
+		sk_for_each_rcu(sk, hlist) {
 			struct inet_sock *inet = inet_sk(sk);
 
 			if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index de6e3515ab4f..98d7e6ba7493 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -408,7 +408,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	struct net_device *dev = dst->dev;
 	struct neighbour *n;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 
 	if (likely(rt->rt_gw_family == AF_INET)) {
 		n = ip_neigh_gw4(dev, rt->rt_gw4);
@@ -424,7 +424,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt))
 		n = NULL;
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return n;
 }
@@ -784,7 +784,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 	if (!n)
 		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
-		if (!(n->nud_state & NUD_VALID)) {
+		if (!(READ_ONCE(n->nud_state) & NUD_VALID)) {
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
@@ -1508,20 +1508,20 @@ void rt_add_uncached_list(struct rtable *rt)
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
 
-	rt->rt_uncached_list = ul;
+	rt->dst.rt_uncached_list = ul;
 
 	spin_lock_bh(&ul->lock);
-	list_add_tail(&rt->rt_uncached, &ul->head);
+	list_add_tail(&rt->dst.rt_uncached, &ul->head);
 	spin_unlock_bh(&ul->lock);
 }
 
 void rt_del_uncached_list(struct rtable *rt)
 {
-	if (!list_empty(&rt->rt_uncached)) {
-		struct uncached_list *ul = rt->rt_uncached_list;
+	if (!list_empty(&rt->dst.rt_uncached)) {
+		struct uncached_list *ul = rt->dst.rt_uncached_list;
 
 		spin_lock_bh(&ul->lock);
-		list_del_init(&rt->rt_uncached);
+		list_del_init(&rt->dst.rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
 }
@@ -1546,13 +1546,13 @@ void rt_flush_dev(struct net_device *dev)
 			continue;
 
 		spin_lock_bh(&ul->lock);
-		list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) {
+		list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = blackhole_netdev;
 			netdev_ref_replace(dev, blackhole_netdev,
 					   &rt->dst.dev_tracker, GFP_ATOMIC);
-			list_move(&rt->rt_uncached, &ul->quarantine);
+			list_move(&rt->dst.rt_uncached, &ul->quarantine);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -1644,7 +1644,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_uses_gateway = 0;
 		rt->rt_gw_family = 0;
 		rt->rt_gw4 = 0;
-		INIT_LIST_HEAD(&rt->rt_uncached);
 
 		rt->dst.output = ip_output;
 		if (flags & RTCF_LOCAL)
@@ -1675,7 +1674,6 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
 			new_rt->rt_gw4 = rt->rt_gw4;
 		else if (rt->rt_gw_family == AF_INET6)
 			new_rt->rt_gw6 = rt->rt_gw6;
-		INIT_LIST_HEAD(&new_rt->rt_uncached);
 
 		new_rt->dst.input = rt->dst.input;
 		new_rt->dst.output = rt->dst.output;
@@ -2858,8 +2856,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 			rt->rt_gw4 = ort->rt_gw4;
 		else if (rt->rt_gw_family == AF_INET6)
 			rt->rt_gw6 = ort->rt_gw6;
-
-		INIT_LIST_HEAD(&rt->rt_uncached);
 	}
 
 	dst_release(dst_orig);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0d0cc4ef2b85..88dfe51e68f3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
 static int tcp_adv_win_scale_min = -31;
 static int tcp_adv_win_scale_max = 31;
+static int tcp_app_win_max = 31;
 static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS;
 static int tcp_min_snd_mss_max = 65535;
 static int ip_privileged_port_min;
@@ -33,8 +34,8 @@ static int ip_ttl_min = 1;
 static int ip_ttl_max = 255;
 static int tcp_syn_retries_min = 1;
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
-static int ip_ping_group_range_min[] = { 0, 0 };
-static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static unsigned long ip_ping_group_range_min[] = { 0, 0 };
+static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
 static int one_day_secs = 24 * 3600;
 static u32 fib_multipath_hash_fields_all_mask __maybe_unused =
@@ -164,7 +165,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 {
 	struct user_namespace *user_ns = current_user_ns();
 	int ret;
-	gid_t urange[2];
+	unsigned long urange[2];
 	kgid_t low, high;
 	struct ctl_table tmp = {
 		.data = &urange,
@@ -177,7 +178,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	inet_get_ping_group_range_table(table, &low, &high);
 	urange[0] = from_kgid_munged(user_ns, low);
 	urange[1] = from_kgid_munged(user_ns, high);
-	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
 
