23 files changed, 139 insertions, 73 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f60fe82..b5116ec 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1693,6 +1693,13 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
 
+	/* 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;
 }
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index f2a7102..22377c8 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -270,6 +270,9 @@ static void ah_input_done(struct crypto_async_request *base, int err)
 	int ihl = ip_hdrlen(skb);
 	int ah_hlen = (ah->hdrlen + 2) << 2;
 
+	if (err)
+		goto out;
+
 	work_iph = AH_SKB_CB(skb)->tmp;
 	auth_data = ah_tmp_auth(work_iph, ihl);
 	icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3d92534..968d8e1 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1319,13 +1319,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	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);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	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);
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 7563831..38c1c97 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1044,15 +1044,17 @@ 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;
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
 		atomic_set(&fi->fib_metrics->refcnt, 1);
-	} else
+	} 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;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1bc623d..08575e3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1112,6 +1112,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
 	if (!pmc)
 		return;
+	spin_lock_init(&pmc->lock);
 	spin_lock_bh(&im->lock);
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
@@ -2071,21 +2072,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 
 static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
-	struct ip_sf_list *psf, *nextpsf;
+	struct ip_sf_list *psf, *nextpsf, *tomb, *sources;
 
-	for (psf = pmc->tomb; psf; psf = nextpsf) {
+	spin_lock_bh(&pmc->lock);
+	tomb = pmc->tomb;
+	pmc->tomb = NULL;
+	sources = pmc->sources;
+	pmc->sources = NULL;
+	pmc->sfmode = MCAST_EXCLUDE;
+	pmc->sfcount[MCAST_INCLUDE] = 0;
+	pmc->sfcount[MCAST_EXCLUDE] = 1;
+	spin_unlock_bh(&pmc->lock);
+
+	for (psf = tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->tomb = NULL;
-	for (psf = pmc->sources; psf; psf = nextpsf) {
+	for (psf = sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->sources = NULL;
-	pmc->sfmode = MCAST_EXCLUDE;
-	pmc->sfcount[MCAST_INCLUDE] = 0;
-	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
 /* Join a multicast group
@@ -2968,12 +2974,6 @@ 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_fragment.c b/net/ipv4/inet_fragment.c
index b5e9317..631c0d0 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -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);
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72..453db95 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -835,8 +835,6 @@ 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
@@ -862,13 +860,9 @@ 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_output.c b/net/ipv4/ip_output.c
index e5c1dbe..2c3c1a2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -936,10 +936,12 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    ((length > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
+	    (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);
@@ -1255,6 +1257,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		return -EINVAL;
 
 	if ((size + skb->len > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) == 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
 		if (skb->ip_summed != CHECKSUM_PARTIAL)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5719d6b..bd7f183 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -609,8 +609,8 @@ 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++;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5d7944f..b120b9b 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;
 
@@ -229,7 +230,7 @@ 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;
 
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index b3cc133..c0cc6aa 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -23,7 +23,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+	const struct sock *sk = skb_to_full_sk(skb);
+	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
@@ -40,7 +41,7 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	fl4.daddr = iph->daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_tos = RT_TOS(iph->tos);
-	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+	fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
 	if (!fl4.flowi4_oif)
 		fl4.flowi4_oif = l3mdev_master_ifindex(dev);
 	fl4.flowi4_mark = skb->mark;
@@ -61,7 +62,7 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
 		struct dst_entry *dst = skb_dst(skb);
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), sk, 0);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index c9b52c3..5a8f7c3 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1304,6 +1304,7 @@ static int __init nf_nat_snmp_basic_init(void)
 static void __exit nf_nat_snmp_basic_fini(void)
 {
 	RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+	synchronize_rcu();
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fd82202..146d861 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -126,6 +126,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	/* ip_route_me_harder expects skb->dst to be set */
 	skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+	nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
+
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   ip4_dst_hoplimit(skb_dst(nskb)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6cd49fd..6a5b778 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1247,7 +1247,7 @@ 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)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3c4043..b6f710d 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -334,6 +334,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b..566cfc5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -958,7 +958,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_notsent_lowat,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_douintvec,
 	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 86fbf0f..6b3d27e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2297,9 +2297,15 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
+	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+	 * 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);
+	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0ea66c2..cb8db34 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -83,7 +83,8 @@ struct bbr {
 		cwnd_gain:10,	/* current gain for setting cwnd */
 		full_bw_cnt:3,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
-		unused_b:6;
+		has_seen_rtt:1, /* have we seen an RTT sample yet? */
+		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
 };
@@ -182,6 +183,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 	return rate >> BW_SCALE;
 }
 
+/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
+static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	u64 rate = bw;
+
+	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
+	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+	return rate;
+}
+
+/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
+static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u64 bw;
+	u32 rtt_us;
+
+	if (tp->srtt_us) {		/* any RTT sample yet? */
+		rtt_us = max(tp->srtt_us >> 3, 1U);
+		bbr->has_seen_rtt = 1;
+	} else {			 /* no RTT sample yet */
+		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
+	}
+	bw = (u64)tp->snd_cwnd * BW_UNIT;
+	do_div(bw, rtt_us);
+	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -191,12 +221,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 rate = bw;
+	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
-	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
-	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
-	if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate)
+	if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
+		bbr_init_pacing_rate_from_rtt(sk);
+	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
 
@@ -769,7 +800,6 @@ static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 bw;
 
 	bbr->prior_cwnd = 0;
 	bbr->tso_segs_goal = 0;	 /* default segs per skb until first ACK */
@@ -785,11 +815,8 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
-	bw = (u64)tp->snd_cwnd * BW_UNIT;
-	do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC);
-	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
-	bbr_set_pacing_rate(sk, bw, bbr_high_gain);
+	bbr->has_seen_rtt = 0;
+	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 01336aa..c038507 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2560,8 +2560,8 @@ 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_time_stamp;
 	}
@@ -3036,8 +3036,7 @@ void tcp_rearm_rto(struct sock *sk)
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta > 0)
-				rto = delta;
+			rto = max(delta, 1);
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc4258f..8592070 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -914,6 +914,7 @@ 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;
@@ -922,11 +923,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	tp = tcp_sk(sk);
 
 	if (clone_it) {
-		skb_mstamp_get(&skb->skb_mstamp);
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
-		tcp_rate_skb_sent(sk, skb);
-
+		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
@@ -934,6 +933,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb_mstamp_get(&skb->skb_mstamp);
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1035,12 +1035,15 @@ 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) {
+		skb_mstamp_get(&oskb->skb_mstamp);
+		tcp_rate_skb_sent(sk, oskb);
+	}
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -2709,10 +2712,11 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb_mstamp_get(&skb->skb_mstamp);
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
+		if (!err)
+			skb_mstamp_get(&skb->skb_mstamp);
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
@@ -3325,6 +3329,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto done;
 	}
 
+	/* data was not sent, this is our new send_head */
+	sk->sk_send_head = 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)
@@ -3344,6 +3352,9 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
@@ -3371,6 +3382,11 @@ 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. */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b1e65b3..74db43b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -654,7 +654,8 @@ 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);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5bab6c3..4363b1e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -813,7 +813,7 @@ 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 && !skb_is_gso(skb)) {   /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b2be1d9..0932c85 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	u16 mac_len = skb->mac_len;
 	int udp_offset, outer_hlen;
 	__wsum partial;
+	bool need_ipsec;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
@@ -62,8 +63,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	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 &&
+			  !need_ipsec &&
 			  (skb->dev->features &
 			   (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
 				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
@@ -232,7 +235,7 @@ 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