Merge tag 'v4.15-rc1' into next-seccomp

Linux 4.15-rc1

93 files changed, 3493 insertions, 2732 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a2557942fa..f48fe6fc7e8c 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -70,11 +70,9 @@ config IP_MULTIPLE_TABLES
 	  address into account. Furthermore, the TOS (Type-Of-Service) field
 	  of the packet can be used for routing decisions as well.
 
-	  If you are interested in this, please see the preliminary
-	  documentation at <http://www.compendium.com.ar/policy-routing.txt>
-	  and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>.
-	  You will need supporting software from
-	  <ftp://ftp.tux.org/pub/net/ip-routing/>.
+	  If you need more information, see the Linux Advanced
+	  Routing and Traffic Control documentation at
+	  <http://lartc.org/howto/lartc.rpdb.html>
 
 	  If unsure, say N.
 
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index afcb435adfbe..c6c8ad1d4b6d 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the Linux TCP/IP (INET) layer.
 #
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 76c2077c3f5b..f00499a46927 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 	unsigned char old_state;
-	int err;
+	int err, tcp_fastopen;
 
 	lock_sock(sk);
 
@@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog)
 		 * because the socket was in TCP_LISTEN state previously but
 		 * was shutdown() rather than close().
 		 */
-		if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
-		    (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+		tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+		if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
+		    (tcp_fastopen & TFO_SERVER_ENABLE) &&
 		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
 			fastopen_queue_tune(sk, backlog);
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once(sock_net(sk));
 		}
 
 		err = inet_csk_listen_start(sk, backlog);
@@ -826,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how)
 		err = -ENOTCONN;
 		/* Hack to wake up other listeners, who can poll for
 		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
+		/* fall through */
 	default:
 		sk->sk_shutdown |= how;
 		if (sk->sk_prot->shutdown)
@@ -839,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how)
 	case TCP_LISTEN:
 		if (!(how & RCV_SHUTDOWN))
 			break;
-		/* Fall through */
+		/* fall through */
 	case TCP_SYN_SENT:
 		err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
 		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
@@ -944,6 +946,8 @@ const struct proto_ops inet_stream_ops = {
 	.sendpage	   = inet_sendpage,
 	.splice_read	   = tcp_splice_read,
 	.read_sock	   = tcp_read_sock,
+	.sendmsg_locked    = tcp_sendmsg_locked,
+	.sendpage_locked   = tcp_sendpage_locked,
 	.peek_len	   = tcp_peek_len,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_sock_common_setsockopt,
@@ -1602,6 +1606,9 @@ static const struct net_protocol igmp_protocol = {
 };
 #endif
 
+/* thinking of making this const? Don't.
+ * early_demux can change based on sysctl.
+ */
 static struct net_protocol tcp_protocol = {
 	.early_demux	=	tcp_v4_early_demux,
 	.early_demux_handler =  tcp_v4_early_demux,
@@ -1612,6 +1619,9 @@ static struct net_protocol tcp_protocol = {
 	.icmp_strict_tag_validation = 1,
 };
 
+/* thinking of making this const? Don't.
+ * early_demux can change based on sysctl.
+ */
 static struct net_protocol udp_protocol = {
 	.early_demux =	udp_v4_early_demux,
 	.early_demux_handler =	udp_v4_early_demux,
@@ -1731,6 +1741,13 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
 #endif
 
+	/* Some igmp sysctl, whose values are always used */
+	net->ipv4.sysctl_igmp_max_memberships = 20;
+	net->ipv4.sysctl_igmp_max_msf = 10;
+	/* IGMP reports for link-local multicast groups are enabled by default */
+	net->ipv4.sysctl_igmp_llm_reports = 1;
+	net->ipv4.sysctl_igmp_qrv = 2;
+
 	return 0;
 }
 
@@ -1771,6 +1788,11 @@ static const struct net_offload ipip_offload = {
 	},
 };
 
+static int __init ipip_offload_init(void)
+{
+	return inet_add_offload(&ipip_offload, IPPROTO_IPIP);
+}
+
 static int __init ipv4_offload_init(void)
 {
 	/*
@@ -1780,9 +1802,10 @@ static int __init ipv4_offload_init(void)
 		pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
 	if (tcpv4_offload_init() < 0)
 		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
+	if (ipip_offload_init() < 0)
+		pr_crit("%s: Cannot add IPIP protocol offload\n", __func__);
 
 	dev_add_offload(&ip_packet_offload);
-	inet_add_offload(&ipip_offload, IPPROTO_IPIP);
 	return 0;
 }
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 37db44f60718..4dd95cdd8070 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -240,7 +240,7 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 		if (err == -EINPROGRESS)
 			goto out;
 
-		if (err == -EBUSY)
+		if (err == -ENOSPC)
 			err = NET_XMIT_DROP;
 		goto out_free;
 	}
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 8b52179ddc6e..a8d7c5a9fb05 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -171,7 +171,7 @@ struct neigh_table arp_tbl = {
 			[NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ,
 			[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
 			[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
-			[NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024,
+			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
 			[NEIGH_VAR_PROXY_QLEN] = 64,
 			[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
 			[NEIGH_VAR_PROXY_DELAY]	= (8 * HZ) / 10,
@@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSARP:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
+		/* fall through */
 	case SIOCGARP:
 		err = copy_from_user(&r, arg, sizeof(struct arpreq));
 		if (err)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index c4c6e1969ed0..82178cc69c96 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1523,9 +1523,17 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
 	int taglen;
 
 	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
-		if (optptr[0] == IPOPT_CIPSO)
+		switch (optptr[0]) {
+		case IPOPT_CIPSO:
 			return optptr;
-		taglen = optptr[1];
+		case IPOPT_END:
+			return NULL;
+		case IPOPT_NOOP:
+			taglen = 1;
+			break;
+		default:
+			taglen = optptr[1];
+		}
 		optlen -= taglen;
 		optptr += taglen;
 	}
@@ -1943,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg(&req_inet->opt, opt);
+	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
 	if (opt)
 		kfree_rcu(opt, rcu);
 
@@ -1965,11 +1973,13 @@ req_setattr_failure:
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
 {
+	struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1);
 	int hdr_delta = 0;
-	struct ip_options_rcu *opt = *opt_ptr;
 
+	if (!opt || opt->opt.cipso == 0)
+		return 0;
 	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
@@ -2031,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
  */
 void cipso_v4_sock_delattr(struct sock *sk)
 {
-	int hdr_delta;
-	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
+	int hdr_delta;
 
 	sk_inet = inet_sk(sk);
-	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (!opt || opt->opt.cipso == 0)
-		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
@@ -2058,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options_rcu *opt;
-	struct inet_request_sock *req_inet;
-
-	req_inet = inet_rsk(req);
-	opt = req_inet->opt;
-	if (!opt || opt->opt.cipso == 0)
-		return;
-
-	cipso_v4_delopt(&req_inet->opt);
+	cipso_v4_delopt(&inet_rsk(req)->ireq_opt);
 }
 
 /**
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 38d9af9b917c..a4573bccd6da 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa)
  */
 struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 {
-	u32 hash = inet_addr_hash(net, addr);
 	struct net_device *result = NULL;
 	struct in_ifaddr *ifa;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
-		if (ifa->ifa_local == addr) {
-			struct net_device *dev = ifa->ifa_dev->dev;
-
-			if (!net_eq(dev_net(dev), net))
-				continue;
-			result = dev;
-			break;
-		}
-	}
-	if (!result) {
+	ifa = inet_lookup_ifaddr_rcu(net, addr);
+	if (!ifa) {
 		struct flowi4 fl4 = { .daddr = addr };
 		struct fib_result res = { 0 };
 		struct fib_table *local;
@@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 		    !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
 		    res.type == RTN_LOCAL)
 			result = FIB_RES_DEV(res);
+	} else {
+		result = ifa->ifa_dev->dev;
 	}
 	if (result && devref)
 		dev_hold(result);
@@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 }
 EXPORT_SYMBOL(__ip_dev_find);
 
+/* called under RCU lock */
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
+{
+	u32 hash = inet_addr_hash(net, addr);
+	struct in_ifaddr *ifa;
+
+	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
+		if (ifa->ifa_local == addr &&
+		    net_eq(dev_net(ifa->ifa_dev->dev), net))
+			return ifa;
+
+	return NULL;
+}
+
 static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
 
 static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
@@ -438,7 +444,7 @@ static void check_lifetime(struct work_struct *work);
 static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
 
 static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
-			     u32 portid)
+			     u32 portid, struct netlink_ext_ack *extack)
 {
 	struct in_device *in_dev = ifa->ifa_dev;
 	struct in_ifaddr *ifa1, **ifap, **last_primary;
@@ -483,6 +489,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	 */
 	ivi.ivi_addr = ifa->ifa_address;
 	ivi.ivi_dev = ifa->ifa_dev;
+	ivi.extack = extack;
 	ret = blocking_notifier_call_chain(&inetaddr_validator_chain,
 					   NETDEV_UP, &ivi);
 	ret = notifier_to_errno(ret);
@@ -515,7 +522,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 
 static int inet_insert_ifa(struct in_ifaddr *ifa)
 {
-	return __inet_insert_ifa(ifa, NULL, 0);
+	return __inet_insert_ifa(ifa, NULL, 0, NULL);
 }
 
 static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
@@ -896,7 +903,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 				return ret;
 			}
 		}
-		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid,
+					 extack);
 	} else {
 		inet_free_ifa(ifa);
 
@@ -1516,6 +1524,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 		if (inetdev_valid_mtu(dev->mtu))
 			break;
 		/* disable IP when MTU is not enough */
+		/* fall through */
 	case NETDEV_UNREGISTER:
 		inetdev_destroy(in_dev);
 		break;
@@ -1751,7 +1760,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 	struct nlattr *a, *tb[IFLA_INET_MAX+1];
 	int err, rem;
 
-	if (dev && !__in_dev_get_rtnl(dev))
+	if (dev && !__in_dev_get_rcu(dev))
 		return -EAFNOSUPPORT;
 
 	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
@@ -1775,7 +1784,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 
 static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
 {
-	struct in_device *in_dev = __in_dev_get_rtnl(dev);
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	struct nlattr *a, *tb[IFLA_INET_MAX+1];
 	int rem;
 
@@ -2491,9 +2500,9 @@ void __init devinet_init(void)
 
 	rtnl_af_register(&inet_af_ops);
 
-	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL);
+	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0);
+	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0);
+	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, 0);
 	rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
-		      inet_netconf_dump_devconf, NULL);
+		      inet_netconf_dump_devconf, 0);
 }
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0cbee0a666ff..d57aa64fa7c7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -258,7 +258,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		esp_output_udp_encap(x, skb, esp);
 
 	if (!skb_cloned(skb)) {
-		if (tailen <= skb_availroom(skb)) {
+		if (tailen <= skb_tailroom(skb)) {
 			nfrags = 1;
 			trailer = skb;
 			tail = skb_tail_pointer(trailer);
@@ -292,8 +292,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 
 			kunmap_atomic(vaddr);
 
-			spin_unlock_bh(&x->lock);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -301,6 +299,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			skb_shinfo(skb)->nr_frags = ++nfrags;
 
 			pfrag->offset = pfrag->offset + allocsize;
+
+			spin_unlock_bh(&x->lock);
+
 			nfrags++;
 
 			skb->len += tailen;
@@ -381,7 +382,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		           (unsigned char *)esph - skb->data,
 		           assoclen + ivlen + esp->clen + alen);
 	if (unlikely(err < 0))
-		goto error;
+		goto error_free;
 
 	if (!esp->inplace) {
 		int allocsize;
@@ -392,7 +393,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		spin_lock_bh(&x->lock);
 		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
 			spin_unlock_bh(&x->lock);
-			goto error;
+			goto error_free;
 		}
 
 		skb_shinfo(skb)->nr_frags = 1;
@@ -409,7 +410,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			           (unsigned char *)esph - skb->data,
 			           assoclen + ivlen + esp->clen + alen);
 		if (unlikely(err < 0))
-			goto error;
+			goto error_free;
 	}
 
 	if ((x->props.flags & XFRM_STATE_ESN))
@@ -431,7 +432,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	case -EINPROGRESS:
 		goto error;
 
-	case -EBUSY:
+	case -ENOSPC:
 		err = NET_XMIT_DROP;
 		break;
 
@@ -442,8 +443,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 
 	if (sg != dsg)
 		esp_ssg_unref(x, tmp);
-	kfree(tmp);
 
+error_free:
+	kfree(tmp);
 error:
 	return err;
 }
@@ -499,18 +501,59 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	return esp_output_tail(x, skb, &esp);
 }
 
+static inline int esp_remove_trailer(struct sk_buff *skb)
+{
+	struct xfrm_state *x = xfrm_input_state(skb);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct crypto_aead *aead = x->data;
+	int alen, hlen, elen;
+	int padlen, trimlen;
+	__wsum csumdiff;
+	u8 nexthdr[2];
+	int ret;
+
+	alen = crypto_aead_authsize(aead);
+	hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
+	elen = skb->len - hlen;
+
+	if (xo && (xo->flags & XFRM_ESP_NO_TRAILER)) {
+		ret = xo->proto;
+		goto out;
+	}
+
+	if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2))
+		BUG();
+
+	ret = -EINVAL;
+	padlen = nexthdr[0];
+	if (padlen + 2 + alen >= elen) {
+		net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n",
+				    padlen + 2, elen - alen);
+		goto out;
+	}
+
+	trimlen = alen + padlen + 2;
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0);
+		skb->csum = csum_block_sub(skb->csum, csumdiff,
+					   skb->len - trimlen);
+	}
+	pskb_trim(skb, skb->len - trimlen);
+
+	ret = nexthdr[1];
+
+out:
+	return ret;
+}
+
 int esp_input_done2(struct sk_buff *skb, int err)
 {
 	const struct iphdr *iph;
 	struct xfrm_state *x = xfrm_input_state(skb);
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct crypto_aead *aead = x->data;
-	int alen = crypto_aead_authsize(aead);
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
-	int elen = skb->len - hlen;
 	int ihl;
-	u8 nexthdr[2];
-	int padlen;
 
 	if (!xo || (xo && !(xo->flags & CRYPTO_DONE)))
 		kfree(ESP_SKB_CB(skb)->tmp);
@@ -518,16 +561,10 @@ int esp_input_done2(struct sk_buff *skb, int err)
 	if (unlikely(err))
 		goto out;
 
-	if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
-		BUG();
-
-	err = -EINVAL;
-	padlen = nexthdr[0];
-	if (padlen + 2 + alen >= elen)
+	err = esp_remove_trailer(skb);
+	if (unlikely(err < 0))
 		goto out;
 
-	/* ... check padding bits here. Silly. :-) */
-
 	iph = ip_hdr(skb);
 	ihl = iph->ihl * 4;
 
@@ -568,15 +605,12 @@ int esp_input_done2(struct sk_buff *skb, int err)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
-	pskb_trim(skb, skb->len - alen - padlen - 2);
-	__skb_pull(skb, hlen);
+	skb_pull_rcsum(skb, hlen);
 	if (x->props.mode == XFRM_MODE_TUNNEL)
 		skb_reset_transport_header(skb);
 	else
 		skb_set_transport_header(skb, -ihl);
 
-	err = nexthdr[1];
-
 	/* RFC4303: Drop dummy packets without any error */
 	if (err == IPPROTO_NONE)
 		err = -EINVAL;
@@ -695,8 +729,10 @@ skip_cow:
 
 	sg_init_table(sg, nfrags);
 	err = skb_to_sgvec(skb, sg, 0, skb->len);
-	if (unlikely(err < 0))
+	if (unlikely(err < 0)) {
+		kfree(tmp);
 		goto out;
+	}
 
 	skb->ip_summed = CHECKSUM_NONE;
 
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index e0666016a764..f8b918c766b0 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -182,11 +182,13 @@ out:
 static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
+	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
 		return -EINVAL;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	if (!(xo->flags & CRYPTO_DONE))
+		skb->ip_summed = CHECKSUM_NONE;
 
 	return esp_input_done2(skb, 0);
 }
@@ -257,7 +259,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
 
 	err = esp_output_tail(x, skb, &esp);
-	if (err < 0)
+	if (err)
 		return err;
 
 	secpath_reset(skb);
@@ -303,3 +305,4 @@ module_init(esp4_offload_init);
 module_exit(esp4_offload_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
+MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 044d2a159a3c..f52d27a422c3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -73,6 +73,11 @@ fail:
 	fib_free_table(main_table);
 	return -ENOMEM;
 }
+
+static bool fib4_has_custom_rules(struct net *net)
+{
+	return false;
+}
 #else
 
 struct fib_table *fib_new_table(struct net *net, u32 id)
@@ -128,6 +133,11 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 	}
 	return NULL;
 }
+
+static bool fib4_has_custom_rules(struct net *net)
+{
+	return net->ipv4.fib_has_custom_rules;
+}
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 static void fib_replace_table(struct net *net, struct fib_table *old,
@@ -345,9 +355,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
 		goto e_inval;
-	if (!rpf && !fib_num_tclassid_users(net) &&
-	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
-		goto last_resort;
 	fib_combine_itag(itag, &res);
 	dev_match = false;
 
@@ -402,13 +409,28 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			struct in_device *idev, u32 *itag)
 {
 	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
+	struct net *net = dev_net(dev);
 
-	if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
-	    IN_DEV_ACCEPT_LOCAL(idev) &&
+	if (!r && !fib_num_tclassid_users(net) &&
 	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
+		if (IN_DEV_ACCEPT_LOCAL(idev))
+			goto ok;
+		/* with custom local routes in place, checking local addresses
+		 * only will be too optimistic, with custom rules, checking
+		 * local addresses only can be too strict, e.g. due to vrf
+		 */
+		if (net->ipv4.fib_has_custom_local_routes ||
+		    fib4_has_custom_rules(net))
+			goto full_check;
+		if (inet_lookup_ifaddr_rcu(net, src))
+			return -EINVAL;
+
+ok:
 		*itag = 0;
 		return 0;
 	}
+
+full_check:
 	return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
 }
 
@@ -759,6 +781,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	err = fib_table_insert(net, tb, &cfg, extack);
+	if (!err && cfg.fc_type == RTN_LOCAL)
+		net->ipv4.fib_has_custom_local_routes = true;
 errout:
 	return err;
 }
@@ -1247,22 +1271,28 @@ static int __net_init ip_fib_net_init(struct net *net)
 	int err;
 	size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ;
 
-	net->ipv4.fib_seq = 0;
+	err = fib4_notifier_init(net);
+	if (err)
+		return err;
 
 	/* Avoid false sharing : Use at least a full cache line */
 	size = max_t(size_t, size, L1_CACHE_BYTES);
 
 	net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL);
-	if (!net->ipv4.fib_table_hash)
-		return -ENOMEM;
+	if (!net->ipv4.fib_table_hash) {
+		err = -ENOMEM;
+		goto err_table_hash_alloc;
+	}
 
 	err = fib4_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto err_rules_init;
 	return 0;
 
-fail:
+err_rules_init:
 	kfree(net->ipv4.fib_table_hash);
+err_table_hash_alloc:
+	fib4_notifier_exit(net);
 	return err;
 }
 
@@ -1292,6 +1322,7 @@ static void ip_fib_net_exit(struct net *net)
 #endif
 	rtnl_unlock();
 	kfree(net->ipv4.fib_table_hash);
+	fib4_notifier_exit(net);
 }
 
 static int __net_init fib_net_init(struct net *net)
@@ -1341,7 +1372,7 @@ void __init ip_fib_init(void)
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0);
 }
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 769ab87ebc4b..e6ff282bb7f4 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _FIB_LOOKUP_H
 #define _FIB_LOOKUP_H
 
@@ -32,6 +33,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 				 struct netlink_ext_ack *extack);
 int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		 struct netlink_ext_ack *extack);
+bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi);
 int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
 		  u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi,
 		  unsigned int);
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
index e0714d975947..b804ccbdb241 100644
--- a/net/ipv4/fib_notifier.c
+++ b/net/ipv4/fib_notifier.c
@@ -1,86 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/rtnetlink.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
+#include <linux/socket.h>
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <net/net_namespace.h>
+#include <net/fib_notifier.h>
 #include <net/netns/ipv4.h>
 #include <net/ip_fib.h>
 
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
-		      enum fib_event_type event_type,
-		      struct fib_notifier_info *info)
+int call_fib4_notifier(struct notifier_block *nb, struct net *net,
+		       enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
 {
-	info->net = net;
-	return nb->notifier_call(nb, event_type, info);
+	info->family = AF_INET;
+	return call_fib_notifier(nb, net, event_type, info);
 }
 
-int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
-		       struct fib_notifier_info *info)
+int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
+			struct fib_notifier_info *info)
 {
+	ASSERT_RTNL();
+
+	info->family = AF_INET;
 	net->ipv4.fib_seq++;
-	info->net = net;
-	return atomic_notifier_call_chain(&fib_chain, event_type, info);
+	return call_fib_notifiers(net, event_type, info);
 }
 
-static unsigned int fib_seq_sum(void)
+static unsigned int fib4_seq_read(struct net *net)
 {
-	unsigned int fib_seq = 0;
-	struct net *net;
-
-	rtnl_lock();
-	for_each_net(net)
-		fib_seq += net->ipv4.fib_seq;
-	rtnl_unlock();
+	ASSERT_RTNL();
 
-	return fib_seq;
+	return net->ipv4.fib_seq + fib4_rules_seq_read(net);
 }
 
-static bool fib_dump_is_consistent(struct notifier_block *nb,
-				   void (*cb)(struct notifier_block *nb),
-				   unsigned int fib_seq)
+static int fib4_dump(struct net *net, struct notifier_block *nb)
 {
-	atomic_notifier_chain_register(&fib_chain, nb);
-	if (fib_seq == fib_seq_sum())
-		return true;
-	atomic_notifier_chain_unregister(&fib_chain, nb);
-	if (cb)
-		cb(nb);
-	return false;
+	int err;
+
+	err = fib4_rules_dump(net, nb);
+	if (err)
+		return err;
+
+	fib_notify(net, nb);
+
+	return 0;
 }
 
-#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
-			  void (*cb)(struct notifier_block *nb))
-{
-	int retries = 0;
+static const struct fib_notifier_ops fib4_notifier_ops_template = {
+	.family		= AF_INET,
+	.fib_seq_read	= fib4_seq_read,
+	.fib_dump	= fib4_dump,
+	.owner		= THIS_MODULE,
+};
 
-	do {
-		unsigned int fib_seq = fib_seq_sum();
-		struct net *net;
+int __net_init fib4_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
 
-		/* Mutex semantics guarantee that every change done to
-		 * FIB tries before we read the change sequence counter
-		 * is now visible to us.
-		 */
-		rcu_read_lock();
-		for_each_net_rcu(net) {
-			fib_rules_notify(net, nb);
-			fib_notify(net, nb);
-		}
-		rcu_read_unlock();
+	net->ipv4.fib_seq = 0;
 
-		if (fib_dump_is_consistent(nb, cb, fib_seq))
-			return 0;
-	} while (++retries < FIB_DUMP_MAX_RETRIES);
+	ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv4.notifier_ops = ops;
 
-	return -EBUSY;
+	return 0;
 }
-EXPORT_SYMBOL(register_fib_notifier);
 
-int unregister_fib_notifier(struct notifier_block *nb)
+void __net_exit fib4_notifier_exit(struct net *net)
 {
-	return atomic_notifier_chain_unregister(&fib_chain, nb);
+	fib_notifier_ops_unregister(net->ipv4.notifier_ops);
 }
-EXPORT_SYMBOL(unregister_fib_notifier);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 778ecf977eb2..35d646a62ad4 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -68,6 +68,16 @@ bool fib4_rule_default(const struct fib_rule *rule)
 }
 EXPORT_SYMBOL_GPL(fib4_rule_default);
 
+int fib4_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, AF_INET);
+}
+
+unsigned int fib4_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, AF_INET);
+}
+
 int __fib_lookup(struct net *net, struct flowi4 *flp,
 		 struct fib_result *res, unsigned int flags)
 {
@@ -185,38 +195,6 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
-static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
-				  enum fib_event_type event_type,
-				  struct fib_rule *rule)
-{
-	struct fib_rule_notifier_info info = {
-		.rule = rule,
-	};
-
-	return call_fib_notifier(nb, net, event_type, &info.info);
-}
-
-static int call_fib_rule_notifiers(struct net *net,
-				   enum fib_event_type event_type,
-				   struct fib_rule *rule)
-{
-	struct fib_rule_notifier_info info = {
-		.rule = rule,
-	};
-
-	return call_fib_notifiers(net, event_type, &info.info);
-}
-
-/* Called with rcu_read_lock() */
-void fib_rules_notify(struct net *net, struct notifier_block *nb)
-{
-	struct fib_rules_ops *ops = net->ipv4.rules_ops;
-	struct fib_rule *rule;
-
-	list_for_each_entry_rcu(rule, &ops->rules_list, list)
-		call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule);
-}
-
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
 	FRA_GENERIC_POLICY,
 	[FRA_FLOW]	= { .type = NLA_U32 },
@@ -273,7 +251,6 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule);
 
 	err = 0;
 errout:
@@ -295,7 +272,6 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule);
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 222100103808..f04d944f8abe 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -44,6 +44,7 @@
 #include <net/netlink.h>
 #include <net/nexthop.h>
 #include <net/lwtunnel.h>
+#include <net/fib_notifier.h>
 
 #include "fib_lookup.h"
 
@@ -219,7 +220,7 @@ static void free_fib_info_rcu(struct rcu_head *head)
 	} endfor_nexthops(fi);
 
 	m = fi->fib_metrics;
-	if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
+	if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
 		kfree(m);
 	kfree(fi);
 }
@@ -600,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi)
 		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
 }
-
-static inline void fib_add_weight(struct fib_info *fi,
-				  const struct fib_nh *nh)
-{
-	fi->fib_weight += nh->nh_weight;
-}
-
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
 
 #define fib_rebalance(fi) do { } while (0)
-#define fib_add_weight(fi, nh) do { } while (0)
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
@@ -695,6 +688,40 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 	return 0;
 }
 
+bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
+{
+	struct nlattr *nla;
+	int remaining;
+
+	if (!cfg->fc_mx)
+		return true;
+
+	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+		int type = nla_type(nla);
+		u32 val;
+
+		if (!type)
+			continue;
+		if (type > RTAX_MAX)
+			return false;
+
+		if (type == RTAX_CC_ALGO) {
+			char tmp[TCP_CA_NAME_MAX];
+			bool ecn_ca = false;
+
+			nla_strlcpy(tmp, nla, sizeof(tmp));
+			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
+		} else {
+			val = nla_get_u32(nla);
+		}
+
+		if (fi->fib_metrics->metrics[type - 1] != val)
+			return false;
+	}
+
+	return true;
+}
+
 
 /*
  * Picture
@@ -739,8 +766,8 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
  *					|
  *					|-> {local prefix} (terminal node)
  */
-static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
-			struct fib_nh *nh, struct netlink_ext_ack *extack)
+static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
+			struct netlink_ext_ack *extack)
 {
 	int err = 0;
 	struct net *net;
@@ -1003,7 +1030,7 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			char tmp[TCP_CA_NAME_MAX];
 
 			nla_strlcpy(tmp, nla, sizeof(tmp));
-			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
 			if (val == TCP_CA_UNSPEC)
 				return -EINVAL;
 		} else {
@@ -1083,15 +1110,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
-		if (!fi->fib_metrics)
-			goto failure;
-		atomic_set(&fi->fib_metrics->refcnt, 1);
-	} else
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
+		refcount_set(&fi->fib_metrics->refcnt, 1);
+	} else {
 		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
-
+	}
+	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
@@ -1221,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		int linkdown = 0;
 
 		change_nexthops(fi) {
-			err = fib_check_nh(cfg, fi, nexthop_nh, extack);
+			err = fib_check_nh(cfg, nexthop_nh, extack);
 			if (err != 0)
 				goto failure;
 			if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
@@ -1238,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 
 	change_nexthops(fi) {
 		fib_info_update_nh_saddr(net, nexthop_nh);
-		fib_add_weight(fi, nexthop_nh);
 	} endfor_nexthops(fi)
 
 	fib_rebalance(fi);
@@ -1328,8 +1356,6 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
-		struct in_device *in_dev;
-
 		if (fi->fib_nh->nh_gw &&
 		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
 			goto nla_put_failure;
@@ -1337,11 +1363,17 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
 			goto nla_put_failure;
 		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
-			in_dev = __in_dev_get_rtnl(fi->fib_nh->nh_dev);
+			struct in_device *in_dev;
+
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev);
 			if (in_dev &&
 			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
 				rtm->rtm_flags |= RTNH_F_DEAD;
+			rcu_read_unlock();
 		}
+		if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD)
+			rtm->rtm_flags |= RTNH_F_OFFLOAD;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid &&
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
@@ -1361,18 +1393,20 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 
 		for_nexthops(fi) {
-			struct in_device *in_dev;
-
 			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
 			if (!rtnh)
 				goto nla_put_failure;
 
 			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
 			if (nh->nh_flags & RTNH_F_LINKDOWN) {
-				in_dev = __in_dev_get_rtnl(nh->nh_dev);
+				struct in_device *in_dev;
+
+				rcu_read_lock();
+				in_dev = __in_dev_get_rcu(nh->nh_dev);
 				if (in_dev &&
 				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
 					rtnh->rtnh_flags |= RTNH_F_DEAD;
+				rcu_read_unlock();
 			}
 			rtnh->rtnh_hops = nh->nh_weight - 1;
 			rtnh->rtnh_ifindex = nh->nh_oif;
@@ -1449,14 +1483,14 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 		if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 		    fib_nh->nh_flags & RTNH_F_LINKDOWN)
 			break;
-		return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type,
-					  &info.info);
+		return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type,
+					   &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
 		    (fib_nh->nh_flags & RTNH_F_DEAD))
-			return call_fib_notifiers(dev_net(fib_nh->nh_dev),
-						  event_type, &info.info);
+			return call_fib4_notifiers(dev_net(fib_nh->nh_dev),
+						   event_type, &info.info);
 	default:
 		break;
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 64668c69dda6..5ddc4aefff12 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -81,39 +81,40 @@
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <net/ip_fib.h>
+#include <net/fib_notifier.h>
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
 static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 				   enum fib_event_type event_type, u32 dst,
-				   int dst_len, struct fib_info *fi,
-				   u8 tos, u8 type, u32 tb_id)
+				   int dst_len, struct fib_alias *fa)
 {
 	struct fib_entry_notifier_info info = {
 		.dst = dst,
 		.dst_len = dst_len,
-		.fi = fi,
-		.tos = tos,
-		.type = type,
-		.tb_id = tb_id,
+		.fi = fa->fa_info,
+		.tos = fa->fa_tos,
+		.type = fa->fa_type,
+		.tb_id = fa->tb_id,
 	};
-	return call_fib_notifier(nb, net, event_type, &info.info);
+	return call_fib4_notifier(nb, net, event_type, &info.info);
 }
 
 static int call_fib_entry_notifiers(struct net *net,
 				    enum fib_event_type event_type, u32 dst,
-				    int dst_len, struct fib_info *fi,
-				    u8 tos, u8 type, u32 tb_id)
+				    int dst_len, struct fib_alias *fa,
+				    struct netlink_ext_ack *extack)
 {
 	struct fib_entry_notifier_info info = {
+		.info.extack = extack,
 		.dst = dst,
 		.dst_len = dst_len,
-		.fi = fi,
-		.tos = tos,
-		.type = type,
-		.tb_id = tb_id,
+		.fi = fa->fa_info,
+		.tos = fa->fa_tos,
+		.type = fa->fa_type,
+		.tb_id = fa->tb_id,
 	};
-	return call_fib_notifiers(net, event_type, &info.info);
+	return call_fib4_notifiers(net, event_type, &info.info);
 }
 
 #define MAX_STAT_DEPTH 32
@@ -1215,9 +1216,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 			new_fa->fa_default = -1;
 
 			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
-						 key, plen, fi,
-						 new_fa->fa_tos, cfg->fc_type,
-						 tb->tb_id);
+						 key, plen, new_fa, extack);
 			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
 				  tb->tb_id, &cfg->fc_nlinfo, nlflags);
 
@@ -1272,8 +1271,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 		tb->tb_num_default++;
 
 	rt_cache_flush(cfg->fc_nlinfo.nl_net);
-	call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type,
-				 tb->tb_id);
+	call_fib_entry_notifiers(net, event, key, plen, new_fa, extack);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, nlflags);
 succeeded:
@@ -1562,7 +1560,8 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 		     fi->fib_prefsrc == cfg->fc_prefsrc) &&
 		    (!cfg->fc_protocol ||
 		     fi->fib_protocol == cfg->fc_protocol) &&
-		    fib_nh_match(cfg, fi, extack) == 0) {
+		    fib_nh_match(cfg, fi, extack) == 0 &&
+		    fib_metrics_match(cfg, fi)) {
 			fa_to_delete = fa;
 			break;
 		}
@@ -1572,8 +1571,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 		return -ESRCH;
 
 	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
-				 fa_to_delete->fa_info, tos,
-				 fa_to_delete->fa_type, tb->tb_id);
+				 fa_to_delete, extack);
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1890,9 +1888,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 
 			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL,
 						 n->key,
-						 KEYLENGTH - fa->fa_slen,
-						 fi, fa->fa_tos, fa->fa_type,
-						 tb->tb_id);
+						 KEYLENGTH - fa->fa_slen, fa,
+						 NULL);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);
@@ -1930,8 +1927,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 			continue;
 
 		call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
-					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
-					fa->fa_type, fa->tb_id);
+					KEYLENGTH - fa->fa_slen, fa);
 	}
 }
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 8e0257d01200..1540db65241a 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -450,6 +450,7 @@ out_unlock:
 out:
 	NAPI_GRO_CB(skb)->flush |= flush;
 	skb_gro_remcsum_cleanup(skb, &grc);
+	skb->remcsum_offload = 0;
 
 	return pp;
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d5cac99170b1..1859c473b21a 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -24,7 +24,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, ufo, gso_partial;
+	bool need_csum, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -47,20 +47,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
 	skb->encap_hdr_csum = need_csum;
 
-	ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
-
 	features &= skb->dev->hw_enc_features;
 
-	/* The only checksum offload we care about from here on out is the
-	 * outer one so strip the existing checksum feature flags based
-	 * on the fact that we will be computing our checksum in software.
-	 */
-	if (ufo) {
-		features &= ~NETIF_F_CSUM_MASK;
-		if (!need_csum)
-			features |= NETIF_F_HW_CSUM;
-	}
-
 	/* segment inner packet. */
 	segs = skb_mac_gso_segment(skb, features);
 	if (IS_ERR_OR_NULL(segs)) {
@@ -98,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
 		pcsum = (__sum16 *)(greh + 1);
 
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c2be26b98b5f..1617604c9284 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -412,7 +412,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	int type = icmp_param->data.icmph.type;
 	int code = icmp_param->data.icmph.code;
 
-	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
+	if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
 		return;
 
 	/* Needed by both icmp_global_allow and icmp_xmit_lock */
@@ -694,7 +694,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					  iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
+	if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
 		goto out_unlock;
 
 
@@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto)
 }
 
 /*
- *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and
  *	ICMP_PARAMETERPROB.
  */
 
@@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb)
 	if (iph->ihl < 5) /* Mangled header, drop. */
 		goto out_err;
 
-	if (icmph->type == ICMP_DEST_UNREACH) {
+	switch (icmph->type) {
+	case ICMP_DEST_UNREACH:
 		switch (icmph->code & 15) {
 		case ICMP_NET_UNREACH:
 		case ICMP_HOST_UNREACH:
@@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb)
 		}
 		if (icmph->code > NR_ICMP_UNREACH)
 			goto out;
-	} else if (icmph->type == ICMP_PARAMETERPROB)
+		break;
+	case ICMP_PARAMETERPROB:
 		info = ntohl(icmph->un.gateway) >> 24;
+		break;
+	case ICMP_TIME_EXCEEDED:
+		__ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS);
+		if (icmph->code == ICMP_EXC_FRAGTIME)
+			goto out;
+		break;
+	}
 
 	/*
 	 *	Throw it at our lower layers
@@ -959,8 +968,9 @@ static bool icmp_timestamp(struct sk_buff *skb)
 	 */
 	icmp_param.data.times[1] = inet_current_timestamp();
 	icmp_param.data.times[2] = icmp_param.data.times[1];
-	if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4))
-		BUG();
+
+	BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4));
+
 	icmp_param.data.icmph	   = *icmp_hdr(skb);
 	icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
 	icmp_param.data.icmph.code = 0;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 28f14afd0dd3..d1f8f302dbf3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -752,18 +752,18 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	return ip_local_out(net, skb->sk, skb);
 }
 
-static void igmp_gq_timer_expire(unsigned long data)
+static void igmp_gq_timer_expire(struct timer_list *t)
 {
-	struct in_device *in_dev = (struct in_device *)data;
+	struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer);
 
 	in_dev->mr_gq_running = 0;
 	igmpv3_send_report(in_dev, NULL);
 	in_dev_put(in_dev);
 }
 
-static void igmp_ifc_timer_expire(unsigned long data)
+static void igmp_ifc_timer_expire(struct timer_list *t)
 {
-	struct in_device *in_dev = (struct in_device *)data;
+	struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
 
 	igmpv3_send_cr(in_dev);
 	if (in_dev->mr_ifc_count) {
@@ -784,9 +784,9 @@ static void igmp_ifc_event(struct in_device *in_dev)
 }
 
 
-static void igmp_timer_expire(unsigned long data)
+static void igmp_timer_expire(struct timer_list *t)
 {
-	struct ip_mc_list *im = (struct ip_mc_list *)data;
+	struct ip_mc_list *im = from_timer(im, t, timer);
 	struct in_device *in_dev = im->interface;
 
 	spin_lock(&im->lock);
@@ -1007,10 +1007,18 @@ int igmp_rcv(struct sk_buff *skb)
 {
 	/* This basically follows the spec line by line -- see RFC1112 */
 	struct igmphdr *ih;
-	struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+	struct net_device *dev = skb->dev;
+	struct in_device *in_dev;
 	int len = skb->len;
 	bool dropped = true;
 
+	if (netif_is_l3_master(dev)) {
+		dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif);
+		if (!dev)
+			goto drop;
+	}
+
+	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev)
 		goto drop;
 
@@ -1377,7 +1385,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	refcount_set(&im->refcnt, 1);
 	spin_lock_init(&im->lock);
 #ifdef CONFIG_IP_MULTICAST
-	setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im);
+	timer_setup(&im->timer, igmp_timer_expire, 0);
 	im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
 #endif
 
@@ -1687,10 +1695,8 @@ void ip_mc_init_dev(struct in_device *in_dev)
 	ASSERT_RTNL();
 
 #ifdef CONFIG_IP_MULTICAST
-	setup_timer(&in_dev->mr_gq_timer, igmp_gq_timer_expire,
-			(unsigned long)in_dev);
-	setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
-			(unsigned long)in_dev);
+	timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0);
+	timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0);
 	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
 #endif
 
@@ -2549,7 +2555,8 @@ done:
 /*
  * 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 dif)
+int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
+		   int dif, int sdif)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ip_mc_socklist *pmc;
@@ -2564,7 +2571,8 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
 	rcu_read_lock();
 	for_each_pmc_rcu(inet, pmc) {
 		if (pmc->multi.imr_multiaddr.s_addr == loc_addr &&
-		    pmc->multi.imr_ifindex == dif)
+		    (pmc->multi.imr_ifindex == dif ||
+		     (sdif && pmc->multi.imr_ifindex == sdif)))
 			break;
 	}
 	ret = inet->mc_all;
@@ -2974,12 +2982,6 @@ static int __net_init igmp_net_init(struct net *net)
 		goto out_sock;
 	}
 
-	/* Sysctl initialization */
-	net->ipv4.sysctl_igmp_max_memberships = 20;
-	net->ipv4.sysctl_igmp_max_msf = 10;
-	/* IGMP reports for link-local multicast groups are enabled by default */
-	net->ipv4.sysctl_igmp_llm_reports = 1;
-	net->ipv4.sysctl_igmp_qrv = 2;
 	return 0;
 
 out_sock:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4089c013cb03..4ca46dc08e63 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
  *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
  *                          and 0.0.0.0 equals to 0.0.0.0 only
  */
-static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
-				const struct in6_addr *sk2_rcv_saddr6,
-				__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				bool sk1_ipv6only, bool sk2_ipv6only,
-				bool match_wildcard)
+static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
+				 const struct in6_addr *sk2_rcv_saddr6,
+				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				 bool sk1_ipv6only, bool sk2_ipv6only,
+				 bool match_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
-				return 1;
+				return true;
 			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
 				return match_wildcard;
 		}
-		return 0;
+		return false;
 	}
 
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
-		return 1;
+		return true;
 
 	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
-		return 1;
+		return true;
 
 	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
-		return 1;
+		return true;
 
 	if (sk2_rcv_saddr6 &&
 	    ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 #endif
 
@@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
  * match_wildcard == false: addresses must be exactly the same, i.e.
  *                          0.0.0.0 only equals to 0.0.0.0
  */
-static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				bool sk2_ipv6only, bool match_wildcard)
+static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				 bool sk2_ipv6only, bool match_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
-			return 1;
+			return true;
 		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
 			return match_wildcard;
 	}
-	return 0;
+	return false;
 }
 
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
-			 bool match_wildcard)
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+			  bool match_wildcard)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
@@ -266,7 +266,7 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tb->fast_sk_family == AF_INET6)
 		return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
-					    &sk->sk_v6_rcv_saddr,
+					    inet6_rcv_saddr(sk),
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
@@ -321,13 +321,14 @@ tb_found:
 			goto fail_unlock;
 	}
 success:
-	if (!hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->owners)) {
 		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
 			tb->fastreuseport = FASTREUSEPORT_ANY;
 			tb->fastuid = uid;
 			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 			tb->fast_ipv6_only = ipv6_only_sock(sk);
+			tb->fast_sk_family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 #endif
@@ -354,6 +355,7 @@ success:
 				tb->fastuid = uid;
 				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 				tb->fast_ipv6_only = ipv6_only_sock(sk);
+				tb->fast_sk_family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 #endif
@@ -473,6 +475,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+	mem_cgroup_sk_alloc(newsk);
 out:
 	release_sock(sk);
 	if (req)
@@ -492,17 +495,15 @@ EXPORT_SYMBOL(inet_csk_accept);
  * to optimize.
  */
 void inet_csk_init_xmit_timers(struct sock *sk,
-			       void (*retransmit_handler)(unsigned long),
-			       void (*delack_handler)(unsigned long),
-			       void (*keepalive_handler)(unsigned long))
+			       void (*retransmit_handler)(struct timer_list *t),
+			       void (*delack_handler)(struct timer_list *t),
+			       void (*keepalive_handler)(struct timer_list *t))
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
-			(unsigned long)sk);
-	setup_timer(&icsk->icsk_delack_timer, delack_handler,
-			(unsigned long)sk);
-	setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
+	timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
+	timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
+	timer_setup(&sk->sk_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
 EXPORT_SYMBOL(inet_csk_init_xmit_timers);
@@ -537,9 +538,11 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct net *net = read_pnet(&ireq->ireq_net);
-	struct ip_options_rcu *opt = ireq->opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	opt = ireq_opt_deref(ireq);
+
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -573,10 +576,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	fl4 = &newinet->cork.fl.u.ip4;
 