 	if (write && ret == 0) {
 		low = make_kgid(user_ns, urange[0]);
@@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &tcp_app_win_max,
 	},
 	{
 		.procname	= "tcp_adv_win_scale",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 288693981b00..8d20d9221238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
+	u8 shutdown;
 	int state;
 
 	sock_poll_wait(file, sock, wait);
@@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
 	 * blocking on fresh not-connected or disconnected socket. --ANK
 	 */
-	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
 		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
 	/* Connected or passive Fast Open socket? */
@@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		if (tcp_stream_is_readable(sk, target))
 			mask |= EPOLLIN | EPOLLRDNORM;
 
-		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+		if (!(shutdown & SEND_SHUTDOWN)) {
 			if (__sk_stream_is_writeable(sk, 1)) {
 				mask |= EPOLLOUT | EPOLLWRNORM;
 			} else {  /* send SIGIO later */
@@ -589,7 +591,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
+	if (READ_ONCE(sk->sk_err) ||
+	    !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR;
 
 	return mask;
@@ -1568,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
+void __tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1770,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
 		tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
 		used = recv_actor(sk, skb);
-		consume_skb(skb);
 		if (used < 0) {
 			if (!copied)
 				copied = used;
@@ -1784,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 			break;
 		}
 	}
-	WRITE_ONCE(tp->copied_seq, seq);
-
-	tcp_rcv_space_adjust(sk);
-
-	/* Clean up data we have read: This will do ACK frames. */
-	if (copied > 0)
-		__tcp_cleanup_rbuf(sk, copied);
-
 	return copied;
 }
 EXPORT_SYMBOL(tcp_read_skb);
@@ -2164,7 +2158,7 @@ static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
 	struct msghdr cmsg_dummy;
 
 	msg_control_addr = (unsigned long)zc->msg_control;
-	cmsg_dummy.msg_control = (void *)msg_control_addr;
+	cmsg_dummy.msg_control_user = (void __user *)msg_control_addr;
 	cmsg_dummy.msg_controllen =
 		(__kernel_size_t)zc->msg_controllen;
 	cmsg_dummy.msg_flags = in_compat_syscall()
@@ -2175,7 +2169,7 @@ static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
 	    zc->msg_controllen == cmsg_dummy.msg_controllen) {
 		tcp_recv_timestamp(&cmsg_dummy, sk, tss);
 		zc->msg_control = (__u64)
-			((uintptr_t)cmsg_dummy.msg_control);
+			((uintptr_t)cmsg_dummy.msg_control_user);
 		zc->msg_controllen =
 			(__u64)cmsg_dummy.msg_controllen;
 		zc->msg_flags = (__u32)cmsg_dummy.msg_flags;
@@ -2866,7 +2860,7 @@ void __tcp_close(struct sock *sk, long timeout)
 	int data_was_unread = 0;
 	int state;
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if (sk->sk_state == TCP_LISTEN) {
 		tcp_set_state(sk, TCP_CLOSE);
@@ -3087,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	int old_state = sk->sk_state;
 	u32 seq;
 
+	/* Deny disconnect if other threads are blocked in sk_wait_event()
+	 * or inet_wait_for_connect().
+	 */
+	if (sk->sk_wait_pending)
+		return -EBUSY;
+
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
 
@@ -3094,7 +3094,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (old_state == TCP_LISTEN) {
 		inet_csk_listen_stop(sk);
 	} else if (unlikely(tp->repair)) {
-		sk->sk_err = ECONNABORTED;
+		WRITE_ONCE(sk->sk_err, ECONNABORTED);
 	} else if (tcp_need_reset(old_state) ||
 		   (tp->snd_nxt != tp->write_seq &&
 		    (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
@@ -3102,9 +3102,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 		 * states
 		 */
 		tcp_send_active_reset(sk, gfp_any());
-		sk->sk_err = ECONNRESET;
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	} else if (old_state == TCP_SYN_SENT)
-		sk->sk_err = ECONNRESET;
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
 
