1 files changed, 146 insertions, 62 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d57641cb3477..df1166b76126 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -121,11 +121,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
 			if (ipv6_addr_loopback(&tw->tw_v6_daddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_daddr) &&
-			     (tw->tw_v6_daddr.s6_addr[12] == 127)) ||
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) ||
 			    ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) &&
-			     (tw->tw_v6_rcv_saddr.s6_addr[12] == 127)))
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr))
 				loopback = true;
 		} else
 #endif
@@ -164,9 +162,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 		 * without appearing to create any others.
 		 */
 		if (likely(!tp->repair)) {
-			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-			if (tp->write_seq == 0)
-				tp->write_seq = 1;
+			u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+			if (!seq)
+				seq = 1;
+			WRITE_ONCE(tp->write_seq, seq);
 			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
 			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
 		}
@@ -253,7 +253,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tp->rx_opt.ts_recent	   = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		if (likely(!tp->repair))
-			tp->write_seq	   = 0;
+			WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	inet->inet_dport = usin->sin_port;
@@ -291,16 +291,17 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcp_seq(inet->inet_saddr,
-						       inet->inet_daddr,
-						       inet->inet_sport,
-						       usin->sin_port);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcp_seq(inet->inet_saddr,
+						  inet->inet_daddr,
+						  inet->inet_sport,
+						  usin->sin_port));
 		tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
 						 inet->inet_saddr,
 						 inet->inet_daddr);
 	}
 
-	inet->inet_id = tp->write_seq ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
@@ -478,7 +479,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
-	fastopen = tp->fastopen_rsk;
+	fastopen = rcu_dereference(tp->fastopen_rsk);
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
@@ -700,9 +701,21 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	rcu_read_lock();
 	hash_location = tcp_parse_md5sig_option(th);
 	if (sk && sk_fullsock(sk)) {
-		key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
-					&ip_hdr(skb)->saddr, AF_INET);
+		const union tcp_md5_addr *addr;
+		int l3index;
+
+		/* sdif set, means packet ingressed via a device
+		 * in an L3 domain and inet_iif is set to it.
+		 */
+		l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0;
+		addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
+		key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 	} else if (hash_location) {
+		const union tcp_md5_addr *addr;
+		int sdif = tcp_v4_sdif(skb);
+		int dif = inet_iif(skb);
+		int l3index;
+
 		/*
 		 * active side is lost. Try to find listening socket through
 		 * source port, and then find md5 key through listening socket.
@@ -713,14 +726,17 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
 					     ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
-					     ntohs(th->source), inet_iif(skb),
-					     tcp_v4_sdif(skb));
+					     ntohs(th->source), dif, sdif);
 		/* don't send rst if it can't find key */
 		if (!sk1)
 			goto out;
 
-		key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
-					&ip_hdr(skb)->saddr, AF_INET);
+		/* sdif set, means packet ingressed via a device
+		 * in an L3 domain and dif is set to it.
+		 */
+		l3index = sdif ? dif : 0;
+		addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
+		key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET);
 		if (!key)
 			goto out;
 
@@ -771,6 +787,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
+		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
 	}
 	ip_send_unicast_reply(ctl_sk,
@@ -866,6 +884,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+			   inet_twsk(sk)->tw_priority : sk->sk_priority;
 	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -900,6 +920,9 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
+	const union tcp_md5_addr *addr;
+	int l3index;
+
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
@@ -911,14 +934,15 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	 * exception of <SYN> segments, MUST be right-shifted by
 	 * Rcv.Wind.Shift bits:
 	 */
+	addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
+	l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0;
 	tcp_v4_send_ack(sk, skb, seq,
 			tcp_rsk(req)->rcv_nxt,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent,
 			0,
-			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
-					  AF_INET),
+			tcp_md5_do_lookup(sk, l3index, addr, AF_INET),
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			ip_hdr(skb)->tos);
 }
@@ -978,7 +1002,7 @@ DEFINE_STATIC_KEY_FALSE(tcp_md5_needed);
 EXPORT_SYMBOL(tcp_md5_needed);
 