-	rcu_read_lock();
-	opt = rcu_dereference(newinet->inet_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -589,13 +591,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
-	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
-	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
@@ -674,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
 
-static void reqsk_timer_handler(unsigned long data)
+static void reqsk_timer_handler(struct timer_list *t)
 {
-	struct request_sock *req = (struct request_sock *)data;
+	struct request_sock *req = from_timer(req, t, rsk_timer);
 	struct sock *sk_listener = req->rsk_listener;
 	struct net *net = sock_net(sk_listener);
 	struct inet_connection_sock *icsk = inet_csk(sk_listener);
@@ -747,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
 	req->num_timeout = 0;
 	req->sk = NULL;
 
-	setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler,
-			    (unsigned long)req);
+	timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
 	mod_timer(&req->rsk_timer, jiffies + timeout);
 
 	inet_ehash_insert(req_to_sk(req), NULL);
@@ -916,7 +915,6 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 		tcp_sk(child)->fastopen_rsk = NULL;
 	}
 	inet_csk_destroy_sock(child);
-	reqsk_put(req);
 }
 
 struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
@@ -987,6 +985,7 @@ void inet_csk_listen_stop(struct sock *sk)
 		sock_hold(child);
 
 		inet_child_forget(sk, req, child);
+		reqsk_put(req);
 		bh_unlock_sock(child);
 		local_bh_enable();
 		sock_put(child);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 3828b3a805cd..c9c35b61a027 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -93,8 +93,17 @@ void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(inet_diag_msg_common_fill);
 
-static size_t inet_sk_attr_size(void)
+static size_t inet_sk_attr_size(struct sock *sk,
+				const struct inet_diag_req_v2 *req,
+				bool net_admin)
 {
+	const struct inet_diag_handler *handler;
+	size_t aux = 0;
+
+	handler = inet_diag_table[req->sdiag_protocol];
+	if (handler && handler->idiag_get_aux_size)
+		aux = handler->idiag_get_aux_size(sk, net_admin);
+
 	return	  nla_total_size(sizeof(struct tcp_info))
 		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
 		+ nla_total_size(1) /* INET_DIAG_TOS */
@@ -105,6 +114,7 @@ static size_t inet_sk_attr_size(void)
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
 		+ nla_total_size(TCP_CA_NAME_MAX)
 		+ nla_total_size(sizeof(struct tcpvegas_info))
+		+ aux
 		+ 64;
 }
 
@@ -260,6 +270,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	handler->idiag_get_info(sk, r, info);
 
+	if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux)
+		if (handler->idiag_get_aux(sk, net_admin, skb) < 0)
+			goto errout;
+
 	if (sk->sk_state < TCP_TIME_WAIT) {
 		union tcp_cc_info info;
 		size_t sz = 0;
@@ -274,6 +288,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+		u32 classid = 0;
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
+#endif
+
+		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
+			goto errout;
+	}
+
 out:
 	nlmsg_end(skb, nlh);
 	return 0;
@@ -438,6 +463,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
 			    const struct nlmsghdr *nlh,
 			    const struct inet_diag_req_v2 *req)
 {
+	bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN);
 	struct net *net = sock_net(in_skb->sk);
 	struct sk_buff *rep;
 	struct sock *sk;
@@ -447,7 +473,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
 	if (IS_ERR(sk))
 		return PTR_ERR(sk);
 
-	rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
+	rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL);
 	if (!rep) {
 		err = -ENOMEM;
 		goto out;
@@ -456,8 +482,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
 	err = sk_diag_fill(sk, rep, req,
 			   sk_user_ns(NETLINK_CB(in_skb).sk),
 			   NETLINK_CB(in_skb).portid,
-			   nlh->nlmsg_seq, 0, nlh,
-			   netlink_net_capable(in_skb, CAP_NET_ADMIN));
+			   nlh->nlmsg_seq, 0, nlh, net_admin);
 	if (err < 0) {
 		WARN_ON(err == -EMSGSIZE);
 		nlmsg_free(rep);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 96e95e83cc61..26a3d0315728 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
 	spin_unlock(&hb->chain_lock);
 
 	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
-		f->frag_expire((unsigned long) fq);
+		f->frag_expire(&fq->timer);
 
 	return evicted;
 }
@@ -164,7 +164,7 @@ static void inet_frag_worker(struct work_struct *work)
 
 	local_bh_disable();
 
-	for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
+	for (i = READ_ONCE(f->next_bucket); budget; --budget) {
 		evicted += inet_evict_bucket(f, &f->hash[i]);
 		i = (i + 1) & (INETFRAGS_HASHSZ - 1);
 		if (evicted > INETFRAGS_EVICT_MAX)
@@ -234,10 +234,8 @@ evict_again:
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
@@ -368,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 	f->constructor(q, arg);
 	add_frag_mem_limit(nf, f->qsize);
 
-	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
+	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
 	refcount_set(&q->refcnt, 1);
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2e3389d614d1..e7d15fb0d94d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -170,7 +170,7 @@ EXPORT_SYMBOL_GPL(__inet_inherit_port);
 
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum, const __be32 daddr,
-				const int dif, bool exact_dif)
+				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
 	struct inet_sock *inet = inet_sk(sk);
@@ -185,9 +185,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			score += 4;
 		}
 		if (sk->sk_bound_dev_if || exact_dif) {
-			if (sk->sk_bound_dev_if != dif)
+			bool dev_match = (sk->sk_bound_dev_if == dif ||
+					  sk->sk_bound_dev_if == sdif);
+
+			if (exact_dif && !dev_match)
 				return -1;
-			score += 4;
+			if (sk->sk_bound_dev_if && dev_match)
+				score += 4;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
@@ -208,7 +212,7 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    struct sk_buff *skb, int doff,
 				    const __be32 saddr, __be16 sport,
 				    const __be32 daddr, const unsigned short hnum,
-				    const int dif)
+				    const int dif, const int sdif)
 {
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
@@ -218,7 +222,8 @@ struct sock *__inet_lookup_listener(struct net *net,
 	u32 phash = 0;
 
 	sk_for_each_rcu(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
+		score = compute_score(sk, net, hnum, daddr,
+				      dif, sdif, exact_dif);
 		if (score > hiscore) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -268,7 +273,7 @@ struct sock *__inet_lookup_established(struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
 				  const __be32 daddr, const u16 hnum,
-				  const int dif)
+				  const int dif, const int sdif)
 {
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
@@ -286,11 +291,12 @@ begin:
 		if (sk->sk_hash != hash)
 			continue;
 		if (likely(INET_MATCH(sk, net, acookie,
-				      saddr, daddr, ports, dif))) {
+				      saddr, daddr, ports, dif, sdif))) {
 			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				goto out;
 			if (unlikely(!INET_MATCH(sk, net, acookie,
-						 saddr, daddr, ports, dif))) {
+						 saddr, daddr, ports,
+						 dif, sdif))) {
 				sock_gen_put(sk);
 				goto begin;
 			}
@@ -321,9 +327,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	__be32 daddr = inet->inet_rcv_saddr;
 	__be32 saddr = inet->inet_daddr;
 	int dif = sk->sk_bound_dev_if;
+	struct net *net = sock_net(sk);
+	int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	struct net *net = sock_net(sk);
 	unsigned int hash = inet_ehashfn(net, daddr, lport,
 					 saddr, inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
@@ -339,7 +346,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 			continue;
 
 		if (likely(INET_MATCH(sk2, net, acookie,
-					 saddr, daddr, ports, dif))) {
+					 saddr, daddr, ports, dif, sdif))) {
 			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
 				if (twsk_unique(sk, sk2, twp))
@@ -449,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
 			return reuseport_add_sock(sk, sk2);
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5b039159e67a..c690cd0d9b3f 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/kmemcheck.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <net/inet_hashtables.h>
@@ -142,9 +141,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
 
-static void tw_timer_handler(unsigned long data)
+static void tw_timer_handler(struct timer_list *t)
 {
-	struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
+	struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
 
 	if (tw->tw_kill)
 		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
@@ -167,8 +166,6 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 	if (tw) {
 		const struct inet_sock *inet = inet_sk(sk);
 
-		kmemcheck_annotate_bitfield(tw, flags);
-
 		tw->tw_dr	    = dr;
 		/* Give us an identity. */
 		tw->tw_daddr	    = inet->inet_daddr;
@@ -188,8 +185,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
 		twsk_net_set(tw, sock_net(sk));
-		setup_pinned_timer(&tw->tw_timer, tw_timer_handler,
-				   (unsigned long)tw);
+		timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
 		/*
 		 * Because we use RCU lookups, we should not set tw_refcnt
 		 * to a non null value before everything is setup for this
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index c5a117cc6619..914d56928578 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -33,7 +33,7 @@
  *  also be removed if the pool is overloaded i.e. if the total amount of
  *  entries is greater-or-equal than the threshold.
  *
- *  Node pool is organised as an AVL tree.
+ *  Node pool is organised as an RB tree.
  *  Such an implementation has been chosen not just for fun.  It's a way to
  *  prevent easy and efficient DoS attacks by creating hash collisions.  A huge
  *  amount of long living nodes in a single hash slot would significantly delay
@@ -45,7 +45,7 @@
  *      AND reference count being 0.
  *  3.  Global variable peer_total is modified under the pool lock.
  *  4.  struct inet_peer fields modification:
- *		avl_left, avl_right, avl_parent, avl_height: pool lock
+ *		rb_node: pool lock
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
@@ -53,30 +53,15 @@
 
 static struct kmem_cache *peer_cachep __read_mostly;
 
-static LIST_HEAD(gc_list);
-static const int gc_delay = 60 * HZ;
-static struct delayed_work gc_work;
-static DEFINE_SPINLOCK(gc_lock);
-
-#define node_height(x) x->avl_height
-
-#define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
-#define peer_avl_empty_rcu ((struct inet_peer __rcu __force *)&peer_fake_node)
-static const struct inet_peer peer_fake_node = {
-	.avl_left	= peer_avl_empty_rcu,
-	.avl_right	= peer_avl_empty_rcu,
-	.avl_height	= 0
-};
-
 void inet_peer_base_init(struct inet_peer_base *bp)
 {
-	bp->root = peer_avl_empty_rcu;
+	bp->rb_root = RB_ROOT;
 	seqlock_init(&bp->lock);
 	bp->total = 0;
 }
 EXPORT_SYMBOL_GPL(inet_peer_base_init);
 
-#define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
+#define PEER_MAX_GC 32
 
 /* Exported for sysctl_net_ipv4.  */
 int inet_peer_threshold __read_mostly = 65536 + 128;	/* start to throw entries more
@@ -84,53 +69,6 @@ int inet_peer_threshold __read_mostly = 65536 + 128;	/* start to throw entries m
 int inet_peer_minttl __read_mostly = 120 * HZ;	/* TTL under high load: 120 sec */
 int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min */
 
-static void inetpeer_gc_worker(struct work_struct *work)
-{
-	struct inet_peer *p, *n, *c;
-	struct list_head list;
-
-	spin_lock_bh(&gc_lock);
-	list_replace_init(&gc_list, &list);
-	spin_unlock_bh(&gc_lock);
-
-	if (list_empty(&list))
-		return;
-
-	list_for_each_entry_safe(p, n, &list, gc_list) {
-
-		if (need_resched())
-			cond_resched();
-
-		c = rcu_dereference_protected(p->avl_left, 1);
-		if (c != peer_avl_empty) {
-			list_add_tail(&c->gc_list, &list);
-			p->avl_left = peer_avl_empty_rcu;
-		}
-
-		c = rcu_dereference_protected(p->avl_right, 1);
-		if (c != peer_avl_empty) {
-			list_add_tail(&c->gc_list, &list);
-			p->avl_right = peer_avl_empty_rcu;
-		}
-
-		n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
-
-		if (refcount_read(&p->refcnt) == 1) {
-			list_del(&p->gc_list);
-			kmem_cache_free(peer_cachep, p);
-		}
-	}
-
-	if (list_empty(&list))
-		return;
-
-	spin_lock_bh(&gc_lock);
-	list_splice(&list, &gc_list);
-	spin_unlock_bh(&gc_lock);
-
-	schedule_delayed_work(&gc_work, gc_delay);
-}
-
 /* Called from ip_output.c:ip_init  */
 void __init inet_initpeers(void)
 {
@@ -153,225 +91,65 @@ void __init inet_initpeers(void)
 			sizeof(struct inet_peer),
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
 			NULL);
-
-	INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker);
 }
 
-#define rcu_deref_locked(X, BASE)				\
-	rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock))
-
-/*
- * Called with local BH disabled and the pool lock held.
- */
-#define lookup(_daddr, _stack, _base)				\
-({								\
-	struct inet_peer *u;					\
-	struct inet_peer __rcu **v;				\
-								\
-	stackptr = _stack;					\
-	*stackptr++ = &_base->root;				\
-	for (u = rcu_deref_locked(_base->root, _base);		\
-	     u != peer_avl_empty;) {				\
-		int cmp = inetpeer_addr_cmp(_daddr, &u->daddr);	\
-		if (cmp == 0)					\
-			break;					\
-		if (cmp == -1)					\
-			v = &u->avl_left;			\
-		else						\
-			v = &u->avl_right;			\
-		*stackptr++ = v;				\
-		u = rcu_deref_locked(*v, _base);		\
-	}							\
-	u;							\
-})
-
-/*
- * Called with rcu_read_lock()
- * Because we hold no lock against a writer, its quite possible we fall
- * in an endless loop.
- * But every pointer we follow is guaranteed to be valid thanks to RCU.
- * We exit from this function if number of links exceeds PEER_MAXDEPTH
- */
-static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
-				    struct inet_peer_base *base)
+/* Called with rcu_read_lock() or base->lock held */
+static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
+				struct inet_peer_base *base,
+				unsigned int seq,
+				struct inet_peer *gc_stack[],
+				unsigned int *gc_cnt,
+				struct rb_node **parent_p,
+				struct rb_node ***pp_p)
 {
-	struct inet_peer *u = rcu_dereference(base->root);
-	int count = 0;
+	struct rb_node **pp, *parent, *next;
+	struct inet_peer *p;
 
-	while (u != peer_avl_empty) {
-		int cmp = inetpeer_addr_cmp(daddr, &u->daddr);
+	pp = &base->rb_root.rb_node;
+	parent = NULL;
+	while (1) {
+		int cmp;
+
+		next = rcu_dereference_raw(*pp);
+		if (!next)
+			break;
+		parent = next;
+		p = rb_entry(parent, struct inet_peer, rb_node);
+		cmp = inetpeer_addr_cmp(daddr, &p->daddr);
 		if (cmp == 0) {
-			/* Before taking a reference, check if this entry was
-			 * deleted (refcnt=0)
-			 */
-			if (!refcount_inc_not_zero(&u->refcnt)) {
-				u = NULL;
-			}
-			return u;
+			if (!refcount_inc_not_zero(&p->refcnt))
+				break;
+			return p;
+		}
+		if (gc_stack) {
+			if (*gc_cnt < PEER_MAX_GC)
+				gc_stack[(*gc_cnt)++] = p;
+		} else if (unlikely(read_seqretry(&base->lock, seq))) {
+			break;
 		}
 		if (cmp == -1)
-			u = rcu_dereference(u->avl_left);
+			pp = &next->rb_left;
 		else
-			u = rcu_dereference(u->avl_right);
-		if (unlikely(++count == PEER_MAXDEPTH))
-			break;
+			pp = &next->rb_right;
 	}
+	*parent_p = parent;
+	*pp_p = pp;
 	return NULL;
 }
 
-/* Called with local BH disabled and the pool lock held. */
-#define lookup_rightempty(start, base)				\
-({								\
-	struct inet_peer *u;					\
-	struct inet_peer __rcu **v;				\
-	*stackptr++ = &start->avl_left;				\
-	v = &start->avl_left;					\
-	for (u = rcu_deref_locked(*v, base);			\
-	     u->avl_right != peer_avl_empty_rcu;) {		\
-		v = &u->avl_right;				\
-		*stackptr++ = v;				\
-		u = rcu_deref_locked(*v, base);			\
-	}							\
-	u;							\
-})
-
-/* Called with local BH disabled and the pool lock held.
- * Variable names are the proof of operation correctness.
- * Look into mm/map_avl.c for more detail description of the ideas.
- */
-static void peer_avl_rebalance(struct inet_peer __rcu **stack[],
-			       struct inet_peer __rcu ***stackend,
-			       struct inet_peer_base *base)
-{
-	struct inet_peer __rcu **nodep;
-	struct inet_peer *node, *l, *r;
-	int lh, rh;
-
-	while (stackend > stack) {
-		nodep = *--stackend;
-		node = rcu_deref_locked(*nodep, base);
-		l = rcu_deref_locked(node->avl_left, base);
-		r = rcu_deref_locked(node->avl_right, base);
-		lh = node_height(l);
-		rh = node_height(r);
-		if (lh > rh + 1) { /* l: RH+2 */
-			struct inet_peer *ll, *lr, *lrl, *lrr;
-			int lrh;
-			ll = rcu_deref_locked(l->avl_left, base);
-			lr = rcu_deref_locked(l->avl_right, base);
-			lrh = node_height(lr);
-			if (lrh <= node_height(ll)) {	/* ll: RH+1 */
-				RCU_INIT_POINTER(node->avl_left, lr);	/* lr: RH or RH+1 */
-				RCU_INIT_POINTER(node->avl_right, r);	/* r: RH */
-				node->avl_height = lrh + 1; /* RH+1 or RH+2 */
-				RCU_INIT_POINTER(l->avl_left, ll);       /* ll: RH+1 */
-				RCU_INIT_POINTER(l->avl_right, node);	/* node: RH+1 or RH+2 */
-				l->avl_height = node->avl_height + 1;
-				RCU_INIT_POINTER(*nodep, l);
-			} else { /* ll: RH, lr: RH+1 */
-				lrl = rcu_deref_locked(lr->avl_left, base);/* lrl: RH or RH-1 */
-				lrr = rcu_deref_locked(lr->avl_right, base);/* lrr: RH or RH-1 */
-				RCU_INIT_POINTER(node->avl_left, lrr);	/* lrr: RH or RH-1 */
-				RCU_INIT_POINTER(node->avl_right, r);	/* r: RH */
-				node->avl_height = rh + 1; /* node: RH+1 */
-				RCU_INIT_POINTER(l->avl_left, ll);	/* ll: RH */
-				RCU_INIT_POINTER(l->avl_right, lrl);	/* lrl: RH or RH-1 */
-				l->avl_height = rh + 1;	/* l: RH+1 */
-				RCU_INIT_POINTER(lr->avl_left, l);	/* l: RH+1 */
-				RCU_INIT_POINTER(lr->avl_right, node);	/* node: RH+1 */
-				lr->avl_height = rh + 2;
-				RCU_INIT_POINTER(*nodep, lr);
-			}
-		} else if (rh > lh + 1) { /* r: LH+2 */
-			struct inet_peer *rr, *rl, *rlr, *rll;
-			int rlh;
-			rr = rcu_deref_locked(r->avl_right, base);
-			rl = rcu_deref_locked(r->avl_left, base);
-			rlh = node_height(rl);
-			if (rlh <= node_height(rr)) {	/* rr: LH+1 */
-				RCU_INIT_POINTER(node->avl_right, rl);	/* rl: LH or LH+1 */
-				RCU_INIT_POINTER(node->avl_left, l);	/* l: LH */
-				node->avl_height = rlh + 1; /* LH+1 or LH+2 */
-				RCU_INIT_POINTER(r->avl_right, rr);	/* rr: LH+1 */
-				RCU_INIT_POINTER(r->avl_left, node);	/* node: LH+1 or LH+2 */
-				r->avl_height = node->avl_height + 1;
-				RCU_INIT_POINTER(*nodep, r);
-			} else { /* rr: RH, rl: RH+1 */
-				rlr = rcu_deref_locked(rl->avl_right, base);/* rlr: LH or LH-1 */
-				rll = rcu_deref_locked(rl->avl_left, base);/* rll: LH or LH-1 */
-				RCU_INIT_POINTER(node->avl_right, rll);	/* rll: LH or LH-1 */
-				RCU_INIT_POINTER(node->avl_left, l);	/* l: LH */
-				node->avl_height = lh + 1; /* node: LH+1 */
-				RCU_INIT_POINTER(r->avl_right, rr);	/* rr: LH */
-				RCU_INIT_POINTER(r->avl_left, rlr);	/* rlr: LH or LH-1 */
-				r->avl_height = lh + 1;	/* r: LH+1 */
-				RCU_INIT_POINTER(rl->avl_right, r);	/* r: LH+1 */
-				RCU_INIT_POINTER(rl->avl_left, node);	/* node: LH+1 */
-				rl->avl_height = lh + 2;
-				RCU_INIT_POINTER(*nodep, rl);
-			}
-		} else {
-			node->avl_height = (lh > rh ? lh : rh) + 1;
-		}
-	}
-}
-
-/* Called with local BH disabled and the pool lock held. */
-#define link_to_pool(n, base)					\
-do {								\
-	n->avl_height = 1;					\
-	n->avl_left = peer_avl_empty_rcu;			\
-	n->avl_right = peer_avl_empty_rcu;			\
-	/* lockless readers can catch us now */			\
-	rcu_assign_pointer(**--stackptr, n);			\
-	peer_avl_rebalance(stack, stackptr, base);		\
-} while (0)
-
 static void inetpeer_free_rcu(struct rcu_head *head)
 {
 	kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu));
 }
 
-static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base,
-			     struct inet_peer __rcu **stack[PEER_MAXDEPTH])
-{
-	struct inet_peer __rcu ***stackptr, ***delp;
-
-	if (lookup(&p->daddr, stack, base) != p)
-		BUG();
-	delp = stackptr - 1; /* *delp[0] == p */
-	if (p->avl_left == peer_avl_empty_rcu) {
-		*delp[0] = p->avl_right;
-		--stackptr;
-	} else {
-		/* look for a node to insert instead of p */
-		struct inet_peer *t;
-		t = lookup_rightempty(p, base);
-		BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t);
-		**--stackptr = t->avl_left;
-		/* t is removed, t->daddr > x->daddr for any
-		 * x in p->avl_left subtree.
-		 * Put t in the old place of p. */
-		RCU_INIT_POINTER(*delp[0], t);
-		t->avl_left = p->avl_left;
-		t->avl_right = p->avl_right;
-		t->avl_height = p->avl_height;
-		BUG_ON(delp[1] != &p->avl_left);
-		delp[1] = &t->avl_left; /* was &p->avl_left */
-	}
-	peer_avl_rebalance(stack, stackptr, base);
-	base->total--;
-	call_rcu(&p->rcu, inetpeer_free_rcu);
-}
-
 /* perform garbage collect on all items stacked during a lookup */
-static int inet_peer_gc(struct inet_peer_base *base,
-			struct inet_peer __rcu **stack[PEER_MAXDEPTH],
-			struct inet_peer __rcu ***stackptr)
+static void inet_peer_gc(struct inet_peer_base *base,
+			 struct inet_peer *gc_stack[],
+			 unsigned int gc_cnt)
 {
-	struct inet_peer *p, *gchead = NULL;
+	struct inet_peer *p;
 	__u32 delta, ttl;
-	int cnt = 0;
+	int i;
 
 	if (base->total >= inet_peer_threshold)
 		ttl = 0; /* be aggressive */
@@ -379,43 +157,38 @@ static int inet_peer_gc(struct inet_peer_base *base,
 		ttl = inet_peer_maxttl
 				- (inet_peer_maxttl - inet_peer_minttl) / HZ *
 					base->total / inet_peer_threshold * HZ;
-	stackptr--; /* last stack slot is peer_avl_empty */
-	while (stackptr > stack) {
-		stackptr--;
-		p = rcu_deref_locked(**stackptr, base);
-		if (refcount_read(&p->refcnt) == 1) {
-			smp_rmb();
-			delta = (__u32)jiffies - p->dtime;
-			if (delta >= ttl && refcount_dec_if_one(&p->refcnt)) {
-				p->gc_next = gchead;
-				gchead = p;
-			}
-		}
+	for (i = 0; i < gc_cnt; i++) {
+		p = gc_stack[i];
+		delta = (__u32)jiffies - p->dtime;
+		if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
+			gc_stack[i] = NULL;
 	}
-	while ((p = gchead) != NULL) {
-		gchead = p->gc_next;
-		cnt++;
-		unlink_from_pool(p, base, stack);
+	for (i = 0; i < gc_cnt; i++) {
+		p = gc_stack[i];
+		if (p) {
+			rb_erase(&p->rb_node, &base->rb_root);
+			base->total--;
+			call_rcu(&p->rcu, inetpeer_free_rcu);
+		}
 	}
-	return cnt;
 }
 
 struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			       const struct inetpeer_addr *daddr,
 			       int create)
 {
-	struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr;
-	struct inet_peer *p;
-	unsigned int sequence;
-	int invalidated, gccnt = 0;
+	struct inet_peer *p, *gc_stack[PEER_MAX_GC];
+	struct rb_node **pp, *parent;
+	unsigned int gc_cnt, seq;
+	int invalidated;
 
 	/* Attempt a lockless lookup first.
 	 * Because of a concurrent writer, we might not find an existing entry.
 	 */
 	rcu_read_lock();
-	sequence = read_seqbegin(&base->lock);
-	p = lookup_rcu(daddr, base);
-	invalidated = read_seqretry(&base->lock, sequence);
+	seq = read_seqbegin(&base->lock);
+	p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
+	invalidated = read_seqretry(&base->lock, seq);
 	rcu_read_unlock();
 
 	if (p)
@@ -428,36 +201,31 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	/* retry an exact lookup, taking the lock before.
 	 * At least, nodes should be hot in our cache.
 	 */
+	parent = NULL;
 	write_seqlock_bh(&base->lock);
-relookup:
-	p = lookup(daddr, stack, base);
-	if (p != peer_avl_empty) {
-		refcount_inc(&p->refcnt);
-		write_sequnlock_bh(&base->lock);
-		return p;
-	}
-	if (!gccnt) {
-		gccnt = inet_peer_gc(base, stack, stackptr);
-		if (gccnt && create)
-			goto relookup;
-	}
-	p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL;
-	if (p) {
-		p->daddr = *daddr;
-		refcount_set(&p->refcnt, 2);
-		atomic_set(&p->rid, 0);
-		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
-		p->rate_tokens = 0;
-		/* 60*HZ is arbitrary, but chosen enough high so that the first
-		 * calculation of tokens is at its maximum.
-		 */
-		p->rate_last = jiffies - 60*HZ;
-		INIT_LIST_HEAD(&p->gc_list);
-
-		/* Link the node. */
-		link_to_pool(p, base);
-		base->total++;
+
+	gc_cnt = 0;
+	p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
+	if (!p && create) {
+		p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
+		if (p) {
+			p->daddr = *daddr;
+			refcount_set(&p->refcnt, 2);
+			atomic_set(&p->rid, 0);
+			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
+			p->rate_tokens = 0;
+			/* 60*HZ is arbitrary, but chosen enough high so that the first
+			 * calculation of tokens is at its maximum.
+			 */
+			p->rate_last = jiffies - 60*HZ;
+
+			rb_link_node(&p->rb_node, parent, pp);
+			rb_insert_color(&p->rb_node, &base->rb_root);
+			base->total++;
+		}
 	}
+	if (gc_cnt)
+		inet_peer_gc(base, gc_stack, gc_cnt);
 	write_sequnlock_bh(&base->lock);
 
 	return p;
@@ -467,8 +235,9 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
 void inet_putpeer(struct inet_peer *p)
 {
 	p->dtime = (__u32)jiffies;
-	smp_mb__before_atomic();
-	refcount_dec(&p->refcnt);
+
+	if (refcount_dec_and_test(&p->refcnt))
+		call_rcu(&p->rcu, inetpeer_free_rcu);
 }
 EXPORT_SYMBOL_GPL(inet_putpeer);
 
@@ -513,30 +282,19 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
 }
 EXPORT_SYMBOL(inet_peer_xrlim_allow);
 
-static void inetpeer_inval_rcu(struct rcu_head *head)
-{
-	struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu);
-
-	spin_lock_bh(&gc_lock);
-	list_add_tail(&p->gc_list, &gc_list);
-	spin_unlock_bh(&gc_lock);
-
-	schedule_delayed_work(&gc_work, gc_delay);
-}
-
 void inetpeer_invalidate_tree(struct inet_peer_base *base)
 {
-	struct inet_peer *root;
+	struct rb_node *p = rb_first(&base->rb_root);
 
-	write_seqlock_bh(&base->lock);
+	while (p) {
+		struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
 
-	root = rcu_deref_locked(base->root, base);
-	if (root != peer_avl_empty) {
-		base->root = peer_avl_empty_rcu;
-		base->total = 0;
-		call_rcu(&root->gc_rcu, inetpeer_inval_rcu);
+		p = rb_next(p);
+		rb_erase(&peer->rb_node, &base->rb_root);
+		inet_putpeer(peer);
+		cond_resched();
 	}
 
-	write_sequnlock_bh(&base->lock);
+	base->total = 0;
 }
 EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 9f0a7b96646f..2dd21c3281a1 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9a8cfac503dc..bbf1b94942c0 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -190,12 +191,13 @@ static bool frag_expire_skip_icmp(u32 user)
 /*
  * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
  */
-static void ip_expire(unsigned long arg)
+static void ip_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct ipq *qp;
 	struct net *net;
 
-	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
+	qp = container_of(frag, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
 
 	rcu_read_lock();
@@ -844,8 +846,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -871,13 +871,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7a7829e839c2..bb6239169b1a 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -48,6 +48,7 @@
 #include <net/rtnetlink.h>
 #include <net/gre.h>
 #include <net/dst_metadata.h>
+#include <net/erspan.h>
 
 /*
    Problems & solutions
@@ -112,9 +113,12 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly;
 static int ipgre_tunnel_init(struct net_device *dev);
+static void erspan_build_header(struct sk_buff *skb,
+				__be32 id, u32 index, bool truncate);
 
 static unsigned int ipgre_net_id __read_mostly;
 static unsigned int gre_tap_net_id __read_mostly;
+static unsigned int erspan_net_id __read_mostly;
 
 static void ipgre_err(struct sk_buff *skb, u32 info,
 		      const struct tnl_ptk_info *tpi)
@@ -246,6 +250,79 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	ipgre_err(skb, info, &tpi);
 }
 
+static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+		      int gre_hdr_len)
+{
+	struct net *net = dev_net(skb->dev);
+	struct metadata_dst *tun_dst = NULL;
+	struct ip_tunnel_net *itn;
+	struct ip_tunnel *tunnel;
+	struct erspanhdr *ershdr;
+	const struct iphdr *iph;
+	__be32 index;
+	int len;
+
+	itn = net_generic(net, erspan_net_id);
+	len = gre_hdr_len + sizeof(*ershdr);
+
+	if (unlikely(!pskb_may_pull(skb, len)))
+		return -ENOMEM;
+
+	iph = ip_hdr(skb);
+	ershdr = (struct erspanhdr *)(skb->data + gre_hdr_len);
+
+	/* The original GRE header does not have key field,
+	 * Use ERSPAN 10-bit session ID as key.
+	 */
+	tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK);
+	index = ershdr->md.index;
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
+				  tpi->flags | TUNNEL_KEY,
+				  iph->saddr, iph->daddr, tpi->key);
+
+	if (tunnel) {
+		if (__iptunnel_pull_header(skb,
+					   gre_hdr_len + sizeof(*ershdr),
+					   htons(ETH_P_TEB),
+					   false, false) < 0)
+			goto drop;
+
+		if (tunnel->collect_md) {
+			struct ip_tunnel_info *info;
+			struct erspan_metadata *md;
+			__be64 tun_id;
+			__be16 flags;
+
+			tpi->flags |= TUNNEL_KEY;
+			flags = tpi->flags;
+			tun_id = key32_to_tunnel_id(tpi->key);
+
+			tun_dst = ip_tun_rx_dst(skb, flags,
+						tun_id, sizeof(*md));
+			if (!tun_dst)
+				return PACKET_REJECT;
+
+			md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
+			if (!md)
+				return PACKET_REJECT;
+
+			md->index = index;
+			info = &tun_dst->u.tun_info;
+			info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+			info->options_len = sizeof(*md);
+		} else {
+			tunnel->index = ntohl(index);
+		}
+
+		skb_reset_mac_header(skb);
+		ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
+		return PACKET_RCVD;
+	}
+drop:
+	kfree_skb(skb);
+	return PACKET_RCVD;
+}
+
 static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 		       struct ip_tunnel_net *itn, int hdr_len, bool raw_proto)
 {
@@ -328,6 +405,11 @@ static int gre_rcv(struct sk_buff *skb)
 	if (hdr_len < 0)
 		goto drop;
 
+	if (unlikely(tpi.proto == htons(ETH_P_ERSPAN))) {
+		if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
+			return 0;
+	}
+
 	if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
 		return 0;
 
@@ -376,39 +458,33 @@ static struct rtable *gre_get_rt(struct sk_buff *skb,
 	return ip_route_output_key(net, fl);
 }
 
-static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
-			__be16 proto)
+static struct rtable *prepare_fb_xmit(struct sk_buff *skb,
+				      struct net_device *dev,
+				      struct flowi4 *fl,
+				      int tunnel_hlen)
 {
 	struct ip_tunnel_info *tun_info;
 	const struct ip_tunnel_key *key;
 	struct rtable *rt = NULL;
-	struct flowi4 fl;
 	int min_headroom;
-	int tunnel_hlen;
-	__be16 df, flags;
 	bool use_cache;
 	int err;
 
 	tun_info = skb_tunnel_info(skb);
-	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-		     ip_tunnel_info_af(tun_info) != AF_INET))
-		goto err_free_skb;
-
 	key = &tun_info->key;
 	use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);
+
 	if (use_cache)
-		rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr);
+		rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl->saddr);
 	if (!rt) {
-		rt = gre_get_rt(skb, dev, &fl, key);
+		rt = gre_get_rt(skb, dev, fl, key);
 		if (IS_ERR(rt))
-				goto err_free_skb;
+			goto err_free_skb;
 		if (use_cache)
 			dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst,
-					  fl.saddr);
+					  fl->saddr);
 	}
 
-	tunnel_hlen = gre_calc_hlen(key->tun_flags);
-
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ tunnel_hlen + sizeof(struct iphdr);
 	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
@@ -420,6 +496,37 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err_free_rt;
 	}
+	return rt;
+
+err_free_rt:
+	ip_rt_put(rt);
+err_free_skb:
+	kfree_skb(skb);
+	dev->stats.tx_dropped++;
+	return NULL;
+}
+
+static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
+			__be16 proto)
+{
+	struct ip_tunnel_info *tun_info;
+	const struct ip_tunnel_key *key;
+	struct rtable *rt = NULL;
+	struct flowi4 fl;
+	int tunnel_hlen;
+	__be16 df, flags;
+
+	tun_info = skb_tunnel_info(skb);
+	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+		     ip_tunnel_info_af(tun_info) != AF_INET))
+		goto err_free_skb;
+
+	key = &tun_info->key;
+	tunnel_hlen = gre_calc_hlen(key->tun_flags);
+
+	rt = prepare_fb_xmit(skb, dev, &fl, tunnel_hlen);
+	if (!rt)
+		return;
 
 	/* Push Tunnel header. */
 	if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM)))
@@ -442,6 +549,64 @@ err_free_skb:
 	dev->stats.tx_dropped++;
 }
 
+static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
+			   __be16 proto)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct ip_tunnel_info *tun_info;
+	const struct ip_tunnel_key *key;
+	struct erspan_metadata *md;
+	struct rtable *rt = NULL;
+	bool truncate = false;
+	struct flowi4 fl;
+	int tunnel_hlen;
+	__be16 df;
+
+	tun_info = skb_tunnel_info(skb);
+	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+		     ip_tunnel_info_af(tun_info) != AF_INET))
+		goto err_free_skb;
+
+	key = &tun_info->key;
+
+	/* ERSPAN has fixed 8 byte GRE header */
+	tunnel_hlen = 8 + sizeof(struct erspanhdr);
+
+	rt = prepare_fb_xmit(skb, dev, &fl, tunnel_hlen);
+	if (!rt)
+		return;
+
+	if (gre_handle_offloads(skb, false))
+		goto err_free_rt;
+
+	if (skb->len > dev->mtu + dev->hard_header_len) {
+		pskb_trim(skb, dev->mtu + dev->hard_header_len);
+		truncate = true;
+	}
+
+	md = ip_tunnel_info_opts(tun_info);
+	if (!md)
+		goto err_free_rt;
+
+	erspan_build_header(skb, tunnel_id_to_key32(key->tun_id),
+			    ntohl(md->index), truncate);
+
+	gre_build_header(skb, 8, TUNNEL_SEQ,
+			 htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++));
+
+	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ?  htons(IP_DF) : 0;
+
+	iptunnel_xmit(skb->sk, rt, skb, fl.saddr, key->u.ipv4.dst, IPPROTO_GRE,
+		      key->tos, key->ttl, df, false);
+	return;
+
+err_free_rt:
+	ip_rt_put(rt);
+err_free_skb:
+	kfree_skb(skb);
+	dev->stats.tx_dropped++;
+}
+
 static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -503,6 +668,86 @@ free_skb:
 	return NETDEV_TX_OK;
 }
 
+static inline u8 tos_to_cos(u8 tos)
+{
+	u8 dscp, cos;
+
+	dscp = tos >> 2;
+	cos = dscp >> 3;
+	return cos;
+}
+
+static void erspan_build_header(struct sk_buff *skb,
+				__be32 id, u32 index, bool truncate)
+{
+	struct iphdr *iphdr = ip_hdr(skb);
+	struct ethhdr *eth = eth_hdr(skb);
+	enum erspan_encap_type enc_type;
+	struct erspanhdr *ershdr;
+	struct qtag_prefix {
+		__be16 eth_type;
+		__be16 tci;
+	} *qp;
+	u16 vlan_tci = 0;
+
+	enc_type = ERSPAN_ENCAP_NOVLAN;
+
+	/* If mirrored packet has vlan tag, extract tci and
+	 *  perserve vlan header in the mirrored frame.
+	 */
+	if (eth->h_proto == htons(ETH_P_8021Q)) {
+		qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN);
+		vlan_tci = ntohs(qp->tci);
+		enc_type = ERSPAN_ENCAP_INFRAME;
+	}
+
+	skb_push(skb, sizeof(*ershdr));
+	ershdr = (struct erspanhdr *)skb->data;
+	memset(ershdr, 0, sizeof(*ershdr));
+
+	ershdr->ver_vlan = htons((vlan_tci & VLAN_MASK) |
+				 (ERSPAN_VERSION << VER_OFFSET));
+	ershdr->session_id = htons((u16)(ntohl(id) & ID_MASK) |
+			   ((tos_to_cos(iphdr->tos) << COS_OFFSET) & COS_MASK) |
+			   (enc_type << EN_OFFSET & EN_MASK) |
+			   ((truncate << T_OFFSET) & T_MASK));
+	ershdr->md.index = htonl(index & INDEX_MASK);
+}
+
+static netdev_tx_t erspan_xmit(struct sk_buff *skb,
+			       struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	bool truncate = false;
+
+	if (tunnel->collect_md) {
+		erspan_fb_xmit(skb, dev, skb->protocol);
+		return NETDEV_TX_OK;
+	}
+
+	if (gre_handle_offloads(skb, false))
+		goto free_skb;
+
+	if (skb_cow_head(skb, dev->needed_headroom))
+		goto free_skb;
+
+	if (skb->len > dev->mtu + dev->hard_header_len) {
+		pskb_trim(skb, dev->mtu + dev->hard_header_len);
+		truncate = true;
+	}
+
+	/* Push ERSPAN header */
+	erspan_build_header(skb, tunnel->parms.o_key, tunnel->index, truncate);
+	tunnel->parms.o_flags &= ~TUNNEL_KEY;
+	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
+	return NETDEV_TX_OK;
+
+free_skb:
+	kfree_skb(skb);
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_OK;
+}
+
 static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 				struct net_device *dev)
 {
@@ -528,20 +773,46 @@ free_skb:
 	return NETDEV_TX_OK;
 }
 
+static void ipgre_link_update(struct net_device *dev, bool set_mtu)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int len;
+
+	len = tunnel->tun_hlen;
+	tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
+	len = tunnel->tun_hlen - len;
+	tunnel->hlen = tunnel->hlen + len;
+
+	dev->needed_headroom = dev->needed_headroom + len;
+	if (set_mtu)
+		dev->mtu = max_t(int, dev->mtu - len, 68);
+
+	if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
+		if (!(tunnel->parms.o_flags & TUNNEL_CSUM) ||
+		    tunnel->encap.type == TUNNEL_ENCAP_NONE) {
+			dev->features |= NETIF_F_GSO_SOFTWARE;
+			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		}
+		dev->features |= NETIF_F_LLTX;
+	}
+}
+
 static int ipgre_tunnel_ioctl(struct net_device *dev,
 			      struct ifreq *ifr, int cmd)
 {
-	int err;
 	struct ip_tunnel_parm p;
+	int err;
 
 	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
 		return -EFAULT;
+
 	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
 		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
-		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
-		    ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
+		    p.iph.ihl != 5 || (p.iph.frag_off & htons(~IP_DF)) ||
+		    ((p.i_flags | p.o_flags) & (GRE_VERSION | GRE_ROUTING)))
 			return -EINVAL;
 	}
+
 	p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
 	p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
 
@@ -549,11 +820,22 @@ static int ipgre_tunnel_ioctl(struct net_device *dev,
 	if (err)
 		return err;
 