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
@@ -3118,7 +3118,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	inet_bhash2_reset_saddr(sk);
 
-	sk->sk_shutdown = 0;
+	WRITE_ONCE(sk->sk_shutdown, 0);
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->srtt_us = 0;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -4078,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	switch (optname) {
 	case TCP_MAXSEG:
 		val = tp->mss_cache;
-		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+		if (tp->rx_opt.user_mss &&
+		    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 			val = tp->rx_opt.user_mss;
 		if (tp->repair)
 			val = tp->rx_opt.mss_clamp;
@@ -4569,7 +4570,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 	const __u8 *hash_location = NULL;
 	struct tcp_md5sig_key *hash_expected;
 	const struct tcphdr *th = tcp_hdr(skb);
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	int genhash, l3index;
 	u8 newhash[16];
 
@@ -4648,7 +4649,7 @@ void tcp_done(struct sock *sk)
 	if (req)
 		reqsk_fastopen_remove(sk, req, false);
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_state_change(sk);
@@ -4692,7 +4693,7 @@ int tcp_abort(struct sock *sk, int err)
 	bh_lock_sock(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
-		sk->sk_err = err;
+		WRITE_ONCE(sk->sk_err, err);
 		/* This barrier is coupled with smp_rmb() in tcp_poll() */
 		smp_wmb();
 		sk_error_report(sk);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ebf917511937..5f93918c063c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -11,6 +11,24 @@
 #include <net/inet_common.h>
 #include <net/tls.h>
 
+void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tcp;
+	int copied;
+
+	if (!skb || !skb->len || !sk_is_tcp(sk))
+		return;
+
+	if (skb_bpf_strparser(skb))
+		return;
+
+	tcp = tcp_sk(sk);
+	copied = tcp->copied_seq + skb->len;
+	WRITE_ONCE(tcp->copied_seq, copied);
+	tcp_rcv_space_adjust(sk);
+	__tcp_cleanup_rbuf(sk, skb->len);
+}
+
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 			   struct sk_msg *msg, u32 apply_bytes, int flags)
 {
@@ -168,20 +186,40 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	ret = sk_wait_event(sk, &timeo,
 			    !list_empty(&psock->ingress_msg) ||
-			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
+			    !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait);
 	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	remove_wait_queue(sk_sleep(sk), &wait);
 	return ret;
 }
 
+static bool is_next_msg_fin(struct sk_psock *psock)
+{
+	struct scatterlist *sge;
+	struct sk_msg *msg_rx;
+	int i;
+
+	msg_rx = sk_psock_peek_msg(psock);
+	i = msg_rx->sg.start;
+	sge = sk_msg_elem(msg_rx, i);
+	if (!sge->length) {
+		struct sk_buff *skb = msg_rx->skb;
+
+		if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			return true;
+	}
+	return false;
+}
+
 static int tcp_bpf_recvmsg_parser(struct sock *sk,
 				  struct msghdr *msg,
 				  size_t len,
 				  int flags,
 				  int *addr_len)
 {
+	struct tcp_sock *tcp = tcp_sk(sk);
+	u32 seq = tcp->copied_seq;
 	struct sk_psock *psock;
-	int copied;
+	int copied = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -194,8 +232,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 		return tcp_recvmsg(sk, msg, len, flags, addr_len);
 
 	lock_sock(sk);
+
+	/* We may have received data on the sk_receive_queue pre-accept and
+	 * then we can not use read_skb in this context because we haven't
+	 * assigned a sk_socket yet so have no link to the ops. The work-around
+	 * is to check the sk_receive_queue and in these cases read skbs off
+	 * queue again. The read_skb hook is not running at this point because
+	 * of lock_sock so we avoid having multiple runners in read_skb.
+	 */
+	if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+		tcp_data_ready(sk);
+		/* This handles the ENOMEM errors if we both receive data
+		 * pre accept and are already under memory pressure. At least
+		 * let user know to retry.
+		 */
+		if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+			copied = -EAGAIN;
+			goto out;
+		}
+	}
+
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	/* The typical case for EFAULT is the socket was gracefully
+	 * shutdown with a FIN pkt. So check here the other case is
+	 * some error on copy_page_to_iter which would be unexpected.
+	 * On fin return correct return code to zero.
+	 */
+	if (copied == -EFAULT) {
+		bool is_fin = is_next_msg_fin(psock);
+
+		if (is_fin) {
+			copied = 0;
+			seq++;
+			goto out;
+		}
+	}
+	seq += copied;
 	if (!copied) {
 		long timeo;
 		int data;
@@ -233,6 +306,10 @@ msg_bytes_ready:
 		copied = -EAGAIN;
 	}
 out:
+	WRITE_ONCE(tcp->copied_seq, seq);
+	tcp_rcv_space_adjust(sk);
+	if (copied > 0)
+		__tcp_cleanup_rbuf(sk, copied);
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return copied;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index db8b4b488c31..1b34050a7538 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -75,14 +75,8 @@ struct tcp_congestion_ops *tcp_ca_find_key(u32 key)
 	return NULL;
 }
 
