Merge remote-tracking branch 'net-next/master' into mac80211-next

Resolve the merge conflict between Felix's/my and Toke's patches
coming into the tree through net and mac80211-next respectively.
Most of Felix's changes go away due to Toke's new infrastructure
work, my patch changes to "goto begin" (the label wasn't there
before) instead of returning NULL so flow control towards drivers
is preserved better.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

33 files changed, 1534 insertions, 343 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 50d6a9b..300b068 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -640,6 +640,21 @@ config TCP_CONG_CDG
 	  D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
 	  delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
 
+config TCP_CONG_BBR
+	tristate "BBR TCP"
+	default n
+	---help---
+
+	BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
+	maximize network utilization and minimize queues. It builds an explicit
+	model of the the bottleneck delivery rate and path round-trip
+	propagation delay. It tolerates packet loss and delay unrelated to
+	congestion. It can operate over LAN, WAN, cellular, wifi, or cable
+	modem links. It can coexist with flows that use loss-based congestion
+	control, and can operate with shallow buffers, deep buffers,
+	bufferbloat, policers, or AQM schemes that do not provide a delay
+	signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+
 choice
 	prompt "Default TCP congestion control"
 	default DEFAULT_CUBIC
@@ -674,6 +689,9 @@ choice
 	config DEFAULT_CDG
 		bool "CDG" if TCP_CONG_CDG=y
 
+	config DEFAULT_BBR
+		bool "BBR" if TCP_CONG_BBR=y
+
 	config DEFAULT_RENO
 		bool "Reno"
 endchoice
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 24629b6..bc6a6c8 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -8,7 +8,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_timewait_sock.o inet_connection_sock.o \
 	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
 	     tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
-	     tcp_recovery.o \
+	     tcp_rate.o tcp_recovery.o \
 	     tcp_offload.o datagram.o raw.o udp.o udplite.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
@@ -41,6 +41,7 @@ obj-$(CONFIG_INET_DIAG) += inet_diag.o
 obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
 obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
 obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
+obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
 obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
 obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
 obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e94b47b..1effc98 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1192,7 +1192,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
-	bool udpfrag = false, fixedid = false, encap;
+	bool udpfrag = false, fixedid = false, gso_partial, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
 	unsigned int offset = 0;
@@ -1245,6 +1245,8 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	if (IS_ERR_OR_NULL(segs))
 		goto out;
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	skb = segs;
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
@@ -1259,9 +1261,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				iph->id = htons(id);
 				id += skb_shinfo(skb)->gso_segs;
 			}
-			tot_len = skb_shinfo(skb)->gso_size +
-				  SKB_GSO_CB(skb)->data_offset +
-				  skb->head - (unsigned char *)iph;
+
+			if (gso_partial)
+				tot_len = skb_shinfo(skb)->gso_size +
+					  SKB_GSO_CB(skb)->data_offset +
+					  skb->head - (unsigned char *)iph;
+			else
+				tot_len = skb->len - nhoff;
 		} else {
 			if (!fixedid)
 				iph->id = htons(id++);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4e56a4c..c3b8047 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -182,26 +182,13 @@ static void fib_flush(struct net *net)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
-			flushed += fib_table_flush(tb);
+			flushed += fib_table_flush(net, tb);
 	}
 
 	if (flushed)
 		rt_cache_flush(net);
 }
 
-void fib_flush_external(struct net *net)
-{
-	struct fib_table *tb;
-	struct hlist_head *head;
-	unsigned int h;
-
-	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
-		head = &net->ipv4.fib_table_hash[h];
-		hlist_for_each_entry(tb, head, tb_hlist)
-			fib_table_flush_external(tb);
-	}
-}
-
 /*
  * Find address type as if only "dev" was present in the system. If
  * on_dev is NULL then all interfaces are taken into consideration.
@@ -590,13 +577,13 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 			if (cmd == SIOCDELRT) {
 				tb = fib_get_table(net, cfg.fc_table);
 				if (tb)
-					err = fib_table_delete(tb, &cfg);
+					err = fib_table_delete(net, tb, &cfg);
 				else
 					err = -ESRCH;
 			} else {
 				tb = fib_new_table(net, cfg.fc_table);
 				if (tb)
-					err = fib_table_insert(tb, &cfg);
+					err = fib_table_insert(net, tb, &cfg);
 				else
 					err = -ENOBUFS;
 			}
@@ -719,7 +706,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = fib_table_delete(tb, &cfg);
+	err = fib_table_delete(net, tb, &cfg);
 errout:
 	return err;
 }
@@ -741,7 +728,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = fib_table_insert(tb, &cfg);
+	err = fib_table_insert(net, tb, &cfg);
 errout:
 	return err;
 }
@@ -828,9 +815,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
 		cfg.fc_scope = RT_SCOPE_HOST;
 