+	if (cmd == SIOCCHGTUNNEL) {
+		struct ip_tunnel *t = netdev_priv(dev);
+
+		t->parms.i_flags = p.i_flags;
+		t->parms.o_flags = p.o_flags;
+
+		if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
+			ipgre_link_update(dev, true);
+	}
+
 	p.i_flags = gre_tnl_flags_to_gre_flags(p.i_flags);
 	p.o_flags = gre_tnl_flags_to_gre_flags(p.o_flags);
 
 	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 		return -EFAULT;
+
 	return 0;
 }
 
@@ -766,15 +1048,14 @@ static int __net_init ipgre_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
 }
 
-static void __net_exit ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
-	ip_tunnel_delete_net(itn, &ipgre_link_ops);
+	ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops);
 }
 
 static struct pernet_operations ipgre_net_ops = {
 	.init = ipgre_init_net,
-	.exit = ipgre_exit_net,
+	.exit_batch = ipgre_exit_batch_net,
 	.id   = &ipgre_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -828,6 +1109,42 @@ out:
 	return ipgre_tunnel_validate(tb, data, extack);
 }
 
+static int erspan_validate(struct nlattr *tb[], struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
+{
+	__be16 flags = 0;
+	int ret;
+
+	if (!data)
+		return 0;
+
+	ret = ipgre_tap_validate(tb, data, extack);
+	if (ret)
+		return ret;
+
+	/* ERSPAN should only have GRE sequence and key flag */
+	if (data[IFLA_GRE_OFLAGS])
+		flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
+	if (data[IFLA_GRE_IFLAGS])
+		flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]);
+	if (!data[IFLA_GRE_COLLECT_METADATA] &&
+	    flags != (GRE_SEQ | GRE_KEY))
+		return -EINVAL;
+
+	/* ERSPAN Session ID only has 10-bit. Since we reuse
+	 * 32-bit key field as ID, check it's range.
+	 */
+	if (data[IFLA_GRE_IKEY] &&
+	    (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK))
+		return -EINVAL;
+
+	if (data[IFLA_GRE_OKEY] &&
+	    (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int ipgre_netlink_parms(struct net_device *dev,
 				struct nlattr *data[],
 				struct nlattr *tb[],
@@ -892,6 +1209,13 @@ static int ipgre_netlink_parms(struct net_device *dev,
 	if (data[IFLA_GRE_FWMARK])
 		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
 
+	if (data[IFLA_GRE_ERSPAN_INDEX]) {
+		t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+
+		if (t->index & ~INDEX_MASK)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -933,6 +1257,7 @@ static int gre_tap_init(struct net_device *dev)
 {
 	__gre_tunnel_init(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
@@ -949,6 +1274,39 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 	.ndo_fill_metadata_dst	= gre_fill_metadata_dst,
 };
 
+static int erspan_tunnel_init(struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int t_hlen;
+
+	tunnel->tun_hlen = 8;
+	tunnel->parms.iph.protocol = IPPROTO_GRE;
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+		       sizeof(struct erspanhdr);
+	t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+	dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
+	dev->mtu = ETH_DATA_LEN - t_hlen - 4;
+	dev->features		|= GRE_FEATURES;
+	dev->hw_features	|= GRE_FEATURES;
+	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
+
+	return ip_tunnel_init(dev);
+}
+
+static const struct net_device_ops erspan_netdev_ops = {
+	.ndo_init		= erspan_tunnel_init,
+	.ndo_uninit		= ip_tunnel_uninit,
+	.ndo_start_xmit		= erspan_xmit,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= ip_tunnel_change_mtu,
+	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_iflink		= ip_tunnel_get_iflink,
+	.ndo_fill_metadata_dst	= gre_fill_metadata_dst,
+};
+
 static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -986,9 +1344,9 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
 	__u32 fwmark = t->fwmark;
+	struct ip_tunnel_parm p;
 	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
@@ -1001,7 +1359,18 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_changelink(dev, tb, &p, fwmark);
+
+	err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+	if (err < 0)
+		return err;
+
+	t->parms.i_flags = p.i_flags;
+	t->parms.o_flags = p.o_flags;
+
+	if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
+		ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+	return 0;
 }
 
 static size_t ipgre_get_size(const struct net_device *dev)
@@ -1041,6 +1410,8 @@ static size_t ipgre_get_size(const struct net_device *dev)
 		nla_total_size(1) +
 		/* IFLA_GRE_FWMARK */
 		nla_total_size(4) +
+		/* IFLA_GRE_ERSPAN_INDEX */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1083,12 +1454,25 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 
+	if (t->index)
+		if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
+			goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static void erspan_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+	dev->netdev_ops = &erspan_netdev_ops;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	ip_tunnel_setup(dev, erspan_net_id);
+}
+
 static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_LINK]		= { .type = NLA_U32 },
 	[IFLA_GRE_IFLAGS]	= { .type = NLA_U16 },
@@ -1107,6 +1491,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_COLLECT_METADATA]	= { .type = NLA_FLAG },
 	[IFLA_GRE_IGNORE_DF]	= { .type = NLA_U8 },
 	[IFLA_GRE_FWMARK]	= { .type = NLA_U32 },
+	[IFLA_GRE_ERSPAN_INDEX]	= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
@@ -1139,6 +1524,21 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
 	.get_link_net	= ip_tunnel_get_link_net,
 };
 
+static struct rtnl_link_ops erspan_link_ops __read_mostly = {
+	.kind		= "erspan",
+	.maxtype	= IFLA_GRE_MAX,
+	.policy		= ipgre_policy,
+	.priv_size	= sizeof(struct ip_tunnel),
+	.setup		= erspan_setup,
+	.validate	= erspan_validate,
+	.newlink	= ipgre_newlink,
+	.changelink	= ipgre_changelink,
+	.dellink	= ip_tunnel_dellink,
+	.get_size	= ipgre_get_size,
+	.fill_info	= ipgre_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
+};
+
 struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 					u8 name_assign_type)
 {
@@ -1189,19 +1589,36 @@ static int __net_init ipgre_tap_init_net(struct net *net)
 	return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0");
 }
 
-static void __net_exit ipgre_tap_exit_net(struct net *net)
+static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
-	ip_tunnel_delete_net(itn, &ipgre_tap_ops);
+	ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops);
 }
 
 static struct pernet_operations ipgre_tap_net_ops = {
 	.init = ipgre_tap_init_net,
-	.exit = ipgre_tap_exit_net,
+	.exit_batch = ipgre_tap_exit_batch_net,
 	.id   = &gre_tap_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
 
+static int __net_init erspan_init_net(struct net *net)
+{
+	return ip_tunnel_init_net(net, erspan_net_id,
+				  &erspan_link_ops, "erspan0");
+}
+
+static void __net_exit erspan_exit_batch_net(struct list_head *net_list)
+{
+	ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops);
+}
+
+static struct pernet_operations erspan_net_ops = {
+	.init = erspan_init_net,
+	.exit_batch = erspan_exit_batch_net,
+	.id   = &erspan_net_id,
+	.size = sizeof(struct ip_tunnel_net),
+};
+
 static int __init ipgre_init(void)
 {
 	int err;
@@ -1214,7 +1631,11 @@ static int __init ipgre_init(void)
 
 	err = register_pernet_device(&ipgre_tap_net_ops);
 	if (err < 0)
-		goto pnet_tap_faied;
+		goto pnet_tap_failed;
+
+	err = register_pernet_device(&erspan_net_ops);
+	if (err < 0)
+		goto pnet_erspan_failed;
 
 	err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
 	if (err < 0) {
@@ -1230,15 +1651,23 @@ static int __init ipgre_init(void)
 	if (err < 0)
 		goto tap_ops_failed;
 
+	err = rtnl_link_register(&erspan_link_ops);
+	if (err < 0)
+		goto erspan_link_failed;
+
 	return 0;
 
+erspan_link_failed:
+	rtnl_link_unregister(&ipgre_tap_ops);
 tap_ops_failed:
 	rtnl_link_unregister(&ipgre_link_ops);
 rtnl_link_failed:
 	gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
 add_proto_failed:
+	unregister_pernet_device(&erspan_net_ops);
+pnet_erspan_failed:
 	unregister_pernet_device(&ipgre_tap_net_ops);
-pnet_tap_faied:
+pnet_tap_failed:
 	unregister_pernet_device(&ipgre_net_ops);
 	return err;
 }
@@ -1247,9 +1676,11 @@ static void __exit ipgre_fini(void)
 {
 	rtnl_link_unregister(&ipgre_tap_ops);
 	rtnl_link_unregister(&ipgre_link_ops);
+	rtnl_link_unregister(&erspan_link_ops);
 	gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
 	unregister_pernet_device(&ipgre_tap_net_ops);
 	unregister_pernet_device(&ipgre_net_ops);
+	unregister_pernet_device(&erspan_net_ops);
 }
 
 module_init(ipgre_init);
@@ -1257,5 +1688,7 @@ module_exit(ipgre_fini);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("gre");
 MODULE_ALIAS_RTNL_LINK("gretap");
+MODULE_ALIAS_RTNL_LINK("erspan");
 MODULE_ALIAS_NETDEV("gre0");
 MODULE_ALIAS_NETDEV("gretap0");
+MODULE_ALIAS_NETDEV("erspan0");
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fa2dc8f692c6..57fc13c6ab2b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -311,9 +311,10 @@ drop:
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt;
+	int (*edemux)(struct sk_buff *skb);
 	struct net_device *dev = skb->dev;
-	void (*edemux)(struct sk_buff *skb);
+	struct rtable *rt;
+	int err;
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
 		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
-			edemux(skb);
+			err = edemux(skb);
+			if (unlikely(err))
+				goto drop_error;
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
@@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	 *	how the packet travels inside Linux networking.
 	 */
 	if (!skb_valid_dst(skb)) {
-		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, dev);
-		if (unlikely(err)) {
-			if (err == -EXDEV)
-				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
-			goto drop;
-		}
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, dev);
+		if (unlikely(err))
+			goto drop_error;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 drop:
 	kfree_skb(skb);
 	return NET_RX_DROP;
+
+drop_error:
+	if (err == -EXDEV)
+		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	goto drop;
 }
 
 /*
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 93157f2f4758..ed194d46c00e 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -86,8 +87,8 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
  * NOTE: dopt cannot point to skb.
  */
 
-int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
-		      const struct ip_options *sopt)
+int __ip_options_echo(struct net *net, struct ip_options *dopt,
+		      struct sk_buff *skb, const struct ip_options *sopt)
 {
 	unsigned char *sptr, *dptr;
 	int soffset, doffset;
@@ -140,7 +141,7 @@ int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
 						__be32 addr;
 
 						memcpy(&addr, dptr+soffset-1, 4);
-						if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_UNICAST) {
+						if (inet_addr_type(net, addr) != RTN_UNICAST) {
 							dopt->ts_needtime = 1;
 							soffset += 8;
 						}
@@ -174,9 +175,6 @@ int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
 				doffset -= 4;
 		}
 		if (doffset > 3) {
-			__be32 daddr = fib_compute_spec_dst(skb);
-
-			memcpy(&start[doffset-1], &daddr, 4);
 			dopt->faddr = faddr;
 			dptr[0] = start[0];
 			dptr[1] = doffset+3;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 50c74cd890bc..e8e675be60ec 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -853,61 +853,6 @@ csum_page(struct page *page, int offset, int copy)
 	return csum;
 }
 
-static inline int ip_ufo_append_data(struct sock *sk,
-			struct sk_buff_head *queue,
-			int getfrag(void *from, char *to, int offset, int len,
-			       int odd, struct sk_buff *skb),
-			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int maxfraglen, unsigned int flags)
-{
-	struct sk_buff *skb;
-	int err;
-
-	/* There is support for UDP fragmentation offload by network
-	 * device, so create one single skb packet containing complete
-	 * udp datagram
-	 */
-	skb = skb_peek_tail(queue);
-	if (!skb) {
-		skb = sock_alloc_send_skb(sk,
-			hh_len + fragheaderlen + transhdrlen + 20,
-			(flags & MSG_DONTWAIT), &err);
-
-		if (!skb)
-			return err;
-
-		/* reserve space for Hardware header */
-		skb_reserve(skb, hh_len);
-
-		/* create space for UDP/IP header */
-		skb_put(skb, fragheaderlen + transhdrlen);
-
-		/* initialize network header pointer */
-		skb_reset_network_header(skb);
-
-		/* initialize protocol header pointer */
-		skb->transport_header = skb->network_header + fragheaderlen;
-
-		skb->csum = 0;
-
-		if (flags & MSG_CONFIRM)
-			skb_set_dst_pending_confirm(skb, 1);
-
-		__skb_queue_tail(queue, skb);
-	} else if (skb_is_gso(skb)) {
-		goto append;
-	}
-
-	skb->ip_summed = CHECKSUM_PARTIAL;
-	/* specify the length of each IP datagram fragment */
-	skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
-	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-
-append:
-	return skb_append_datato_frags(sk, skb, getfrag, from,
-				       (length - transhdrlen));
-}
-
 static int __ip_append_data(struct sock *sk,
 			    struct flowi4 *fl4,
 			    struct sk_buff_head *queue,
@@ -965,18 +910,6 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) ||
-	     (skb && skb_is_gso(skb))) &&
-	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
-	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
-		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
-					 hh_len, fragheaderlen, transhdrlen,
-					 maxfraglen, flags);
-		if (err)
-			goto error;
-		return 0;
-	}
 
 	/* So, what's going on in the loop below?
 	 *
@@ -1287,27 +1220,14 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	if (!skb)
 		return -EINVAL;
 
-	if ((size + skb->len > mtu) &&
-	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO)) {
-		if (skb->ip_summed != CHECKSUM_PARTIAL)
-			return -EOPNOTSUPP;
-
-		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-	}
 	cork->length += size;
 
 	while (size > 0) {
-		if (skb_is_gso(skb)) {
-			len = size;
-		} else {
+		/* Check if the remaining data fits into current packet. */
+		len = mtu - skb->len;
+		if (len < size)
+			len = maxfraglen - skb->len;
 
-			/* Check if the remaining data fits into current packet. */
-			len = mtu - skb->len;
-			if (len < size)
-				len = maxfraglen - skb->len;
-		}
 		if (len <= 0) {
 			struct sk_buff *skb_prev;
 			int alloclen;
@@ -1601,7 +1521,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	int err;
 	int oif;
 
-	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
+	if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt))
 		return;
 
 	ipc.addr = daddr;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ecc4b4a2413e..60fb1eb7d7d8 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -80,7 +81,8 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb)
 }
 
 
-static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
+static void ip_cmsg_recv_retopts(struct net *net, struct msghdr *msg,
+				 struct sk_buff *skb)
 {
 	unsigned char optbuf[sizeof(struct ip_options) + 40];
 	struct ip_options *opt = (struct ip_options *)optbuf;
@@ -88,7 +90,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 	if (IPCB(skb)->opt.optlen == 0)
 		return;
 
-	if (ip_options_echo(opt, skb)) {
+	if (ip_options_echo(net, opt, skb)) {
 		msg->msg_flags |= MSG_CTRUNC;
 		return;
 	}
@@ -204,7 +206,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 	}
 
 	if (flags & IP_CMSG_RETOPTS) {
-		ip_cmsg_recv_retopts(msg, skb);
+		ip_cmsg_recv_retopts(sock_net(sk), msg, skb);
 
 		flags &= ~IP_CMSG_RETOPTS;
 		if (!flags)
@@ -1219,22 +1221,20 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		 * (e.g., process binds socket to eth0 for Tx which is
 		 * redirected to loopback in the rtable/dst).
 		 */
+		struct rtable *rt = skb_rtable(skb);
+		bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags);
+
 		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX)
 			pktinfo->ipi_ifindex = inet_iif(skb);
+		else if (l3slave && rt && rt->rt_iif)
+			pktinfo->ipi_ifindex = rt->rt_iif;
 
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	/* We need to keep the dst for __ip_options_echo()
-	 * We could restrict the test to opt.ts_needtime || opt.srr,
-	 * but the following is good enough as IP options are not often used.
-	 */
-	if (unlikely(IPCB(skb)->opt.optlen))
-		skb_dst_force(skb);
-	else
-		skb_dst_drop(skb);
+	skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 129d1a3616f8..fe6fee728ce4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -176,7 +176,7 @@ skip_key_lookup:
 		return cand;
 
 	t = rcu_dereference(itn->collect_md_tun);
-	if (t)
+	if (t && t->dev->flags & IFF_UP)
 		return t;
 
 	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
@@ -618,8 +618,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
-	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
-		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
 tx_error:
 	dev->stats.tx_errors++;
@@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
 	}
 }
 
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
+void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
+			   struct rtnl_link_ops *ops)
 {
+	struct ip_tunnel_net *itn;
+	struct net *net;
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	ip_tunnel_destroy(itn, &list, ops);
+	list_for_each_entry(net, net_list, exit_list) {
+		itn = net_generic(net, id);
+		ip_tunnel_destroy(itn, &list, ops);
+	}
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
 
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p, __u32 fwmark)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 0192c255e508..949f432a5f04 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 	int mtu;
 
@@ -197,15 +198,6 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tunnel->err_count > 0) {
-		if (time_before(jiffies,
-				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
-			tunnel->err_count--;
-			dst_link_failure(skb);
-		} else
-			tunnel->err_count = 0;
-	}
-
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
@@ -229,7 +221,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(dev, err);
 	return NETDEV_TX_OK;
 
@@ -452,15 +444,14 @@ static int __net_init vti_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_exit vti_exit_net(struct net *net)
+static void __net_exit vti_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
-	ip_tunnel_delete_net(itn, &vti_link_ops);
+	ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
 }
 
 static struct pernet_operations vti_net_ops = {
 	.init = vti_init_net,
-	.exit = vti_exit_net,
+	.exit_batch = vti_exit_batch_net,
 	.id   = &vti_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -584,33 +575,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.get_link_net	= ip_tunnel_get_link_net,
 };
 
-static bool is_vti_tunnel(const struct net_device *dev)
-{
-	return dev->netdev_ops == &vti_netdev_ops;
-}
-
-static int vti_device_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-
-	if (!is_vti_tunnel(dev))
-		return NOTIFY_DONE;
-
-	switch (event) {
-	case NETDEV_DOWN:
-		if (!net_eq(tunnel->net, dev_net(dev)))
-			xfrm_garbage_collect(tunnel->net);
-		break;
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block vti_notifier_block __read_mostly = {
-	.notifier_call = vti_device_event,
-};
-
 static int __init vti_init(void)
 {
 	const char *msg;
@@ -618,8 +582,6 @@ static int __init vti_init(void)
 
 	pr_info("IPv4 over IPsec tunneling driver\n");
 
-	register_netdevice_notifier(&vti_notifier_block);
-
 	msg = "tunnel device";
 	err = register_pernet_device(&vti_net_ops);
 	if (err < 0)
@@ -652,7 +614,6 @@ xfrm_proto_ah_failed:
 xfrm_proto_esp_failed:
 	unregister_pernet_device(&vti_net_ops);
 pernet_dev_failed:
-	unregister_netdevice_notifier(&vti_notifier_block);
 	pr_err("vti init: failed to register %s\n", msg);
 	return err;
 }
@@ -664,7 +625,6 @@ static void __exit vti_fini(void)
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
 	unregister_pernet_device(&vti_net_ops);
-	unregister_netdevice_notifier(&vti_notifier_block);
 }
 
 module_init(vti_init);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4c5dfe6bd34d..abdebca848c9 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  Automatic Configuration of IP -- use DHCP, BOOTP, RARP, or
  *  user-supplied information to configure own IP address and routes.
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fb1ad22b5e29..c891235b4966 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
+	/* All the routers (except for Linux) return only
+	 * 8 bytes of packet payload. It means, that precise relaying of
+	 * ICMP in the real Internet is absolutely infeasible.
+	 */
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	struct ip_tunnel *t;
-	int err;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	struct ip_tunnel *t;
+	int err = 0;
+
+	switch (type) {
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+			/* Impossible event. */
+			goto out;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			 * rfc2003 contains "deep thoughts" about NET_UNREACH,
+			 * I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			goto out;
+		break;
+
+	case ICMP_REDIRECT:
+		break;
+
+	default:
+		goto out;
+	}
 
-	err = -ENOENT;
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (!t)
+	if (!t) {
+		err = -ENOENT;
 		goto out;
+	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, iph->protocol, 0);
-		err = 0;
+		ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
+				 iph->protocol, 0);
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      iph->protocol, 0);
-		err = 0;
+		ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0) {
+		err = -ENOENT;
 		goto out;
+	}
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
@@ -634,15 +659,14 @@ static int __net_init ipip_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
 }
 
-static void __net_exit ipip_exit_net(struct net *net)
+static void __net_exit ipip_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
-	ip_tunnel_delete_net(itn, &ipip_link_ops);
+	ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops);
 }
 
 static struct pernet_operations ipip_net_ops = {
 	.init = ipip_init_net,
-	.exit = ipip_exit_net,
+	.exit_batch = ipip_exit_batch_net,
 	.id   = &ipip_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 06863ea3fc5b..fd5f19c988e4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -67,6 +67,7 @@
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
 #include <net/nexthop.h>
+#include <net/switchdev.h>
 
 struct ipmr_rule {
 	struct fib_rule		common;
@@ -111,7 +112,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
 static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
 static void mroute_clean_tables(struct mr_table *mrt, bool all);
-static void ipmr_expire_process(unsigned long arg);
+static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
 #define ipmr_for_each_table(mrt, net) \
@@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, RTNL_FAMILY_IPMR);
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #else
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
@@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	net->ipv4.mrt = NULL;
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return 0;
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return 0;
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #endif
 
 static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -342,8 +375,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 	INIT_LIST_HEAD(&mrt->mfc_cache_list);
 	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
 
-	setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
-		    (unsigned long)mrt);
+	timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0);
 
 	mrt->mroute_reg_vif_num = -1;
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -587,6 +619,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 }
 #endif
 
+static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct vif_device *vif,
+					vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_vif_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct vif_device *vif,
+					 vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 /**
  *	vif_delete - Delete a VIF entry
  *	@notify: Set to 1, if the caller is a notifier_call
@@ -594,6 +702,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		      struct list_head *head)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct vif_device *v;
 	struct net_device *dev;
 	struct in_device *in_dev;
@@ -603,6 +712,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 
 	v = &mrt->vif_table[vifi];
 
+	if (VIF_EXISTS(mrt, vifi))
+		call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi,
+					      mrt->id);
+
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
 	v->dev = NULL;
@@ -652,10 +765,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
 	kmem_cache_free(mrt_cachep, c);
 }
 
-static inline void ipmr_cache_free(struct mfc_cache *c)
+void ipmr_cache_free(struct mfc_cache *c)
 {
 	call_rcu(&c->rcu, ipmr_cache_free_rcu);
 }
+EXPORT_SYMBOL(ipmr_cache_free);
 
 /* Destroy an unresolved cache entry, killing queued skbs
  * and reporting error to netlink readers.
@@ -689,9 +803,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
 }
 
 /* Timer process for the unresolved queue. */
-static void ipmr_expire_process(unsigned long arg)
+static void ipmr_expire_process(struct timer_list *t)
 {
-	struct mr_table *mrt = (struct mr_table *)arg;
+	struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
 	unsigned long now;
 	unsigned long expires;
 	struct mfc_cache *c, *next;
@@ -754,6 +868,9 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		   struct vifctl *vifc, int mrtsock)
 {
 	int vifi = vifc->vifc_vifi;
+	struct switchdev_attr attr = {
+		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
+	};
 	struct vif_device *v = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct in_device *in_dev;
@@ -828,6 +945,13 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 
 	/* Fill in the VIF structures */
 
+	attr.orig_dev = dev;
+	if (!switchdev_port_attr_get(dev, &attr)) {
+		memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len);
+		v->dev_parent_id.id_len = attr.u.ppid.id_len;
+	} else {
+		v->dev_parent_id.id_len = 0;
+	}
 	v->rate_limit = vifc->vifc_rate_limit;
 	v->local = vifc->vifc_lcl_addr.s_addr;
 	v->remote = vifc->vifc_rmt_addr.s_addr;
@@ -851,6 +975,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 	if (vifi+1 > mrt->maxvif)
 		mrt->maxvif = vifi+1;
 	write_unlock_bh(&mrt_lock);
+	call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id);
 	return 0;
 }
 
@@ -949,6 +1074,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 	if (c) {
 		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+		refcount_set(&c->mfc_un.res.refcount, 1);
 	}
 	return c;
 }
@@ -1150,6 +1276,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
 
 static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c;
 
 	/* The entries are added/deleted only under RTNL */
@@ -1161,8 +1288,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 		return -ENOENT;
 	rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 	list_del_rcu(&c->list);
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_DELROUTE);
-	ipmr_cache_free(c);
+	ipmr_cache_put(c);
 
 	return 0;
 }
@@ -1189,6 +1317,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
@@ -1238,6 +1368,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
@@ -1245,6 +1376,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 /* Close the multicast socket, and clear the vif tables etc */
 static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c, *tmp;
 	LIST_HEAD(list);
 	int i;
@@ -1263,8 +1395,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 			continue;
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 		list_del_rcu(&c->list);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_DELROUTE);
-		ipmr_cache_free(c);
+		ipmr_cache_put(c);
 	}
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -1393,6 +1527,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 	case MRT_ADD_MFC:
 	case MRT_DEL_MFC:
 		parent = -1;
+		/* fall through */
 	case MRT_ADD_MFC_PROXY:
 	case MRT_DEL_MFC_PROXY:
 		if (optlen != sizeof(mfc)) {
@@ -1724,10 +1859,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
 	return dst_output(net, sk, skb);
 }
 
+#ifdef CONFIG_NET_SWITCHDEV
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+				   int in_vifi, int out_vifi)
+{
+	struct vif_device *out_vif = &mrt->vif_table[out_vifi];
+	struct vif_device *in_vif = &mrt->vif_table[in_vifi];
+
+	if (!skb->offload_mr_fwd_mark)
+		return false;
+	if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len)
+		return false;
+	return netdev_phys_item_id_same(&out_vif->dev_parent_id,
+					&in_vif->dev_parent_id);
+}
+#else
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+				   int in_vifi, int out_vifi)
+{
+	return false;
+}
+#endif
+
 /* Processing handlers for ipmr_forward */
 
 static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
-			    struct sk_buff *skb, struct mfc_cache *c, int vifi)
+			    int in_vifi, struct sk_buff *skb,
+			    struct mfc_cache *c, int vifi)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct vif_device *vif = &mrt->vif_table[vifi];
@@ -1748,6 +1906,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		goto out_free;
 	}
 
+	if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi))
+		goto out_free;
+
 	if (vif->flags & VIFF_TUNNEL) {
 		rt = ip_route_output_ports(net, &fl4, NULL,
 					   vif->remote, vif->local,
@@ -1925,8 +2086,8 @@ forward:
 				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 				if (skb2)
-					ipmr_queue_xmit(net, mrt, skb2, cache,
-							psend);
+					ipmr_queue_xmit(net, mrt, true_vifi,
+							skb2, cache, psend);
 			}
 			psend = ct;
 		}
@@ -1937,9 +2098,10 @@ last_forward:
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb2)
-				ipmr_queue_xmit(net, mrt, skb2, cache, psend);
+				ipmr_queue_xmit(net, mrt, true_vifi, skb2,
+						cache, psend);
 		} else {
-			ipmr_queue_xmit(net, mrt, skb, cache, psend);
+			ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend);
 			return;
 		}
 	}
@@ -2156,6 +2318,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	    nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
 		return -EMSGSIZE;
 
+	if (c->mfc_flags & MFC_OFFLOAD)
+		rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
 	if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
 		return -EMSGSIZE;
 
@@ -3048,14 +3213,87 @@ static const struct net_protocol pim_protocol = {
 };
 #endif
 
+static unsigned int ipmr_seq_read(struct net *net)
+{
+	ASSERT_RTNL();
+
+	return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
+}
+
+static int ipmr_dump(struct net *net, struct notifier_block *nb)
+{
+	struct mr_table *mrt;
+	int err;
+
+	err = ipmr_rules_dump(net, nb);
+	if (err)
+		return err;
+
+	ipmr_for_each_table(mrt, net) {
+		struct vif_device *v = &mrt->vif_table[0];
+		struct mfc_cache *mfc;
+		int vifi;
+
+		/* Notifiy on table VIF entries */
+		read_lock(&mrt_lock);
+		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+			if (!v->dev)
+				continue;
+
+			call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
+						     v, vifi, mrt->id);
+		}
+		read_unlock(&mrt_lock);
+
+		/* Notify on table MFC entries */
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+			call_ipmr_mfc_entry_notifier(nb, net,
+						     FIB_EVENT_ENTRY_ADD, mfc,
+						     mrt->id);
+	}
+
+	return 0;
+}
+
+static const struct fib_notifier_ops ipmr_notifier_ops_template = {
+	.family		= RTNL_FAMILY_IPMR,
+	.fib_seq_read	= ipmr_seq_read,
+	.fib_dump	= ipmr_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ipmr_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
+
+	net->ipv4.ipmr_seq = 0;
+
+	ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv4.ipmr_notifier_ops = ops;
+
+	return 0;
+}
+
+static void __net_exit ipmr_notifier_exit(struct net *net)
+{
+	fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
+	net->ipv4.ipmr_notifier_ops = NULL;
+}
+
 /* Setup for IP multicast routing */
 static int __net_init ipmr_net_init(struct net *net)
 {
 	int err;
 
+	err = ipmr_notifier_init(net);
+	if (err)
+		goto ipmr_notifier_fail;
+
 	err = ipmr_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto ipmr_rules_fail;
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -3072,7 +3310,9 @@ proc_cache_fail:
 proc_vif_fail:
 	ipmr_rules_exit(net);
 #endif
-fail:
+ipmr_rules_fail:
+	ipmr_notifier_exit(net);
+ipmr_notifier_fail:
 	return err;
 }
 
@@ -3082,6 +3322,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	remove_proc_entry("ip_mr_cache", net->proc_net);
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 #endif
+	ipmr_notifier_exit(net);
 	ipmr_rules_exit(net);
 }
 
@@ -3114,14 +3355,14 @@ int __init ip_mr_init(void)
 	}
 #endif
 	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE,
-		      ipmr_rtm_getroute, ipmr_rtm_dumproute, NULL);
+		      ipmr_rtm_getroute, ipmr_rtm_dumproute, 0);
 	rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE,
-		      ipmr_rtm_route, NULL, NULL);
+		      ipmr_rtm_route, NULL, 0);
 	rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE,
-		      ipmr_rtm_route, NULL, NULL);
+		      ipmr_rtm_route, NULL, 0);
 
 	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETLINK,
-		      NULL, ipmr_rtm_dumplink, NULL);
+		      NULL, ipmr_rtm_dumplink, 0);
 	return 0;
 
 #ifdef CONFIG_IP_PIMSM_V2
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index f462fee66ac8..adcdae358365 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the netfilter modules on top of IPv4.
 #
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 0bc3c3d73e61..f88221aebc9d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -268,14 +268,14 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 		acpar.targinfo = t->data;
 		verdict = t->u.kernel.target->target(skb, &acpar);
 
-		/* Target might have changed stuff. */
-		arp = arp_hdr(skb);
-
-		if (verdict == XT_CONTINUE)
+		if (verdict == XT_CONTINUE) {
+			/* Target might have changed stuff. */
+			arp = arp_hdr(skb);
 			e = arpt_next_entry(e);
-		else
+		} else {
 			/* Verdict */
 			break;
+		}
 	} while (!acpar.hotdrop);
 	xt_write_recseq_end(addend);
 	local_bh_enable();
@@ -629,7 +629,27 @@ static void get_counters(const struct xt_table_info *t,
 
 			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i;
+			cond_resched();
+		}
+	}
+}
+
+static void get_old_counters(const struct xt_table_info *t,
+			     struct xt_counters counters[])
+{
+	struct arpt_entry *iter;
+	unsigned int cpu, i;
+
+	for_each_possible_cpu(cpu) {
+		i = 0;
+		xt_entry_foreach(iter, t->entries, t->size) {
+			struct xt_counters *tmp;
+
+			tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+			ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+			++i;
 		}
+		cond_resched();
 	}
 }
 
@@ -909,8 +929,7 @@ static int __do_replace(struct net *net, const char *name,
 	    (newinfo->number <= oldinfo->initial_entries))
 		module_put(t->me);
 
-	/* Get the old counters, and synchronize with replace */
-	get_counters(oldinfo, counters);
+	get_old_counters(oldinfo, counters);
 
 	/* Decrease module usage counts and free resource */
 	loc_cpu_old_entry = oldinfo->entries;
@@ -1117,7 +1136,6 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
-	struct xt_target *target;
 	struct arpt_entry *de;
 	unsigned int origsize;
 	int h;
@@ -1132,7 +1150,6 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_arpt_get_target(e);
-	target = t->u.kernel.target;
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2a55a40211cb..4cbe5e80f3bf 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -35,12 +35,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("IPv4 packet filter");
 
-#ifdef CONFIG_NETFILTER_DEBUG
-#define IP_NF_ASSERT(x)		WARN_ON(!(x))
-#else
-#define IP_NF_ASSERT(x)
-#endif
-
 void *ipt_alloc_initial_table(const struct xt_table *info)
 {
 	return xt_alloc_initial_table(ipt, IPT);
@@ -151,7 +145,7 @@ static const char *const comments[] = {
 	[NF_IP_TRACE_COMMENT_POLICY]	= "policy",
 };
 
-static struct nf_loginfo trace_loginfo = {
+static const struct nf_loginfo trace_loginfo = {
 	.type = NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
@@ -263,7 +257,7 @@ ipt_do_table(struct sk_buff *skb,
 	acpar.hotdrop = false;
 	acpar.state   = state;
 
-	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
+	WARN_ON(!(table->valid_hooks & (1 << hook)));
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
 	private = table->private;
@@ -293,7 +287,7 @@ ipt_do_table(struct sk_buff *skb,
 		const struct xt_entry_match *ematch;
 		struct xt_counters *counter;
 
-		IP_NF_ASSERT(e);
+		WARN_ON(!e);
 		if (!ip_packet_match(ip, indev, outdev,
 		    &e->ip, acpar.fragoff)) {
  no_match:
@@ -312,7 +306,7 @@ ipt_do_table(struct sk_buff *skb,
 		ADD_COUNTER(*counter, skb->len, 1);
 
 		t = ipt_get_target(e);
-		IP_NF_ASSERT(t->u.kernel.target);
+		WARN_ON(!t->u.kernel.target);
 
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
 		/* The packet is traced: log it */
@@ -352,13 +346,14 @@ ipt_do_table(struct sk_buff *skb,
 		acpar.targinfo = t->data;
 
 		verdict = t->u.kernel.target->target(skb, &acpar);
-		/* Target might have changed stuff. */
-		ip = ip_hdr(skb);
-		if (verdict == XT_CONTINUE)
+		if (verdict == XT_CONTINUE) {
+			/* Target might have changed stuff. */
+			ip = ip_hdr(skb);
 			e = ipt_next_entry(e);
-		else
+		} else {
 			/* Verdict */
 			break;
+		}
 	} while (!acpar.hotdrop);
 
 	xt_write_recseq_end(addend);
@@ -781,10 +776,31 @@ get_counters(const struct xt_table_info *t,
 
 			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i; /* macro does multi eval of i */
+			cond_resched();
 		}
 	}
 }
 
+static void get_old_counters(const struct xt_table_info *t,
+			     struct xt_counters counters[])
+{
+	struct ipt_entry *iter;
+	unsigned int cpu, i;
+
+	for_each_possible_cpu(cpu) {
+		i = 0;
+		xt_entry_foreach(iter, t->entries, t->size) {
+			const struct xt_counters *tmp;
+
+			tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+			ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+			++i; /* macro does multi eval of i */
+		}
+
+		cond_resched();
+	}
+}
+
 static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
@@ -1074,8 +1090,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	    (newinfo->number <= oldinfo->initial_entries))
 		module_put(t->me);
 
-	/* Get the old counters, and synchronize with replace */
-	get_counters(oldinfo, counters);
+	get_old_counters(oldinfo, counters);
 
 	/* Decrease module usage counts and free resource */
 	xt_entry_foreach(iter, oldinfo->entries, oldinfo->size)
@@ -1355,7 +1370,6 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
-	struct xt_target *target;
 	struct ipt_entry *de;
 	unsigned int origsize;
 	int h;
@@ -1374,7 +1388,6 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ipt_get_target(e);
-	target = t->u.kernel.target;
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 7d72decb80f9..17b4ca562944 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -117,7 +117,8 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
 		 * functions are also incrementing the refcount on their own,
 		 * so it's safe to remove the entry even if it's in use. */
 #ifdef CONFIG_PROC_FS
-		proc_remove(c->pde);
+		if (cn->procdir)
+			proc_remove(c->pde);
 #endif
 		return;
 	}
@@ -624,7 +625,7 @@ arp_mangle(void *priv,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops cip_arp_ops __read_mostly = {
+static const struct nf_hook_ops cip_arp_ops = {
 	.hook = arp_mangle,
 	.pf = NFPROTO_ARP,
 	.hooknum = NF_ARP_OUT,
@@ -815,6 +816,7 @@ static void clusterip_net_exit(struct net *net)
 #ifdef CONFIG_PROC_FS
 	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 	proc_remove(cn->procdir);
+	cn->procdir = NULL;
 #endif
 	nf_unregister_net_hook(net, &cip_arp_ops);
 }
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index f1528f7175a8..f75fc6b53115 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv,
 	if (synproxy == NULL)
 		return NF_ACCEPT;
 
-	if (nf_is_loopback_packet(skb))
+	if (nf_is_loopback_packet(skb) ||
+	    ip_hdr(skb)->protocol != IPPROTO_TCP)
 		return NF_ACCEPT;
 
 	thoff = ip_hdrlen(skb);
@@ -416,7 +417,7 @@ static unsigned int ipv4_synproxy_hook(void *priv,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops ipv4_synproxy_ops[] __read_mostly = {
+static const struct nf_hook_ops ipv4_synproxy_ops[] = {
 	{
 		.hook		= ipv4_synproxy_hook,
 		.pf		= NFPROTO_IPV4,
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 138a24bc76ad..a1a07b338ccf 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -67,7 +67,7 @@ static unsigned int iptable_nat_ipv4_local_fn(void *priv,
 	return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain);
 }
 
-static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
+static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
 	/* Before packet filtering, change destination */
 	{
 		.hook		= iptable_nat_ipv4_in,
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 2e14ed11a35c..89af9d88ca21 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -63,13 +63,6 @@ static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static void ipv4_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
-{
-	seq_printf(s, "src=%pI4 dst=%pI4 ",
-		   &tuple->src.u3.ip, &tuple->dst.u3.ip);
-}
-
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {
@@ -174,7 +167,7 @@ static unsigned int ipv4_conntrack_local(void *priv,
 
 /* Connection tracking may drop packets, but never alters them, so
    make it the first hook. */
-static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
+static const struct nf_hook_ops ipv4_conntrack_ops[] = {
 	{
 		.hook		= ipv4_conntrack_in,
 		.pf		= NFPROTO_IPV4,
@@ -303,11 +296,6 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
 
 	return 0;
 }
-
-static int ipv4_nlattr_tuple_size(void)
-{
-	return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1);
-}
 #endif
 
 static struct nf_sockopt_ops so_getorigdst = {
@@ -356,18 +344,17 @@ static void ipv4_hooks_unregister(struct net *net)
 	mutex_unlock(&register_ipv4_hooks);
 }
 
-struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
+const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.name		 = "ipv4",
 	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
 	.invert_tuple	 = ipv4_invert_tuple,
-	.print_tuple	 = ipv4_print_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
-	.nlattr_tuple_size = ipv4_nlattr_tuple_size,
 	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
 	.nla_policy	 = ipv4_nla_policy,
+	.nla_size	 = NLA_ALIGN(NLA_HDRLEN + sizeof(u32)) + /* CTA_IP_V4_SRC */
+			   NLA_ALIGN(NLA_HDRLEN + sizeof(u32)),  /* CTA_IP_V4_DST */
 #endif
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,
@@ -398,24 +385,12 @@ static struct nf_conntrack_l4proto *builtin_l4proto4[] = {
 
 static int ipv4_net_init(struct net *net)
 {
-	int ret = 0;
-
-	ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
-					    ARRAY_SIZE(builtin_l4proto4));
-	if (ret < 0)
-		return ret;
-	ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4);
-	if (ret < 0) {
-		pr_err("nf_conntrack_ipv4: pernet registration failed\n");
-		nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
-						ARRAY_SIZE(builtin_l4proto4));
-	}
-	return ret;
+	return nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
+					     ARRAY_SIZE(builtin_l4proto4));
 }
 
 static void ipv4_net_exit(struct net *net)
 {
-	nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
 	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
 					ARRAY_SIZE(builtin_l4proto4));
 }
@@ -433,6 +408,11 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
 
 	need_conntrack();
 
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	if (WARN_ON(nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1) !=
+	    nf_conntrack_l3proto_ipv4.nla_size))
+		return -EINVAL;
+#endif
 	ret = nf_register_sockopt(&so_getorigdst);
 	if (ret < 0) {
 		pr_err("Unable to register netfilter socket option\n");
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 73c591d8a9a8..1849fedd9b81 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -71,16 +71,6 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-/* Print out the per-protocol part of the tuple. */
-static void icmp_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
-{
-	seq_printf(s, "type=%u code=%u id=%u ",
-		   tuple->dst.u.icmp.type,
-		   tuple->dst.u.icmp.code,
-		   ntohs(tuple->src.u.icmp.id));
-}
-
 static unsigned int *icmp_get_timeouts(struct net *net)
 {
 	return &icmp_pernet(net)->timeout;
@@ -91,8 +81,6 @@ static int icmp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
 		       enum ip_conntrack_info ctinfo,
-		       u_int8_t pf,
-		       unsigned int hooknum,
 		       unsigned int *timeout)
 {
 	/* Do not immediately delete the connection after the first
@@ -137,7 +125,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
 
-	NF_CT_ASSERT(!skb_nfct(skb));
+	WARN_ON(skb_nfct(skb));
 	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
@@ -176,6 +164,12 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
+static void icmp_error_log(const struct sk_buff *skb, struct net *net,
+			   u8 pf, const char *msg)
+{
+	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg);
+}
+
 /* Small and modified version of icmp_rcv */
 static int
 icmp_error(struct net *net, struct nf_conn *tmpl,
@@ -188,18 +182,14 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	/* Not enough header? */
 	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
 	if (icmph == NULL) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL,
-				      NULL, "nf_ct_icmp: short packet ");
+		icmp_error_log(skb, net, pf, "short packet");
 		return -NF_ACCEPT;
 	}
 