 /* Find the Key structure for an address.  */
-struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
+struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 					   const union tcp_md5_addr *addr,
 					   int family)
 {
@@ -998,7 +1022,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
 	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
 		if (key->family != family)
 			continue;
-
+		if (key->l3index && key->l3index != l3index)
+			continue;
 		if (family == AF_INET) {
 			mask = inet_make_mask(key->prefixlen);
 			match = (key->addr.a4.s_addr & mask) ==
@@ -1022,7 +1047,8 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup);
 
 static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 						      const union tcp_md5_addr *addr,
-						      int family, u8 prefixlen)
+						      int family, u8 prefixlen,
+						      int l3index)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
@@ -1041,6 +1067,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
 		if (key->family != family)
 			continue;
+		if (key->l3index && key->l3index != l3index)
+			continue;
 		if (!memcmp(&key->addr, addr, size) &&
 		    key->prefixlen == prefixlen)
 			return key;
@@ -1052,23 +1080,26 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk)
 {
 	const union tcp_md5_addr *addr;
+	int l3index;
 
+	l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
+						 addr_sk->sk_bound_dev_if);
 	addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr;
-	return tcp_md5_do_lookup(sk, addr, AF_INET);
+	return tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 }
 EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
 /* This can be called on a newly created socket, from other files */
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
-		   int family, u8 prefixlen, const u8 *newkey, u8 newkeylen,
-		   gfp_t gfp)
+		   int family, u8 prefixlen, int l3index,
+		   const u8 *newkey, u8 newkeylen, gfp_t gfp)
 {
 	/* Add Key to the list */
 	struct tcp_md5sig_key *key;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_info *md5sig;
 
-	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
 	if (key) {
 		/* Pre-existing entry - just update that one. */
 		memcpy(key->key, newkey, newkeylen);
@@ -1100,6 +1131,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	key->keylen = newkeylen;
 	key->family = family;
 	key->prefixlen = prefixlen;
+	key->l3index = l3index;
 	memcpy(&key->addr, addr,
 	       (family == AF_INET6) ? sizeof(struct in6_addr) :
 				      sizeof(struct in_addr));
@@ -1109,11 +1141,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 EXPORT_SYMBOL(tcp_md5_do_add);
 
 int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
-		   u8 prefixlen)
+		   u8 prefixlen, int l3index)
 {
 	struct tcp_md5sig_key *key;
 
-	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
 	if (!key)
 		return -ENOENT;
 	hlist_del_rcu(&key->node);
@@ -1144,7 +1176,9 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 {
 	struct tcp_md5sig cmd;
 	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
+	const union tcp_md5_addr *addr;
 	u8 prefixlen = 32;
+	int l3index = 0;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -1162,16 +1196,34 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 			return -EINVAL;
 	}
 
+	if (optname == TCP_MD5SIG_EXT &&
+	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
+		struct net_device *dev;
+
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex);
+		if (dev && netif_is_l3_master(dev))
+			l3index = dev->ifindex;
+
+		rcu_read_unlock();
+
+		/* ok to reference set/not set outside of rcu;
+		 * right now device MUST be an L3 master
+		 */
+		if (!dev || !l3index)
+			return -EINVAL;
+	}
+
+	addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr;
+
 	if (!cmd.tcpm_keylen)
-		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
-				      AF_INET, prefixlen);
+		return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index);
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
 
-	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
-			      AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen,
-			      GFP_KERNEL);
+	return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index,
+			      cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
 static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp,
@@ -1281,7 +1333,8 @@ EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
 /* Called with rcu_read_lock() */
 static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
-				    const struct sk_buff *skb)
+				    const struct sk_buff *skb,
+				    int dif, int sdif)
 {
 #ifdef CONFIG_TCP_MD5SIG
 	/*
@@ -1296,11 +1349,17 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
 	struct tcp_md5sig_key *hash_expected;
 	const struct iphdr *iph = ip_hdr(skb);
 	const struct tcphdr *th = tcp_hdr(skb);
-	int genhash;
+	const union tcp_md5_addr *addr;
 	unsigned char newhash[16];
+	int genhash, l3index;
+
+	/* sdif set, means packet ingressed via a device
+	 * in an L3 domain and dif is set to the l3mdev
+	 */
+	l3index = sdif ? dif : 0;
 
-	hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
-					  AF_INET);
+	addr = (union tcp_md5_addr *)&iph->saddr;
+	hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 	hash_location = tcp_parse_md5sig_option(th);
 