-/*
- * Attach new congestion control algorithm to the list
- * of available options.
- */
-int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
+int tcp_validate_congestion_control(struct tcp_congestion_ops *ca)
 {
-	int ret = 0;
-
 	/* all algorithms must implement these */
 	if (!ca->ssthresh || !ca->undo_cwnd ||
 	    !(ca->cong_avoid || ca->cong_control)) {
@@ -90,6 +84,20 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+/* Attach new congestion control algorithm to the list
+ * of available options.
+ */
+int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
+{
+	int ret;
+
+	ret = tcp_validate_congestion_control(ca);
+	if (ret)
+		return ret;
+
 	ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name));
 
 	spin_lock(&tcp_cong_list_lock);
@@ -130,6 +138,50 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
 }
 EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
 
+/* Replace a registered old ca with a new one.
+ *
+ * The new ca must have the same name as the old one, that has been
+ * registered.
+ */
+int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca)
+{
+	struct tcp_congestion_ops *existing;
+	int ret;
+
+	ret = tcp_validate_congestion_control(ca);
+	if (ret)
+		return ret;
+
+	ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name));
+
+	spin_lock(&tcp_cong_list_lock);
+	existing = tcp_ca_find_key(old_ca->key);
+	if (ca->key == TCP_CA_UNSPEC || !existing || strcmp(existing->name, ca->name)) {
+		pr_notice("%s not registered or non-unique key\n",
+			  ca->name);
+		ret = -EINVAL;
+	} else if (existing != old_ca) {
+		pr_notice("invalid old congestion control algorithm to replace\n");
+		ret = -EINVAL;
+	} else {
+		/* Add the new one before removing the old one to keep
+		 * one implementation available all the time.
+		 */
+		list_add_tail_rcu(&ca->list, &tcp_cong_list);
+		list_del_rcu(&existing->list);
+		pr_debug("%s updated\n", ca->name);
+	}
+	spin_unlock(&tcp_cong_list_lock);
+
+	/* Wait for outstanding readers to complete before the
+	 * module or struct_ops gets removed entirely.
+	 */
+	if (!ret)
+		synchronize_rcu();
+
+	return ret;
+}
+
 u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
 {
 	const struct tcp_congestion_ops *ca;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc072d2cfcd8..bf8b22218dd4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -458,7 +458,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
 static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
 			     unsigned int skbtruesize)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
 	int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
 	int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
@@ -3874,7 +3874,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	/* We passed data and got it acked, remove any soft error
 	 * log. Something worked...
 	 */
-	sk->sk_err_soft = 0;
+	WRITE_ONCE(sk->sk_err_soft, 0);
 	icsk->icsk_probes_out = 0;
 	tp->rcv_tstamp = tcp_jiffies32;
 	if (!prior_packets)
@@ -4322,15 +4322,15 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb)
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
-		sk->sk_err = ECONNREFUSED;
+		WRITE_ONCE(sk->sk_err, ECONNREFUSED);
 		break;
 	case TCP_CLOSE_WAIT:
-		sk->sk_err = EPIPE;
+		WRITE_ONCE(sk->sk_err, EPIPE);
 		break;
 	case TCP_CLOSE:
 		return;
 	default:
-		sk->sk_err = ECONNRESET;
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	}
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
 	smp_wmb();
@@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk)
 
 	inet_csk_schedule_ack(sk);
 