 	/* See ip_conntrack_proto_tcp.c */
 	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
 	    nf_ip_checksum(skb, hooknum, dataoff, 0)) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
-				      "nf_ct_icmp: bad HW ICMP checksum ");
+		icmp_error_log(skb, net, pf, "bad hw icmp checksum");
 		return -NF_ACCEPT;
 	}
 
@@ -210,9 +200,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	 *		  discarded.
 	 */
 	if (icmph->type > NR_ICMP_TYPES) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
-				      "nf_ct_icmp: invalid ICMP type ");
+		icmp_error_log(skb, net, pf, "invalid icmp type");
 		return -NF_ACCEPT;
 	}
 
@@ -270,9 +258,14 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[],
 	return 0;
 }
 
-static int icmp_nlattr_tuple_size(void)
+static unsigned int icmp_nlattr_tuple_size(void)
 {
-	return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+	static unsigned int size __read_mostly;
+
+	if (!size)
+		size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+
+	return size;
 }
 #endif
 
@@ -362,10 +355,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly =
 {
 	.l3proto		= PF_INET,
 	.l4proto		= IPPROTO_ICMP,
-	.name			= "icmp",
 	.pkt_to_tuple		= icmp_pkt_to_tuple,
 	.invert_tuple		= icmp_invert_tuple,
-	.print_tuple		= icmp_print_tuple,
 	.packet			= icmp_packet,
 	.get_timeouts		= icmp_get_timeouts,
 	.new			= icmp_new,
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 346bf7ccac08..37fe1616ca0b 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -90,7 +90,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops ipv4_defrag_ops[] = {
+static const struct nf_hook_ops ipv4_defrag_ops[] = {
 	{
 		.hook		= ipv4_conntrack_defrag,
 		.pf		= NFPROTO_IPV4,
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index 2f3895ddc275..df5c2a2061a4 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -25,7 +25,7 @@
 #include <linux/netfilter/xt_LOG.h>
 #include <net/netfilter/nf_log.h>
 
-static struct nf_loginfo default_loginfo = {
+static const struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index c83a9963269b..4388de0e5380 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -24,7 +24,7 @@
 #include <linux/netfilter/xt_LOG.h>
 #include <net/netfilter/nf_log.h>
 
-static struct nf_loginfo default_loginfo = {
+static const struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 574f7ebba0b6..ac8342dcb55e 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -252,16 +252,16 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 	if (set_h245_addr(skb, protoff, data, dataoff, taddr,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  htons((port & htons(1)) ? nated_port + 1 :
-						    nated_port)) == 0) {
-		/* Save ports */
-		info->rtp_port[i][dir] = rtp_port;
-		info->rtp_port[i][!dir] = htons(nated_port);
-	} else {
+						    nated_port))) {
 		nf_ct_unexpect_related(rtp_exp);
 		nf_ct_unexpect_related(rtcp_exp);
 		return -1;
 	}
 
+	/* Save ports */
+	info->rtp_port[i][dir] = rtp_port;
+	info->rtp_port[i][!dir] = htons(nated_port);
+
 	/* Success */
 	pr_debug("nf_nat_h323: expect RTP %pI4:%hu->%pI4:%hu\n",
 		 &rtp_exp->tuple.src.u3.ip,
@@ -370,15 +370,15 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
 	/* Modify signal */
 	if (set_h225_addr(skb, protoff, data, dataoff, taddr,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
-			  htons(nated_port)) == 0) {
-		/* Save ports */
-		info->sig_port[dir] = port;
-		info->sig_port[!dir] = htons(nated_port);
-	} else {
+			  htons(nated_port))) {
 		nf_ct_unexpect_related(exp);
 		return -1;
 	}
 
+	/* Save ports */
+	info->sig_port[dir] = port;
+	info->sig_port[!dir] = htons(nated_port);
+
 	pr_debug("nf_nat_q931: expect H.245 %pI4:%hu->%pI4:%hu\n",
 		 &exp->tuple.src.u3.ip,
 		 ntohs(exp->tuple.src.u.tcp.port),
@@ -462,24 +462,27 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
 	/* Modify signal */
 	if (set_h225_addr(skb, protoff, data, 0, &taddr[idx],
 			  &ct->tuplehash[!dir].tuple.dst.u3,
-			  htons(nated_port)) == 0) {
-		/* Save ports */
-		info->sig_port[dir] = port;
-		info->sig_port[!dir] = htons(nated_port);
-
-		/* Fix for Gnomemeeting */
-		if (idx > 0 &&
-		    get_h225_addr(ct, *data, &taddr[0], &addr, &port) &&
-		    (ntohl(addr.ip) & 0xff000000) == 0x7f000000) {
-			set_h225_addr(skb, protoff, data, 0, &taddr[0],
-				      &ct->tuplehash[!dir].tuple.dst.u3,
-				      info->sig_port[!dir]);
-		}
-	} else {
+			  htons(nated_port))) {
 		nf_ct_unexpect_related(exp);
 		return -1;
 	}
 
+	/* Save ports */
+	info->sig_port[dir] = port;
+	info->sig_port[!dir] = htons(nated_port);
+
+	/* Fix for Gnomemeeting */
+	if (idx > 0 &&
+	    get_h225_addr(ct, *data, &taddr[0], &addr, &port) &&
+	    (ntohl(addr.ip) & 0xff000000) == 0x7f000000) {
+		if (set_h225_addr(skb, protoff, data, 0, &taddr[0],
+				  &ct->tuplehash[!dir].tuple.dst.u3,
+				  info->sig_port[!dir])) {
+			nf_ct_unexpect_related(exp);
+			return -1;
+		}
+	}
+
 	/* Success */
 	pr_debug("nf_nat_ras: expect Q.931 %pI4:%hu->%pI4:%hu\n",
 		 &exp->tuple.src.u3.ip,
@@ -550,9 +553,9 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct,
 	}
 
 	/* Modify signal */
-	if (!set_h225_addr(skb, protoff, data, dataoff, taddr,
-			   &ct->tuplehash[!dir].tuple.dst.u3,
-			   htons(nated_port)) == 0) {
+	if (set_h225_addr(skb, protoff, data, dataoff, taddr,
+			  &ct->tuplehash[!dir].tuple.dst.u3,
+			  htons(nated_port))) {
 		nf_ct_unexpect_related(exp);
 		return -1;
 	}
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index feedd759ca80..0443ca4120b0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -190,7 +190,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 	struct nf_conntrack_tuple target;
 	unsigned long statusbit;
 
-	NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY);
+	WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);
 
 	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
 		return 0;
@@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 			else
 				return NF_ACCEPT;
 		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+		/* Only ICMPs can be IP_CT_IS_REPLY: */
+		/* fall through */
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
@@ -306,8 +307,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 
 	default:
 		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		WARN_ON(ctinfo != IP_CT_ESTABLISHED &&
+			ctinfo != IP_CT_ESTABLISHED_REPLY);
 		if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
 			goto oif_changed;
 	}
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index f39037fca923..0c366aad89cb 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -34,12 +34,12 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 	const struct rtable *rt;
 	__be32 newsrc, nh;
 
-	NF_CT_ASSERT(hooknum == NF_INET_POST_ROUTING);
+	WARN_ON(hooknum != NF_INET_POST_ROUTING);
 
 	ct = nf_ct_get(skb, &ctinfo);
 
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
+	WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			 ctinfo == IP_CT_RELATED_REPLY)));
 
 	/* Source address is 0.0.0.0 - locally generated packet that is
 	 * probably not supposed to be masqueraded.
@@ -96,7 +96,7 @@ static int masq_device_event(struct notifier_block *this,
 		 * conntracks which were associated with that device,
 		 * and forget them.
 		 */
-		NF_CT_ASSERT(dev->ifindex != 0);
+		WARN_ON(dev->ifindex == 0);
 
 		nf_ct_iterate_cleanup_net(net, device_cmp,
 					  (void *)(long)dev->ifindex, 0, 0);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index eeacbdaf7cdf..5cd06ba3535d 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -132,6 +132,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
+	niph = ip_hdr(nskb);
+
 	/* "Never happens" */
 	if (nskb->len > dst_mtu(skb_dst(nskb)))
 		goto free_nskb;
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index de3681df2ce7..e50976e3c213 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -32,9 +32,10 @@ void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 			const struct nft_pktinfo *pkt)
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
+	int noff = skb_network_offset(pkt->skb);
 	u32 *dst = &regs->data[priv->dreg];
 	const struct net_device *dev = NULL;
-	const struct iphdr *iph;
+	struct iphdr *iph, _iph;
 	__be32 addr;
 
 	if (priv->flags & NFTA_FIB_F_IIF)
@@ -42,7 +43,12 @@ void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 	else if (priv->flags & NFTA_FIB_F_OIF)
 		dev = nft_out(pkt);
 
-	iph = ip_hdr(pkt->skb);
+	iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
+	if (!iph) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
 	if (priv->flags & NFTA_FIB_F_DADDR)
 		addr = iph->daddr;
 	else
@@ -61,8 +67,9 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		   const struct nft_pktinfo *pkt)
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
+	int noff = skb_network_offset(pkt->skb);
 	u32 *dest = &regs->data[priv->dreg];
-	const struct iphdr *iph;
+	struct iphdr *iph, _iph;
 	struct fib_result res;
 	struct flowi4 fl4 = {
 		.flowi4_scope = RT_SCOPE_UNIVERSE,
@@ -95,7 +102,12 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		return;
 	}
 
-	iph = ip_hdr(pkt->skb);
+	iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
+	if (!iph) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
 	if (ipv4_is_zeronet(iph->saddr)) {
 		if (ipv4_is_lbcast(iph->daddr) ||
 		    ipv4_is_local_multicast(iph->daddr)) {
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 43eb6567b3a0..9f37c4727861 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -206,18 +206,12 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST),
 	SNMP_MIB_ITEM("ListenOverflows", LINUX_MIB_LISTENOVERFLOWS),
 	SNMP_MIB_ITEM("ListenDrops", LINUX_MIB_LISTENDROPS),
-	SNMP_MIB_ITEM("TCPPrequeued", LINUX_MIB_TCPPREQUEUED),
-	SNMP_MIB_ITEM("TCPDirectCopyFromBacklog", LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG),
-	SNMP_MIB_ITEM("TCPDirectCopyFromPrequeue", LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE),
-	SNMP_MIB_ITEM("TCPPrequeueDropped", LINUX_MIB_TCPPREQUEUEDROPPED),
 	SNMP_MIB_ITEM("TCPHPHits", LINUX_MIB_TCPHPHITS),
-	SNMP_MIB_ITEM("TCPHPHitsToUser", LINUX_MIB_TCPHPHITSTOUSER),
 	SNMP_MIB_ITEM("TCPPureAcks", LINUX_MIB_TCPPUREACKS),
 	SNMP_MIB_ITEM("TCPHPAcks", LINUX_MIB_TCPHPACKS),
 	SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY),
 	SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY),
 	SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING),
-	SNMP_MIB_ITEM("TCPFACKReorder", LINUX_MIB_TCPFACKREORDER),
 	SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER),
 	SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER),
 	SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER),
@@ -230,14 +224,12 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES),
 	SNMP_MIB_ITEM("TCPLossFailures", LINUX_MIB_TCPLOSSFAILURES),
 	SNMP_MIB_ITEM("TCPFastRetrans", LINUX_MIB_TCPFASTRETRANS),
-	SNMP_MIB_ITEM("TCPForwardRetrans", LINUX_MIB_TCPFORWARDRETRANS),
 	SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS),
 	SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS),
 	SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES),
 	SNMP_MIB_ITEM("TCPLossProbeRecovery", LINUX_MIB_TCPLOSSPROBERECOVERY),
 	SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
 	SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
-	SNMP_MIB_ITEM("TCPSchedulerFailed", LINUX_MIB_TCPSCHEDULERFAILED),
 	SNMP_MIB_ITEM("TCPRcvCollapsed", LINUX_MIB_TCPRCVCOLLAPSED),
 	SNMP_MIB_ITEM("TCPDSACKOldSent", LINUX_MIB_TCPDSACKOLDSENT),
 	SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT),
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b0bb5d0a30bd..33b70bfd1122 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -122,7 +122,8 @@ void raw_unhash_sk(struct sock *sk)
 EXPORT_SYMBOL_GPL(raw_unhash_sk);
 
 struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
-		unsigned short num, __be32 raddr, __be32 laddr, int dif)
+			     unsigned short num, __be32 raddr, __be32 laddr,
+			     int dif, int sdif)
 {
 	sk_for_each_from(sk) {
 		struct inet_sock *inet = inet_sk(sk);
@@ -130,7 +131,8 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
 		if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
 		    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
 		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
-		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
+		      sk->sk_bound_dev_if != sdif))
 			goto found; /* gotcha */
 	}
 	sk = NULL;
@@ -171,6 +173,7 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
  */
 static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 {
+	int sdif = inet_sdif(skb);
 	struct sock *sk;
 	struct hlist_head *head;
 	int delivered = 0;
@@ -184,13 +187,13 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 	net = dev_net(skb->dev);
 	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
 			     iph->saddr, iph->daddr,
-			     skb->dev->ifindex);
+			     skb->dev->ifindex, sdif);
 
 	while (sk) {
 		delivered = 1;
 		if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
 		    ip_mc_sf_allow(sk, iph->daddr, iph->saddr,
-				   skb->dev->ifindex)) {
+				   skb->dev->ifindex, sdif)) {
 			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
 
 			/* Not releasing hash table! */
@@ -199,7 +202,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 		}
 		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
 				     iph->saddr, iph->daddr,
-				     skb->dev->ifindex);
+				     skb->dev->ifindex, sdif);
 	}
 out:
 	read_unlock(&raw_v4_hashinfo.lock);
@@ -297,12 +300,15 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 	read_lock(&raw_v4_hashinfo.lock);
 	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
 	if (raw_sk) {
+		int dif = skb->dev->ifindex;
+		int sdif = inet_sdif(skb);
+
 		iph = (const struct iphdr *)skb->data;
 		net = dev_net(skb->dev);
 
 		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
 						iph->daddr, iph->saddr,
-						skb->dev->ifindex)) != NULL) {
+						dif, sdif)) != NULL) {
 			raw_err(raw_sk, skb, info);
 			raw_sk = sk_next(raw_sk);
 			iph = (const struct iphdr *)skb->data;
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index e1a51ca68d23..c200065ef9a5 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -46,13 +46,13 @@ static struct sock *raw_lookup(struct net *net, struct sock *from,
 		sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
 				     r->id.idiag_dst[0],
 				     r->id.idiag_src[0],
-				     r->id.idiag_if);
+				     r->id.idiag_if, 0);
 #if IS_ENABLED(CONFIG_IPV6)
 	else
 		sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
 				     (const struct in6_addr *)r->id.idiag_src,
 				     (const struct in6_addr *)r->id.idiag_dst,
-				     r->id.idiag_if);
+				     r->id.idiag_if, 0);
 #endif
 	return sk;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0383e66f59bc..43b69af242e1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -495,7 +495,7 @@ u32 ip_idents_reserve(u32 hash, int segs)
 {
 	u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ;
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
-	u32 old = ACCESS_ONCE(*p_tstamp);
+	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
 	u32 new, delta = 0;
 
@@ -651,9 +651,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rt;
+	u32 genid, hval;
 	unsigned int i;
 	int depth;
-	u32 hval = fnhe_hashfun(daddr);
+
+	genid = fnhe_genid(dev_net(nh->nh_dev));
+	hval = fnhe_hashfun(daddr);
 
 	spin_lock_bh(&fnhe_lock);
 
@@ -676,12 +679,13 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	}
 
 	if (fnhe) {
+		if (fnhe->fnhe_genid != genid)
+			fnhe->fnhe_genid = genid;
 		if (gw)
 			fnhe->fnhe_gw = gw;
-		if (pmtu) {
+		if (pmtu)
 			fnhe->fnhe_pmtu = pmtu;
-			fnhe->fnhe_expires = max(1UL, expires);
-		}
+		fnhe->fnhe_expires = max(1UL, expires);
 		/* Update all cached dsts too */
 		rt = rcu_dereference(fnhe->fnhe_rth_input);
 		if (rt)
@@ -700,7 +704,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 			fnhe->fnhe_next = hash->chain;
 			rcu_assign_pointer(hash->chain, fnhe);
 		}
-		fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev));
+		fnhe->fnhe_genid = genid;
 		fnhe->fnhe_daddr = daddr;
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
@@ -1250,7 +1254,7 @@ static void set_class_tag(struct rtable *rt, u32 tag)
 static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 {
 	unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
-	unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size,
+	unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
 				    ip_rt_min_advmss);
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);
@@ -1267,7 +1271,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)
@@ -1398,7 +1402,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *) dst;
 
-	if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
 		kfree(p);
 
 	if (!list_empty(&rt->rt_uncached)) {
@@ -1456,7 +1460,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
 		if (fi->fib_metrics != &dst_default_metrics) {
 			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-			atomic_inc(&fi->fib_metrics->refcnt);
+			refcount_inc(&fi->fib_metrics->refcnt);
 		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
@@ -1520,43 +1524,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
-static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-				u8 tos, struct net_device *dev, int our)
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag)
 {
-	struct rtable *rth;
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	unsigned int flags = RTCF_MULTICAST;
-	u32 itag = 0;
 	int err;
 
 	/* Primary sanity checks. */
-
 	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
 	    skb->protocol != htons(ETH_P_IP))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_zeronet(saddr)) {
 		if (!ipv4_is_local_multicast(daddr))
-			goto e_inval;
+			return -EINVAL;
 	} else {
 		err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
-					  in_dev, &itag);
+					  in_dev, itag);
 		if (err < 0)
-			goto e_err;
+			return err;
 	}
+	return 0;
+}
+
+/* called in rcu_read_lock() section */
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			     u8 tos, struct net_device *dev, int our)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	unsigned int flags = RTCF_MULTICAST;
+	struct rtable *rth;
+	u32 itag = 0;
+	int err;
+
+	err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
+	if (err)
+		return err;
+
 	if (our)
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
 	if (!rth)
-		goto e_nobufs;
+		return -ENOBUFS;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
@@ -1572,13 +1589,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	skb_dst_set(skb, &rth->dst);
 	return 0;
-
-e_nobufs:
-	return -ENOBUFS;
-e_inval:
-	return -EINVAL;
-e_err:
-	return err;
 }
 
 
@@ -2236,7 +2246,7 @@ add:
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
-	rth->rt_iif	= orig_oif ? : 0;
+	rth->rt_iif = orig_oif;
 	if (res->table)
 		rth->rt_table_id = res->table->tb_id;
 
@@ -2439,6 +2449,12 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 		/* L3 master device is the loopback for that domain */
 		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? :
 			net->loopback_dev;
+
+		/* make sure orig_oif points to fib result device even
+		 * though packet rx/tx happens over loopback or l3mdev
+		 */
+		orig_oif = FIB_RES_OIF(*res);
+
 		fl4->flowi4_oif = dev_out->ifindex;
 		flags |= RTCF_LOCAL;
 		goto make_route;
@@ -2501,7 +2517,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 	struct rtable *ort = (struct rtable *) dst_orig;
 	struct rtable *rt;
 
-	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
 
@@ -2750,26 +2766,34 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		err = 0;
 		if (IS_ERR(rt))
 			err = PTR_ERR(rt);
+		else
+			skb_dst_set(skb, &rt->dst);
 	}
 
 	if (err)
 		goto errout_free;
 
-	skb_dst_set(skb, &rt->dst);
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
 		table_id = rt->rt_table_id;
 
-	if (rtm->rtm_flags & RTM_F_FIB_MATCH)
+	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
+		if (!res.fi) {
+			err = fib_props[res.type].error;
+			if (!err)
+				err = -EHOSTUNREACH;
+			goto errout_free;
+		}
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
 				    rt->rt_type, res.prefix, res.prefixlen,
 				    fl4.flowi4_tos, res.fi, 0);
-	else
+	} else {
 		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
 				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
+	}
 	if (err < 0)
 		goto errout_free;
 
@@ -3018,7 +3042,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 
 int __init ip_rt_init(void)
 {
-	int rc = 0;
 	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
@@ -3067,14 +3090,15 @@ int __init ip_rt_init(void)
 	xfrm_init();
 	xfrm4_init();
 #endif
-	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL,
+		      RTNL_FLAG_DOIT_UNLOCKED);
 
 #ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&sysctl_route_ops);
 #endif
 	register_pernet_subsys(&rt_genid_ops);
 	register_pernet_subsys(&ipv4_inetpeer_ops);
-	return rc;
+	return 0;
 }
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 03ad8778c395..fda37f2862c9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
@@ -385,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
 
-	tcp_select_initial_window(tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9bf809726066..93e172118a94 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem.
  *
@@ -25,6 +26,7 @@
 #include <net/inet_frag.h>
 #include <net/ping.h>
 #include <net/protocol.h>
+#include <net/netevent.h>
 
 static int zero;
 static int one = 1;
@@ -45,6 +47,9 @@ 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 };
 
+/* obsolete */
+static int sysctl_tcp_low_latency __read_mostly;
+
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
@@ -196,6 +201,8 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
 				       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct net *net = container_of(ctl->data, struct net,
+				       ipv4.tcp_congestion_control);
 	char val[TCP_CA_NAME_MAX];
 	struct ctl_table tbl = {
 		.data = val,
@@ -203,11 +210,11 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
 	};
 	int ret;
 
-	tcp_get_default_congestion_control(val);
+	tcp_get_default_congestion_control(net, val);
 
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		ret = tcp_set_default_congestion_control(val);
+		ret = tcp_set_default_congestion_control(net, val);
 	return ret;
 }
 
@@ -248,10 +255,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
 	return ret;
 }
 
-static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
 	int ret;
@@ -262,7 +271,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 		return -ENOMEM;
 
 	rcu_read_lock();
-	ctxt = rcu_dereference(tcp_fastopen_ctx);
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
 		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
@@ -279,12 +288,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		/* Generate a dummy secret but don't publish it. This
-		 * is needed so we don't regenerate a new key on the
-		 * first invocation of tcp_fastopen_cookie_gen
-		 */
-		tcp_fastopen_init_key_once(false);
-		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+		tcp_fastopen_reset_cipher(net, NULL, user_key,
+					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
@@ -355,11 +360,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
 					     void __user *buffer,
 					     size_t *lenp, loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen_blackhole_timeout);
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		tcp_fastopen_active_timeout_reset();
+		atomic_set(&net->ipv4.tfo_active_disable_times, 0);
 
 	return ret;
 }
@@ -382,15 +389,25 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 	return ret;
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_fib_multipath_hash_policy);
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net);
+
+	return ret;
+}
+#endif
+
 static struct ctl_table ipv4_table[] = {
 	{
-		.procname	= "tcp_retrans_collapse",
-		.data		= &sysctl_tcp_retrans_collapse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_max_orphans",
 		.data		= &sysctl_tcp_max_orphans,
 		.maxlen		= sizeof(int),
@@ -398,48 +415,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_fastopen",
-		.data		= &sysctl_tcp_fastopen,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_fastopen_key",
-		.mode		= 0600,
-		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
-		.proc_handler	= proc_tcp_fastopen_key,
-	},
-	{
-		.procname	= "tcp_fastopen_blackhole_timeout_sec",
-		.data		= &sysctl_tcp_fastopen_blackhole_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_tfo_blackhole_detect_timeout,
-		.extra1		= &zero,
-	},
-	{
-		.procname	= "tcp_abort_on_overflow",
-		.data		= &sysctl_tcp_abort_on_overflow,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_stdurg",
-		.data		= &sysctl_tcp_stdurg,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_rfc1337",
-		.data		= &sysctl_tcp_rfc1337,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "inet_peer_threshold",
 		.data		= &inet_peer_threshold,
 		.maxlen		= sizeof(int),
@@ -461,34 +436,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
-		.procname	= "tcp_fack",
-		.data		= &sysctl_tcp_fack,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_recovery",
-		.data		= &sysctl_tcp_recovery,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_max_reordering",
-		.data		= &sysctl_tcp_max_reordering,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_dsack",
-		.data		= &sysctl_tcp_dsack,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_mem",
 		.maxlen		= sizeof(sysctl_tcp_mem),
 		.data		= &sysctl_tcp_mem,
@@ -496,113 +443,12 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
-		.procname	= "tcp_wmem",
-		.data		= &sysctl_tcp_wmem,
-		.maxlen		= sizeof(sysctl_tcp_wmem),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
-	{
-		.procname	= "tcp_rmem",
-		.data		= &sysctl_tcp_rmem,
-		.maxlen		= sizeof(sysctl_tcp_rmem),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
-	{
-		.procname	= "tcp_app_win",
-		.data		= &sysctl_tcp_app_win,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_adv_win_scale",
-		.data		= &sysctl_tcp_adv_win_scale,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &tcp_adv_win_scale_min,
-		.extra2		= &tcp_adv_win_scale_max,
-	},
-	{
-		.procname	= "tcp_frto",
-		.data		= &sysctl_tcp_frto,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_min_rtt_wlen",
-		.data		= &sysctl_tcp_min_rtt_wlen,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_low_latency",
 		.data		= &sysctl_tcp_low_latency,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "tcp_no_metrics_save",
-		.data		= &sysctl_tcp_nometrics_save,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_moderate_rcvbuf",
-		.data		= &sysctl_tcp_moderate_rcvbuf,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_tso_win_divisor",
-		.data		= &sysctl_tcp_tso_win_divisor,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_congestion_control",
-		.mode		= 0644,
-		.maxlen		= TCP_CA_NAME_MAX,
-		.proc_handler	= proc_tcp_congestion_control,
-	},
-	{
-		.procname	= "tcp_workaround_signed_windows",
-		.data		= &sysctl_tcp_workaround_signed_windows,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_limit_output_bytes",
-		.data		= &sysctl_tcp_limit_output_bytes,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_challenge_ack_limit",
-		.data		= &sysctl_tcp_challenge_ack_limit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_slow_start_after_idle",
-		.data		= &sysctl_tcp_slow_start_after_idle,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 #ifdef CONFIG_NETLABEL
 	{
 		.procname	= "cipso_cache_enable",
@@ -646,65 +492,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler   = proc_allowed_congestion_control,
 	},
 	{
-		.procname       = "tcp_thin_linear_timeouts",
-		.data           = &sysctl_tcp_thin_linear_timeouts,
-		.maxlen         = sizeof(int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec
-	},
-	{
-		.procname	= "tcp_early_retrans",
-		.data		= &sysctl_tcp_early_retrans,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &four,
-	},
-	{
-		.procname	= "tcp_min_tso_segs",
-		.data		= &sysctl_tcp_min_tso_segs,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-		.extra2		= &gso_max_segs,
-	},
-	{
-		.procname	= "tcp_pacing_ss_ratio",
-		.data		= &sysctl_tcp_pacing_ss_ratio,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &thousand,
-	},
-	{
-		.procname	= "tcp_pacing_ca_ratio",
-		.data		= &sysctl_tcp_pacing_ca_ratio,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &thousand,
-	},
-	{
-		.procname	= "tcp_autocorking",
-		.data		= &sysctl_tcp_autocorking,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
-	{
-		.procname	= "tcp_invalid_ratelimit",
-		.data		= &sysctl_tcp_invalid_ratelimit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
-	},
-	{
 		.procname	= "tcp_available_ulp",
 		.maxlen		= TCP_ULP_BUF_MAX,
 		.mode		= 0444,
@@ -973,6 +760,13 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 #endif
 	{
+		.procname	= "tcp_congestion_control",
+		.data		= &init_net.ipv4.tcp_congestion_control,
+		.mode		= 0644,
+		.maxlen		= TCP_CA_NAME_MAX,
+		.proc_handler	= proc_tcp_congestion_control,
+	},
+	{
 		.procname	= "tcp_keepalive_time",
 		.data		= &init_net.ipv4.sysctl_tcp_keepalive_time,
 		.maxlen		= sizeof(int),
@@ -1082,6 +876,28 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_fastopen",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_fastopen_key",
+		.mode		= 0600,
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+		.proc_handler	= proc_tcp_fastopen_key,
+	},
+	{
+		.procname	= "tcp_fastopen_blackhole_timeout_sec",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_tfo_blackhole_detect_timeout,
+		.extra1		= &zero,
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
@@ -1097,7 +913,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_policy,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_fib_multipath_hash_policy,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
@@ -1141,6 +957,216 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_early_retrans",
+		.data		= &init_net.ipv4.sysctl_tcp_early_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &four,
+	},
+	{
+		.procname	= "tcp_recovery",
+		.data		= &init_net.ipv4.sysctl_tcp_recovery,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname       = "tcp_thin_linear_timeouts",
+		.data           = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec
+	},
+	{
+		.procname	= "tcp_slow_start_after_idle",
+		.data		= &init_net.ipv4.sysctl_tcp_slow_start_after_idle,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_retrans_collapse",
+		.data		= &init_net.ipv4.sysctl_tcp_retrans_collapse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_stdurg",
+		.data		= &init_net.ipv4.sysctl_tcp_stdurg,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_rfc1337",
+		.data		= &init_net.ipv4.sysctl_tcp_rfc1337,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_abort_on_overflow",
+		.data		= &init_net.ipv4.sysctl_tcp_abort_on_overflow,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_fack",
+		.data		= &init_net.ipv4.sysctl_tcp_fack,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_max_reordering",
+		.data		= &init_net.ipv4.sysctl_tcp_max_reordering,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_dsack",
+		.data		= &init_net.ipv4.sysctl_tcp_dsack,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_app_win",
+		.data		= &init_net.ipv4.sysctl_tcp_app_win,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_adv_win_scale",
+		.data		= &init_net.ipv4.sysctl_tcp_adv_win_scale,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_adv_win_scale_min,
+		.extra2		= &tcp_adv_win_scale_max,
+	},
+	{
+		.procname	= "tcp_frto",
+		.data		= &init_net.ipv4.sysctl_tcp_frto,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_no_metrics_save",
+		.data		= &init_net.ipv4.sysctl_tcp_nometrics_save,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_moderate_rcvbuf",
+		.data		= &init_net.ipv4.sysctl_tcp_moderate_rcvbuf,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_tso_win_divisor",
+		.data		= &init_net.ipv4.sysctl_tcp_tso_win_divisor,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_workaround_signed_windows",
+		.data		= &init_net.ipv4.sysctl_tcp_workaround_signed_windows,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_limit_output_bytes",
+		.data		= &init_net.ipv4.sysctl_tcp_limit_output_bytes,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_challenge_ack_limit",
+		.data		= &init_net.ipv4.sysctl_tcp_challenge_ack_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_min_tso_segs",
+		.data		= &init_net.ipv4.sysctl_tcp_min_tso_segs,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &gso_max_segs,
+	},
+	{
+		.procname	= "tcp_min_rtt_wlen",
+		.data		= &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_autocorking",
+		.data		= &init_net.ipv4.sysctl_tcp_autocorking,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	= "tcp_invalid_ratelimit",
+		.data		= &init_net.ipv4.sysctl_tcp_invalid_ratelimit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+	},
+	{
+		.procname	= "tcp_pacing_ss_ratio",
+		.data		= &init_net.ipv4.sysctl_tcp_pacing_ss_ratio,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &thousand,
+	},
+	{
+		.procname	= "tcp_pacing_ca_ratio",
+		.data		= &init_net.ipv4.sysctl_tcp_pacing_ca_ratio,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &thousand,
+	},
+	{
+		.procname	= "tcp_wmem",
+		.data		= &init_net.ipv4.sysctl_tcp_wmem,
+		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_wmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+	},
+	{
+		.procname	= "tcp_rmem",
+		.data		= &init_net.ipv4.sysctl_tcp_rmem,
+		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_rmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 71ce33decd97..bf97317e6c97 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -269,6 +269,8 @@
 #include <linux/err.h>
 #include <linux/time.h>
 #include <linux/slab.h>
+#include <linux/errqueue.h>
+#include <linux/static_key.h>
 
 #include <net/icmp.h>
 #include <net/inet_common.h>
@@ -281,24 +283,22 @@
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
 
-int sysctl_tcp_min_tso_segs __read_mostly = 2;
-
-int sysctl_tcp_autocorking __read_mostly = 1;
+#include <trace/events/tcp.h>
 
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
 long sysctl_tcp_mem[3] __read_mostly;
-int sysctl_tcp_wmem[3] __read_mostly;
-int sysctl_tcp_rmem[3] __read_mostly;
-
 EXPORT_SYMBOL(sysctl_tcp_mem);
-EXPORT_SYMBOL(sysctl_tcp_rmem);
-EXPORT_SYMBOL(sysctl_tcp_wmem);
 
 atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */
 EXPORT_SYMBOL(tcp_memory_allocated);
 
+#if IS_ENABLED(CONFIG_SMC)
+DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
+EXPORT_SYMBOL(tcp_have_smc);
+#endif
+
 /*
  * Current number of TCP sockets.
  */
@@ -388,6 +388,19 @@ static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
 	return period;
 }
 
+static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp)
+{
+	u32 rate = READ_ONCE(tp->rate_delivered);
+	u32 intv = READ_ONCE(tp->rate_interval_us);
+	u64 rate64 = 0;
+
+	if (rate && intv) {
+		rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
+		do_div(rate64, intv);
+	}
+	return rate64;
+}
+
 /* Address-family independent initialization for a tcp_sock.
  *
  * NOTE: A lot of things set to zero explicitly by call to
@@ -399,9 +412,10 @@ void tcp_init_sock(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->out_of_order_queue = RB_ROOT;
+	sk->tcp_rtx_queue = RB_ROOT;
 	tcp_init_xmit_timers(sk);
-	tcp_prequeue_init(tp);
 	INIT_LIST_HEAD(&tp->tsq_node);
+	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -428,6 +442,7 @@ void tcp_init_sock(struct sock *sk)
 	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
+	tp->rack.reo_wnd_steps = 1;
 
 	sk->sk_state = TCP_CLOSE;
 
@@ -436,15 +451,29 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	sk->sk_sndbuf = sysctl_tcp_wmem[1];
-	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
+	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
 
 	sk_sockets_allocated_inc(sk);
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
-static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
+void tcp_init_transfer(struct sock *sk, int bpf_op)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	tcp_mtup_init(sk);
+	icsk->icsk_af_ops->rebuild_header(sk);
+	tcp_init_metrics(sk);
+	tcp_call_bpf(sk, bpf_op);
+	tcp_init_congestion_control(sk);
+	tcp_init_buffer_space(sk);
+}
+
+static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
+{
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+
 	if (tsflags && skb) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -662,7 +691,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sysctl_tcp_autocorking &&
+	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
 	       skb != tcp_write_queue_head(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
@@ -673,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 
-	if (!tcp_send_head(sk))
-		return;
-
 	skb = tcp_write_queue_tail(sk);
+	if (!skb)
+		return;
 	if (!(flags & MSG_MORE) || forced_push(tp))
 		tcp_mark_push(tp, skb);
 
@@ -856,6 +884,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 			 * available to the caller, no more, no less.
 			 */
 			skb->reserved_tailroom = skb->end - skb->tail - size;
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -935,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		int copy, i;
 		bool can_coalesce;
 
-		if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 ||
+		if (!skb || (copy = size_goal - skb->len) <= 0 ||
 		    !tcp_skb_can_collapse_to(skb)) {
 new_segment:
 			if (!sk_stream_memory_free(sk))
 				goto wait_for_sndbuf;
 
 			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
-						  skb_queue_empty(&sk->sk_write_queue));
+					tcp_rtx_and_write_queues_empty(sk));
 			if (!skb)
 				goto wait_for_memory;
 
@@ -1014,7 +1043,7 @@ wait_for_memory:
 
 out:
 	if (copied) {
-		tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk));
+		tcp_tx_timestamp(sk, sk->sk_tsflags);
 		if (!(flags & MSG_SENDPAGE_NOTLAST))
 			tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
@@ -1034,23 +1063,29 @@ out_err:
 }
 EXPORT_SYMBOL_GPL(do_tcp_sendpages);
 
-int tcp_sendpage(struct sock *sk, struct page *page, int offset,
-		 size_t size, int flags)
+int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
+			size_t size, int flags)
 {
-	ssize_t res;
-
 	if (!(sk->sk_route_caps & NETIF_F_SG) ||
 	    !sk_check_csum_caps(sk))
-		return sock_no_sendpage(sk->sk_socket, page, offset, size,
-					flags);
-
-	lock_sock(sk);
+		return sock_no_sendpage_locked(sk, page, offset, size, flags);
 
 	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
 
-	res = do_tcp_sendpages(sk, page, offset, size, flags);
+	return do_tcp_sendpages(sk, page, offset, size, flags);
+}
+EXPORT_SYMBOL_GPL(tcp_sendpage_locked);
+
+int tcp_sendpage(struct sock *sk, struct page *page, int offset,
+		 size_t size, int flags)
+{
+	int ret;
+
+	lock_sock(sk);
+	ret = tcp_sendpage_locked(sk, page, offset, size, flags);
 	release_sock(sk);
-	return res;
+
+	return ret;
 }
 EXPORT_SYMBOL(tcp_sendpage);
 
@@ -1107,7 +1142,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
 	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
 	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
@@ -1144,9 +1179,10 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	return err;
 }
 
-int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
 	struct sockcm_cookie sockc;
 	int flags, err, copied = 0;
@@ -1155,9 +1191,25 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	bool sg;
 	long timeo;
 
-	lock_sock(sk);
-
 	flags = msg->msg_flags;
+
+	if (flags & MSG_ZEROCOPY && size) {
+		if (sk->sk_state != TCP_ESTABLISHED) {
+			err = -EINVAL;
+			goto out_err;
+		}
+
+		skb = tcp_write_queue_tail(sk);
+		uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
+		if (!uarg) {
+			err = -ENOBUFS;
+			goto out_err;
+		}
+
+		if (!(sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG))
+			uarg->zerocopy = 0;
+	}
+
 	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
@@ -1223,7 +1275,7 @@ restart:
 		int max = size_goal;
 
 		skb = tcp_write_queue_tail(sk);
-		if (tcp_send_head(sk)) {
+		if (skb) {
 			if (skb->ip_summed == CHECKSUM_NONE)
 				max = mss_now;
 			copy = max - skb->len;
@@ -1243,7 +1295,7 @@ new_segment:
 				process_backlog = false;
 				goto restart;
 			}
-			first_skb = skb_queue_empty(&sk->sk_write_queue);
+			first_skb = tcp_rtx_and_write_queues_empty(sk);
 			skb = sk_stream_alloc_skb(sk,
 						  select_size(sk, sg, first_skb),
 						  sk->sk_allocation,
@@ -1281,7 +1333,7 @@ new_segment:
 			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
 			if (err)
 				goto do_fault;
-		} else {
+		} else if (!uarg || !uarg->zerocopy) {
 			bool merge = true;
 			int i = skb_shinfo(skb)->nr_frags;
 			struct page_frag *pfrag = sk_page_frag(sk);
@@ -1319,6 +1371,13 @@ new_segment:
 				page_ref_inc(pfrag->page);
 			}
 			pfrag->offset += copy;
+		} else {
+			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
+			if (err == -EMSGSIZE || err == -EEXIST)
+				goto new_segment;
+			if (err < 0)
+				goto do_error;
+			copy = err;
 		}
 
 		if (!copied)
@@ -1361,11 +1420,11 @@ wait_for_memory:
 
 out:
 	if (copied) {
-		tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk));
+		tcp_tx_timestamp(sk, sockc.tsflags);
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
 out_nopush:
-	release_sock(sk);
+	sock_zerocopy_put(uarg);
 	return copied + copied_syn;
 
 do_fault:
@@ -1382,6 +1441,7 @@ do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
+	sock_zerocopy_put_abort(uarg);
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
@@ -1389,9 +1449,20 @@ out_err:
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);
+
+int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	int ret;
+
+	lock_sock(sk);
+	ret = tcp_sendmsg_locked(sk, msg, size);
+	release_sock(sk);
+
+	return ret;
+}
 EXPORT_SYMBOL(tcp_sendmsg);
 
 /*
@@ -1450,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 
 	/* XXX -- need to support SO_PEEK_OFF */
 
+	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
+		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
+		if (err)
+			return err;
+		copied += skb->len;
+	}
+
 	skb_queue_walk(&sk->sk_write_queue, skb) {
 		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
@@ -1525,20 +1603,6 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-static void tcp_prequeue_process(struct sock *sk)
-{
-	struct sk_buff *skb;
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUED);
-
-	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-		sk_backlog_rcv(sk, skb);
-
-	/* Clear memory counter. */
-	tp->ucopy.memory = 0;
-}
-
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1652,6 +1716,61 @@ int tcp_peek_len(struct socket *sock)
 }
 EXPORT_SYMBOL(tcp_peek_len);
 
+static void tcp_update_recv_tstamps(struct sk_buff *skb,
+				    struct scm_timestamping *tss)
+{
+	if (skb->tstamp)
+		tss->ts[0] = ktime_to_timespec(skb->tstamp);
+	else
+		tss->ts[0] = (struct timespec) {0};
+
+	if (skb_hwtstamps(skb)->hwtstamp)
+		tss->ts[2] = ktime_to_timespec(skb_hwtstamps(skb)->hwtstamp);
+	else
+		tss->ts[2] = (struct timespec) {0};
+}
+
+/* Similar to __sock_recv_timestamp, but does not require an skb */
+void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+			struct scm_timestamping *tss)
+{
+	struct timeval tv;
+	bool has_timestamping = false;
+
+	if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
+		if (sock_flag(sk, SOCK_RCVTSTAMP)) {
+			if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
+				put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS,
+					 sizeof(tss->ts[0]), &tss->ts[0]);
+			} else {
+				tv.tv_sec = tss->ts[0].tv_sec;
+				tv.tv_usec = tss->ts[0].tv_nsec / 1000;
+
+				put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP,
+					 sizeof(tv), &tv);
+			}
+		}
+
+		if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE)
+			has_timestamping = true;
+		else
+			tss->ts[0] = (struct timespec) {0};
+	}
+
+	if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
+		if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)
+			has_timestamping = true;
+		else
+			tss->ts[2] = (struct timespec) {0};
+	}
+
+	if (has_timestamping) {
+		tss->ts[1] = (struct timespec) {0};
+		put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING,
+			 sizeof(*tss), tss);
+	}
+}
+
 /*
  *	This routine copies from a sock struct into the user buffer.
  *
@@ -1671,9 +1790,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	int err;
 	int target;		/* Read at least this many bytes */
 	long timeo;
-	struct task_struct *user_recv = NULL;
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
+	struct scm_timestamping tss;
+	bool has_tss = false;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -1806,51 +1926,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 
 		tcp_cleanup_rbuf(sk, copied);
 