 	/* We've parsed the options - do we have a hash? */
@@ -1326,11 +1385,11 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
-		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
+		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n",
 				     &iph->saddr, ntohs(th->source),
 				     &iph->daddr, ntohs(th->dest),
 				     genhash ? " tcp_v4_calc_md5_hash failed"
-				     : "");
+				     : "", l3index);
 		return true;
 	}
 	return false;
@@ -1367,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
-static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.mss_clamp	=	TCP_MSS_DEFAULT,
 #ifdef CONFIG_TCP_MD5SIG
 	.req_md5_lookup	=	tcp_v4_md5_lookup,
@@ -1414,7 +1473,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *newtp;
 	struct sock *newsk;
 #ifdef CONFIG_TCP_MD5SIG
+	const union tcp_md5_addr *addr;
 	struct tcp_md5sig_key *key;
+	int l3index;
 #endif
 	struct ip_options_rcu *inet_opt;
 
@@ -1443,7 +1504,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	newinet->inet_id = newtp->write_seq ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
@@ -1462,9 +1523,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_initialize_rcv_mss(newsk);
 
 #ifdef CONFIG_TCP_MD5SIG
+	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
 	/* Copy over the MD5 key from the original socket */
-	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
-				AF_INET);
+	addr = (union tcp_md5_addr *)&newinet->inet_daddr;
+	key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 	if (key) {
 		/*
 		 * We're using one, so create a matching key
@@ -1472,8 +1534,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
-			       AF_INET, 32, key->key, key->keylen, GFP_ATOMIC);
+		tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index,
+			       key->key, key->keylen, GFP_ATOMIC);
 		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
 	}
 #endif
@@ -1515,6 +1577,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+			 struct tcphdr *th, u32 *cookie)
+{
+	u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+	mss = tcp_get_syncookie_mss(&tcp_request_sock_ops,
+				    &tcp_request_sock_ipv4_ops, sk, th);
+	if (mss) {
+		*cookie = __cookie_v4_init_sequence(iph, th, &mss);
+		tcp_synq_overflow(sk);
+	}
+#endif
+	return mss;
+}
+
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
@@ -1625,7 +1702,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
+	u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
 	struct skb_shared_info *shinfo;
 	const struct tcphdr *th;
 	struct tcphdr *thtail;
@@ -1788,6 +1865,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	struct sk_buff *skb_to_free;
 	int sdif = inet_sdif(skb);
+	int dif = inet_iif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	bool refcounted;
@@ -1836,7 +1914,7 @@ process:
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
@@ -1894,10 +1972,10 @@ process:
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	if (tcp_v4_inbound_md5_hash(sk, skb))
+	if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))
 		goto discard_and_relse;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
@@ -2102,7 +2180,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk);
+	BUG_ON(rcu_access_pointer(tp->fastopen_rsk));
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
@@ -2127,13 +2205,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -2141,9 +2220,9 @@ get_head:
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == afinfo->family)
@@ -2431,17 +2510,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
-		rx_queue = sk->sk_ack_backlog;
+		rx_queue = READ_ONCE(sk->sk_ack_backlog);
 	else
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
 		 */
-		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      READ_ONCE(tp->copied_seq), 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
 		i, src, srcp, dest, destp, state,
-		tp->write_seq - tp->snd_una,
+		READ_ONCE(tp->write_seq) - tp->snd_una,
 		rx_queue,
 		timer_active,
 		jiffies_delta_to_clock_t(timer_expires - jiffies),
@@ -2598,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
 	int cpu;
 
 	if (net->ipv4.tcp_congestion_control)
-		module_put(net->ipv4.tcp_congestion_control->owner);
+		bpf_module_put(net->ipv4.tcp_congestion_control,
+			       net->ipv4.tcp_congestion_control->owner);
 
 	for_each_possible_cpu(cpu)
 		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
@@ -2637,6 +2718,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
 	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
+	net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS;
 
 	net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
 	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
@@ -2652,12 +2734,13 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
 	net->ipv4.sysctl_tcp_tw_reuse = 2;
+	net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1;
 
 	cnt = tcp_hashinfo.ehash_mask + 1;
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
-	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
@@ -2703,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net)
 
 	/* Reno is always built in */
 	if (!net_eq(net, &init_net) &&
-	    try_module_get(init_net.ipv4.tcp_congestion_control->owner))
+	    bpf_try_module_get(init_net.ipv4.tcp_congestion_control,
+			       init_net.ipv4.tcp_congestion_control->owner))
 		net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
 	else
 		net->ipv4.tcp_congestion_control = &tcp_reno;