-	sk->sk_shutdown |= RCV_SHUTDOWN;
+	WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 	sock_set_flag(sk, SOCK_DONE);
 
 	switch (sk->sk_state) {
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
 	}
 }
 
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -5693,7 +5693,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
  */
 static bool tcp_reset_check(const struct sock *sk, const struct sk_buff *skb)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	return unlikely(TCP_SKB_CB(skb)->seq == (tp->rcv_nxt - 1) &&
 			(1 << sk->sk_state) & (TCPF_CLOSE_WAIT | TCPF_LAST_ACK |
@@ -5714,6 +5714,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	    tp->rx_opt.saw_tstamp &&
 	    tcp_paws_discard(sk, skb)) {
 		if (!th->rst) {
+			if (unlikely(th->syn))
+				goto syn_challenge;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
 			if (!tcp_oow_rate_limited(sock_net(sk), skb,
 						  LINUX_MIB_TCPACKSKIPPEDPAWS,
@@ -6597,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 
 		tcp_set_state(sk, TCP_FIN_WAIT2);
-		sk->sk_shutdown |= SEND_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
 
 		sk_dst_confirm(sk);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ea370afa70ed..06d2573685ca 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -361,7 +361,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 	 * for the case, if this connection will not able to recover.
 	 */
 	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
-		sk->sk_err_soft = EMSGSIZE;
+		WRITE_ONCE(sk->sk_err_soft, EMSGSIZE);
 
 	mtu = dst_mtu(dst);
 
@@ -596,13 +596,13 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 		ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th);
 
 		if (!sock_owned_by_user(sk)) {
-			sk->sk_err = err;
+			WRITE_ONCE(sk->sk_err, err);
 
 			sk_error_report(sk);
 
 			tcp_done(sk);
 		} else {
-			sk->sk_err_soft = err;
+			WRITE_ONCE(sk->sk_err_soft, err);
 		}
 		goto out;
 	}
@@ -625,10 +625,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 
 	inet = inet_sk(sk);
 	if (!sock_owned_by_user(sk) && inet->recverr) {
-		sk->sk_err = err;
+		WRITE_ONCE(sk->sk_err, err);
 		sk_error_report(sk);
 	} else	{ /* Only an error on timeout */
-		sk->sk_err_soft = err;
+		WRITE_ONCE(sk->sk_err_soft, err);
 	}
 
 out:
@@ -829,6 +829,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
 		xfrm_sk_clone_policy(ctl_sk, sk);
+	} else {
+		ctl_sk->sk_mark = 0;
+		ctl_sk->sk_priority = 0;
 	}
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -836,7 +839,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 			      &arg, arg.iov[0].iov_len,
 			      transmit_time);
 
-	ctl_sk->sk_mark = 0;
 	xfrm_sk_free_policy(ctl_sk);
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
@@ -935,7 +937,6 @@ static void tcp_v4_send_ack(const struct sock *sk,
 			      &arg, arg.iov[0].iov_len,
 			      transmit_time);
 
-	ctl_sk->sk_mark = 0;
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	local_bh_enable();
@@ -2780,7 +2781,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
 static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter)
 {
 	while (iter->cur_sk < iter->end_sk)
-		sock_put(iter->batch[iter->cur_sk++]);
+		sock_gen_put(iter->batch[iter->cur_sk++]);
 }
 
 static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter,
@@ -2941,7 +2942,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		 * st->bucket.  See tcp_seek_last_pos().
 		 */
 		st->offset++;
-		sock_put(iter->batch[iter->cur_sk++]);
+		sock_gen_put(iter->batch[iter->cur_sk++]);
 	}
 
 	if (iter->cur_sk < iter->end_sk)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9a7ef7732c24..dac0d62120e6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -463,7 +463,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 }
 EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
 