-		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
-			/* Install new reader */
-			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
-				user_recv = current;
-				tp->ucopy.task = user_recv;
-				tp->ucopy.msg = msg;
-			}
-
-			tp->ucopy.len = len;
-
-			WARN_ON(tp->copied_seq != tp->rcv_nxt &&
-				!(flags & (MSG_PEEK | MSG_TRUNC)));
-
-			/* Ugly... If prequeue is not empty, we have to
-			 * process it before releasing socket, otherwise
-			 * order will be broken at second iteration.
-			 * More elegant solution is required!!!
-			 *
-			 * Look: we have the following (pseudo)queues:
-			 *
-			 * 1. packets in flight
-			 * 2. backlog
-			 * 3. prequeue
-			 * 4. receive_queue
-			 *
-			 * Each queue can be processed only if the next ones
-			 * are empty. At this point we have empty receive_queue.
-			 * But prequeue _can_ be not empty after 2nd iteration,
-			 * when we jumped to start of loop because backlog
-			 * processing added something to receive_queue.
-			 * We cannot release_sock(), because backlog contains
-			 * packets arrived _after_ prequeued ones.
-			 *
-			 * Shortly, algorithm is clear --- to process all
-			 * the queues in order. We could make it more directly,
-			 * requeueing packets from backlog to prequeue, if
-			 * is not empty. It is more elegant, but eats cycles,
-			 * unfortunately.
-			 */
-			if (!skb_queue_empty(&tp->ucopy.prequeue))
-				goto do_prequeue;
-
-			/* __ Set realtime policy in scheduler __ */
-		}
-
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1859,31 +1934,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			sk_wait_data(sk, &timeo, last);
 		}
 
-		if (user_recv) {
-			int chunk;
-
-			/* __ Restore normal policy in scheduler __ */
-
-			chunk = len - tp->ucopy.len;
-			if (chunk != 0) {
-				NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
-				len -= chunk;
-				copied += chunk;
-			}
-
-			if (tp->rcv_nxt == tp->copied_seq &&
-			    !skb_queue_empty(&tp->ucopy.prequeue)) {
-do_prequeue:
-				tcp_prequeue_process(sk);
-
-				chunk = len - tp->ucopy.len;
-				if (chunk != 0) {
-					NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
-					len -= chunk;
-					copied += chunk;
-				}
-			}
-		}
 		if ((flags & MSG_PEEK) &&
 		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
 			net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
@@ -1941,6 +1991,10 @@ skip_copy:
 		if (used + offset < skb->len)
 			continue;
 
+		if (TCP_SKB_CB(skb)->has_rxtstamp) {
+			tcp_update_recv_tstamps(skb, &tss);
+			has_tss = true;
+		}
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
@@ -1955,29 +2009,13 @@ skip_copy:
 		break;
 	} while (len > 0);
 
-	if (user_recv) {
-		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
-			int chunk;
-
-			tp->ucopy.len = copied > 0 ? len : 0;
-
-			tcp_prequeue_process(sk);
-
-			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
-				NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
-				len -= chunk;
-				copied += chunk;
-			}
-		}
-
-		tp->ucopy.task = NULL;
-		tp->ucopy.len = 0;
-	}
-
 	/* According to UNIX98, msg_name/msg_namelen are ignored
 	 * on connected socket. I was just happy when found this 8) --ANK
 	 */
 
+	if (has_tss)
+		tcp_recv_timestamp(msg, sk, &tss);
+
 	/* Clean up data we have read: This will do ACK frames. */
 	tcp_cleanup_rbuf(sk, copied);
 
@@ -2002,6 +2040,8 @@ void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
+	trace_tcp_set_state(sk, oldstate, state);
+
 	switch (state) {
 	case TCP_ESTABLISHED:
 		if (oldstate != TCP_ESTABLISHED)
@@ -2289,6 +2329,37 @@ static inline bool tcp_need_reset(int state)
 		TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
 }
 
+static void tcp_rtx_queue_purge(struct sock *sk)
+{
+	struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+		/* Since we are deleting whole queue, no need to
+		 * list_del(&skb->tcp_tsorted_anchor)
+		 */
+		tcp_rtx_queue_unlink(skb, sk);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
+void tcp_write_queue_purge(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+		tcp_skb_tsorted_anchor_cleanup(skb);
+		sk_wmem_free_skb(sk, skb);
+	}
+	tcp_rtx_queue_purge(sk);
+	INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
+	sk_mem_reclaim(sk);
+	tcp_clear_all_retrans_hints(tcp_sk(sk));
+}
+
 int tcp_disconnect(struct sock *sk, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -2347,7 +2418,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	 * issue in __tcp_select_window()
 	 */
 	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
-	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
 	dst_release(sk->sk_rx_dst);
@@ -2439,8 +2509,6 @@ static int tcp_repair_options_est(struct sock *sk,
 				return -EINVAL;
 
 			tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
-			if (sysctl_tcp_fack)
-				tcp_enable_fack(tp);
 			break;
 		case TCPOPT_TIMESTAMP:
 			if (opt.opt_val != 0)
@@ -2481,7 +2549,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true);
+		err = tcp_set_congestion_control(sk, name, true, true);
 		release_sock(sk);
 		return err;
 	}
@@ -2503,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		release_sock(sk);
 		return err;
 	}
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+		if (optlen != sizeof(key))
+			return -EINVAL;
+
+		if (copy_from_user(key, optval, optlen))
+			return -EFAULT;
+
+		return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key));
+	}
 	default:
 		/* fallthru */
 		break;
@@ -2734,7 +2813,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
 		    TCPF_LISTEN))) {
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once(net);
 
 			fastopen_queue_tune(sk, val);
 		} else {
@@ -2744,7 +2823,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN_CONNECT:
 		if (val > 1 || val < 0) {
 			err = -EINVAL;
-		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+		} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
 			if (sk->sk_state == TCP_CLOSE)
 				tp->fastopen_connect = val;
 			else
@@ -2753,6 +2832,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EOPNOTSUPP;
 		}
 		break;
+	case TCP_FASTOPEN_NO_COOKIE:
+		if (val > 1 || val < 0)
+			err = -EINVAL;
+		else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+			err = -EINVAL;
+		else
+			tp->fastopen_no_cookie = val;
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -2823,7 +2910,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 now, intv;
+	u32 now;
 	u64 rate64;
 	bool slow;
 	u32 rate;
@@ -2890,7 +2977,6 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_lost = tp->lost_out;
 	info->tcpi_retrans = tp->retrans_out;
-	info->tcpi_fackets = tp->fackets_out;
 
 	now = tcp_jiffies32;
 	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
@@ -2922,13 +3008,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_data_segs_out = tp->data_segs_out;
 
 	info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0;
-	rate = READ_ONCE(tp->rate_delivered);
-	intv = READ_ONCE(tp->rate_interval_us);
-	if (rate && intv) {
-		rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
-		do_div(rate64, intv);
+	rate64 = tcp_compute_delivery_rate(tp);
+	if (rate64)
 		info->tcpi_delivery_rate = rate64;
-	}
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -2938,8 +3020,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *stats;
 	struct tcp_info info;
+	u64 rate64;
+	u32 rate;
 
-	stats = alloc_skb(5 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC);
+	stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
+			  3 * nla_total_size(sizeof(u32)) +
+			  2 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
 	if (!stats)
 		return NULL;
 
@@ -2954,6 +3040,20 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 			  tp->data_segs_out, TCP_NLA_PAD);
 	nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS,
 			  tp->total_retrans, TCP_NLA_PAD);
+
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD);
+
+	rate64 = tcp_compute_delivery_rate(tp);
+	nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD);
+
+	nla_put_u32(stats, TCP_NLA_SND_CWND, tp->snd_cwnd);
+	nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);
+	nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));
+
+	nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits);
+	nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);
 	return stats;
 }
 
@@ -3075,6 +3175,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		return 0;
 
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+		struct tcp_fastopen_context *ctx;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		rcu_read_lock();
+		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+		if (ctx)
+			memcpy(key, ctx->key, sizeof(key));
+		else
+			len = 0;
+		rcu_read_unlock();
+
+		len = min_t(unsigned int, len, sizeof(key));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, key, len))
+			return -EFAULT;
+		return 0;
+	}
 	case TCP_THIN_LINEAR_TIMEOUTS:
 		val = tp->thin_lto;
 		break;
@@ -3137,6 +3259,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->fastopen_connect;
 		break;
 
+	case TCP_FASTOPEN_NO_COOKIE:
+		val = tp->fastopen_no_cookie;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp_raw() + tp->tsoffset;
 		break;
@@ -3502,13 +3628,13 @@ void __init tcp_init(void)
 	max_wshare = min(4UL*1024*1024, limit);
 	max_rshare = min(6UL*1024*1024, limit);
 
-	sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
-	sysctl_tcp_wmem[1] = 16*1024;
-	sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
+	init_net.ipv4.sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
+	init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024;
+	init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
 
-	sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
-	sysctl_tcp_rmem[1] = 87380;
-	sysctl_tcp_rmem[2] = max(87380, max_rshare);
+	init_net.ipv4.sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
+	init_net.ipv4.sysctl_tcp_rmem[1] = 87380;
+	init_net.ipv4.sysctl_tcp_rmem[2] = max(87380, max_rshare);
 
 	pr_info("Hash tables configured (established %u bind %u)\n",
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 609965f0e298..fc3614377413 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -49,7 +49,6 @@ MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wma
 struct bictcp {
 	u32	cnt;		/* increase cwnd by 1 after ACKs */
 	u32	last_max_cwnd;	/* last maximum snd_cwnd */
-	u32	loss_cwnd;	/* congestion window at last loss */
 	u32	last_cwnd;	/* the last snd_cwnd */
 	u32	last_time;	/* time when updated last_cwnd */
 	u32	epoch_start;	/* beginning of an epoch */
@@ -72,7 +71,6 @@ static void bictcp_init(struct sock *sk)
 	struct bictcp *ca = inet_csk_ca(sk);
 
 	bictcp_reset(ca);
-	ca->loss_cwnd = 0;
 
 	if (initial_ssthresh)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
@@ -172,22 +170,12 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk)
 	else
 		ca->last_max_cwnd = tp->snd_cwnd;
 
-	ca->loss_cwnd = tp->snd_cwnd;
-
 	if (tp->snd_cwnd <= low_window)
 		return max(tp->snd_cwnd >> 1U, 2U);
 	else
 		return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-static u32 bictcp_undo_cwnd(struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	const struct bictcp *ca = inet_csk_ca(sk);
-
-	return max(tp->snd_cwnd, ca->loss_cwnd);
-}
-
 static void bictcp_state(struct sock *sk, u8 new_state)
 {
 	if (new_state == TCP_CA_Loss)
@@ -214,7 +202,7 @@ static struct tcp_congestion_ops bictcp __read_mostly = {
 	.ssthresh	= bictcp_recalc_ssthresh,
 	.cong_avoid	= bictcp_cong_avoid,
 	.set_state	= bictcp_state,
-	.undo_cwnd	= bictcp_undo_cwnd,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.pkts_acked     = bictcp_acked,
 	.owner		= THIS_MODULE,
 	.name		= "bic",
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 50a0f3e51d5b..06fbe102a425 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -85,7 +85,6 @@ struct cdg {
 	u8  state;
 	u8  delack;
 	u32 rtt_seq;
-	u32 undo_cwnd;
 	u32 shadow_wnd;
 	u16 backoff_cnt;
 	u16 sample_cnt;
@@ -330,8 +329,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk)
 	struct cdg *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	ca->undo_cwnd = tp->snd_cwnd;
-
 	if (ca->state == CDG_BACKOFF)
 		return max(2U, (tp->snd_cwnd * min(1024U, backoff_beta)) >> 10);
 
@@ -344,13 +341,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk)
 	return max(2U, tp->snd_cwnd >> 1);
 }
 
-static u32 tcp_cdg_undo_cwnd(struct sock *sk)
-{
-	struct cdg *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->undo_cwnd);
-}
-
 static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev)
 {
 	struct cdg *ca = inet_csk_ca(sk);
@@ -399,11 +389,11 @@ static void tcp_cdg_release(struct sock *sk)
 	kfree(ca->gradients);
 }
 
-struct tcp_congestion_ops tcp_cdg __read_mostly = {
+static struct tcp_congestion_ops tcp_cdg __read_mostly = {
 	.cong_avoid = tcp_cdg_cong_avoid,
 	.cwnd_event = tcp_cdg_cwnd_event,
 	.pkts_acked = tcp_cdg_acked,
-	.undo_cwnd = tcp_cdg_undo_cwnd,
+	.undo_cwnd = tcp_reno_undo_cwnd,
 	.ssthresh = tcp_cdg_ssthresh,
 	.release = tcp_cdg_release,
 	.init = tcp_cdg_init,
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index fde983f6376b..bc6c02f16243 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -33,9 +33,11 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name)
 }
 
 /* Must be called with rcu lock held */
-static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name)
+static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
+						       const char *name)
 {
-	const struct tcp_congestion_ops *ca = tcp_ca_find(name);
+	struct tcp_congestion_ops *ca = tcp_ca_find(name);
+
 #ifdef CONFIG_MODULES
 	if (!ca && capable(CAP_NET_ADMIN)) {
 		rcu_read_unlock();
@@ -115,7 +117,7 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
 }
 EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
 
-u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
+u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
 {
 	const struct tcp_congestion_ops *ca;
 	u32 key = TCP_CA_UNSPEC;
@@ -123,7 +125,7 @@ u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
 	might_sleep();
 
 	rcu_read_lock();
-	ca = __tcp_ca_find_autoload(name);
+	ca = tcp_ca_find_autoload(net, name);
 	if (ca) {
 		key = ca->key;
 		*ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN;
@@ -153,23 +155,18 @@ EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
 /* Assign choice of congestion control. */
 void tcp_assign_congestion_control(struct sock *sk)
 {
+	struct net *net = sock_net(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_congestion_ops *ca;
+	const struct tcp_congestion_ops *ca;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
-		if (likely(try_module_get(ca->owner))) {
-			icsk->icsk_ca_ops = ca;
-			goto out;
-		}
-		/* Fallback to next available. The last really
-		 * guaranteed fallback is Reno from this list.
-		 */
-	}
-out:
+	ca = rcu_dereference(net->ipv4.tcp_congestion_control);
+	if (unlikely(!try_module_get(ca->owner)))
+		ca = &tcp_reno;
+	icsk->icsk_ca_ops = ca;
 	rcu_read_unlock();
-	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else
@@ -189,8 +186,8 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_dontxmit(sk);
 }
 
-void tcp_reinit_congestion_control(struct sock *sk,
-				   const struct tcp_congestion_ops *ca)
+static void tcp_reinit_congestion_control(struct sock *sk,
+					  const struct tcp_congestion_ops *ca)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -214,29 +211,27 @@ void tcp_cleanup_congestion_control(struct sock *sk)
 }
 
 /* Used by sysctl to change default congestion control */
-int tcp_set_default_congestion_control(const char *name)
+int tcp_set_default_congestion_control(struct net *net, const char *name)
 {
 	struct tcp_congestion_ops *ca;
-	int ret = -ENOENT;
-
-	spin_lock(&tcp_cong_list_lock);
-	ca = tcp_ca_find(name);
-#ifdef CONFIG_MODULES
-	if (!ca && capable(CAP_NET_ADMIN)) {
-		spin_unlock(&tcp_cong_list_lock);
+	const struct tcp_congestion_ops *prev;
+	int ret;
 
-		request_module("tcp_%s", name);
-		spin_lock(&tcp_cong_list_lock);
-		ca = tcp_ca_find(name);
-	}
-#endif
+	rcu_read_lock();
+	ca = tcp_ca_find_autoload(net, name);
+	if (!ca) {
+		ret = -ENOENT;
+	} else if (!try_module_get(ca->owner)) {
+		ret = -EBUSY;
+	} else {
+		prev = xchg(&net->ipv4.tcp_congestion_control, ca);
+		if (prev)
+			module_put(prev->owner);
 
-	if (ca) {
-		ca->flags |= TCP_CONG_NON_RESTRICTED;	/* default is always allowed */
-		list_move(&ca->list, &tcp_cong_list);
+		ca->flags |= TCP_CONG_NON_RESTRICTED;
 		ret = 0;
 	}
-	spin_unlock(&tcp_cong_list_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -244,7 +239,8 @@ int tcp_set_default_congestion_control(const char *name)
 /* Set default value from kernel configuration at bootup */
 static int __init tcp_congestion_default(void)
 {
-	return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
+	return tcp_set_default_congestion_control(&init_net,
+						  CONFIG_DEFAULT_TCP_CONG);
 }
 late_initcall(tcp_congestion_default);
 
@@ -264,14 +260,12 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen)
 }
 
 /* Get current default congestion control */
-void tcp_get_default_congestion_control(char *name)
+void tcp_get_default_congestion_control(struct net *net, char *name)
 {
-	struct tcp_congestion_ops *ca;
-	/* We will always have reno... */
-	BUG_ON(list_empty(&tcp_cong_list));
+	const struct tcp_congestion_ops *ca;
 
 	rcu_read_lock();
-	ca = list_entry(tcp_cong_list.next, struct tcp_congestion_ops, list);
+	ca = rcu_dereference(net->ipv4.tcp_congestion_control);
 	strncpy(name, ca->name, TCP_CA_NAME_MAX);
 	rcu_read_unlock();
 }
@@ -338,7 +332,7 @@ out:
  * tcp_reinit_congestion_control (if the current congestion control was
  * already initialized.
  */
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -351,18 +345,29 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
 	if (!load)
 		ca = tcp_ca_find(name);
 	else
-		ca = __tcp_ca_find_autoload(name);
+		ca = tcp_ca_find_autoload(sock_net(sk), name);
+
 	/* No change asking for existing value */
 	if (ca == icsk->icsk_ca_ops) {
 		icsk->icsk_ca_setsockopt = 1;
 		goto out;
 	}
+
 	if (!ca) {
 		err = -ENOENT;
 	} else if (!load) {
-		icsk->icsk_ca_ops = ca;
-		if (!try_module_get(ca->owner))
+		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
+
+		if (try_module_get(ca->owner)) {
+			if (reinit) {
+				tcp_reinit_congestion_control(sk, ca);
+			} else {
+				icsk->icsk_ca_ops = ca;
+				module_put(old_ca->owner);
+			}
+		} else {
 			err = -EBUSY;
+		}
 	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
 		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
 		err = -EPERM;
@@ -456,7 +461,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
-	return max(tp->snd_cwnd, tp->snd_ssthresh << 1);
+	return max(tp->snd_cwnd, tp->prior_cwnd);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 57ae5b5ae643..78bfadfcf342 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -83,7 +83,6 @@ MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (mse
 struct bictcp {
 	u32	cnt;		/* increase cwnd by 1 after ACKs */
 	u32	last_max_cwnd;	/* last maximum snd_cwnd */
-	u32	loss_cwnd;	/* congestion window at last loss */
 	u32	last_cwnd;	/* the last snd_cwnd */
 	u32	last_time;	/* time when updated last_cwnd */
 	u32	bic_origin_point;/* origin point of bic function */
@@ -142,7 +141,6 @@ static void bictcp_init(struct sock *sk)
 	struct bictcp *ca = inet_csk_ca(sk);
 
 	bictcp_reset(ca);
-	ca->loss_cwnd = 0;
 
 	if (hystart)
 		bictcp_hystart_reset(sk);
@@ -366,18 +364,9 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk)
 	else
 		ca->last_max_cwnd = tp->snd_cwnd;
 
-	ca->loss_cwnd = tp->snd_cwnd;
-
 	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-static u32 bictcp_undo_cwnd(struct sock *sk)
-{
-	struct bictcp *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
 static void bictcp_state(struct sock *sk, u8 new_state)
 {
 	if (new_state == TCP_CA_Loss) {
@@ -470,7 +459,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
 	.ssthresh	= bictcp_recalc_ssthresh,
 	.cong_avoid	= bictcp_cong_avoid,
 	.set_state	= bictcp_state,
-	.undo_cwnd	= bictcp_undo_cwnd,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.cwnd_event	= bictcp_cwnd_event,
 	.pkts_acked     = bictcp_acked,
 	.owner		= THIS_MODULE,
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index a748c74aa8b7..abbf0edcf6c2 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -16,6 +16,7 @@
 
 #include <linux/tcp.h>
 
+#include <net/netlink.h>
 #include <net/tcp.h>
 
 static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
@@ -36,6 +37,100 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		tcp_get_info(sk, info);
 }
 
+#ifdef CONFIG_TCP_MD5SIG
+static void tcp_diag_md5sig_fill(struct tcp_diag_md5sig *info,
+				 const struct tcp_md5sig_key *key)
+{
+	info->tcpm_family = key->family;
+	info->tcpm_prefixlen = key->prefixlen;
+	info->tcpm_keylen = key->keylen;
+	memcpy(info->tcpm_key, key->key, key->keylen);
+
+	if (key->family == AF_INET)
+		info->tcpm_addr[0] = key->addr.a4.s_addr;
+	#if IS_ENABLED(CONFIG_IPV6)
+	else if (key->family == AF_INET6)
+		memcpy(&info->tcpm_addr, &key->addr.a6,
+		       sizeof(info->tcpm_addr));
+	#endif
+}
+
+static int tcp_diag_put_md5sig(struct sk_buff *skb,
+			       const struct tcp_md5sig_info *md5sig)
+{
+	const struct tcp_md5sig_key *key;
+	struct tcp_diag_md5sig *info;
+	struct nlattr *attr;
+	int md5sig_count = 0;
+
+	hlist_for_each_entry_rcu(key, &md5sig->head, node)
+		md5sig_count++;
+	if (md5sig_count == 0)
+		return 0;
+
+	attr = nla_reserve(skb, INET_DIAG_MD5SIG,
+			   md5sig_count * sizeof(struct tcp_diag_md5sig));
+	if (!attr)
+		return -EMSGSIZE;
+
+	info = nla_data(attr);
+	memset(info, 0, md5sig_count * sizeof(struct tcp_diag_md5sig));
+	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
+		tcp_diag_md5sig_fill(info++, key);
+		if (--md5sig_count == 0)
+			break;
+	}
+
+	return 0;
+}
+#endif
+
+static int tcp_diag_get_aux(struct sock *sk, bool net_admin,
+			    struct sk_buff *skb)
+{
+#ifdef CONFIG_TCP_MD5SIG
+	if (net_admin) {
+		struct tcp_md5sig_info *md5sig;
+		int err = 0;
+
+		rcu_read_lock();
+		md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info);
+		if (md5sig)
+			err = tcp_diag_put_md5sig(skb, md5sig);
+		rcu_read_unlock();
+		if (err < 0)
+			return err;
+	}
+#endif
+
+	return 0;
+}
+
+static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
+{
+	size_t size = 0;
+
+#ifdef CONFIG_TCP_MD5SIG
+	if (net_admin && sk_fullsock(sk)) {
+		const struct tcp_md5sig_info *md5sig;
+		const struct tcp_md5sig_key *key;
+		size_t md5sig_count = 0;
+
+		rcu_read_lock();
+		md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info);
+		if (md5sig) {
+			hlist_for_each_entry_rcu(key, &md5sig->head, node)
+				md5sig_count++;
+		}
+		rcu_read_unlock();
+		size += nla_total_size(md5sig_count *
+				       sizeof(struct tcp_diag_md5sig));
+	}
+#endif
+
+	return size;
+}
+
 static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			  const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
@@ -68,13 +163,15 @@ static int tcp_diag_destroy(struct sk_buff *in_skb,
 #endif
 
 static const struct inet_diag_handler tcp_diag_handler = {
-	.dump		 = tcp_diag_dump,
-	.dump_one	 = tcp_diag_dump_one,
-	.idiag_get_info	 = tcp_diag_get_info,
-	.idiag_type	 = IPPROTO_TCP,
-	.idiag_info_size = sizeof(struct tcp_info),
+	.dump			= tcp_diag_dump,
+	.dump_one		= tcp_diag_dump_one,
+	.idiag_get_info		= tcp_diag_get_info,
+	.idiag_get_aux		= tcp_diag_get_aux,
+	.idiag_get_aux_size	= tcp_diag_get_aux_size,
+	.idiag_type		= IPPROTO_TCP,
+	.idiag_info_size	= sizeof(struct tcp_info),
 #ifdef CONFIG_INET_DIAG_DESTROY
-	.destroy	 = tcp_diag_destroy,
+	.destroy		= tcp_diag_destroy,
 #endif
 };
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index ce9c7fef200f..78c192ee03a4 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -9,15 +10,18 @@
 #include <net/inetpeer.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
-
-struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-
-static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
-
-void tcp_fastopen_init_key_once(bool publish)
+void tcp_fastopen_init_key_once(struct net *net)
 {
-	static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	struct tcp_fastopen_context *ctxt;
+
+	rcu_read_lock();
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+	if (ctxt) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
 
 	/* tcp_fastopen_reset_cipher publishes the new context
 	 * atomically, so we allow this race happening here.
@@ -25,8 +29,8 @@ void tcp_fastopen_init_key_once(bool publish)
 	 * All call sites of tcp_fastopen_cookie_gen also check
 	 * for a valid cookie, so this is an acceptable risk.
 	 */
-	if (net_get_random_once(key, sizeof(key)) && publish)
-		tcp_fastopen_reset_cipher(key, sizeof(key));
+	get_random_bytes(key, sizeof(key));
+	tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
 }
 
 static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -37,10 +41,37 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
 	kfree(ctx);
 }
 
-int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+void tcp_fastopen_destroy_cipher(struct sock *sk)
+{
+	struct tcp_fastopen_context *ctx;
+
+	ctx = rcu_dereference_protected(
+			inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1);
+	if (ctx)
+		call_rcu(&ctx->rcu, tcp_fastopen_ctx_free);
+}
+
+void tcp_fastopen_ctx_destroy(struct net *net)
+{
+	struct tcp_fastopen_context *ctxt;
+
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	if (ctxt)
+		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
+}
+
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+			      void *key, unsigned int len)
 {
-	int err;
 	struct tcp_fastopen_context *ctx, *octx;
+	struct fastopen_queue *q;
+	int err;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -61,26 +92,37 @@ error:		kfree(ctx);
 	}
 	memcpy(ctx->key, key, len);
 
-	spin_lock(&tcp_fastopen_ctx_lock);
 
-	octx = rcu_dereference_protected(tcp_fastopen_ctx,
-				lockdep_is_held(&tcp_fastopen_ctx_lock));
-	rcu_assign_pointer(tcp_fastopen_ctx, ctx);
-	spin_unlock(&tcp_fastopen_ctx_lock);
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+	if (sk) {
+		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+		octx = rcu_dereference_protected(q->ctx,
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+		rcu_assign_pointer(q->ctx, ctx);
+	} else {
+		octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+		rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+	}
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
 
 	if (octx)
 		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
 	return err;
 }
 
-static bool __tcp_fastopen_cookie_gen(const void *path,
+static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
 				      struct tcp_fastopen_cookie *foc)
 {
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
 	rcu_read_lock();
-	ctx = rcu_dereference(tcp_fastopen_ctx);
+
+	ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
+	if (!ctx)
+		ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
+
 	if (ctx) {
 		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -96,7 +138,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
  *
  * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
  */
-static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+static bool tcp_fastopen_cookie_gen(struct sock *sk,
+				    struct request_sock *req,
 				    struct sk_buff *syn,
 				    struct tcp_fastopen_cookie *foc)
 {
@@ -104,7 +147,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct iphdr *iph = ip_hdr(syn);
 
 		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
-		return __tcp_fastopen_cookie_gen(path, foc);
+		return __tcp_fastopen_cookie_gen(sk, path, foc);
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -112,13 +155,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
 		struct tcp_fastopen_cookie tmp;
 
-		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+		if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
 			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
 				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
-			return __tcp_fastopen_cookie_gen(buf, foc);
+			return __tcp_fastopen_cookie_gen(sk, buf, foc);
 		}
 	}
 #endif
@@ -171,7 +214,6 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
 
 static struct sock *tcp_fastopen_create_child(struct sock *sk,
 					      struct sk_buff *skb,
-					      struct dst_entry *dst,
 					      struct request_sock *req)
 {
 	struct tcp_sock *tp;
@@ -217,12 +259,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	refcount_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	inet_csk(child)->icsk_af_ops->rebuild_header(child);
-	tcp_init_congestion_control(child);
-	tcp_mtup_init(child);
-	tcp_init_metrics(child);
-	tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-	tcp_init_buffer_space(child);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
@@ -272,6 +309,15 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	return true;
 }
 
+static bool tcp_fastopen_no_cookie(const struct sock *sk,
+				   const struct dst_entry *dst,
+				   int flag)
+{
+	return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+	       tcp_sk(sk)->fastopen_no_cookie ||
+	       (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
+}
+
 /* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
  * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
  * cookie request (foc->len == 0).
@@ -279,27 +325,29 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      struct dst_entry *dst)
+			      const struct dst_entry *dst)
 {
-	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	struct sock *child;
 
 	if (foc->len == 0) /* Client requests a cookie */
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
 
-	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
 	      (syn_data || foc->len >= 0) &&
 	      tcp_fastopen_queue_check(sk))) {
 		foc->len = -1;
 		return NULL;
 	}
 
-	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+	if (syn_data &&
+	    tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
-	    tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
 	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
 	    foc->len == valid_foc.len &&
 	    !memcmp(foc->val, valid_foc.val, foc->len)) {
@@ -312,7 +360,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 		 * data in SYN_RECV state.
 		 */
 fastopen:
-		child = tcp_fastopen_create_child(sk, skb, dst, req);
+		child = tcp_fastopen_create_child(sk, skb, req);
 		if (child) {
 			foc->len = -1;
 			NET_INC_STATS(sock_net(sk),
@@ -332,6 +380,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			       struct tcp_fastopen_cookie *cookie)
 {
 	unsigned long last_syn_loss = 0;
+	const struct dst_entry *dst;
 	int syn_loss = 0;
 
 	tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);
@@ -349,7 +398,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		return false;
 	}
 
-	if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+	dst = __sk_dst_get(sk);
+
+	if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) {
 		cookie->len = -1;
 		return true;
 	}
@@ -403,25 +454,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect);
  * TFO connection with data exchanges.
  */
 
-/* Default to 1hr */
-unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
-static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
-static unsigned long tfo_active_disable_stamp __read_mostly;
-
 /* Disable active TFO and record current jiffies and
  * tfo_active_disable_times
  */
 void tcp_fastopen_active_disable(struct sock *sk)
 {
-	atomic_inc(&tfo_active_disable_times);
-	tfo_active_disable_stamp = jiffies;
-	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
-}
+	struct net *net = sock_net(sk);
 
-/* Reset tfo_active_disable_times to 0 */
-void tcp_fastopen_active_timeout_reset(void)
-{
-	atomic_set(&tfo_active_disable_times, 0);
+	atomic_inc(&net->ipv4.tfo_active_disable_times);
+	net->ipv4.tfo_active_disable_stamp = jiffies;
+	NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
 }
 
 /* Calculate timeout for tfo active disable
@@ -430,17 +472,18 @@ void tcp_fastopen_active_timeout_reset(void)
  */
 bool tcp_fastopen_active_should_disable(struct sock *sk)
 {
-	int tfo_da_times = atomic_read(&tfo_active_disable_times);
-	int multiplier;
+	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+	int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
 	unsigned long timeout;
+	int multiplier;
 
 	if (!tfo_da_times)
 		return false;
 
 	/* Limit timout to max: 2^6 * initial timeout */
 	multiplier = 1 << min(tfo_da_times - 1, 6);
-	timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
-	if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+	timeout = multiplier * tfo_bh_timeout * HZ;
+	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
 		return true;
 
 	/* Mark check bit so we can check for successful active TFO
@@ -459,27 +502,25 @@ bool tcp_fastopen_active_should_disable(struct sock *sk)
 void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node *p;
-	struct sk_buff *skb;
 	struct dst_entry *dst;
+	struct sk_buff *skb;
 
 	if (!tp->syn_fastopen)
 		return;
 
 	if (!tp->data_segs_in) {
-		p = rb_first(&tp->out_of_order_queue);
-		if (p && !rb_next(p)) {
-			skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = skb_rb_first(&tp->out_of_order_queue);
+		if (skb && !skb_rb_next(skb)) {
 			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
 				tcp_fastopen_active_disable(sk);
 				return;
 			}
 		}
 	} else if (tp->syn_fastopen_ch &&
-		   atomic_read(&tfo_active_disable_times)) {
+		   atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
 		dst = sk_dst_get(sk);
 		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
-			tcp_fastopen_active_timeout_reset();
+			atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
 		dst_release(dst);
 	}
 }
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 6d9879e93648..d1c33c91eadc 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -94,7 +94,6 @@ static const struct hstcp_aimd_val {
 
 struct hstcp {
 	u32	ai;
-	u32	loss_cwnd;
 };
 
 static void hstcp_init(struct sock *sk)
@@ -153,22 +152,14 @@ static u32 hstcp_ssthresh(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct hstcp *ca = inet_csk_ca(sk);
 
-	ca->loss_cwnd = tp->snd_cwnd;
 	/* Do multiplicative decrease */
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * hstcp_aimd_vals[ca->ai].md) >> 8), 2U);
 }
 
-static u32 hstcp_cwnd_undo(struct sock *sk)
-{
-	const struct hstcp *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
 static struct tcp_congestion_ops tcp_highspeed __read_mostly = {
 	.init		= hstcp_init,
 	.ssthresh	= hstcp_ssthresh,
-	.undo_cwnd	= hstcp_cwnd_undo,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.cong_avoid	= hstcp_cong_avoid,
 
 	.owner		= THIS_MODULE,
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 3eb78cde6ff0..082d479462fa 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -66,7 +66,6 @@ static inline void htcp_reset(struct htcp *ca)
 
 static u32 htcp_cwnd_undo(struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
 	struct htcp *ca = inet_csk_ca(sk);
 
 	if (ca->undo_last_cong) {
@@ -76,7 +75,7 @@ static u32 htcp_cwnd_undo(struct sock *sk)
 		ca->undo_last_cong = 0;
 	}
 
-	return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta);
+	return tcp_reno_undo_cwnd(sk);
 }
 
 static inline void measure_rtt(struct sock *sk, u32 srtt)
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 60352ff4f5a8..7c843578f233 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -48,7 +48,6 @@ struct illinois {
 	u32	end_seq;	/* right edge of current RTT */
 	u32	alpha;		/* Additive increase */
 	u32	beta;		/* Muliplicative decrease */
-	u32	loss_cwnd;	/* cwnd on loss */
 	u16	acked;		/* # packets acked by current ACK */
 	u8	rtt_above;	/* average rtt has gone above threshold */
 	u8	rtt_low;	/* # of rtts measurements below threshold */
@@ -297,18 +296,10 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct illinois *ca = inet_csk_ca(sk);
 
-	ca->loss_cwnd = tp->snd_cwnd;
 	/* Multiplicative decrease */
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->beta) >> BETA_SHIFT), 2U);
 }
 
-static u32 tcp_illinois_cwnd_undo(struct sock *sk)
-{
-	const struct illinois *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
 /* Extract info for Tcp socket info provided via netlink. */
 static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
 				union tcp_cc_info *info)
@@ -336,7 +327,7 @@ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
 static struct tcp_congestion_ops tcp_illinois __read_mostly = {
 	.init		= tcp_illinois_init,
 	.ssthresh	= tcp_illinois_ssthresh,
-	.undo_cwnd	= tcp_illinois_cwnd_undo,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.cong_avoid	= tcp_illinois_cong_avoid,
 	.set_state	= tcp_illinois_state,
 	.get_info	= tcp_illinois_info,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2920e0cb09f8..734cfc8ff76e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -75,25 +76,10 @@
 #include <linux/ipsec.h>
 #include <asm/unaligned.h>
 #include <linux/errqueue.h>
+#include <trace/events/tcp.h>
+#include <linux/static_key.h>
 
-int sysctl_tcp_fack __read_mostly;
-int sysctl_tcp_max_reordering __read_mostly = 300;
-int sysctl_tcp_dsack __read_mostly = 1;
-int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-
-/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 1000;
-
-int sysctl_tcp_stdurg __read_mostly;
-int sysctl_tcp_rfc1337 __read_mostly;
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly = 2;
-int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
-int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 3;
-int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
@@ -107,13 +93,14 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 #define FLAG_ORIG_SACK_ACKED	0x200 /* Never retransmitted data are (s)acked	*/
 #define FLAG_SND_UNA_ADVANCED	0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
 #define FLAG_DSACKING_ACK	0x800 /* SACK blocks contained D-SACK info */
+#define FLAG_SET_XMIT_TIMER	0x1000 /* Set TLP or RTO timer */
 #define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
 #define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 #define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
-#define FLAG_CA_ALERT		(FLAG_DATA_SACKED|FLAG_ECE)
+#define FLAG_CA_ALERT		(FLAG_DATA_SACKED|FLAG_ECE|FLAG_DSACKING_ACK)
 #define FLAG_FORWARD_PROGRESS	(FLAG_ACKED|FLAG_DATA_SACKED)
 
 #define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
@@ -333,7 +320,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
-		sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
+		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -366,8 +353,8 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
-	int truesize = tcp_win_from_space(skb->truesize) >> 1;
-	int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1;
+	int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
+	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {
 		if (truesize <= skb->len)
@@ -392,7 +379,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 		/* Check #2. Increase window, if skb with such overhead
 		 * will fit to rcvbuf in future.
 		 */
-		if (tcp_win_from_space(skb->truesize) <= skb->len)
+		if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
 			incr = 2 * tp->advmss;
 		else
 			incr = __tcp_grow_window(sk, skb);
@@ -418,11 +405,11 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
 	/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
 	 * Allow enough cushion so that sender is not limited by our window
 	 */
-	if (sysctl_tcp_moderate_rcvbuf)
+	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
 		rcvmem <<= 2;
 
 	if (sk->sk_rcvbuf < rcvmem)
-		sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
+		sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 }
 
 /* 4. Try to fixup all. It is made immediately after connection enters
@@ -430,6 +417,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
  */
 void tcp_init_buffer_space(struct sock *sk)
 {
+	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
@@ -448,14 +436,14 @@ void tcp_init_buffer_space(struct sock *sk)
 	if (tp->window_clamp >= maxwin) {
 		tp->window_clamp = maxwin;
 
-		if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
+		if (tcp_app_win && maxwin > 4 * tp->advmss)
 			tp->window_clamp = max(maxwin -
-					       (maxwin >> sysctl_tcp_app_win),
+					       (maxwin >> tcp_app_win),
 					       4 * tp->advmss);
 	}
 
 	/* Force reservation of one segment. */
-	if (sysctl_tcp_app_win &&
+	if (tcp_app_win &&
 	    tp->window_clamp > 2 * tp->advmss &&
 	    tp->window_clamp + tp->advmss > maxwin)
 		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
@@ -469,15 +457,16 @@ static void tcp_clamp_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct net *net = sock_net(sk);
 
 	icsk->icsk_ack.quick = 0;
 
-	if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
+	if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
-				    sysctl_tcp_rmem[2]);
+				    net->ipv4.sysctl_tcp_rmem[2]);
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -608,7 +597,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (sysctl_tcp_moderate_rcvbuf &&
+	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvwin, rcvmem, rcvbuf;
 
@@ -632,10 +621,11 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		}
 
 		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
-		while (tcp_win_from_space(rcvmem) < tp->advmss)
+		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
 			rcvmem += 128;
 
-		rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
+		rcvbuf = min(rcvwin / tp->advmss * rcvmem,
+			     sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
 			sk->sk_rcvbuf = rcvbuf;
 
@@ -779,15 +769,6 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 	tp->srtt_us = max(1U, srtt);
 }
 
-/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
- * Note: TCP stack does not yet implement pacing.
- * FQ packet scheduler can be used to implement cheap but effective
- * TCP pacing, to smooth the burst on large writes when packets
- * in flight is significantly lower than cwnd (or rwin)
- */
-int sysctl_tcp_pacing_ss_ratio __read_mostly = 200;
-int sysctl_tcp_pacing_ca_ratio __read_mostly = 120;
-
 static void tcp_update_pacing_rate(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -805,21 +786,21 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	 *	 end of slow start and should slow down.
 	 */
 	if (tp->snd_cwnd < tp->snd_ssthresh / 2)
-		rate *= sysctl_tcp_pacing_ss_ratio;
+		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
 	else
-		rate *= sysctl_tcp_pacing_ca_ratio;
+		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
 
 	rate *= max(tp->snd_cwnd, tp->packets_out);
 
 	if (likely(tp->srtt_us))
 		do_div(rate, tp->srtt_us);
 
-	/* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate
+	/* WRITE_ONCE() is needed because sch_fq fetches sk_pacing_rate
 	 * without any lock. We want to make sure compiler wont store
 	 * intermediate values in this location.
 	 */
-	ACCESS_ONCE(sk->sk_pacing_rate) = min_t(u64, rate,
-						sk->sk_max_pacing_rate);
+	WRITE_ONCE(sk->sk_pacing_rate, min_t(u64, rate,
+					     sk->sk_max_pacing_rate));
 }
 
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
@@ -861,60 +842,46 @@ __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
 	return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
 }
 
-/*
- * Packet counting of FACK is based on in-order assumptions, therefore TCP
- * disables it when reordering is detected
- */
-void tcp_disable_fack(struct tcp_sock *tp)
-{
-	/* RFC3517 uses different metric in lost marker => reset on change */
-	if (tcp_is_fack(tp))
-		tp->lost_skb_hint = NULL;
-	tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED;
-}
-
 /* Take a notice that peer is sending D-SACKs */
 static void tcp_dsack_seen(struct tcp_sock *tp)
 {
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
+	tp->rack.dsack_seen = 1;
 }
 
-static void tcp_update_reordering(struct sock *sk, const int metric,
-				  const int ts)
+/* It's reordering when higher sequence was delivered (i.e. sacked) before
+ * some lower never-retransmitted sequence ("low_seq"). The maximum reordering
+ * distance is approximated in full-mss packet distance ("reordering").
+ */
+static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
+				      const int ts)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int mib_idx;
+	const u32 mss = tp->mss_cache;
+	u32 fack, metric;
 