 	if (cmd == RTM_NEWROUTE)
-		fib_table_insert(tb, &cfg);
+		fib_table_insert(net, tb, &cfg);
 	else
-		fib_table_delete(tb, &cfg);
+		fib_table_delete(net, tb, &cfg);
 }
 
 void fib_add_ifaddr(struct in_ifaddr *ifa)
@@ -1254,7 +1241,7 @@ static void ip_fib_net_exit(struct net *net)
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
 			hlist_del(&tb->tb_hlist);
-			fib_table_flush(tb);
+			fib_table_flush(net, tb);
 			fib_free_table(tb);
 		}
 	}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 770bebe..2e50062 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -164,6 +164,14 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int call_fib_rule_notifiers(struct net *net,
+				   enum fib_event_type event_type)
+{
+	struct fib_notifier_info info;
+
+	return call_fib_notifiers(net, event_type, &info);
+}
+
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
 	FRA_GENERIC_POLICY,
 	[FRA_FLOW]	= { .type = NLA_U32 },
@@ -220,7 +228,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
-	fib_flush_external(rule->fr_net);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
 
 	err = 0;
 errout:
@@ -242,7 +250,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
-	fib_flush_external(rule->fr_net);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 241f27b..31cef36 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -73,6 +73,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/vmalloc.h>
+#include <linux/notifier.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/protocol.h>
@@ -80,10 +81,47 @@
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <net/ip_fib.h>
-#include <net/switchdev.h>
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
+static BLOCKING_NOTIFIER_HEAD(fib_chain);
+
+int register_fib_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&fib_chain, nb);
+}
+EXPORT_SYMBOL(register_fib_notifier);
+
+int unregister_fib_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&fib_chain, nb);
+}
+EXPORT_SYMBOL(unregister_fib_notifier);
+
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
+{
+	info->net = net;
+	return blocking_notifier_call_chain(&fib_chain, event_type, 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, u32 nlflags)
+{
+	struct fib_entry_notifier_info info = {
+		.dst = dst,
+		.dst_len = dst_len,
+		.fi = fi,
+		.tos = tos,
+		.type = type,
+		.tb_id = tb_id,
+		.nlflags = nlflags,
+	};
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 #define MAX_STAT_DEPTH 32
 
 #define KEYLENGTH	(8*sizeof(t_key))
@@ -1076,7 +1114,8 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 }
 
 /* Caller must hold RTNL. */
-int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_insert(struct net *net, struct fib_table *tb,
+		     struct fib_config *cfg)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct fib_alias *fa, *new_fa;
@@ -1175,17 +1214,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->tb_id = tb->tb_id;
 			new_fa->fa_default = -1;
 
-			err = switchdev_fib_ipv4_add(key, plen, fi,
-						     new_fa->fa_tos,
-						     cfg->fc_type,
-						     cfg->fc_nlflags,
-						     tb->tb_id);
-			if (err) {
-				switchdev_fib_ipv4_abort(fi);
-				kmem_cache_free(fn_alias_kmem, new_fa);
-				goto out;
-			}
-
 			hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
 
 			alias_free_mem_rcu(fa);
@@ -1193,6 +1221,11 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			fib_release_info(fi_drop);
 			if (state & FA_S_ACCESSED)
 				rt_cache_flush(cfg->fc_nlinfo.nl_net);
+
+			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_ADD,
+						 key, plen, fi,
+						 new_fa->fa_tos, cfg->fc_type,
+						 tb->tb_id, cfg->fc_nlflags);
 			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
 				tb->tb_id, &cfg->fc_nlinfo, nlflags);
 
@@ -1228,30 +1261,22 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->tb_id = tb->tb_id;
 	new_fa->fa_default = -1;
 
-	/* (Optionally) offload fib entry to switch hardware. */
-	err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
-				     cfg->fc_nlflags, tb->tb_id);
-	if (err) {
-		switchdev_fib_ipv4_abort(fi);
-		goto out_free_new_fa;
-	}
-
 	/* Insert new entry to the list. */
 	err = fib_insert_alias(t, tp, l, new_fa, fa, key);
 	if (err)
-		goto out_sw_fib_del;
+		goto out_free_new_fa;
 
 	if (!plen)
 		tb->tb_num_default++;
 
 	rt_cache_flush(cfg->fc_nlinfo.nl_net);
+	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, key, plen, fi, tos,
+				 cfg->fc_type, tb->tb_id, cfg->fc_nlflags);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, nlflags);
 succeeded:
 	return 0;
 