-static void smc_check_reset_syn_req(struct tcp_sock *oldtp,
+static void smc_check_reset_syn_req(const struct tcp_sock *oldtp,
 				    struct request_sock *req,
 				    struct tcp_sock *newtp)
 {
@@ -492,7 +492,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct tcp_request_sock *treq = tcp_rsk(req);
 	struct inet_connection_sock *newicsk;
-	struct tcp_sock *oldtp, *newtp;
+	const struct tcp_sock *oldtp;
+	struct tcp_sock *newtp;
 	u32 seq;
 
 	if (!newsk)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 45dda7889387..4851211aa60d 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -60,12 +60,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	struct tcphdr *th;
 	unsigned int thlen;
 	unsigned int seq;
-	__be32 delta;
 	unsigned int oldlen;
 	unsigned int mss;
 	struct sk_buff *gso_skb = skb;
 	__sum16 newcheck;
 	bool ooo_okay, copy_destructor;
+	__wsum delta;
 
 	th = tcp_hdr(skb);
 	thlen = th->doff * 4;
@@ -75,7 +75,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, thlen))
 		goto out;
 
-	oldlen = (u16)~skb->len;
+	oldlen = ~skb->len;
 	__skb_pull(skb, thlen);
 
 	mss = skb_shinfo(skb)->gso_size;
@@ -110,7 +110,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	if (skb_is_gso(segs))
 		mss *= skb_shinfo(segs)->gso_segs;
 
-	delta = htonl(oldlen + (thlen + mss));
+	delta = (__force __wsum)htonl(oldlen + thlen + mss);
 
 	skb = segs;
 	th = tcp_hdr(skb);
@@ -119,8 +119,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
 		tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);
 
-	newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
-					       (__force u32)delta));
+	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 
 	while (skb->next) {
 		th->fin = th->psh = 0;
@@ -165,11 +164,11 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc));
 	}
 
-	delta = htonl(oldlen + (skb_tail_pointer(skb) -
-				skb_transport_header(skb)) +
-		      skb->data_len);
-	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
-				(__force u32)delta));
+	delta = (__force __wsum)htonl(oldlen +
+				      (skb_tail_pointer(skb) -
+				       skb_transport_header(skb)) +
+				      skb->data_len);
+	th->check = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		gso_reset_checksum(skb, ~th->check);
 	else
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 71d01cf3c13e..cfe128b81a01 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3605,7 +3605,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
 	tcp_options_write(th, NULL, &opts);
 	th->doff = (tcp_header_size >> 2);
-	__TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
@@ -3699,7 +3699,7 @@ static void tcp_connect_init(struct sock *sk)
 	tp->rx_opt.rcv_wscale = rcv_wscale;
 	tp->rcv_ssthresh = tp->rcv_wnd;
 
-	sk->sk_err = 0;
+	WRITE_ONCE(sk->sk_err, 0);
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->snd_wnd = 0;
 	tcp_init_wl(tp, 0);
@@ -4127,8 +4127,13 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	if (!res) {
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
-		if (unlikely(tcp_passive_fastopen(sk)))
-			tcp_sk(sk)->total_retrans++;
+		if (unlikely(tcp_passive_fastopen(sk))) {
+			/* sk has const attribute because listeners are lockless.
+			 * However in this case, we are dealing with a passive fastopen
+			 * socket thus we can change total_retrans value.
+			 */
+			tcp_sk_rw(sk)->total_retrans++;
+		}
 		trace_tcp_retransmit_synack(sk, req);
 	}
 	return res;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 50abaa941387..acf4869c5d3b 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -4,7 +4,7 @@
 
 static u32 tcp_rack_reo_wnd(const struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	if (!tp->reord_seen) {
 		/* If reordering has not been observed, be aggressive during
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index cb79127f45c3..39eb947fe392 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -67,7 +67,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 
 static void tcp_write_err(struct sock *sk)
 {
-	sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
+	WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
 	sk_error_report(sk);
 
 	tcp_write_queue_purge(sk);
@@ -110,7 +110,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		shift++;
 
 	/* If some dubious ICMP arrived, penalize even more. */
-	if (sk->sk_err_soft)
+	if (READ_ONCE(sk->sk_err_soft))
 		shift++;
 
 	if (tcp_check_oom(sk, shift)) {
@@ -146,7 +146,7 @@ static int tcp_orphan_retries(struct sock *sk, bool alive)
 	int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
 
 	/* We know from an ICMP that something is wrong. */
-	if (sk->sk_err_soft && !alive)
+	if (READ_ONCE(sk->sk_err_soft) && !alive)
 		retries = 0;
 