-	if (WARN_ON_ONCE(metric < 0))
+	fack = tcp_highest_sack_seq(tp);
+	if (!before(low_seq, fack))
 		return;
 
-	if (metric > tp->reordering) {
-		tp->reordering = min(sysctl_tcp_max_reordering, metric);
-
+	metric = fack - low_seq;
+	if ((metric > tp->reordering * mss) && mss) {
 #if FASTRETRANS_DEBUG > 1
 		pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
 			 tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
 			 tp->reordering,
-			 tp->fackets_out,
+			 0,
 			 tp->sacked_out,
 			 tp->undo_marker ? tp->undo_retrans : 0);
 #endif
-		tcp_disable_fack(tp);
+		tp->reordering = min_t(u32, (metric + mss - 1) / mss,
+				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
 	}
 
 	tp->rack.reord = 1;
-
 	/* This exciting event is worth to be remembered. 8) */
-	if (ts)
-		mib_idx = LINUX_MIB_TCPTSREORDER;
-	else if (tcp_is_reno(tp))
-		mib_idx = LINUX_MIB_TCPRENOREORDER;
-	else if (tcp_is_fack(tp))
-		mib_idx = LINUX_MIB_TCPFACKREORDER;
-	else
-		mib_idx = LINUX_MIB_TCPSACKREORDER;
-
-	NET_INC_STATS(sock_net(sk), mib_idx);
+	NET_INC_STATS(sock_net(sk),
+		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
 
 /* This must be called before lost_out is incremented */
@@ -988,7 +955,6 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
  * 3. Loss detection event of two flavors:
  *	A. Scoreboard estimator decided the packet is lost.
  *	   A'. Reno "three dupacks" marks head of queue lost.
- *	   A''. Its FACK modification, head until snd.fack is lost.
  *	B. SACK arrives sacking SND.NXT at the moment, when the
  *	   segment was retransmitted.
  * 4. D-SACK added new rule: D-SACK changes any tag to S.
@@ -1131,8 +1097,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 }
 
 struct tcp_sacktag_state {
-	int	reord;
-	int	fack_count;
+	u32	reord;
 	/* Timestamps for earliest and latest never-retransmitted segment
 	 * that was SACKed. RTO needs the earliest RTT to stay conservative,
 	 * but congestion control should still get an accurate delay signal.
@@ -1141,6 +1106,7 @@ struct tcp_sacktag_state {
 	u64	last_sackt;
 	struct rate_sample *rate;
 	int	flag;
+	unsigned int mss_now;
 };
 
 /* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1190,7 +1156,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 		if (pkt_len >= skb->len && !in_sack)
 			return 0;
 
-		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
+		err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+				   pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
 	}
@@ -1206,15 +1173,15 @@ static u8 tcp_sacktag_one(struct sock *sk,
 			  u64 xmit_time)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int fack_count = state->fack_count;
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
 		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
-		if (sacked & TCPCB_SACKED_ACKED)
-			state->reord = min(fack_count, state->reord);
+		if ((sacked & TCPCB_SACKED_ACKED) &&
+		    before(start_seq, state->reord))
+				state->reord = start_seq;
 	}
 
 	/* Nothing to do; acked frame is about to be dropped (was ACKed). */
@@ -1240,9 +1207,10 @@ static u8 tcp_sacktag_one(struct sock *sk,
 				 * which was in hole. It is reordering.
 				 */
 				if (before(start_seq,
-					   tcp_highest_sack_seq(tp)))
-					state->reord = min(fack_count,
-							   state->reord);
+					   tcp_highest_sack_seq(tp)) &&
+				    before(start_seq, state->reord))
+					state->reord = start_seq;
+
 				if (!after(end_seq, tp->high_seq))
 					state->flag |= FLAG_ORIG_SACK_ACKED;
 				if (state->first_sackt == 0)
@@ -1261,15 +1229,10 @@ static u8 tcp_sacktag_one(struct sock *sk,
 		tp->sacked_out += pcount;
 		tp->delivered += pcount;  /* Out-of-order packets delivered */
 
-		fack_count += pcount;
-
 		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
-		if (!tcp_is_fack(tp) && tp->lost_skb_hint &&
+		if (tp->lost_skb_hint &&
 		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
 			tp->lost_cnt_hint += pcount;
-
-		if (fack_count > tp->fackets_out)
-			tp->fackets_out = fack_count;
 	}
 
 	/* D-SACK. We can detect redundant retransmission in S|R and plain R
@@ -1287,13 +1250,13 @@ static u8 tcp_sacktag_one(struct sock *sk,
 /* Shift newly-SACKed bytes from this skb to the immediately previous
  * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
  */
-static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
+static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
+			    struct sk_buff *skb,
 			    struct tcp_sacktag_state *state,
 			    unsigned int pcount, int shifted, int mss,
 			    bool dup_sack)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
 	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
 	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */
 
@@ -1362,8 +1325,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp))
 		TCP_SKB_CB(prev)->tx.delivered_mstamp = 0;
 
-	tcp_unlink_write_queue(skb, sk);
-	sk_wmem_free_skb(sk, skb);
+	tcp_rtx_queue_unlink_and_free(skb, sk);
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED);
 
@@ -1413,9 +1375,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		goto fallback;
 
 	/* Can only happen with delayed DSACK + discard craziness */
-	if (unlikely(skb == tcp_write_queue_head(sk)))
+	prev = skb_rb_prev(skb);
+	if (!prev)
 		goto fallback;
-	prev = tcp_write_queue_prev(sk, skb);
 
 	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
 		goto fallback;
@@ -1494,18 +1456,17 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
-	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
+	if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
 		goto out;
 
 	/* Hole filled allows collapsing with the next as well, this is very
 	 * useful when hole on every nth skb pattern happens
 	 */
-	if (prev == tcp_write_queue_tail(sk))
+	skb = skb_rb_next(prev);
+	if (!skb)
 		goto out;
-	skb = tcp_write_queue_next(sk, prev);
 
 	if (!skb_can_shift(skb) ||
-	    (skb == tcp_send_head(sk)) ||
 	    ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
 	    (mss != tcp_skb_seglen(skb)))
 		goto out;
@@ -1513,11 +1474,11 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	len = skb->len;
 	if (skb_shift(prev, skb, len)) {
 		pcount += tcp_skb_pcount(skb);
-		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+		tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+				len, mss, 0);
 	}
 
 out:
-	state->fack_count += pcount;
 	return prev;
 
 noop:
@@ -1537,13 +1498,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *tmp;
 
-	tcp_for_write_queue_from(skb, sk) {
+	skb_rbtree_walk_from(skb) {
 		int in_sack = 0;
 		bool dup_sack = dup_sack_in;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
 		/* queue is in-order => we can short-circuit the walk early */
 		if (!before(TCP_SKB_CB(skb)->seq, end_seq))
 			break;
@@ -1592,34 +1550,48 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						tcp_skb_pcount(skb),
 						skb->skb_mstamp);
 			tcp_rate_skb_delivered(sk, skb, state->rate);
+			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+				list_del_init(&skb->tcp_tsorted_anchor);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
 				tcp_advance_highest_sack(sk, skb);
 		}
-
-		state->fack_count += tcp_skb_pcount(skb);
 	}
 	return skb;
 }
 
-/* Avoid all extra work that is being done by sacktag while walking in
- * a normal way
- */
+static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk,
+					   struct tcp_sacktag_state *state,
+					   u32 seq)
+{
+	struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node;
+	struct sk_buff *skb;
+
+	while (*p) {
+		parent = *p;
+		skb = rb_to_skb(parent);
+		if (before(seq, TCP_SKB_CB(skb)->seq)) {
+			p = &parent->rb_left;
+			continue;
+		}
+		if (!before(seq, TCP_SKB_CB(skb)->end_seq)) {
+			p = &parent->rb_right;
+			continue;
+		}
+		return skb;
+	}
+	return NULL;
+}
+
 static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
 					struct tcp_sacktag_state *state,
 					u32 skip_to_seq)
 {
-	tcp_for_write_queue_from(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
-
-		if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
-			break;
+	if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq))
+		return skb;
 
-		state->fack_count += tcp_skb_pcount(skb);
-	}
-	return skb;
+	return tcp_sacktag_bsearch(sk, state, skip_to_seq);
 }
 
 static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
@@ -1664,13 +1636,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 	int first_sack_index;
 
 	state->flag = 0;
-	state->reord = tp->packets_out;
+	state->reord = tp->snd_nxt;
 
-	if (!tp->sacked_out) {
-		if (WARN_ON(tp->fackets_out))
-			tp->fackets_out = 0;
+	if (!tp->sacked_out)
 		tcp_highest_sack_reset(sk);
-	}
 
 	found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
 					 num_sacks, prior_snd_una);
@@ -1741,8 +1710,8 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 	}
 
-	skb = tcp_write_queue_head(sk);
-	state->fack_count = 0;
+	state->mss_now = tcp_current_mss(sk);
+	skb = NULL;
 	i = 0;
 
 	if (!tp->sacked_out) {
@@ -1799,7 +1768,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 				skb = tcp_highest_sack(sk);
 				if (!skb)
 					break;
-				state->fack_count = tp->fackets_out;
 				cache++;
 				goto walk;
 			}
@@ -1814,7 +1782,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 			skb = tcp_highest_sack(sk);
 			if (!skb)
 				break;
-			state->fack_count = tp->fackets_out;
 		}
 		skb = tcp_sacktag_skip(skb, sk, state, start_seq);
 
@@ -1834,9 +1801,8 @@ advance_sp:
 	for (j = 0; j < used_sacks; j++)
 		tp->recv_sack_cache[i++] = sp[j];
 
-	if ((state->reord < tp->fackets_out) &&
-	    ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
-		tcp_update_reordering(sk, tp->fackets_out - state->reord, 0);
+	if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss || tp->undo_marker)
+		tcp_check_sack_reordering(sk, state->reord, 0);
 
 	tcp_verify_left_out(tp);
 out:
@@ -1874,8 +1840,13 @@ static bool tcp_limit_reno_sacked(struct tcp_sock *tp)
 static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	if (tcp_limit_reno_sacked(tp))
-		tcp_update_reordering(sk, tp->packets_out + addend, 0);
+
+	if (!tcp_limit_reno_sacked(tp))
+		return;
+
+	tp->reordering = min_t(u32, tp->packets_out + addend,
+			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
 
 /* Emulate SACKs for SACKless connection: account for a new dupack. */
@@ -1921,7 +1892,6 @@ void tcp_clear_retrans(struct tcp_sock *tp)
 	tp->lost_out = 0;
 	tp->undo_marker = 0;
 	tp->undo_retrans = -1;
-	tp->fackets_out = 0;
 	tp->sacked_out = 0;
 }
 
@@ -1951,6 +1921,7 @@ void tcp_enter_loss(struct sock *sk)
 	    !after(tp->high_seq, tp->snd_una) ||
 	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
+		tp->prior_cwnd = tp->snd_cwnd;
 		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
 		tcp_ca_event(sk, CA_EVENT_LOSS);
 		tcp_init_undo(tp);
@@ -1965,19 +1936,15 @@ void tcp_enter_loss(struct sock *sk)
 	if (tcp_is_reno(tp))
 		tcp_reset_reno_sack(tp);
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
 	if (is_reneg) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
 		tp->sacked_out = 0;
-		tp->fackets_out = 0;
 	}
 	tcp_clear_all_retrans_hints(tp);
 
-	tcp_for_write_queue(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
-
+	skb_rbtree_walk_from(skb) {
 		mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
 			     is_reneg);
 		if (mark_lost)
@@ -2011,7 +1978,7 @@ void tcp_enter_loss(struct sock *sk)
 	 * falsely raise the receive window, which results in repeated
 	 * timeouts and stop-and-go behavior.
 	 */
-	tp->frto = sysctl_tcp_frto &&
+	tp->frto = net->ipv4.sysctl_tcp_frto &&
 		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
@@ -2040,19 +2007,10 @@ static bool tcp_check_sack_reneging(struct sock *sk, int flag)
 	return false;
 }
 
-static inline int tcp_fackets_out(const struct tcp_sock *tp)
-{
-	return tcp_is_reno(tp) ? tp->sacked_out + 1 : tp->fackets_out;
-}
-
 /* Heurestics to calculate number of duplicate ACKs. There's no dupACKs
  * counter when SACK is enabled (without SACK, sacked_out is used for
  * that purpose).
  *
- * Instead, with FACK TCP uses fackets_out that includes both SACKed
- * segments up to the highest received SACK block so far and holes in
- * between them.
- *
  * With reordering, holes may still be in flight, so RFC3517 recovery
  * uses pure sacked_out (total number of SACKed segments) even though
  * it violates the RFC that uses duplicate ACKs, often these are equal
@@ -2062,10 +2020,10 @@ static inline int tcp_fackets_out(const struct tcp_sock *tp)
  */
 static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
 {
-	return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
+	return tp->sacked_out + 1;
 }
 
-/* Linux NewReno/SACK/FACK/ECN state machine.
+/* Linux NewReno/SACK/ECN state machine.
  * --------------------------------------
  *
  * "Open"	Normal state, no dubious events, fast path.
@@ -2130,16 +2088,6 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
  *		dynamically measured and adjusted. This is implemented in
  *		tcp_rack_mark_lost.
  *
- *		FACK (Disabled by default. Subsumbed by RACK):
- *		It is the simplest heuristics. As soon as we decided
- *		that something is lost, we decide that _all_ not SACKed
- *		packets until the most forward SACK are lost. I.e.
- *		lost_out = fackets_out - sacked_out and left_out = fackets_out.
- *		It is absolutely correct estimate, if network does not reorder
- *		packets. And it loses any connection to reality when reordering
- *		takes place. We use FACK by default until reordering
- *		is suspected on the path to this destination.
- *
  *		If the receiver does not support SACK:
  *
  *		NewReno (RFC6582): in Recovery we assume that one segment
@@ -2188,7 +2136,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 }
 
 /* Detect loss in event "A" above by marking head of queue up as lost.
- * For FACK or non-SACK(Reno) senders, the first "packets" number of segments
+ * For non-SACK(Reno) senders, the first "packets" number of segments
  * are considered lost. For RFC3517 SACK, a segment is considered lost if it
  * has at least tp->reordering SACKed seqments above it; "packets" refers to
  * the maximum SACKed segments to pass before reaching this limit.
@@ -2203,20 +2151,18 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;
 
 	WARN_ON(packets > tp->packets_out);
-	if (tp->lost_skb_hint) {
-		skb = tp->lost_skb_hint;
-		cnt = tp->lost_cnt_hint;
+	skb = tp->lost_skb_hint;
+	if (skb) {
 		/* Head already handled? */
-		if (mark_head && skb != tcp_write_queue_head(sk))
+		if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una))
 			return;
+		cnt = tp->lost_cnt_hint;
 	} else {
-		skb = tcp_write_queue_head(sk);
+		skb = tcp_rtx_queue_head(sk);
 		cnt = 0;
 	}
 
-	tcp_for_write_queue_from(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
+	skb_rbtree_walk_from(skb) {
 		/* TODO: do this better */
 		/* this is not the most efficient way to do this... */
 		tp->lost_skb_hint = skb;
@@ -2226,12 +2172,12 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 			break;
 
 		oldcnt = cnt;
-		if (tcp_is_fack(tp) || tcp_is_reno(tp) ||
+		if (tcp_is_reno(tp) ||
 		    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 			cnt += tcp_skb_pcount(skb);
 
 		if (cnt > packets) {
-			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+			if (tcp_is_sack(tp) ||
 			    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
 			    (oldcnt >= packets))
 				break;
@@ -2240,7 +2186,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 			/* If needed, chop off the prefix to mark as lost. */
 			lost = (packets - oldcnt) * mss;
 			if (lost < skb->len &&
-			    tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
+			    tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+					 lost, mss, GFP_ATOMIC) < 0)
 				break;
 			cnt = packets;
 		}
@@ -2261,11 +2208,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
 
 	if (tcp_is_reno(tp)) {
 		tcp_mark_head_lost(sk, 1, 1);
-	} else if (tcp_is_fack(tp)) {
-		int lost = tp->fackets_out - tp->reordering;
-		if (lost <= 0)
-			lost = 1;
-		tcp_mark_head_lost(sk, lost, 0);
 	} else {
 		int sacked_upto = tp->sacked_out - tp->reordering;
 		if (sacked_upto >= 0)
@@ -2324,16 +2266,16 @@ static bool tcp_any_retrans_done(const struct sock *sk)
 	if (tp->retrans_out)
 		return true;
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
 		return true;
 
 	return false;
 }
 
-#if FASTRETRANS_DEBUG > 1
 static void DBGUNDO(struct sock *sk, const char *msg)
 {
+#if FASTRETRANS_DEBUG > 1
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 
@@ -2355,10 +2297,8 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 			 tp->packets_out);
 	}
 #endif
-}
-#else
-#define DBGUNDO(x...) do { } while (0)
 #endif
+}
 
 static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 {
@@ -2367,9 +2307,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 	if (unmark_loss) {
 		struct sk_buff *skb;
 
-		tcp_for_write_queue(skb, sk) {
-			if (skb == tcp_send_head(sk))
-				break;
+		skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
 		}
 		tp->lost_out = 0;
@@ -2414,6 +2352,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 			mib_idx = LINUX_MIB_TCPFULLUNDO;
 
 		NET_INC_STATS(sock_net(sk), mib_idx);
+	} else if (tp->rack.reo_wnd_persist) {
+		tp->rack.reo_wnd_persist--;
 	}
 	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
 		/* Hold old state until something *above* high_seq
@@ -2433,6 +2373,8 @@ static bool tcp_try_undo_dsack(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (tp->undo_marker && !tp->undo_retrans) {
+		tp->rack.reo_wnd_persist = min(TCP_RACK_RECOVERY_THRESH,
+					       tp->rack.reo_wnd_persist + 1);
 		DBGUNDO(sk, "D-SACK");
 		tcp_undo_cwnd_reduction(sk, false);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
@@ -2520,8 +2462,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk)
 		return;
 
 	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
-	    (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
+	if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+	    (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
 		tp->snd_cwnd = tp->snd_ssthresh;
 		tp->snd_cwnd_stamp = tcp_jiffies32;
 	}
@@ -2612,11 +2554,8 @@ void tcp_simple_retransmit(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	unsigned int mss = tcp_current_mss(sk);
-	u32 prior_lost = tp->lost_out;
 
-	tcp_for_write_queue(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
+	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 		if (tcp_skb_seglen(skb) > mss &&
 		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
 			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
@@ -2629,7 +2568,7 @@ void tcp_simple_retransmit(struct sock *sk)
 
 	tcp_clear_retrans_hints_partial(tp);
 
-	if (prior_lost == tp->lost_out)
+	if (!tp->lost_out)
 		return;
 
 	if (tcp_is_reno(tp))
@@ -2710,7 +2649,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 			 * is updated in tcp_ack()). Otherwise fall back to
 			 * the conventional recovery.
 			 */
-			if (tcp_send_head(sk) &&
+			if (!tcp_write_queue_empty(sk) &&
 			    after(tcp_wnd_end(tp), tp->snd_nxt)) {
 				*rexmit = REXMIT_NEW;
 				return;
@@ -2737,15 +2676,15 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 }
 
 /* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, const int acked)
+static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (tp->undo_marker && tcp_packet_delayed(tp)) {
 		/* Plain luck! Hole if filled with delayed
-		 * packet, rather than with a retransmit.
+		 * packet, rather than with a retransmit. Check reordering.
 		 */
-		tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
+		tcp_check_sack_reordering(sk, prior_snd_una, 1);
 
 		/* We are getting evidence that the reordering degree is higher
 		 * than we realized. If there are no retransmits out then we
@@ -2772,7 +2711,7 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Use RACK to detect loss */
-	if (sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
 		u32 prior_retrans = tp->retrans_out;
 
 		tcp_rack_mark_lost(sk);
@@ -2781,6 +2720,14 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
 	}
 }
 
+static bool tcp_force_fast_retransmit(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	return after(tcp_highest_sack_seq(tp),
+		     tp->snd_una + tp->reordering * tp->mss_cache);
+}
+
 /* Process an event, which can update packets-in-flight not trivially.
  * Main goal of this function is to calculate new estimate for left_out,
  * taking into account both packets sitting in receiver's buffer and
@@ -2793,19 +2740,17 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
  * It does _not_ decide what to send, it is made in function
  * tcp_xmit_retransmit_queue().
  */
-static void tcp_fastretrans_alert(struct sock *sk, const int acked,
+static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 				  bool is_dupack, int *ack_flag, int *rexmit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int fast_rexmit = 0, flag = *ack_flag;
 	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
-				    (tcp_fackets_out(tp) > tp->reordering));
+				     tcp_force_fast_retransmit(sk));
 
-	if (WARN_ON(!tp->packets_out && tp->sacked_out))
+	if (!tp->packets_out && tp->sacked_out)
 		tp->sacked_out = 0;
-	if (WARN_ON(!tp->sacked_out && tp->fackets_out))
-		tp->fackets_out = 0;
 
 	/* Now state machine starts.
 	 * A. ECE, hence prohibit cwnd undoing, the reduction is required. */
@@ -2852,11 +2797,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 			if (tcp_is_reno(tp) && is_dupack)
 				tcp_add_reno_sack(sk);
 		} else {
-			if (tcp_try_undo_partial(sk, acked))
+			if (tcp_try_undo_partial(sk, prior_snd_una))
 				return;
 			/* Partial ACK arrived. Force fast retransmit. */
 			do_lost = tcp_is_reno(tp) ||
-				  tcp_fackets_out(tp) > tp->reordering;
+				  tcp_force_fast_retransmit(sk);
 		}
 		if (tcp_try_undo_dsack(sk)) {
 			tcp_try_keep_open(sk);
@@ -2871,6 +2816,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 		      (*ack_flag & FLAG_LOST_RETRANS)))
 			return;
 		/* Change state if cwnd is undone or retransmits are lost */
+		/* fall through */
 	default:
 		if (tcp_is_reno(tp)) {
 			if (flag & FLAG_SND_UNA_ADVANCED)
@@ -2911,8 +2857,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
+	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;
 
 	minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
 			   rtt_us ? : jiffies_to_usecs(1));
@@ -3004,21 +2950,24 @@ void tcp_rearm_rto(struct sock *sk)
 		/* Offset the time elapsed after installing regular RTO */
 		if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
-			struct sk_buff *skb = tcp_write_queue_head(sk);
-			u64 rto_time_stamp = skb->skb_mstamp +
-					     jiffies_to_usecs(rto);
-			s64 delta_us = rto_time_stamp - tp->tcp_mstamp;
+			s64 delta_us = tcp_rto_delta_us(sk);
 			/* delta_us may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta_us > 0)
-				rto = usecs_to_jiffies(delta_us);
+			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
 	}
 }
 
+/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */
+static void tcp_set_xmit_timer(struct sock *sk)
+{
+	if (!tcp_schedule_loss_probe(sk, true))
+		tcp_rearm_rto(sk);
+}
+
 /* If we get here, the whole TSO packet has not been acked. */
 static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
 {
@@ -3051,28 +3000,31 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 
 	shinfo = skb_shinfo(skb);
 	if (!before(shinfo->tskey, prior_snd_una) &&
-	    before(shinfo->tskey, tcp_sk(sk)->snd_una))
-		__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
+		tcp_skb_tsorted_save(skb) {
+			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+		} tcp_skb_tsorted_restore(skb);
+	}
 }
 
 /* Remove acknowledged frames from the retransmission queue. If our packet
  * is before the ack sequence we can discard it as it's confirmed to have
  * arrived at the other end.
  */
-static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
-			       u32 prior_snd_una, int *acked,
+static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
+			       u32 prior_snd_una,
 			       struct tcp_sacktag_state *sack)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u64 first_ackt, last_ackt;
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 prior_sacked = tp->sacked_out;
-	u32 reord = tp->packets_out;
+	u32 reord = tp->snd_nxt; /* lowest acked un-retx un-sacked seq */
+	struct sk_buff *skb, *next;
 	bool fully_acked = true;
 	long sack_rtt_us = -1L;
 	long seq_rtt_us = -1L;
 	long ca_rtt_us = -1L;
-	struct sk_buff *skb;
 	u32 pkts_acked = 0;
 	u32 last_in_flight = 0;
 	bool rtt_update;
@@ -3080,8 +3032,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 	first_ackt = 0;
 
-	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+	for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+		const u32 start_seq = scb->seq;
 		u8 sacked = scb->sacked;
 		u32 acked_pcount;
 
@@ -3098,8 +3051,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 				break;
 			fully_acked = false;
 		} else {
-			/* Speedup tcp_unlink_write_queue() and next loop */
-			prefetchw(skb->next);
 			acked_pcount = tcp_skb_pcount(skb);
 		}
 
@@ -3114,7 +3065,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 				first_ackt = last_ackt;
 
 			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
-			reord = min(pkts_acked, reord);
+			if (before(start_seq, reord))
+				reord = start_seq;
 			if (!after(scb->end_seq, tp->high_seq))
 				flag |= FLAG_ORIG_SACK_ACKED;
 		}
@@ -3151,12 +3103,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		if (!fully_acked)
 			break;
 
-		tcp_unlink_write_queue(skb, sk);
-		sk_wmem_free_skb(sk, skb);
+		next = skb_rb_next(skb);
 		if (unlikely(skb == tp->retransmit_skb_hint))
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
 	if (!skb)
@@ -3180,7 +3132,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 					ca_rtt_us, sack->rate);
 
 	if (flag & FLAG_ACKED) {
-		tcp_rearm_rto(sk);
+		flag |= FLAG_SET_XMIT_TIMER;  /* set TLP or RTO timer */
 		if (unlikely(icsk->icsk_mtup.probe_size &&
 			     !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
 			tcp_mtup_probe_success(sk);
@@ -3192,23 +3144,19 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			int delta;
 
 			/* Non-retransmitted hole got filled? That's reordering */
-			if (reord < prior_fackets && reord <= tp->fackets_out)
-				tcp_update_reordering(sk, tp->fackets_out - reord, 0);
+			if (before(reord, prior_fack))
+				tcp_check_sack_reordering(sk, reord, 0);
 
-			delta = tcp_is_fack(tp) ? pkts_acked :
-						  prior_sacked - tp->sacked_out;
+			delta = prior_sacked - tp->sacked_out;
 			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
 		}
-
-		tp->fackets_out -= min(pkts_acked, tp->fackets_out);
-
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
 		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) {
 		/* Do not re-arm RTO if the sack RTT is measured from data sent
 		 * after when the head was last (re)transmitted. Otherwise the
 		 * timeout may continue to extend in loss recovery.
 		 */
-		tcp_rearm_rto(sk);
+		flag |= FLAG_SET_XMIT_TIMER;  /* set TLP or RTO timer */
 	}
 
 	if (icsk->icsk_ca_ops->pkts_acked) {
@@ -3242,18 +3190,19 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		}
 	}
 #endif
-	*acked = pkts_acked;
 	return flag;
 }
 
 static void tcp_ack_probe(struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *head = tcp_send_head(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Was it a usable window open? */
-
-	if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) {
+	if (!head)
+		return;
+	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
 		icsk->icsk_backoff = 0;
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
 		/* Socket must be waked up by subsequent tcp_data_snd_check().
@@ -3373,7 +3322,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 			tp->pred_flags = 0;
 			tcp_fast_path_check(sk);
 
-			if (tcp_send_head(sk))
+			if (!tcp_write_queue_empty(sk))
 				tcp_slow_start_after_idle_check(sk);
 
 			if (nwin > tp->max_window) {
@@ -3394,7 +3343,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
 	if (*last_oow_ack_time) {
 		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
 
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
 			NET_INC_STATS(net, mib_idx);
 			return true;	/* rate-limited: don't send yet! */
 		}
@@ -3430,10 +3379,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (__tcp_oow_rate_limited(sock_net(sk),
+	if (__tcp_oow_rate_limited(net,
 				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
 				   &tp->last_oow_ack_time))
 		return;
@@ -3441,16 +3391,16 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
-		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+		u32 half = (ack_limit + 1) >> 1;
 
 		challenge_timestamp = now;
-		WRITE_ONCE(challenge_count, half +
-			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
+		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
 	}
 	count = READ_ONCE(challenge_count);
 	if (count > 0) {
 		WRITE_ONCE(challenge_count, count - 1);
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+		NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
 }
@@ -3548,18 +3498,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
-	u32 prior_fackets;
 	int prior_packets = tp->packets_out;
 	u32 delivered = tp->delivered;
 	u32 lost = tp->lost;
-	int acked = 0; /* Number of packets newly acked */
 	int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */
+	u32 prior_fack;
 
 	sack_state.first_sackt = 0;
 	sack_state.rate = &rs;
 
-	/* We very likely will need to access write queue head. */
-	prefetchw(sk->sk_write_queue.next);
+	/* We very likely will need to access rtx queue. */
+	prefetch(sk->tcp_rtx_queue.rb_node);
 
 	/* If the ack is older than previous acks
 	 * then we can probably ignore it.
@@ -3580,15 +3529,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, tp->snd_nxt))
 		goto invalid_ack;
 
-	if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
-		tcp_rearm_rto(sk);
-
 	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
 		icsk->icsk_retransmits = 0;
 	}
 
-	prior_fackets = tp->fackets_out;
+	prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
 	rs.prior_in_flight = tcp_packets_in_flight(tp);
 
 	/* ts_recent update must be made after we are sure that the packet
@@ -3644,21 +3590,25 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		goto no_queue;
 
 	/* See if we can take anything off of the retransmit queue. */
-	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked,
-				    &sack_state);
+	flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state);
+
+	tcp_rack_update_reo_wnd(sk, &rs);
+
+	if (tp->tlp_high_seq)
+		tcp_process_tlp_ack(sk, ack, flag);
+	/* If needed, reset TLP/RTO timer; RACK may later override this. */
+	if (flag & FLAG_SET_XMIT_TIMER)
+		tcp_set_xmit_timer(sk);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+				      &rexmit);
 	}
-	if (tp->tlp_high_seq)
-		tcp_process_tlp_ack(sk, ack, flag);
 
 	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
 		sk_dst_confirm(sk);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
-		tcp_schedule_loss_probe(sk);
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
 	tcp_rate_gen(sk, delivered, lost, sack_state.rate);
@@ -3669,13 +3619,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK)
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+				      &rexmit);
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
 	 */
-	if (tcp_send_head(sk))
-		tcp_ack_probe(sk);
+	tcp_ack_probe(sk);
 
 	if (tp->tlp_high_seq)
 		tcp_process_tlp_ack(sk, ack, flag);
@@ -3692,7 +3642,8 @@ old_ack:
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 						&sack_state);
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+				      &rexmit);
 		tcp_xmit_recovery(sk, rexmit);
 	}
 
@@ -3717,6 +3668,21 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
 	foc->exp = exp_opt;
 }
 
+static void smc_parse_options(const struct tcphdr *th,
+			      struct tcp_options_received *opt_rx,
+			      const unsigned char *ptr,
+			      int opsize)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (th->syn && !(opsize & 1) &&
+		    opsize >= TCPOLEN_EXP_SMC_BASE &&
+		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+			opt_rx->smc_ok = 1;
+	}
+#endif
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -3824,6 +3790,9 @@ void tcp_parse_options(const struct net *net,
 					tcp_parse_fastopen_option(opsize -
 						TCPOLEN_EXP_FASTOPEN_BASE,
 						ptr + 2, th->syn, foc, true);
+				else
+					smc_parse_options(th, opt_rx, ptr,
+							  opsize);
 				break;
 
 			}
@@ -3991,6 +3960,8 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
 /* When we get a reset we do this. */
 void tcp_reset(struct sock *sk)
 {
+	trace_tcp_receive_reset(sk);
+
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
@@ -4113,7 +4084,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4148,7 +4119,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk);
 
-		if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -4267,6 +4238,7 @@ static void tcp_sack_remove(struct tcp_sock *tp)
 /**
  * tcp_try_coalesce - try to merge skb to prior one
  * @sk: socket
+ * @dest: destination queue
  * @to: prior buffer
  * @from: buffer to add in queue
  * @fragstolen: pointer to boolean
@@ -4299,6 +4271,12 @@ static bool tcp_try_coalesce(struct sock *sk,
 	TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
 	TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
 	TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
+
+	if (TCP_SKB_CB(from)->has_rxtstamp) {
+		TCP_SKB_CB(to)->has_rxtstamp = true;
+		to->tstamp = from->tstamp;
+	}
+
 	return true;
 }
 
@@ -4321,7 +4299,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
 	p = rb_first(&tp->out_of_order_queue);
 	while (p) {
-		skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = rb_to_skb(p);
 		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
 
@@ -4385,7 +4363,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node **p, *q, *parent;
+	struct rb_node **p, *parent;
 	struct sk_buff *skb1;
 	u32 seq, end_seq;
 	bool fragstolen;
@@ -4425,7 +4403,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) {
+	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
+			     skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4443,7 +4422,7 @@ coalesce_done:
 	parent = NULL;
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(seq, TCP_SKB_CB(skb1)->seq)) {
 			p = &parent->rb_left;
 			continue;
@@ -4475,7 +4454,8 @@ coalesce_done:
 				__kfree_skb(skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) {
+		} else if (tcp_try_coalesce(sk, skb1,
+					    skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
@@ -4487,9 +4467,7 @@ insert:
 
 merge_right:
 	/* Remove other segments covered by skb. */
-	while ((q = rb_next(&skb->rbnode)) != NULL) {
-		skb1 = rb_entry(q, struct sk_buff, rbnode);
-
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
 		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
 			break;
 		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
@@ -4504,7 +4482,7 @@ merge_right:
 		tcp_drop(sk, skb1);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
-	if (!q)
+	if (!skb1)
 		tp->ooo_last_skb = skb;
 
 add_sack:
@@ -4526,7 +4504,8 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 
 	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
-		 tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
+		 tcp_try_coalesce(sk, tail,
+				  skb, fragstolen)) ? 1 : 0;
 	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
@@ -4588,8 +4567,8 @@ err:
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	bool fragstolen = false;
-	int eaten = -1;
+	bool fragstolen;
+	int eaten;
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -4611,32 +4590,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			goto out_of_window;
 
 		/* Ok. In sequence. In window. */
-		if (tp->ucopy.task == current &&
-		    tp->copied_seq == tp->rcv_nxt && tp->ucopy.len &&
-		    sock_owned_by_user(sk) && !tp->urg_data) {
-			int chunk = min_t(unsigned int, skb->len,
-					  tp->ucopy.len);
-
-			__set_current_state(TASK_RUNNING);
-
-			if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) {
-				tp->ucopy.len -= chunk;
-				tp->copied_seq += chunk;
-				eaten = (chunk == skb->len);
-				tcp_rcv_space_adjust(sk);
-			}
-		}
-
-		if (eaten <= 0) {
 queue_and_out:
-			if (eaten < 0) {
-				if (skb_queue_len(&sk->sk_receive_queue) == 0)
-					sk_forced_mem_schedule(sk, skb->truesize);
-				else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
-					goto drop;
-			}
-			eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
-		}
+		if (skb_queue_len(&sk->sk_receive_queue) == 0)
+			sk_forced_mem_schedule(sk, skb->truesize);
+		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+			goto drop;
+
+		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
@@ -4708,7 +4668,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li
 	if (list)
 		return !skb_queue_is_last(list, skb) ? skb->next : NULL;
 
-	return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode);
+	return skb_rb_next(skb);
 }
 
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
@@ -4729,7 +4689,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
 }
 
 /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
-static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -4737,7 +4697,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
 			p = &parent->rb_left;
 		else
@@ -4784,7 +4744,7 @@ restart:
 		 *   overlaps to the next one.
 		 */
 		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
-		    (tcp_win_from_space(skb->truesize) > skb->len ||
+		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
 		     before(TCP_SKB_CB(skb)->seq, start))) {
 			end_of_skbs = false;
 			break;
@@ -4856,26 +4816,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb, *head;
-	struct rb_node *p;
 	u32 start, end;
 
-	p = rb_first(&tp->out_of_order_queue);
-	skb = rb_entry_safe(p, struct sk_buff, rbnode);
+	skb = skb_rb_first(&tp->out_of_order_queue);
 new_range:
 	if (!skb) {
-		p = rb_last(&tp->out_of_order_queue);
-		/* Note: This is possible p is NULL here. We do not
-		 * use rb_entry_safe(), as ooo_last_skb is valid only
-		 * if rbtree is not empty.
-		 */
-		tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode);
+		tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
 		return;
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
 
 	for (head = skb;;) {
-		skb = tcp_skb_next(skb, NULL);
+		skb = skb_rb_next(skb);
 
 		/* Range is terminated when we see a gap or when
 		 * we are at the queue end.
@@ -4918,14 +4871,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
-		tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+		tcp_drop(sk, rb_to_skb(node));
 		sk_mem_reclaim(sk);
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 		    !tcp_under_memory_pressure(sk))
 			break;
 		node = prev;
 	} while (node);
-	tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+	tp->ooo_last_skb = rb_to_skb(prev);
 
 	/* Reset SACK state.  A conforming SACK implementation will
 	 * do the same at a timeout based retransmit.  When a connection
@@ -5100,7 +5053,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 ptr = ntohs(th->urg_ptr);
 
-	if (ptr && !sysctl_tcp_stdurg)
+	if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
 		ptr--;
 	ptr += ntohl(th->seq);
 
@@ -5186,26 +5139,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 	}
 }
 
-static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int chunk = skb->len - hlen;
-	int err;
-
-	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk);
-	else
-		err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg);
-
-	if (!err) {
-		tp->ucopy.len -= chunk;
-		tp->copied_seq += chunk;
-		tcp_rcv_space_adjust(sk);
-	}
-
-	return err;
-}
-
 /* Accept RST for rcv_nxt - 1 after a FIN.
  * When tcp connections are abruptly terminated from Mac OSX (via ^C), a
  * FIN is sent followed by a RST packet. The RST is sent with the same
@@ -5358,8 +5291,9 @@ discard:
  *	tcp_data_queue when everything is OK.
  */
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct tcphdr *th, unsigned int len)
+			 const struct tcphdr *th)
 {
+	unsigned int len = skb->len;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tcp_mstamp_refresh(tp);
@@ -5445,56 +5379,28 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			int eaten = 0;
 			bool fragstolen = false;
 
-			if (tp->ucopy.task == current &&
-			    tp->copied_seq == tp->rcv_nxt &&
-			    len - tcp_header_len <= tp->ucopy.len &&
-			    sock_owned_by_user(sk)) {
-				__set_current_state(TASK_RUNNING);
-
-				if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
-					/* Predicted packet is in window by definition.
-					 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
-					 * Hence, check seq<=rcv_wup reduces to:
-					 */
-					if (tcp_header_len ==
-					    (sizeof(struct tcphdr) +
-					     TCPOLEN_TSTAMP_ALIGNED) &&
-					    tp->rcv_nxt == tp->rcv_wup)
-						tcp_store_ts_recent(tp);
-
-					tcp_rcv_rtt_measure_ts(sk, skb);
-
-					__skb_pull(skb, tcp_header_len);
-					tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
-					NET_INC_STATS(sock_net(sk),
-							LINUX_MIB_TCPHPHITSTOUSER);
-					eaten = 1;
-				}
-			}
-			if (!eaten) {
-				if (tcp_checksum_complete(skb))
-					goto csum_error;
+			if (tcp_checksum_complete(skb))
+				goto csum_error;
 
-				if ((int)skb->truesize > sk->sk_forward_alloc)
-					goto step5;
+			if ((int)skb->truesize > sk->sk_forward_alloc)
+				goto step5;
 
-				/* Predicted packet is in window by definition.
-				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
-				 * Hence, check seq<=rcv_wup reduces to:
-				 */
-				if (tcp_header_len ==
-				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
-				    tp->rcv_nxt == tp->rcv_wup)
-					tcp_store_ts_recent(tp);
+			/* Predicted packet is in window by definition.
+			 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
+			 * Hence, check seq<=rcv_wup reduces to:
+			 */
+			if (tcp_header_len ==
+			    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
+			    tp->rcv_nxt == tp->rcv_wup)
+				tcp_store_ts_recent(tp);
 
-				tcp_rcv_rtt_measure_ts(sk, skb);
+			tcp_rcv_rtt_measure_ts(sk, skb);
 
-				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
-				/* Bulk data transfer: receiver */
-				eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
-						      &fragstolen);
-			}
+			/* Bulk data transfer: receiver */
+			eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
+					      &fragstolen);
 
 			tcp_event_data_recv(sk, skb);
 
@@ -5567,20 +5473,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		security_inet_conn_established(sk, skb);
 	}
 
-	/* Make sure socket is routed, for correct metrics.  */
-	icsk->icsk_af_ops->rebuild_header(sk);
-
-	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
-	tcp_init_congestion_control(sk);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
 	 */
 	tp->lsndtime = tcp_jiffies32;
 
-	tcp_init_buffer_space(sk);
-
 	if (sock_flag(sk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
 
@@ -5588,14 +5487,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		__tcp_fast_path_on(tp, tp->snd_wnd);
 	else
 		tp->pred_flags = 0;
-
 }
 
 static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 				    struct tcp_fastopen_cookie *cookie)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
+	struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL;
 	u16 mss = tp->rx_opt.mss_clamp, try_exp = 0;
 	bool syn_drop = false;
 
@@ -5630,9 +5528,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
-		tcp_for_write_queue_from(data, sk) {
-			if (data == tcp_send_head(sk) ||
-			    __tcp_retransmit_skb(sk, data, 1))
+		skb_rbtree_walk_from(data) {
+			if (__tcp_retransmit_skb(sk, data, 1))
 				break;
 		}
 		tcp_rearm_rto(sk);
@@ -5650,6 +5547,16 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	return false;
 }
 
+static void smc_check_reset_syn(struct tcp_sock *tp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc && !tp->rx_opt.smc_ok)
+			tp->syn_smc = 0;
+	}
+#endif
+}
+
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 					 const struct tcphdr *th)
 {
@@ -5745,10 +5652,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		if (tcp_is_sack(tp) && sysctl_tcp_fack)
-			tcp_enable_fack(tp);
-
-		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -5757,6 +5660,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 * is initialized. */
 		tp->copied_seq = tp->rcv_nxt;
 
+		smc_check_reset_syn(tp);
+
 		smp_mb();
 
 		tcp_finish_connect(sk, skb);
@@ -5974,15 +5879,18 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (req) {
 			inet_csk(sk)->icsk_retransmits = 0;
 			reqsk_fastopen_remove(sk, req, false);
+			/* Re-arm the timer because data may have been sent out.
+			 * This is similar to the regular data transmission case
+			 * when new data has just been ack'ed.
+			 *
+			 * (TFO) - we could try to be more aggressive and
+			 * retransmitting any data sooner based on when they
+			 * are sent out.
+			 */
+			tcp_rearm_rto(sk);
 		} else {
-			/* Make sure socket is routed, for correct metrics. */
-			icsk->icsk_af_ops->rebuild_header(sk);
-			tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tcp_init_congestion_control(sk);
-
-			tcp_mtup_init(sk);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tp->copied_seq = tp->rcv_nxt;
-			tcp_init_buffer_space(sk);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
@@ -6002,19 +5910,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (tp->rx_opt.tstamp_ok)
 			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
 
-		if (req) {
-			/* Re-arm the timer because data may have been sent out.
-			 * This is similar to the regular data transmission case
-			 * when new data has just been ack'ed.
-			 *
-			 * (TFO) - we could try to be more aggressive and
-			 * retransmitting any data sooner based on when they
-			 * are sent out.
-			 */
-			tcp_rearm_rto(sk);
-		} else
-			tcp_init_metrics(sk);
-
 		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
 			tcp_update_pacing_rate(sk);
 
@@ -6111,6 +6006,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
+		/* fall through */
 	case TCP_FIN_WAIT1:
 	case TCP_FIN_WAIT2:
 		/* RFC 793 says to queue data in these states,
@@ -6219,6 +6115,9 @@ static void tcp_openreq_init(struct request_sock *req,
 	ireq->ir_rmt_port = tcp_hdr(skb)->source;
 	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
 	ireq->ir_mark = inet_request_mark(sk, skb);
+#if IS_ENABLED(CONFIG_SMC)
+	ireq->smc_ok = rx_opt->smc_ok;
+#endif
 }
 
 struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
@@ -6231,8 +6130,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
 	if (req) {
 		struct inet_request_sock *ireq = inet_rsk(req);
 
-		kmemcheck_annotate_bitfield(ireq, flags);
-		ireq->opt = NULL;
+		ireq->ireq_opt = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 		ireq->pktopts = NULL;
 #endif
@@ -6303,9 +6201,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sock *fastopen_sk = NULL;
-	struct dst_entry *dst = NULL;
 	struct request_sock *req;
 	bool want_cookie = false;
+	struct dst_entry *dst;
 	struct flowi fl;
 
 	/* TW buckets are converted to open requests without
@@ -6355,6 +6253,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tmp_opt.tstamp_ok)
 		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
 
+	dst = af_ops->route_req(sk, &fl, req);
+	if (!dst)
+		goto drop_and_free;
+
 	if (!want_cookie && !isn) {
 		/* Kill the following clause, if you dislike this way. */
 		if (!net->ipv4.sysctl_tcp_syncookies &&
@@ -6375,11 +6277,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 		isn = af_ops->init_seq(skb);
 	}
-	if (!dst) {
-		dst = af_ops->route_req(sk, &fl, req);
-		if (!dst)
-			goto drop_and_free;
-	}
 
 	tcp_ecn_create_request(req, skb, sk, dst);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a20e7f03d5f7..c6bc0c4d19c6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,7 +85,7 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_low_latency __read_mostly;
+#include <trace/events/tcp.h>
 
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
@@ -385,7 +385,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
 				       th->dest, iph->saddr, ntohs(th->source),
-				       inet_iif(icmp_skb));
+				       inet_iif(icmp_skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;
@@ -482,7 +482,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 					       TCP_TIMEOUT_INIT;
 		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
-		skb = tcp_write_queue_head(sk);
+		skb = tcp_rtx_queue_head(sk);
 		BUG_ON(!skb);
 
 		tcp_mstamp_refresh(tp);
@@ -661,7 +661,8 @@ 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));
+					     ntohs(th->source), inet_iif(skb),
+					     tcp_v4_sdif(skb));
 		/* don't send rst if it can't find key */
 		if (!sk1)
 			goto out;
@@ -702,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	 * routing might fail in this case. No choice here, if we choose to force
 	 * input interface, we will misroute in case of asymmetric route.
 	 */
-	if (sk)
+	if (sk) {
 		arg.bound_dev_if = sk->sk_bound_dev_if;
+		trace_tcp_send_reset(sk, skb);
+	}
 
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -878,7 +881,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
@@ -890,7 +893,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1266,10 +1269,11 @@ static void tcp_v4_init_req(struct request_sock *req,
 			    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
+	struct net *net = sock_net(sk_listener);
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1356,10 +1360,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr	      = ireq->ir_loc_addr;
-	inet_opt	      = ireq->opt;
-	rcu_assign_pointer(newinet->inet_opt, inet_opt);
-	ireq->opt	      = NULL;
+	newinet->inet_saddr   = ireq->ir_loc_addr;
+	inet_opt	      = rcu_dereference(ireq->ireq_opt);
+	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1404,9 +1407,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-	if (*own_req)
+	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
-
+		ireq->ireq_opt = NULL;
+	} else {
+		newinet->inet_opt = NULL;
+	}
 	return newsk;
 
 exit_overflow:
@@ -1417,6 +1423,7 @@ exit:
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
@@ -1458,7 +1465,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 				sk->sk_rx_dst = NULL;
 			}
 		}
-		tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
+		tcp_rcv_established(sk, skb, tcp_hdr(skb));
 		return 0;
 	}
 
@@ -1504,28 +1511,28 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-void tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
 
 	if (skb->pkt_type != PACKET_HOST)
-		return;
+		return 0;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	th = tcp_hdr(skb);
 
 	if (th->doff < sizeof(struct tcphdr) / 4)
-		return;
+		return 0;
 
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
 				       iph->daddr, ntohs(th->dest),
-				       skb->skb_iif);
+				       skb->skb_iif, inet_sdif(skb));
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
@@ -1539,63 +1546,9 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 				skb_dst_set_noref(skb, dst);
 		}
 	}
+	return 0;
 }
 
-/* Packet is added to VJ-style prequeue for processing in process
- * context, if a reader task is waiting. Apparently, this exciting
- * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
- * failed somewhere. Latency? Burstiness? Well, at least now we will
- * see, why it failed. 8)8)				  --ANK
- *
- */
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (sysctl_tcp_low_latency || !tp->ucopy.task)
-		return false;
-
-	if (skb->len <= tcp_hdrlen(skb) &&
-	    skb_queue_len(&tp->ucopy.prequeue) == 0)
-		return false;
-
-	/* Before escaping RCU protected region, we need to take care of skb
-	 * dst. Prequeue is only enabled for established sockets.
-	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
-	 * Instead of doing full sk_rx_dst validity here, let's perform
-	 * an optimistic check.
-	 */
-	if (likely(sk->sk_rx_dst))
-		skb_dst_drop(skb);
-	else
-		skb_dst_force_safe(skb);
-
-	__skb_queue_tail(&tp->ucopy.prequeue, skb);
-	tp->ucopy.memory += skb->truesize;
-	if (skb_queue_len(&tp->ucopy.prequeue) >= 32 ||
-	    tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
-		struct sk_buff *skb1;
-
-		BUG_ON(sock_owned_by_user(sk));
-		__NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED,
-				skb_queue_len(&tp->ucopy.prequeue));
-
-		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk_backlog_rcv(sk, skb1);
-
-		tp->ucopy.memory = 0;
-	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-		wake_up_interruptible_sync_poll(sk_sleep(sk),
-					   POLLIN | POLLRDNORM | POLLRDBAND);
-		if (!inet_csk_ack_scheduled(sk))
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  (3 * tcp_rto_min(sk)) / 4,
-						  TCP_RTO_MAX);
-	}
-	return true;
-}
-EXPORT_SYMBOL(tcp_prequeue);
-
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
@@ -1645,6 +1598,7 @@ EXPORT_SYMBOL(tcp_filter);
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	bool refcounted;
@@ -1692,10 +1646,12 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
+	TCP_SKB_CB(skb)->has_rxtstamp =
+			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
 
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
-			       th->dest, &refcounted);
+			       th->dest, sdif, &refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1722,15 +1678,15 @@ process:
 		 */
 		sock_hold(sk);
 		refcounted = true;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
 		}
 		if (nsk == sk) {
 			reqsk_put(req);
-		} else if (tcp_filter(sk, skb)) {
-			goto discard_and_relse;
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
 			goto discard_and_relse;
@@ -1770,8 +1726,7 @@ process:
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-		if (!tcp_prequeue(sk, skb))
-			ret = tcp_v4_do_rcv(sk, skb);
+		ret = tcp_v4_do_rcv(sk, skb);
 	} else if (tcp_add_backlog(sk, skb)) {
 		goto discard_and_relse;
 	}
@@ -1824,15 +1779,17 @@ do_time_wait:
 							__tcp_hdrlen(th),
 							iph->saddr, th->source,
 							iph->daddr, th->dest,
-							inet_iif(skb));
+							inet_iif(skb),
+							sdif);
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;
 			refcounted = false;
 			goto process;
 		}
-		/* Fall through to ACK */
 	}
+		/* to ACK */
+		/* fall through */
 	case TCP_TW_ACK:
 		tcp_v4_timewait_ack(sk, skb);
 		break;
@@ -1912,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	trace_tcp_destroy_sock(sk);
+
 	tcp_clear_xmit_timers(sk);
 
 	tcp_cleanup_congestion_control(sk);
@@ -1936,9 +1895,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 #endif
 
-	/* Clean prequeue, it must be empty really */
-	__skb_queue_purge(&tp->ucopy.prequeue);
-
 	/* Clean up a referenced TCP bind bucket. */
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
@@ -1947,6 +1903,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
+	tcp_fastopen_destroy_cipher(sk);
 	tcp_saved_syn_free(tp);
 
 	sk_sockets_allocated_dec(sk);
@@ -2452,8 +2409,8 @@ struct proto tcp_prot = {
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
 	.sysctl_mem		= sysctl_tcp_mem,
-	.sysctl_wmem		= sysctl_tcp_wmem,
-	.sysctl_rmem		= sysctl_tcp_rmem,
+	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
+	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp_sock),
 	.slab_flags		= SLAB_TYPESAFE_BY_RCU,
@@ -2473,6 +2430,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
 {
 	int cpu;
 
+	module_put(net->ipv4.tcp_congestion_control->owner);
+
 	for_each_possible_cpu(cpu)
 		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
 	free_percpu(net->ipv4.tcp_sk);
@@ -2527,6 +2486,50 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
+	net->ipv4.sysctl_tcp_early_retrans = 3;
+	net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION;
+	net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior.  */
+	net->ipv4.sysctl_tcp_retrans_collapse = 1;
+	net->ipv4.sysctl_tcp_max_reordering = 300;
+	net->ipv4.sysctl_tcp_dsack = 1;
+	net->ipv4.sysctl_tcp_app_win = 31;
+	net->ipv4.sysctl_tcp_adv_win_scale = 1;
+	net->ipv4.sysctl_tcp_frto = 2;
+	net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+	/* This limits the percentage of the congestion window which we
+	 * will allow a single TSO frame to consume.  Building TSO frames
+	 * which are too large can cause TCP streams to be bursty.
+	 */
+	net->ipv4.sysctl_tcp_tso_win_divisor = 3;
+	/* Default TSQ limit of four TSO segments */
+	net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+	/* rfc5961 challenge ack rate limiting */
+	net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+	net->ipv4.sysctl_tcp_min_tso_segs = 2;
+	net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
+	net->ipv4.sysctl_tcp_autocorking = 1;
+	net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+	net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
+	net->ipv4.sysctl_tcp_pacing_ca_ratio = 120;
+	if (net != &init_net) {
+		memcpy(net->ipv4.sysctl_tcp_rmem,
+		       init_net.ipv4.sysctl_tcp_rmem,
+		       sizeof(init_net.ipv4.sysctl_tcp_rmem));
+		memcpy(net->ipv4.sysctl_tcp_wmem,
+		       init_net.ipv4.sysctl_tcp_wmem,
+		       sizeof(init_net.ipv4.sysctl_tcp_wmem));
+	}
+	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
+	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+	atomic_set(&net->ipv4.tfo_active_disable_times, 0);
+
+	/* Reno is always built in */
+	if (!net_eq(net, &init_net) &&
+	    try_module_get(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;
 
 	return 0;
 fail:
@@ -2537,7 +2540,12 @@ fail:
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
+	struct net *net;
+
 	inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		tcp_fastopen_ctx_destroy(net);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 102b2c90bb80..7097f92d16e5 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
@@ -20,8 +21,6 @@
 #include <net/tcp.h>
 #include <net/genetlink.h>
 
-int sysctl_tcp_nometrics_save __read_mostly;
-
 static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr,
 						   const struct inetpeer_addr *daddr,
 						   struct net *net, unsigned int hash);
@@ -330,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
 	int m;
 
 	sk_dst_confirm(sk);
-	if (sysctl_tcp_nometrics_save || !dst)
+	if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
 		return;
 
 	rcu_read_lock();
@@ -471,10 +470,8 @@ void tcp_init_metrics(struct sock *sk)
 		tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	}
 	val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
-	if (val && tp->reordering != val) {
-		tcp_disable_fack(tp);
+	if (val && tp->reordering != val)
 		tp->reordering = val;
-	}
 
 	crtt = tcp_metric_get(tm, TCP_METRIC_RTT);
 	rcu_read_unlock();
@@ -892,10 +889,14 @@ static void tcp_metrics_flush_all(struct net *net)
 
 	for (row = 0; row < max_rows; row++, hb++) {
 		struct tcp_metrics_block __rcu **pp;
+		bool match;
+
 		spin_lock_bh(&tcp_metrics_lock);
 		pp = &hb->chain;
 		for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
-			if (net_eq(tm_net(tm), net)) {
+			match = net ? net_eq(tm_net(tm), net) :
+				!atomic_read(&tm_net(tm)->count);
+			if (match) {
 				*pp = tm->tcpm_next;
 				kfree_rcu(tm, rcu_head);
 			} else {
@@ -1018,14 +1019,14 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit tcp_net_metrics_exit(struct net *net)
+static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list)
 {
-	tcp_metrics_flush_all(net);
+	tcp_metrics_flush_all(NULL);
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
-	.init	=	tcp_net_metrics_init,
-	.exit	=	tcp_net_metrics_exit,
+	.init		=	tcp_net_metrics_init,
+	.exit_batch	=	tcp_net_metrics_exit_batch,
 };
 
 void __init tcp_metrics_init(void)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0ff83c1637d8..e36eff0403f4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -23,13 +23,12 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 #include <linux/workqueue.h>
+#include <linux/static_key.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
 #include <net/busy_poll.h>
 
-int sysctl_tcp_abort_on_overflow __read_mostly;
-
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
 	if (seq == s_win)
@@ -180,7 +179,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			 * Oh well... nobody has a sufficient solution to this
 			 * protocol bug yet.
 			 */
-			if (sysctl_tcp_rfc1337 == 0) {
+			if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
 kill:
 				inet_twsk_deschedule_put(tw);
 				return TCP_TW_SUCCESS;
@@ -298,8 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			key = tp->af_specific->md5_lookup(sk, sk);
 			if (key) {
 				tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
-				if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
-					BUG();
+				BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
 			}
 		} while (0);
 #endif
@@ -371,7 +369,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 		full_space = rcv_wnd * mss;
 
 	/* tcp_full_space because it is guaranteed to be the first packet */
-	tcp_select_initial_window(full_space,
+	tcp_select_initial_window(sk_listener, full_space,
 		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
 		&req->rsk_rcv_wnd,
 		&req->rsk_window_clamp,
@@ -417,6 +415,21 @@ 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,
+				    struct request_sock *req,
+				    struct tcp_sock *newtp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	struct inet_request_sock *ireq;
+
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		ireq = inet_rsk(req);
+		if (oldtp->syn_smc && !ireq->smc_ok)
+			newtp->syn_smc = 0;
+	}
+#endif
+}
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
@@ -434,6 +447,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 		struct tcp_sock *newtp = tcp_sk(newsk);
+		struct tcp_sock *oldtp = tcp_sk(sk);
+
+		smc_check_reset_syn_req(oldtp, req, newtp);
 
 		/* Now setup tcp_sock */
 		newtp->pred_flags = 0;
@@ -445,8 +461,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
 
-		tcp_prequeue_init(newtp);
 		INIT_LIST_HEAD(&newtp->tsq_node);
+		INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
@@ -459,7 +475,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
 		newtp->sacked_out = 0;
-		newtp->fackets_out = 0;
 		newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 		newtp->tlp_high_seq = 0;
 		newtp->lsndtime = tcp_jiffies32;
@@ -493,10 +508,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 						       keepalive_time_when(newtp));
 
 		newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
-		if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
-			if (sysctl_tcp_fack)
-				tcp_enable_fack(newtp);
-		}
+		newtp->rx_opt.sack_ok = ireq->sack_ok;
 		newtp->window_clamp = req->rsk_window_clamp;
 		newtp->rcv_ssthresh = req->rsk_rcv_wnd;
 		newtp->rcv_wnd = req->rsk_rcv_wnd;
@@ -535,6 +547,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->syn_data_acked = 0;
 		newtp->rack.mstamp = 0;
 		newtp->rack.advanced = 0;
+		newtp->rack.reo_wnd_steps = 1;
+		newtp->rack.last_delivered = 0;
+		newtp->rack.reo_wnd_persist = 0;
+		newtp->rack.dsack_seen = 0;
 
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 	}
@@ -765,7 +781,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	return inet_csk_complete_hashdance(sk, child, req, own_req);
 
 listen_overflow:
-	if (!sysctl_tcp_abort_on_overflow) {
+	if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) {
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 6d650ed3cb59..0b5a05bd82e3 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -39,7 +39,7 @@
  * nv_cong_dec_mult	Decrease cwnd by X% (30%) of congestion when detected
  * nv_ssthresh_factor	On congestion set ssthresh to this * <desired cwnd> / 8
  * nv_rtt_factor	RTT averaging factor
- * nv_loss_dec_factor	Decrease cwnd by this (50%) when losses occur
+ * nv_loss_dec_factor	Decrease cwnd to this (80%) when losses occur
  * nv_dec_eval_min_calls	Wait this many RTT measurements before dec cwnd
  * nv_inc_eval_min_calls	Wait this many RTT measurements before inc cwnd
  * nv_ssthresh_eval_min_calls	Wait this many RTT measurements before stopping
@@ -61,7 +61,7 @@ static int nv_min_cwnd __read_mostly = 2;
 static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */
 static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */
 static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */
-static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */
+static int nv_loss_dec_factor __read_mostly = 819; /* => 80% */
 static int nv_cwnd_growth_rate_neg __read_mostly = 8;
 static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */
 static int nv_dec_eval_min_calls __read_mostly = 60;
@@ -86,7 +86,6 @@ struct tcpnv {
 				 * < 0 => less than 1 packet/RTT */
 	u8  available8;
 	u16 available16;
-	u32 loss_cwnd;	/* cwnd at last loss */
 	u8  nv_allow_cwnd_growth:1, /* whether cwnd can grow */
 		nv_reset:1,	    /* whether to reset values */
 		nv_catchup:1;	    /* whether we are growing because
@@ -102,6 +101,11 @@ struct tcpnv {
 	u32 nv_last_rtt;	/* last rtt */
 	u32 nv_min_rtt;		/* active min rtt. Used to determine slope */
 	u32 nv_min_rtt_new;	/* min rtt for future use */
+	u32 nv_base_rtt;        /* If non-zero it represents the threshold for
+				 * congestion */
+	u32 nv_lower_bound_rtt; /* Used in conjunction with nv_base_rtt. It is
+				 * set to 80% of nv_base_rtt. It helps reduce
+				 * unfairness between flows */
 	u32 nv_rtt_max_rate;	/* max rate seen during current RTT */
 	u32 nv_rtt_start_seq;	/* current RTT ends when packet arrives
 				 * acking beyond nv_rtt_start_seq */
@@ -121,7 +125,6 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	ca->nv_reset = 0;
-	ca->loss_cwnd = 0;
 	ca->nv_no_cong_cnt = 0;
 	ca->nv_rtt_cnt = 0;
 	ca->nv_last_rtt = 0;
@@ -134,9 +137,24 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
 static void tcpnv_init(struct sock *sk)
 {
 	struct tcpnv *ca = inet_csk_ca(sk);
+	int base_rtt;
 
 	tcpnv_reset(ca, sk);
 
+	/* See if base_rtt is available from socket_ops bpf program.
+	 * It is meant to be used in environments, such as communication
+	 * within a datacenter, where we have reasonable estimates of
+	 * RTTs
+	 */
+	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+	if (base_rtt > 0) {
+		ca->nv_base_rtt = base_rtt;
+		ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
+	} else {
+		ca->nv_base_rtt = 0;
+		ca->nv_lower_bound_rtt = 0;
+	}
+
 	ca->nv_allow_cwnd_growth = 1;
 	ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ;
 	ca->nv_min_rtt = NV_INIT_RTT;
@@ -146,6 +164,19 @@ static void tcpnv_init(struct sock *sk)
 	ca->cwnd_growth_factor = 0;
 }
 
+/* If provided, apply upper (base_rtt) and lower (lower_bound_rtt)
+ * bounds to RTT.
+ */
+inline u32 nv_get_bounded_rtt(struct tcpnv *ca, u32 val)
+{
+	if (ca->nv_lower_bound_rtt > 0 && val < ca->nv_lower_bound_rtt)
+		return ca->nv_lower_bound_rtt;
+	else if (ca->nv_base_rtt > 0 && val > ca->nv_base_rtt)
+		return ca->nv_base_rtt;
+	else
+		return val;
+}
+
 static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -177,19 +208,10 @@ static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 static u32 tcpnv_recalc_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct tcpnv *ca = inet_csk_ca(sk);
 
-	ca->loss_cwnd = tp->snd_cwnd;
 	return max((tp->snd_cwnd * nv_loss_dec_factor) >> 10, 2U);
 }
 
-static u32 tcpnv_undo_cwnd(struct sock *sk)
-{
-	struct tcpnv *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
 static void tcpnv_state(struct sock *sk, u8 new_state)
 {
 	struct tcpnv *ca = inet_csk_ca(sk);
@@ -220,7 +242,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcpnv *ca = inet_csk_ca(sk);
 	unsigned long now = jiffies;
-	s64 rate64 = 0;
+	u64 rate64;
 	u32 rate, max_win, cwnd_by_slope;
 	u32 avg_rtt;
 	u32 bytes_acked = 0;
@@ -262,8 +284,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	}
 
 	/* rate in 100's bits per second */
-	rate64 = ((u64)sample->in_flight) * 8000000;
-	rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100));
+	rate64 = ((u64)sample->in_flight) * 80000;
+	do_div(rate64, avg_rtt ?: 1);
+	rate = (u32)rate64;
 
 	/* Remember the maximum rate seen during this RTT
 	 * Note: It may be more than one RTT. This function should be
@@ -276,6 +299,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	if (ca->nv_eval_call_cnt < 255)
 		ca->nv_eval_call_cnt++;
 
+	/* Apply bounds to rtt. Only used to update min_rtt */
+	avg_rtt = nv_get_bounded_rtt(ca, avg_rtt);
+
 	/* update min rtt if necessary */
 	if (avg_rtt < ca->nv_min_rtt)
 		ca->nv_min_rtt = avg_rtt;
@@ -446,7 +472,7 @@ static struct tcp_congestion_ops tcpnv __read_mostly = {
 	.ssthresh	= tcpnv_recalc_ssthresh,
 	.cong_avoid	= tcpnv_cong_avoid,
 	.set_state	= tcpnv_state,
-	.undo_cwnd	= tcpnv_undo_cwnd,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.pkts_acked     = tcpnv_acked,
 	.get_info	= tcpnv_get_info,
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 11f69bbf9307..b6a2aa1dcf56 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -149,11 +149,19 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	 * is freed by GSO engine
 	 */
 	if (copy_destructor) {
+		int delta;
+
 		swap(gso_skb->sk, skb->sk);
 		swap(gso_skb->destructor, skb->destructor);
 		sum_truesize += skb->truesize;
-		refcount_add(sum_truesize - gso_skb->truesize,
-			   &skb->sk->sk_wmem_alloc);
+		delta = sum_truesize - gso_skb->truesize;
+		/* In some pathological cases, delta can be negative.
+		 * We need to either use refcount_add() or refcount_sub_and_test()
+		 */
+		if (likely(delta >= 0))
+			refcount_add(delta, &skb->sk->sk_wmem_alloc);
+		else
+			WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc));
 	}
 
 	delta = htonl(oldlen + (skb_tail_pointer(skb) -
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4e985dea1dd2..a4d214c7b506 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -41,40 +41,25 @@
 #include <linux/compiler.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/static_key.h>
 
-/* People can turn this off for buggy TCP's found in printers etc. */
-int sysctl_tcp_retrans_collapse __read_mostly = 1;
-
-/* People can turn this on to work with those rare, broken TCPs that
- * interpret the window field as a signed quantity.
- */
-int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
-
-/* Default TSQ limit of four TSO segments */
-int sysctl_tcp_limit_output_bytes __read_mostly = 262144;
-
-/* This limits the percentage of the congestion window which we
- * will allow a single TSO frame to consume.  Building TSO frames
- * which are too large can cause TCP streams to be bursty.
- */
-int sysctl_tcp_tso_win_divisor __read_mostly = 3;
-
-/* By default, RFC2861 behavior.  */
-int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+#include <trace/events/tcp.h>
 
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			   int push_one, gfp_t gfp);
 
 /* Account for new data that has been sent to the network. */
-static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
+static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
-	tcp_advance_send_head(sk, skb);
 	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
 
+	__skb_unlink(skb, &sk->sk_write_queue);
+	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
+
 	tp->packets_out += tcp_skb_pcount(skb);
 	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
@@ -203,7 +188,7 @@ u32 tcp_default_init_rwnd(u32 mss)
  * be a multiple of mss if possible. We assume here that mss >= 1.
  * This MUST be enforced by all callers.
  */
-void tcp_select_initial_window(int __space, __u32 mss,
+void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 			       __u32 *rcv_wnd, __u32 *window_clamp,
 			       int wscale_ok, __u8 *rcv_wscale,
 			       __u32 init_rcv_wnd)
@@ -227,7 +212,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
 	 * which we interpret as a sign the remote TCP is not
 	 * misinterpreting the window field as a signed quantity.
 	 */
-	if (sysctl_tcp_workaround_signed_windows)
+	if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
 		(*rcv_wnd) = space;
@@ -235,7 +220,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
 	(*rcv_wscale) = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
@@ -287,7 +272,8 @@ static u16 tcp_select_window(struct sock *sk)
 	/* Make sure we do not exceed the maximum possible
 	 * scaled window.
 	 */
-	if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
+	if (!tp->rx_opt.rcv_wscale &&
+	    sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -395,7 +381,6 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 {
 	skb->ip_summed = CHECKSUM_PARTIAL;
-	skb->csum = 0;
 
 	TCP_SKB_CB(skb)->tcp_flags = flags;
 	TCP_SKB_CB(skb)->sacked = 0;
@@ -418,6 +403,22 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_MD5		(1 << 2)
 #define OPTION_WSCALE		(1 << 3)
 #define OPTION_FAST_OPEN_COOKIE	(1 << 8)
+#define OPTION_SMC		(1 << 9)
+
+static void smc_options_write(__be32 *ptr, u16 *options)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (unlikely(OPTION_SMC & *options)) {
+			*ptr++ = htonl((TCPOPT_NOP  << 24) |
+				       (TCPOPT_NOP  << 16) |
+				       (TCPOPT_EXP <<  8) |
+				       (TCPOLEN_EXP_SMC_BASE));
+			*ptr++ = htonl(TCPOPT_SMC_MAGIC);
+		}
+	}
+#endif
+}
 
 struct tcp_out_options {
 	u16 options;		/* bit field of OPTION_* */
@@ -536,6 +537,41 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 		}
 		ptr += (len + 3) >> 2;
 	}
+
+	smc_options_write(ptr, &options);
+}
+
+static void smc_set_option(const struct tcp_sock *tp,
+			   struct tcp_out_options *opts,
+			   unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc) {
+			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+				opts->options |= OPTION_SMC;
+				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+			}
+		}
+	}
+#endif
+}
+
+static void smc_set_option_cond(const struct tcp_sock *tp,
+				const struct inet_request_sock *ireq,
+				struct tcp_out_options *opts,
+				unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc && ireq->smc_ok) {
+			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+				opts->options |= OPTION_SMC;
+				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+			}
+		}
+	}
+#endif
 }
 
 /* Compute TCP options for SYN packets. This is not the final
@@ -603,11 +639,14 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	smc_set_option(tp, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct request_sock *req,
+static unsigned int tcp_synack_options(const struct sock *sk,
+				       struct request_sock *req,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
@@ -663,6 +702,8 @@ static unsigned int tcp_synack_options(struct request_sock *req,
 		}
 	}
 
+	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -739,8 +780,10 @@ static void tcp_tsq_handler(struct sock *sk)
 		struct tcp_sock *tp = tcp_sk(sk);
 
 		if (tp->lost_out > tp->retrans_out &&
-		    tp->snd_cwnd > tcp_packets_in_flight(tp))
+		    tp->snd_cwnd > tcp_packets_in_flight(tp)) {
+			tcp_mstamp_refresh(tp);
 			tcp_xmit_retransmit_queue(sk);
+		}
 
 		tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
 			       0, GFP_ATOMIC);
@@ -971,6 +1014,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 		      HRTIMER_MODE_ABS_PINNED);
 }
 
+static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	skb->skb_mstamp = tp->tcp_mstamp;
+	list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+}
+
 /* This routine actually transmits TCP packets queued in by
  * tcp_do_sendmsg().  This is used by both the initial
  * transmission and possible later retransmissions.
@@ -991,6 +1040,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
+	struct sk_buff *oskb = NULL;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
@@ -998,19 +1048,22 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 	tp = tcp_sk(sk);
 
-	skb->skb_mstamp = tp->tcp_mstamp;
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
-		tcp_rate_skb_sent(sk, skb);
+		oskb = skb;
+
+		tcp_skb_tsorted_save(oskb) {
+			if (unlikely(skb_cloned(oskb)))
+				skb = pskb_copy(oskb, gfp_mask);
+			else
+				skb = skb_clone(oskb, gfp_mask);
+		} tcp_skb_tsorted_restore(oskb);
 
-		if (unlikely(skb_cloned(skb)))
-			skb = pskb_copy(skb, gfp_mask);
-		else
-			skb = skb_clone(skb, gfp_mask);
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb->skb_mstamp = tp->tcp_mstamp;
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1122,12 +1175,15 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
-	if (likely(err <= 0))
-		return err;
-
-	tcp_enter_cwr(sk);
-
-	return net_xmit_eval(err);
+	if (unlikely(err > 0)) {
+		tcp_enter_cwr(sk);
+		err = net_xmit_eval(err);
+	}
+	if (!err && oskb) {
+		tcp_update_skb_after_send(tp, oskb);
+		tcp_rate_skb_sent(sk, oskb);
+	}
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -1162,21 +1218,6 @@ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
 	}
 }
 
-/* When a modification to fackets out becomes necessary, we need to check
- * skb is counted to fackets_out or not.
- */
-static void tcp_adjust_fackets_out(struct sock *sk, const struct sk_buff *skb,
-				   int decr)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tp->sacked_out || tcp_is_reno(tp))
-		return;
-
-	if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
-		tp->fackets_out -= decr;
-}
-
 /* Pcount in the middle of the write queue got changed, we need to do various
  * tweaks to fix counters
  */
@@ -1197,11 +1238,9 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
 	if (tcp_is_reno(tp) && decr > 0)
 		tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
 
-	tcp_adjust_fackets_out(sk, skb, decr);
-
 	if (tp->lost_skb_hint &&
 	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
-	    (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)))
+	    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 		tp->lost_cnt_hint -= decr;
 
 	tcp_verify_left_out(tp);
@@ -1236,12 +1275,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2)
 	TCP_SKB_CB(skb)->eor = 0;
 }
 
+/* Insert buff after skb on the write or rtx queue of sk.  */
+static void tcp_insert_write_queue_after(struct sk_buff *skb,
+					 struct sk_buff *buff,
+					 struct sock *sk,
+					 enum tcp_queue tcp_queue)
+{
+	if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE)
+		__skb_queue_after(&sk->sk_write_queue, skb, buff);
+	else
+		tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
+}
+
 /* Function to create two new TCP segments.  Shrinks the given segment
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.
  * Remember, these are still headerless SKBs at this point.
  */
-int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
+int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+		 struct sk_buff *skb, u32 len,
 		 unsigned int mss_now, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1324,7 +1376,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
-	tcp_insert_write_queue_after(skb, buff, sk);
+	tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
+	if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE)
+		list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor);
 
 	return 0;
 }
@@ -1602,7 +1656,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		if (tp->packets_out > tp->snd_cwnd_used)
 			tp->snd_cwnd_used = tp->packets_out;
 
-		if (sysctl_tcp_slow_start_after_idle &&
+		if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
 		    (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
 		    !ca_ops->cong_control)
 			tcp_cwnd_application_limited(sk);
@@ -1611,10 +1665,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		 * is caused by insufficient sender buffer:
 		 * 1) just sent some data (see tcp_write_xmit)
 		 * 2) not cwnd limited (this else condition)
-		 * 3) no more data to send (null tcp_send_head )
+		 * 3) no more data to send (tcp_write_queue_empty())
 		 * 4) application is hitting buffer limit (SOCK_NOSPACE)
 		 */
-		if (!tcp_send_head(sk) && sk->sk_socket &&
+		if (tcp_write_queue_empty(sk) && sk->sk_socket &&
 		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) &&
 		    (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
 			tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED);
@@ -1666,7 +1720,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 {
 	u32 bytes, segs;
 
-	bytes = min(sk->sk_pacing_rate >> 10,
+	bytes = min(sk->sk_pacing_rate >> sk->sk_pacing_shift,
 		    sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
 
 	/* Goal is to send at least one packet per ms,
@@ -1689,7 +1743,8 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 	u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
 
 	return tso_segs ? :
-		tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+		tcp_tso_autosize(sk, mss_now,
+				 sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 }
 
 /* Returns the portion of skb which can be sent right away */
@@ -1803,40 +1858,6 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp,
 	return !after(end_seq, tcp_wnd_end(tp));
 }
 
-/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
- * should be put on the wire right now.  If so, it returns the number of
- * packets allowed by the congestion window.
- */
-static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
-				 unsigned int cur_mss, int nonagle)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	unsigned int cwnd_quota;
-
-	tcp_init_tso_segs(skb, cur_mss);
-
-	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
-		return 0;
-
-	cwnd_quota = tcp_cwnd_test(tp, skb);
-	if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
-		cwnd_quota = 0;
-
-	return cwnd_quota;
-}
-
-/* Test if sending is allowed right now. */
-bool tcp_may_send_now(struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_send_head(sk);
-
-	return skb &&
-		tcp_snd_test(sk, skb, tcp_current_mss(sk),
-			     (tcp_skb_is_last(sk, skb) ?
-			      tp->nonagle : TCP_NAGLE_PUSH));
-}
-
 /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
  * which is put after SKB on the list.  It is very much like
  * tcp_fragment() except that it may make several kinds of assumptions
@@ -1844,7 +1865,8 @@ bool tcp_may_send_now(struct sock *sk)
  * know that all the data is in scatter-gather pages, and that the
  * packet has never been sent out before (and thus is not cloned).
  */
-static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
+static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+			struct sk_buff *skb, unsigned int len,
 			unsigned int mss_now, gfp_t gfp)
 {
 	struct sk_buff *buff;
@@ -1853,7 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* All of a TSO frame must be composed of paged data.  */
 	if (skb->len != skb->data_len)
-		return tcp_fragment(sk, skb, len, mss_now, gfp);
+		return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
@@ -1889,7 +1911,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
-	tcp_insert_write_queue_after(skb, buff, sk);
+	tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
 
 	return 0;
 }
@@ -1939,7 +1961,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
 		goto send_now;
 
-	win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+	win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
 	if (win_divisor) {
 		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
 
@@ -1959,8 +1981,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 			goto send_now;
 	}
 
-	head = tcp_write_queue_head(sk);
-
+	/* TODO : use tsorted_sent_queue ? */
+	head = tcp_rtx_queue_head(sk);
+	if (!head)
+		goto send_now;
 	age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp);
 	/* If next ACK is likely to come too late (half srtt), do not defer */
 	if (age < (tp->srtt_us >> 4))
@@ -2091,6 +2115,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb->ip_summed = skb->ip_summed;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
+	tcp_highest_sack_replace(sk, skb, nskb);
 
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
@@ -2173,18 +2198,18 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 {
 	unsigned int limit;
 
-	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
-	limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
+	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> sk->sk_pacing_shift);
+	limit = min_t(u32, limit,
+		      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
 	limit <<= factor;
 
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
-		/* Always send the 1st or 2nd skb in write queue.
+		/* Always send skb if rtx queue is empty.
 		 * No need to wait for TX completion to call us back,
 		 * after softirq/tasklet schedule.
 		 * This helps when TX completions are delayed too much.
 		 */
-		if (skb == sk->sk_write_queue.next ||
-		    skb->prev == sk->sk_write_queue.next)
+		if (tcp_rtx_queue_empty(sk))
 			return false;
 
 		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2202,9 +2227,10 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new)
 {
 	const u32 now = tcp_jiffies32;
+	enum tcp_chrono old = tp->chrono_type;
 
-	if (tp->chrono_type > TCP_CHRONO_UNSPEC)
-		tp->chrono_stat[tp->chrono_type - 1] += now - tp->chrono_start;
+	if (old > TCP_CHRONO_UNSPEC)
+		tp->chrono_stat[old - 1] += now - tp->chrono_start;
 	tp->chrono_start = now;
 	tp->chrono_type = new;
 }
@@ -2234,7 +2260,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type)
 	 * it's the "most interesting" or current chrono we are
 	 * tracking and starts busy chrono if we have pending data.
 	 */
-	if (tcp_write_queue_empty(sk))
+	if (tcp_rtx_and_write_queues_empty(sk))
 		tcp_chrono_set(tp, TCP_CHRONO_UNSPEC);
 	else if (type == tp->chrono_type)
 		tcp_chrono_set(tp, TCP_CHRONO_BUSY);
@@ -2267,6 +2293,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 	sent_pkts = 0;
 
+	tcp_mstamp_refresh(tp);
 	if (!push_one) {
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
@@ -2278,7 +2305,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	}
 
 	max_segs = tcp_tso_segs(sk, mss_now);
-	tcp_mstamp_refresh(tp);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -2290,7 +2316,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp" is used as a start point for the retransmit timer */
-			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_update_skb_after_send(tp, skb);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2329,7 +2355,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 						    nonagle);
 
 		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+		    unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
+					  skb, limit, mss_now, gfp)))
 			break;
 
 		if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
@@ -2364,67 +2391,61 @@ repair:
 
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
-			tcp_schedule_loss_probe(sk);
+			tcp_schedule_loss_probe(sk, false);
 		is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
-	return !tp->packets_out && tcp_send_head(sk);
+	return !tp->packets_out && !tcp_write_queue_empty(sk);
 }
 
-bool tcp_schedule_loss_probe(struct sock *sk)
+bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 timeout, tlp_time_stamp, rto_time_stamp;
-	u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
+	u32 timeout, rto_delta_us;
+	int early_retrans;
 
-	/* No consecutive loss probes. */
-	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
-		tcp_rearm_rto(sk);
-		return false;
-	}
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
 	 */
 	if (tp->fastopen_rsk)
 		return false;
 
-	/* TLP is only scheduled when next timer event is RTO. */
-	if (icsk->icsk_pending != ICSK_TIME_RETRANS)
-		return false;
-
+	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) ||
+	if ((early_retrans != 3 && early_retrans != 4) ||
 	    !tp->packets_out || !tcp_is_sack(tp) ||
 	    icsk->icsk_ca_state != TCP_CA_Open)
 		return false;
 
 	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
-	     tcp_send_head(sk))
+	     !tcp_write_queue_empty(sk))
 		return false;
 
-	/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
+	/* Probe timeout is 2*rtt. Add minimum RTO to account
 	 * for delayed ack when there's one outstanding packet. If no RTT
 	 * sample is available then probe after TCP_TIMEOUT_INIT.
 	 */
-	timeout = rtt << 1 ? : TCP_TIMEOUT_INIT;
-	if (tp->packets_out == 1)
-		timeout = max_t(u32, timeout,
-				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
-	timeout = max_t(u32, timeout, msecs_to_jiffies(10));
-
-	/* If RTO is shorter, just schedule TLP in its place. */
-	tlp_time_stamp = tcp_jiffies32 + timeout;
-	rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout;
-	if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) {
-		s32 delta = rto_time_stamp - tcp_jiffies32;
-		if (delta > 0)
-			timeout = delta;
+	if (tp->srtt_us) {
+		timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+		if (tp->packets_out == 1)
+			timeout += TCP_RTO_MIN;
+		else
+			timeout += TCP_TIMEOUT_MIN;
+	} else {
+		timeout = TCP_TIMEOUT_INIT;
 	}
 
+	/* If the RTO formula yields an earlier time, then use that time. */
+	rto_delta_us = advancing_rto ?
+			jiffies_to_usecs(inet_csk(sk)->icsk_rto) :
+			tcp_rto_delta_us(sk);  /* How far in future is RTO? */
+	if (rto_delta_us > 0)
+		timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
+
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
 				  TCP_RTO_MAX);
 	return true;
@@ -2456,18 +2477,14 @@ void tcp_send_loss_probe(struct sock *sk)
 	int mss = tcp_current_mss(sk);
 
 	skb = tcp_send_head(sk);
-	if (skb) {
-		if (tcp_snd_wnd_test(tp, skb, mss)) {
-			pcount = tp->packets_out;
-			tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
-			if (tp->packets_out > pcount)
-				goto probe_sent;
-			goto rearm_timer;
-		}
-		skb = tcp_write_queue_prev(sk, skb);
-	} else {
-		skb = tcp_write_queue_tail(sk);
+	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
+		pcount = tp->packets_out;
+		tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+		if (tp->packets_out > pcount)
+			goto probe_sent;
+		goto rearm_timer;
 	}
+	skb = skb_rb_last(&sk->tcp_rtx_queue);
 
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
@@ -2485,10 +2502,11 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 
 	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
-		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
+		if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+					  (pcount - 1) * mss, mss,
 					  GFP_ATOMIC)))
 			goto rearm_timer;
-		skb = tcp_write_queue_next(sk, skb);
+		skb = skb_rb_next(skb);
 	}
 