 	/* However, if socket sent something recently, select some safe
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
 void tcp_delack_timer_handler(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
-	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+		return;
+
+	/* Handling the sack compression case */
+	if (tp->compressed_ack) {
+		tcp_mstamp_refresh(tp);
+		tcp_sack_compress_send_ack(sk);
+		return;
+	}
+
+	if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		return;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
 			inet_csk_exit_pingpong_mode(sk);
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
-		tcp_mstamp_refresh(tcp_sk(sk));
+		tcp_mstamp_refresh(tp);
 		tcp_send_ack(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c605d171eb2d..9482def1f310 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -578,12 +578,12 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 #endif
 
-static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
+static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk,
 				       __be16 loc_port, __be32 loc_addr,
 				       __be16 rmt_port, __be32 rmt_addr,
 				       int dif, int sdif, unsigned short hnum)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
 
 	if (!net_eq(sock_net(sk), net) ||
 	    udp_sk(sk)->udp_port_hash != hnum ||
@@ -1531,10 +1531,21 @@ static void busylock_release(spinlock_t *busy)
 		spin_unlock(busy);
 }
 
+static int udp_rmem_schedule(struct sock *sk, int size)
+{
+	int delta;
+
+	delta = size - sk->sk_forward_alloc;
+	if (delta > 0 && !__sk_mem_schedule(sk, delta, SK_MEM_RECV))
+		return -ENOBUFS;
+
+	return 0;
+}
+
 int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff_head *list = &sk->sk_receive_queue;
-	int rmem, delta, amt, err = -ENOMEM;
+	int rmem, err = -ENOMEM;
 	spinlock_t *busy = NULL;
 	int size;
 
@@ -1567,16 +1578,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 		goto uncharge_drop;
 
 	spin_lock(&list->lock);
-	if (size >= sk->sk_forward_alloc) {
-		amt = sk_mem_pages(size);
-		delta = amt << PAGE_SHIFT;
-		if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
-			err = -ENOBUFS;
-			spin_unlock(&list->lock);
-			goto uncharge_drop;
-		}
-
-		sk->sk_forward_alloc += delta;
+	err = udp_rmem_schedule(sk, size);
+	if (err) {
+		spin_unlock(&list->lock);
+		goto uncharge_drop;
 	}
 
 	sk->sk_forward_alloc -= size;
@@ -1813,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp);
 int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
 	struct sk_buff *skb;
-	int err, copied;
+	int err;
 
 try_again:
 	skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
@@ -1832,10 +1837,7 @@ try_again:
 	}
 
 	WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
-	copied = recv_actor(sk, skb);
-	kfree_skb(skb);
-
-	return copied;
+	return recv_actor(sk, skb);
 }
 EXPORT_SYMBOL(udp_read_skb);
 
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index e0c9cc39b81e..143f93a12f25 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -22,6 +22,8 @@ static int udplite_sk_init(struct sock *sk)
 {
 	udp_init_sock(sk);
 	udp_sk(sk)->pcflag = UDPLITE_BIT;
+	pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
+		     "please contact the netdev mailing list\n");
 	return 0;
 }
 
@@ -64,6 +66,8 @@ struct proto 	udplite_prot = {
 	.per_cpu_fw_alloc  = &udp_memory_per_cpu_fw_alloc,
 
 	.sysctl_mem	   = sysctl_udp_mem,
+	.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+	.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
 	.obj_size	   = sizeof(struct udp_sock),
 	.h.udp_table	   = &udplite_table,
 };
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index ad2afeef4f10..eac206a290d0 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -164,6 +164,7 @@ drop:
 	kfree_skb(skb);
 	return 0;
 }
+EXPORT_SYMBOL(xfrm4_udp_encap_rcv);
 
 int xfrm4_rcv(struct sk_buff *skb)
 {
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 3d0dfa6cf9f9..9403bbaf1b61 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,7 +91,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 		xdst->u.rt.rt_gw6 = rt->rt_gw6;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
-	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 	rt_add_uncached_list(&xdst->u.rt);
 
 	return 0;
@@ -121,8 +120,7 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
 	dst_destroy_metrics_generic(dst);
-	if (xdst->u.rt.rt_uncached_list)
-		rt_del_uncached_list(&xdst->u.rt);
+	rt_del_uncached_list(&xdst->u.rt);
 	xfrm_dst_destroy(xdst);
 }