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
@@ -2688,7 +2706,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
+	struct sk_buff *next_skb = skb_rb_next(skb);
 	int skb_size, next_skb_size;
 
 	skb_size = skb->len;
@@ -2703,9 +2721,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 		else if (!skb_shift(skb, next_skb, next_skb_size))
 			return false;
 	}
-	tcp_highest_sack_combine(sk, next_skb, skb);
-
-	tcp_unlink_write_queue(next_skb, sk);
+	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	if (next_skb->ip_summed == CHECKSUM_PARTIAL)
 		skb->ip_summed = CHECKSUM_PARTIAL;
@@ -2734,7 +2750,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	tcp_skb_collapse_tstamp(skb, next_skb);
 
-	sk_wmem_free_skb(sk, next_skb);
+	tcp_rtx_queue_unlink_and_free(next_skb, sk);
 	return true;
 }
 
@@ -2745,8 +2761,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
 		return false;
 	if (skb_cloned(skb))
 		return false;
-	if (skb == tcp_send_head(sk))
-		return false;
 	/* Some heuristics for collapsing over SACK'd could be invented */
 	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
 		return false;
@@ -2764,12 +2778,12 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 	struct sk_buff *skb = to, *tmp;
 	bool first = true;
 
-	if (!sysctl_tcp_retrans_collapse)
+	if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
 		return;
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		return;
 
-	tcp_for_write_queue_from_safe(skb, tmp, sk) {
+	skb_rbtree_walk_from_safe(skb, tmp) {
 		if (!tcp_can_collapse(sk, skb))
 			break;
 
@@ -2844,7 +2858,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 	len = cur_mss * segs;
 	if (skb->len > len) {
-		if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC))
+		if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
+				 cur_mss, GFP_ATOMIC))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
 		if (skb_unclone(skb, GFP_ATOMIC))
@@ -2878,16 +2893,23 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb->skb_mstamp = tp->tcp_mstamp;
-		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
-		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			     -ENOBUFS;
+		tcp_skb_tsorted_save(skb) {
+			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
+			err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+				     -ENOBUFS;
+		} tcp_skb_tsorted_restore(skb);
+
+		if (!err) {
+			tcp_update_skb_after_send(tp, skb);
+			tcp_rate_skb_sent(sk, skb);
+		}
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
 
 	if (likely(!err)) {
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+		trace_tcp_retransmit_skb(sk, skb);
 	} else if (err != -EBUSY) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
@@ -2924,36 +2946,25 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
  * retransmitted data is acknowledged.  It tries to continue
  * resending the rest of the retransmit queue, until either
  * we've sent it all or the congestion window limit is reached.
- * If doing SACK, the first ACK which comes back for a timeout
- * based retransmit packet might feed us FACK information again.
- * If so, we use it to avoid unnecessarily retransmissions.
  */
 void tcp_xmit_retransmit_queue(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *skb, *rtx_head, *hole = NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
-	struct sk_buff *hole = NULL;
 	u32 max_segs;
 	int mib_idx;
 
 	if (!tp->packets_out)
 		return;
 
-	if (tp->retransmit_skb_hint) {
-		skb = tp->retransmit_skb_hint;
-	} else {
-		skb = tcp_write_queue_head(sk);
-	}
-
+	rtx_head = tcp_rtx_queue_head(sk);
+	skb = tp->retransmit_skb_hint ?: rtx_head;
 	max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
-	tcp_for_write_queue_from(skb, sk) {
+	skb_rbtree_walk_from(skb) {
 		__u8 sacked;
 		int segs;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
 		if (tcp_pacing_check(sk))
 			break;
 
@@ -2998,7 +3009,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += tcp_skb_pcount(skb);
 
-		if (skb == tcp_write_queue_head(sk) &&
+		if (skb == rtx_head &&
 		    icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  inet_csk(sk)->icsk_rto,
@@ -3040,12 +3051,15 @@ void tcp_send_fin(struct sock *sk)
 	 * Note: in the latter case, FIN packet will be sent after a timeout,
 	 * as TCP stack thinks it has already been transmitted.
 	 */
-	if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) {
+	if (!tskb && tcp_under_memory_pressure(sk))
+		tskb = skb_rb_last(&sk->tcp_rtx_queue);
+
+	if (tskb) {
 coalesce:
 		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
 		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
-		if (!tcp_send_head(sk)) {
+		if (tcp_write_queue_empty(sk)) {
 			/* This means tskb was already sent.
 			 * Pretend we included the FIN on previous transmit.
 			 * We need to set tp->snd_nxt to the value it would have
@@ -3062,6 +3076,7 @@ coalesce:
 				goto coalesce;
 			return;
 		}
+		INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_mem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
@@ -3098,6 +3113,11 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
+
+	/* skb of trace_tcp_send_reset() keeps the skb that caused RST,
+	 * skb here is different to the troublesome skb, so use NULL
+	 */
+	trace_tcp_send_reset(sk, NULL);
 }
 
 /* Send a crossed SYN-ACK during socket establishment.
@@ -3110,20 +3130,24 @@ int tcp_send_synack(struct sock *sk)
 {
 	struct sk_buff *skb;
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
-		pr_debug("%s: wrong queue state\n", __func__);
+		pr_err("%s: wrong queue state\n", __func__);
 		return -EFAULT;
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
 		if (skb_cloned(skb)) {
-			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
+			struct sk_buff *nskb;
+
+			tcp_skb_tsorted_save(skb) {
+				nskb = skb_copy(skb, GFP_ATOMIC);
+			} tcp_skb_tsorted_restore(skb);
 			if (!nskb)
 				return -ENOMEM;
-			tcp_unlink_write_queue(skb, sk);
+			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
-			__tcp_add_write_queue_head(sk, nskb);
-			sk_wmem_free_skb(sk, skb);
+			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
 			sk->sk_wmem_queued += nskb->truesize;
 			sk_mem_charge(sk, nskb->truesize);
 			skb = nskb;
@@ -3200,8 +3224,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
-	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
-			  sizeof(*th);
+	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
+					     foc) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3214,13 +3238,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	skb->mark = ireq->ir_mark;
-	/* Setting of flags are superfluous here for callers (and ECE is
-	 * not even correctly set)
-	 */
-	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
-			     TCPHDR_SYN | TCPHDR_ACK);
-
-	th->seq = htonl(TCP_SKB_CB(skb)->seq);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	th->seq = htonl(tcp_rsk(req)->snt_isn);
 	/* XXX data is queued and acked as is. No buffer/window check */
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
@@ -3307,7 +3326,7 @@ static void tcp_connect_init(struct sock *sk)
 	if (rcv_wnd == 0)
 		rcv_wnd = dst_metric(dst, RTAX_INITRWND);
 
-	tcp_select_initial_window(tcp_full_space(sk),
+	tcp_select_initial_window(sk, tcp_full_space(sk),
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
@@ -3346,7 +3365,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	tcb->end_seq += skb->len;
 	__skb_header_release(skb);
-	__tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
 	tp->write_seq = tcb->end_seq;
@@ -3394,6 +3412,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		int copied = copy_from_iter(skb_put(syn_data, space), space,
 					    &fo->data->msg_iter);
 		if (unlikely(!copied)) {
+			tcp_skb_tsorted_anchor_cleanup(syn_data);
 			kfree_skb(syn_data);
 			goto fallback;
 		}
@@ -3424,10 +3443,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
 	if (!err) {
 		tp->syn_data = (fo->copied > 0);
+		tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
 
+	/* data was not sent, put it in write_queue */
+	__skb_queue_tail(&sk->sk_write_queue, syn_data);
+	tp->packets_out -= tcp_skb_pcount(syn_data);
+
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
 	if (fo->cookie.len > 0)
@@ -3448,6 +3472,10 @@ int tcp_connect(struct sock *sk)
 	int err;
 
 	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
@@ -3464,6 +3492,7 @@ int tcp_connect(struct sock *sk)
 	tp->retrans_stamp = tcp_time_stamp(tp);
 	tcp_connect_queue_skb(sk, buff);
 	tcp_ecn_send_syn(sk, buff);
+	tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
 
 	/* Send off SYN; include data in Fast Open. */
 	err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
@@ -3476,6 +3505,11 @@ int tcp_connect(struct sock *sk)
 	 */
 	tp->snd_nxt = tp->write_seq;
 	tp->pushed_seq = tp->write_seq;
+	buff = tcp_send_head(sk);
+	if (unlikely(buff)) {
+		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
+	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
 
 	/* Timer for repeating the SYN until an answer. */
@@ -3653,7 +3687,8 @@ int tcp_write_wakeup(struct sock *sk, int mib)
 		    skb->len > mss) {
 			seg_size = min(seg_size, mss);
 			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-			if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
+			if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
+					 skb, seg_size, mss, GFP_ATOMIC))
 				return -1;
 		} else if (!tcp_skb_pcount(skb))
 			tcp_set_skb_tso_segs(skb, mss);
@@ -3683,7 +3718,7 @@ void tcp_send_probe0(struct sock *sk)
 
 	err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
 
-	if (tp->packets_out || !tcp_send_head(sk)) {
+	if (tp->packets_out || tcp_write_queue_empty(sk)) {
 		/* Cancel probe timer, if it is not required. */
 		icsk->icsk_probes_out = 0;
 		icsk->icsk_backoff = 0;
@@ -3724,6 +3759,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
 		if (unlikely(tcp_passive_fastopen(sk)))
 			tcp_sk(sk)->total_retrans++;
+		trace_tcp_retransmit_synack(sk, req);
 	}
 	return res;
 }
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f6c50af24a64..697f4c67b2e3 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -105,8 +105,9 @@ static inline int tcp_probe_avail(void)
  * Note: arguments must match tcp_rcv_established()!
  */
 static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-				 const struct tcphdr *th, unsigned int len)
+				 const struct tcphdr *th)
 {
+	unsigned int len = skb->len;
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_sock *inet = inet_sk(sk);
 
@@ -145,7 +146,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 				BUG();
 			}
 
-			p->length = skb->len;
+			p->length = len;
 			p->snd_nxt = tp->snd_nxt;
 			p->snd_una = tp->snd_una;
 			p->snd_cwnd = tp->snd_cwnd;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index fe9a493d0208..d3ea89020c69 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/tcp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOSS_DETECTION;
-
 static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -45,7 +44,8 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
+	u32 min_rtt = tcp_min_rtt(tp);
+	struct sk_buff *skb, *n;
 	u32 reo_wnd;
 
 	*reo_timeout = 0;
@@ -55,48 +55,36 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 	 * to queuing or delayed ACKs.
 	 */
 	reo_wnd = 1000;
-	if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U)
-		reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd);
+	if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) {
+		reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
+		reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
+	}
 
-	tcp_for_write_queue(skb, sk) {
+	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
+				 tcp_tsorted_anchor) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+		s32 remaining;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
-		/* Skip ones already (s)acked */
-		if (!after(scb->end_seq, tp->snd_una) ||
-		    scb->sacked & TCPCB_SACKED_ACKED)
+		/* Skip ones marked lost but not yet retransmitted */
+		if ((scb->sacked & TCPCB_LOST) &&
+		    !(scb->sacked & TCPCB_SACKED_RETRANS))
 			continue;
 
-		if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
-					tp->rack.end_seq, scb->end_seq)) {
-			/* Step 3 in draft-cheng-tcpm-rack-00.txt:
-			 * A packet is lost if its elapsed time is beyond
-			 * the recent RTT plus the reordering window.
-			 */
-			u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp,
-							 skb->skb_mstamp);
-			s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
-
-			if (remaining < 0) {
-				tcp_rack_mark_skb_lost(sk, skb);
-				continue;
-			}
-
-			/* Skip ones marked lost but not yet retransmitted */
-			if ((scb->sacked & TCPCB_LOST) &&
-			    !(scb->sacked & TCPCB_SACKED_RETRANS))
-				continue;
+		if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
+					 tp->rack.end_seq, scb->end_seq))
+			break;
 
+		/* A packet is lost if it has not been s/acked beyond
+		 * the recent RTT plus the reordering window.
+		 */
+		remaining = tp->rack.rtt_us + reo_wnd -
+			    tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+		if (remaining < 0) {
+			tcp_rack_mark_skb_lost(sk, skb);
+			list_del_init(&skb->tcp_tsorted_anchor);
+		} else {
 			/* Record maximum wait time (+1 to avoid 0) */
 			*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
-
-		} else if (!(scb->sacked & TCPCB_RETRANS)) {
-			/* Original data are sent sequentially so stop early
-			 * b/c the rest are all sent after rack_sent
-			 */
-			break;
 		}
 	}
 }
@@ -113,7 +101,7 @@ void tcp_rack_mark_lost(struct sock *sk)
 	tp->rack.advanced = 0;
 	tcp_rack_detect_loss(sk, &timeout);
 	if (timeout) {
-		timeout = usecs_to_jiffies(timeout + TCP_REO_TIMEOUT_MIN);
+		timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
 					  timeout, inet_csk(sk)->icsk_rto);
 	}
@@ -175,3 +163,44 @@ void tcp_rack_reo_timeout(struct sock *sk)
 	if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
 		tcp_rearm_rto(sk);
 }
+
+/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
+ *
+ * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
+ * by srtt), since there is possibility that spurious retransmission was
+ * due to reordering delay longer than reo_wnd.
+ *
+ * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
+ * no. of successful recoveries (accounts for full DSACK-based loss
+ * recovery undo). After that, reset it to default (min_rtt/4).
+ *
+ * At max, reo_wnd is incremented only once per rtt. So that the new
+ * DSACK on which we are reacting, is due to the spurious retx (approx)
+ * after the reo_wnd has been updated last time.
+ *
+ * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
+ * absolute value to account for change in rtt.
+ */
+void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+	    !rs->prior_delivered)
+		return;
+
+	/* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
+	if (before(rs->prior_delivered, tp->rack.last_delivered))
+		tp->rack.dsack_seen = 0;
+
+	/* Adjust the reo_wnd if update is pending */
+	if (tp->rack.dsack_seen) {
+		tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
+					       tp->rack.reo_wnd_steps + 1);
+		tp->rack.dsack_seen = 0;
+		tp->rack.last_delivered = tp->delivered;
+		tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
+	} else if (!tp->rack.reo_wnd_persist) {
+		tp->rack.reo_wnd_steps = 1;
+	}
+}
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index f2123075ce6e..addc122f8818 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -15,10 +15,6 @@
 #define TCP_SCALABLE_AI_CNT	50U
 #define TCP_SCALABLE_MD_SCALE	3
 
-struct scalable {
-	u32 loss_cwnd;
-};
-
 static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -36,23 +32,13 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 static u32 tcp_scalable_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct scalable *ca = inet_csk_ca(sk);
-
-	ca->loss_cwnd = tp->snd_cwnd;
 
 	return max(tp->snd_cwnd - (tp->snd_cwnd>>TCP_SCALABLE_MD_SCALE), 2U);
 }
 
-static u32 tcp_scalable_cwnd_undo(struct sock *sk)
-{
-	const struct scalable *ca = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
 static struct tcp_congestion_ops tcp_scalable __read_mostly = {
 	.ssthresh	= tcp_scalable_ssthresh,
-	.undo_cwnd	= tcp_scalable_cwnd_undo,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.cong_avoid	= tcp_scalable_cong_avoid,
 
 	.owner		= THIS_MODULE,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c0feeeef962a..16df6dd44b98 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,8 +22,6 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_thin_linear_timeouts __read_mostly;
-
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
@@ -109,26 +107,23 @@ static int tcp_orphan_retries(struct sock *sk, bool alive)
 
 static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 {
-	struct net *net = sock_net(sk);
+	const struct net *net = sock_net(sk);
+	int mss;
 
 	/* Black hole detection */
-	if (net->ipv4.sysctl_tcp_mtu_probing) {
-		if (!icsk->icsk_mtup.enabled) {
-			icsk->icsk_mtup.enabled = 1;
-			icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
-			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
-		} else {
-			struct net *net = sock_net(sk);
-			struct tcp_sock *tp = tcp_sk(sk);
-			int mss;
-
-			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
-			mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
-			mss = max(mss, 68 - tp->tcp_header_len);
-			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
-			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
-		}
+	if (!net->ipv4.sysctl_tcp_mtu_probing)
+		return;
+
+	if (!icsk->icsk_mtup.enabled) {
+		icsk->icsk_mtup.enabled = 1;
+		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
+	} else {
+		mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
+		mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
+		mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len);
+		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 	}
+	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 }
 
 
@@ -156,8 +151,13 @@ static bool retransmits_timed_out(struct sock *sk,
 		return false;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (unlikely(!start_ts))
-		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
+	if (unlikely(!start_ts)) {
+		struct sk_buff *head = tcp_rtx_queue_head(sk);
+
+		if (!head)
+			return false;
+		start_ts = tcp_skb_timestamp(head);
+	}
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
@@ -239,7 +239,6 @@ static int tcp_write_timeout(struct sock *sk)
 /* Called with BH disabled */
 void tcp_delack_timer_handler(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	sk_mem_reclaim_partial(sk);
@@ -254,17 +253,6 @@ void tcp_delack_timer_handler(struct sock *sk)
 	}
 	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
 
-	if (!skb_queue_empty(&tp->ucopy.prequeue)) {
-		struct sk_buff *skb;
-
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);
-
-		while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk_backlog_rcv(sk, skb);
-
-		tp->ucopy.memory = 0;
-	}
-
 	if (inet_csk_ack_scheduled(sk)) {
 		if (!icsk->icsk_ack.pingpong) {
 			/* Delayed ACK missed: inflate ATO. */
@@ -295,15 +283,17 @@ out:
  *
  *  Returns: Nothing (void)
  */
-static void tcp_delack_timer(unsigned long data)
+static void tcp_delack_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_delack_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
 	} else {
-		inet_csk(sk)->icsk_ack.blocked = 1;
+		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
@@ -316,11 +306,12 @@ static void tcp_delack_timer(unsigned long data)
 static void tcp_probe_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *skb = tcp_send_head(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int max_probes;
 	u32 start_ts;
 
-	if (tp->packets_out || !tcp_send_head(sk)) {
+	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
 		return;
 	}
@@ -333,9 +324,9 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	start_ts = tcp_skb_timestamp(tcp_send_head(sk));
+	start_ts = tcp_skb_timestamp(skb);
 	if (!start_ts)
-		tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp;
+		skb->skb_mstamp = tp->tcp_mstamp;
 	else if (icsk->icsk_user_timeout &&
 		 (s32)(tcp_time_stamp(tp) - start_ts) >
 		 jiffies_to_msecs(icsk->icsk_user_timeout))
@@ -420,7 +411,7 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (!tp->packets_out)
 		goto out;
 
-	WARN_ON(tcp_write_queue_empty(sk));
+	WARN_ON(tcp_rtx_queue_empty(sk));
 
 	tp->tlp_high_seq = 0;
 
@@ -453,7 +444,7 @@ void tcp_retransmit_timer(struct sock *sk)
 			goto out;
 		}
 		tcp_enter_loss(sk);
-		tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1);
+		tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1);
 		__sk_dst_reset(sk);
 		goto out_reset_timer;
 	}
@@ -485,7 +476,7 @@ void tcp_retransmit_timer(struct sock *sk)
 
 	tcp_enter_loss(sk);
 
-	if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) {
+	if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) {
 		/* Retransmission failed because of local congestion,
 		 * do not backoff.
 		 */
@@ -526,7 +517,7 @@ out_reset_timer:
 	 * linear-timeout retransmissions into a black hole
 	 */
 	if (sk->sk_state == TCP_ESTABLISHED &&
-	    (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) &&
+	    (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) &&
 	    tcp_stream_is_thin(tp) &&
 	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
 		icsk->icsk_backoff = 0;
@@ -582,9 +573,11 @@ out:
 	sk_mem_reclaim(sk);
 }
 
-static void tcp_write_timer(unsigned long data)
+static void tcp_write_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_retransmit_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
@@ -619,9 +612,9 @@ void tcp_set_keepalive(struct sock *sk, int val)
 EXPORT_SYMBOL_GPL(tcp_set_keepalive);
 
 
-static void tcp_keepalive_timer (unsigned long data)
+static void tcp_keepalive_timer (struct timer_list *t)
 {
-	struct sock *sk = (struct sock *) data;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 elapsed;
@@ -652,13 +645,14 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
+	if (!sock_flag(sk, SOCK_KEEPOPEN) ||
+	    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)))
 		goto out;
 
 	elapsed = keepalive_time_when(tp);
 
 	/* It is alive without keepalive 8) */
-	if (tp->packets_out || tcp_send_head(sk))
+	if (tp->packets_out || !tcp_write_queue_empty(sk))
 		goto resched;
 
 	elapsed = keepalive_time_elapsed(tp);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 2417f55374c5..6bb9e14c710a 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -122,14 +122,14 @@ int tcp_set_ulp(struct sock *sk, const char *name)
 
 	ulp_ops = __tcp_ulp_find_autoload(name);
 	if (!ulp_ops)
-		err = -ENOENT;
-	else
-		err = ulp_ops->init(sk);
+		return -ENOENT;
 
-	if (err)
-		goto out;
+	err = ulp_ops->init(sk);
+	if (err) {
+		module_put(ulp_ops->owner);
+		return err;
+	}
 
 	icsk->icsk_ulp_ops = ulp_ops;
- out:
-	return err;
+	return 0;
 }
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 218cfcc77650..ee113ff15fd0 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
 
 static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 {
-	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
+	return  min(tp->snd_ssthresh, tp->snd_cwnd);
 }
 
 static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index 248cfc0ff9ae..4f24d0e37d9c 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * TCP Vegas congestion control interface
  */
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 76005d4b8dfc..6fcf482d611b 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -30,7 +30,6 @@ struct veno {
 	u32 basertt;		/* the min of all Veno rtt measurements seen (in usec) */
 	u32 inc;		/* decide whether to increase cwnd */
 	u32 diff;		/* calculate the diff rate */
-	u32 loss_cwnd;		/* cwnd when loss occured */
 };
 
 /* There are several situations when we must "re-start" Veno:
@@ -194,7 +193,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct veno *veno = inet_csk_ca(sk);
 
-	veno->loss_cwnd = tp->snd_cwnd;
 	if (veno->diff < beta)
 		/* in "non-congestive state", cut cwnd by 1/5 */
 		return max(tp->snd_cwnd * 4 / 5, 2U);
@@ -203,17 +201,10 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
 		return max(tp->snd_cwnd >> 1U, 2U);
 }
 
-static u32 tcp_veno_cwnd_undo(struct sock *sk)
-{
-	const struct veno *veno = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, veno->loss_cwnd);
-}
-
 static struct tcp_congestion_ops tcp_veno __read_mostly = {
 	.init		= tcp_veno_init,
 	.ssthresh	= tcp_veno_ssthresh,
-	.undo_cwnd	= tcp_veno_cwnd_undo,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
 	.cong_avoid	= tcp_veno_cong_avoid,
 	.pkts_acked	= tcp_veno_pkts_acked,
 	.set_state	= tcp_veno_state,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index e6ff99c4bd3b..96e829b2e2fc 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -37,7 +37,6 @@ struct yeah {
 	u32 fast_count;
 
 	u32 pkts_acked;
-	u32 loss_cwnd;
 };
 
 static void tcp_yeah_init(struct sock *sk)
@@ -220,22 +219,14 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
-	yeah->loss_cwnd = tp->snd_cwnd;
 
 	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
-static u32 tcp_yeah_cwnd_undo(struct sock *sk)
-{
-	const struct yeah *yeah = inet_csk_ca(sk);
-
-	return max(tcp_sk(sk)->snd_cwnd, yeah->loss_cwnd);
-}
-
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
 	.init		= tcp_yeah_init,
 	.ssthresh	= tcp_yeah_ssthresh,
-	.undo_cwnd      = tcp_yeah_cwnd_undo,
+	.undo_cwnd      = tcp_reno_undo_cwnd,
 	.cong_avoid	= tcp_yeah_cong_avoid,
 	.set_state	= tcp_vegas_state,
 	.cwnd_event	= tcp_vegas_cwnd_event,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b057653ceca9..e4ff25c947c5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		}
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 /**
@@ -380,8 +377,8 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 
 static int compute_score(struct sock *sk, struct net *net,
 			 __be32 saddr, __be16 sport,
-			 __be32 daddr, unsigned short hnum, int dif,
-			 bool exact_dif)
+			 __be32 daddr, unsigned short hnum,
+			 int dif, int sdif, bool exact_dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -413,10 +410,15 @@ static int compute_score(struct sock *sk, struct net *net,
 	}
 
 	if (sk->sk_bound_dev_if || exact_dif) {
-		if (sk->sk_bound_dev_if != dif)
+		bool dev_match = (sk->sk_bound_dev_if == dif ||
+				  sk->sk_bound_dev_if == sdif);
+
+		if (exact_dif && !dev_match)
 			return -1;
-		score += 4;
+		if (sk->sk_bound_dev_if && dev_match)
+			score += 4;
 	}
+
 	if (sk->sk_incoming_cpu == raw_smp_processor_id())
 		score++;
 	return score;
@@ -436,10 +438,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 
 /* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
-		__be32 saddr, __be16 sport,
-		__be32 daddr, unsigned int hnum, int dif, bool exact_dif,
-		struct udp_hslot *hslot2,
-		struct sk_buff *skb)
+				     __be32 saddr, __be16 sport,
+				     __be32 daddr, unsigned int hnum,
+				     int dif, int sdif, bool exact_dif,
+				     struct udp_hslot *hslot2,
+				     struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	int score, badness, matches = 0, reuseport = 0;
@@ -449,7 +452,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, exact_dif);
+				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -477,8 +480,8 @@ static struct sock *udp4_lib_lookup2(struct net *net,
  * harder than this. -DaveM
  */
 struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
-		__be16 sport, __be32 daddr, __be16 dport,
-		int dif, struct udp_table *udptable, struct sk_buff *skb)
+		__be16 sport, __be32 daddr, __be16 dport, int dif,
+		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	unsigned short hnum = ntohs(dport);
@@ -496,7 +499,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 			goto begin;
 
 		result = udp4_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif,
+					  daddr, hnum, dif, sdif,
 					  exact_dif, hslot2, skb);
 		if (!result) {
 			unsigned int old_slot2 = slot2;
@@ -511,7 +514,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 				goto begin;
 
 			result = udp4_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif,
+						  daddr, hnum, dif, sdif,
 						  exact_dif, hslot2, skb);
 		}
 		return result;
@@ -521,7 +524,7 @@ begin:
 	badness = 0;
 	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, exact_dif);
+				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -554,7 +557,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 
 	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
 				 iph->daddr, dport, inet_iif(skb),
-				 udptable, skb);
+				 inet_sdif(skb), udptable, skb);
 }
 
 struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
@@ -576,7 +579,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 	struct sock *sk;
 
 	sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
-			       dif, &udp_table, NULL);
+			       dif, 0, &udp_table, NULL);
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
 	return sk;
@@ -587,7 +590,7 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 				       __be16 loc_port, __be32 loc_addr,
 				       __be16 rmt_port, __be32 rmt_addr,
-				       int dif, unsigned short hnum)
+				       int dif, int sdif, unsigned short hnum)
 {
 	struct inet_sock *inet = inet_sk(sk);
 
@@ -597,9 +600,10 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
 	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
 	    ipv6_only_sock(sk) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
+	     sk->sk_bound_dev_if != sdif))
 		return false;
-	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))
 		return false;
 	return true;
 }
@@ -628,8 +632,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	struct net *net = dev_net(skb->dev);
 
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
-			iph->saddr, uh->source, skb->dev->ifindex, udptable,
-			NULL);
+			       iph->saddr, uh->source, skb->dev->ifindex, 0,
+			       udptable, NULL);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;	/* No socket for error */
@@ -802,7 +806,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx) {			 /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -1054,7 +1058,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		net_dbg_ratelimited("cork app bug 2\n");
+		net_dbg_ratelimited("socket already corked\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1137,7 +1141,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	if (unlikely(!up->pending)) {
 		release_sock(sk);
 
-		net_dbg_ratelimited("udp cork app bug 3\n");
+		net_dbg_ratelimited("cork failed\n");
 		return -EINVAL;
 	}
 
@@ -1163,34 +1167,36 @@ out:
 	return ret;
 }
 
-#if BITS_PER_LONG == 64
+#define UDP_SKB_IS_STATELESS 0x80000000
+
 static void udp_set_dev_scratch(struct sk_buff *skb)
 {
-	struct udp_dev_scratch *scratch;
+	struct udp_dev_scratch *scratch = udp_skb_scratch(skb);
 
 	BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long));
-	scratch = (struct udp_dev_scratch *)&skb->dev_scratch;
-	scratch->truesize = skb->truesize;
+	scratch->_tsize_state = skb->truesize;
+#if BITS_PER_LONG == 64
 	scratch->len = skb->len;
 	scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
 	scratch->is_linear = !skb_is_nonlinear(skb);
+#endif
+	/* all head states execept sp (dst, sk, nf) are always cleared by
+	 * udp_rcv() and we need to preserve secpath, if present, to eventually
+	 * process IP_CMSG_PASSSEC at recvmsg() time
+	 */
+	if (likely(!skb_sec_path(skb)))
+		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
 static int udp_skb_truesize(struct sk_buff *skb)
 {
-	return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize;
-}
-#else
-static void udp_set_dev_scratch(struct sk_buff *skb)
-{
-	skb->dev_scratch = skb->truesize;
+	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
 }
 
-static int udp_skb_truesize(struct sk_buff *skb)
+static bool udp_skb_has_head_state(struct sk_buff *skb)
 {
-	return skb->dev_scratch;
+	return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS);
 }
-#endif
 
 /* fully reclaim rmem/fwd memory allocated for skb */
 static void udp_rmem_release(struct sock *sk, int size, int partial,
@@ -1203,8 +1209,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2) &&
-		    !skb_queue_empty(&up->reader_queue))
+		if (size < (sk->sk_rcvbuf >> 2))
 			return;
 	} else {
 		size += up->forward_deficit;
@@ -1388,12 +1393,15 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		unlock_sock_fast(sk, slow);
 	}
 
-	/* we cleared the head states previously only if the skb lacks any IP
-	 * options, see __udp_queue_rcv_skb().
+	if (!skb_unref(skb))
+		return;
+
+	/* In the more common cases we cleared the head states previously,
+	 * see __udp_queue_rcv_skb().
 	 */
-	if (unlikely(IPCB(skb)->opt.optlen > 0))
+	if (unlikely(udp_skb_has_head_state(skb)))
 		skb_release_head_state(skb);
-	consume_stateless_skb(skb);
+	__consume_stateless_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_consume_udp);
 
@@ -1576,7 +1584,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
-	peeking = off = sk_peek_offset(sk, flags);
+	peeking = flags & MSG_PEEK;
+	off = sk_peek_offset(sk, flags);
 	skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
 	if (!skb)
 		return err;
@@ -1784,13 +1793,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id_once(sk, skb);
 	}
 
-	/* At recvmsg() time we need skb->dst to process IP options-related
-	 * cmsg, elsewhere can we clear all pending head states while they are
-	 * hot in the cache
-	 */
-	if (likely(IPCB(skb)->opt.optlen == 0))
-		skb_release_head_state(skb);
-
 	rc = __udp_enqueue_schedule_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
@@ -1811,8 +1813,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 static struct static_key udp_encap_needed __read_mostly;
 void udp_encap_enable(void)
 {
-	if (!static_key_enabled(&udp_encap_needed))
-		static_key_slow_inc(&udp_encap_needed);
+	static_key_enable(&udp_encap_needed);
 }
 EXPORT_SYMBOL(udp_encap_enable);
 
@@ -1851,7 +1852,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 */
 
 		/* if we're overly short, let UDP handle it */
-		encap_rcv = ACCESS_ONCE(up->encap_rcv);
+		encap_rcv = READ_ONCE(up->encap_rcv);
 		if (encap_rcv) {
 			int ret;
 
@@ -1930,15 +1931,18 @@ drop:
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
 	if (dst_hold_safe(dst)) {
 		old = xchg(&sk->sk_rx_dst, dst);
 		dst_release(old);
+		return old != dst;
 	}
+	return false;
 }
+EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
 /*
  *	Multicasts and broadcasts go to each listener.
@@ -1957,6 +1961,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
 	unsigned int offset = offsetof(typeof(*sk), sk_node);
 	int dif = skb->dev->ifindex;
+	int sdif = inet_sdif(skb);
 	struct hlist_node *node;
 	struct sk_buff *nskb;
 
@@ -1971,7 +1976,7 @@ start_lookup:
 
 	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
 		if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr,
-					 uh->source, saddr, dif, hnum))
+					 uh->source, saddr, dif, sdif, hnum))
 			continue;
 
 		if (!first) {
@@ -2161,7 +2166,7 @@ drop:
 static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 						  __be16 loc_port, __be32 loc_addr,
 						  __be16 rmt_port, __be32 rmt_addr,
-						  int dif)
+						  int dif, int sdif)
 {
 	struct sock *sk, *result;
 	unsigned short hnum = ntohs(loc_port);
@@ -2175,7 +2180,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	result = NULL;
 	sk_for_each_rcu(sk, &hslot->head) {
 		if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr,
-					rmt_port, rmt_addr, dif, hnum)) {
+					rmt_port, rmt_addr, dif, sdif, hnum)) {
 			if (result)
 				return NULL;
 			result = sk;
@@ -2192,7 +2197,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 static struct sock *__udp4_lib_demux_lookup(struct net *net,
 					    __be16 loc_port, __be32 loc_addr,
 					    __be16 rmt_port, __be32 rmt_addr,
-					    int dif)
+					    int dif, int sdif)
 {
 	unsigned short hnum = ntohs(loc_port);
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
@@ -2204,7 +2209,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		if (INET_MATCH(sk, net, acookie, rmt_addr,
-			       loc_addr, ports, dif))
+			       loc_addr, ports, dif, sdif))
 			return sk;
 		/* Only check first socket in chain */
 		break;
@@ -2212,47 +2217,46 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	return NULL;
 }
 
-void udp_v4_early_demux(struct sk_buff *skb)
+int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct in_device *in_dev = NULL;
 	const struct iphdr *iph;
 	const struct udphdr *uh;
 	struct sock *sk = NULL;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int sdif = inet_sdif(skb);
 	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	uh = udp_hdr(skb);
 
-	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST) {
-		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+	if (skb->pkt_type == PACKET_MULTICAST) {
+		in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
-			return;
+			return 0;
 
-		/* we are supposed to accept bcast packets */
-		if (skb->pkt_type == PACKET_MULTICAST) {
-			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-					       iph->protocol);
-			if (!ours)
-				return;
-		}
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return 0;
 
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
-						   uh->source, iph->saddr, dif);
+						   uh->source, iph->saddr,
+						   dif, sdif);
 	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
-					     uh->source, iph->saddr, dif);
+					     uh->source, iph->saddr, dif, sdif);
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
-		return;
+		return 0;
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
@@ -2261,12 +2265,23 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	if (dst)
 		dst = dst_check(dst, 0);
 	if (dst) {
+		u32 itag = 0;
+
 		/* set noref for now.
 		 * any place which wants to hold dst has to call
 		 * dst_hold_safe()
 		 */
 		skb_dst_set_noref(skb, dst);
+
+		/* for unconnected multicast sockets we need to validate
+		 * the source on each packet
+		 */
+		if (!inet_sk(sk)->inet_daddr && in_dev)
+			return ip_mc_validate_source(skb, iph->daddr,
+						     iph->saddr, iph->tos,
+						     skb->dev, in_dev, &itag);
 	}
+	return 0;
 }
 
 int udp_rcv(struct sk_buff *skb)
@@ -2282,7 +2297,7 @@ void udp_destroy_sock(struct sock *sk)
 	unlock_sock_fast(sk, slow);
 	if (static_key_false(&udp_encap_needed) && up->encap_type) {
 		void (*encap_destroy)(struct sock *sk);
-		encap_destroy = ACCESS_ONCE(up->encap_destroy);
+		encap_destroy = READ_ONCE(up->encap_destroy);
 		if (encap_destroy)
 			encap_destroy(sk);
 	}
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 4515836d2a3a..d0390d844ac8 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -45,7 +45,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		sk = __udp4_lib_lookup(net,
 				req->id.idiag_src[0], req->id.idiag_sport,
 				req->id.idiag_dst[0], req->id.idiag_dport,
-				req->id.idiag_if, tbl, NULL);
+				req->id.idiag_if, 0, tbl, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (req->sdiag_family == AF_INET6)
 		sk = __udp6_lib_lookup(net,
@@ -53,7 +53,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 				req->id.idiag_sport,
 				(struct in6_addr *)req->id.idiag_dst,
 				req->id.idiag_dport,
-				req->id.idiag_if, tbl, NULL);
+				req->id.idiag_if, 0, tbl, NULL);
 #endif
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
@@ -182,7 +182,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
 		sk = __udp4_lib_lookup(net,
 				req->id.idiag_dst[0], req->id.idiag_dport,
 				req->id.idiag_src[0], req->id.idiag_sport,
-				req->id.idiag_if, tbl, NULL);
+				req->id.idiag_if, 0, tbl, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (req->sdiag_family == AF_INET6) {
 		if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
@@ -190,7 +190,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
 			sk = __udp4_lib_lookup(net,
 					req->id.idiag_dst[3], req->id.idiag_dport,
 					req->id.idiag_src[3], req->id.idiag_sport,
-					req->id.idiag_if, tbl, NULL);
+					req->id.idiag_if, 0, tbl, NULL);
 
 		else
 			sk = __udp6_lib_lookup(net,
@@ -198,7 +198,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
 					req->id.idiag_dport,
 					(struct in6_addr *)req->id.idiag_src,
 					req->id.idiag_sport,
-					req->id.idiag_if, tbl, NULL);
+					req->id.idiag_if, 0, tbl, NULL);
 	}
 #endif
 	else {
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index a8cf8c6fb60c..e7d18b140287 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _UDP4_IMPL_H
 #define _UDP4_IMPL_H
 #include <net/udp.h>
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 781250151d40..01801b77bd0d 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -21,7 +21,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	__be16 new_protocol, bool is_ipv6)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
-	bool remcsum, need_csum, offload_csum, ufo, gso_partial;
+	bool remcsum, need_csum, offload_csum, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct udphdr *uh = udp_hdr(skb);
 	u16 mac_offset = skb->mac_header;
@@ -61,8 +61,6 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
 	skb->remcsum_offload = remcsum;
 
-	ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
-
 	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
 	/* Try to offload checksum if possible */
 	offload_csum = !!(need_csum &&
@@ -77,7 +75,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	 * outer one so strip the existing checksum feature flags and
 	 * instead set the flag based on our outer checksum offload value.
 	 */
-	if (remcsum || ufo) {
+	if (remcsum) {
 		features &= ~NETIF_F_CSUM_MASK;
 		if (!need_csum || offload_csum)
 			features |= NETIF_F_HW_CSUM;
@@ -122,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		 * will be using a length value equal to only one MSS sized
 		 * segment instead of the entire frame.
 		 */
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);
@@ -212,15 +210,6 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (unlikely(skb->len <= mss))
 		goto out;
 
-	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
-		/* Packet is from an untrusted source, reset gso_segs. */
-
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
-
-		segs = NULL;
-		goto out;
-	}
-
 	/* Do software UFO. Complete and fill in the UDP checksum as
 	 * HW cannot do checksum of UDP packets sent as multiple
 	 * IP fragments.
@@ -235,7 +224,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	/* If there is no outer header we can fake a checksum offload
 	 * due to the fact that we have already done the checksum in
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 58bd39fb14b4..6539ff15e9a3 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -82,7 +82,8 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct udp_tunnel_info ti;
 
-	if (!dev->netdev_ops->ndo_udp_tunnel_add)
+	if (!dev->netdev_ops->ndo_udp_tunnel_add ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
 		return;
 
 	ti.type = type;
@@ -93,6 +94,24 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
 
+void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_del ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port);
+
 /* Notify netdevs that UDP port started listening */
 void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
 {
@@ -109,6 +128,8 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
 	for_each_netdev_rcu(net, dev) {
 		if (!dev->netdev_ops->ndo_udp_tunnel_add)
 			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
 		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
 	}
 	rcu_read_unlock();
@@ -131,6 +152,8 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
 	for_each_netdev_rcu(net, dev) {
 		if (!dev->netdev_ops->ndo_udp_tunnel_del)
 			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
 		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
 	}
 	rcu_read_unlock();
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 1fc684111ce6..e50b7fea57ee 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * xfrm4_input.c
  *
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 71b4ecc195c7..05017e2c849c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * xfrm4_policy.c
  *
@@ -20,7 +21,8 @@
 static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 					    int tos, int oif,
 					    const xfrm_address_t *saddr,
-					    const xfrm_address_t *daddr)
+					    const xfrm_address_t *daddr,
+					    u32 mark)
 {
 	struct rtable *rt;
 
@@ -28,6 +30,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 	fl4->daddr = daddr->a4;
 	fl4->flowi4_tos = tos;
 	fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
+	fl4->flowi4_mark = mark;
 	if (saddr)
 		fl4->saddr = saddr->a4;
 
@@ -42,20 +45,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 
 static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
 					  const xfrm_address_t *saddr,
-					  const xfrm_address_t *daddr)
+					  const xfrm_address_t *daddr,
+					  u32 mark)
 {
 	struct flowi4 fl4;
 
-	return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr);
+	return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark);
 }
 
 static int xfrm4_get_saddr(struct net *net, int oif,
-			   xfrm_address_t *saddr, xfrm_address_t *daddr)
+			   xfrm_address_t *saddr, xfrm_address_t *daddr,
+			   u32 mark)
 {
 	struct dst_entry *dst;
 	struct flowi4 fl4;
 
-	dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr);
+	dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark);
 	if (IS_ERR(dst))
 		return -EHOSTUNREACH;
 
@@ -213,14 +218,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	fl4->flowi4_tos = iph->tos;
 }
 
-static inline int xfrm4_garbage_collect(struct dst_ops *ops)
-{
-	struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
-
-	xfrm_garbage_collect_deferred(net);
-	return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
-}
-
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
 			      struct sk_buff *skb, u32 mtu)
 {
@@ -259,14 +256,13 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
-	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
 	.redirect =		xfrm4_redirect,
 	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
 	.local_out =		__ip_local_out,
-	.gc_thresh =		INT_MAX,
+	.gc_thresh =		32768,
 };
 
 static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index d6660a8c0ea5..80c40b4981bb 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * xfrm4_state.c
  *