-out_sw_fib_del:
-	switchdev_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
 out_free_new_fa:
 	kmem_cache_free(fn_alias_kmem, new_fa);
 out:
@@ -1490,7 +1515,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 }
 
 /* Caller must hold RTNL. */
-int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_delete(struct net *net, struct fib_table *tb,
+		     struct fib_config *cfg)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
 	struct fib_alias *fa, *fa_to_delete;
@@ -1543,9 +1569,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 	if (!fa_to_delete)
 		return -ESRCH;
 
-	switchdev_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
-			       cfg->fc_type, tb->tb_id);
-
+	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
+				 fa_to_delete->fa_info, tos, cfg->fc_type,
+				 tb->tb_id, 0);
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1734,82 +1760,8 @@ out:
 	return NULL;
 }
 
-/* Caller must hold RTNL */
-void fib_table_flush_external(struct fib_table *tb)
-{
-	struct trie *t = (struct trie *)tb->tb_data;
-	struct key_vector *pn = t->kv;
-	unsigned long cindex = 1;
-	struct hlist_node *tmp;
-	struct fib_alias *fa;
-
-	/* walk trie in reverse order */
-	for (;;) {
-		unsigned char slen = 0;
-		struct key_vector *n;
-
-		if (!(cindex--)) {
-			t_key pkey = pn->key;
-
-			/* cannot resize the trie vector */
-			if (IS_TRIE(pn))
-				break;
-
-			/* resize completed node */
-			pn = resize(t, pn);
-			cindex = get_index(pkey, pn);
-
-			continue;
-		}
-
-		/* grab the next available node */
-		n = get_child(pn, cindex);
-		if (!n)
-			continue;
-
-		if (IS_TNODE(n)) {
-			/* record pn and cindex for leaf walking */
-			pn = n;
-			cindex = 1ul << n->bits;
-
-			continue;
-		}
-
-		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
-			struct fib_info *fi = fa->fa_info;
-
-			/* if alias was cloned to local then we just
-			 * need to remove the local copy from main
-			 */
-			if (tb->tb_id != fa->tb_id) {
-				hlist_del_rcu(&fa->fa_list);
-				alias_free_mem_rcu(fa);
-				continue;
-			}
-
-			/* record local slen */
-			slen = fa->fa_slen;
-
-			if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD))
-				continue;
-
-			switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen,
-					       fi, fa->fa_tos, fa->fa_type,
-					       tb->tb_id);
-		}
-
-		/* update leaf slen */
-		n->slen = slen;
-
-		if (hlist_empty(&n->leaf)) {
-			put_child_root(pn, n->key, NULL);
-			node_free(n);
-		}
-	}
-}
-
 /* Caller must hold RTNL. */
-int fib_table_flush(struct fib_table *tb)
+int fib_table_flush(struct net *net, struct fib_table *tb)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *pn = t->kv;
@@ -1858,9 +1810,11 @@ int fib_table_flush(struct fib_table *tb)
 				continue;
 			}
 
-			switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen,
-					       fi, fa->fa_tos, fa->fa_type,
-					       tb->tb_id);
+			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, 0);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index ecd1e09..96e0efe 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;
+	bool need_csum, ufo, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -69,6 +69,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	outer_hlen = skb_tnl_header_len(skb);
 	gre_offset = outer_hlen - tnl_hlen;
 	skb = segs;
@@ -96,7 +98,7 @@ 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 (skb_is_gso(skb)) {
+		if (gso_partial) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 4b351af..d6feabb 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -312,6 +312,7 @@ 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;
+	struct net_device *dev = skb->dev;
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -341,7 +342,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	 */
 	if (!skb_valid_dst(skb)) {
 		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, skb->dev);
+					       iph->tos, dev);
 		if (unlikely(err)) {
 			if (err == -EXDEV)
 				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
@@ -370,7 +371,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 		__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
 	} else if (skb->pkt_type == PACKET_BROADCAST ||
 		   skb->pkt_type == PACKET_MULTICAST) {
-		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+		struct in_device *in_dev = __in_dev_get_rcu(dev);
 
 		/* RFC 1122 3.3.6:
 		 *
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index cc701fa..5d7944f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -88,6 +88,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	struct net_device *dev;
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
+	struct xfrm_mode *inner_mode;
 	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
 	u32 orig_mark = skb->mark;
 	int ret;
@@ -105,7 +106,19 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	}
 
 	x = xfrm_input_state(skb);
-	family = x->inner_mode->afinfo->family;
+
+	inner_mode = x->inner_mode;
+
+	if (x->sel.family == AF_UNSPEC) {
+		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+		if (inner_mode == NULL) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINSTATEMODEERROR);
+			return -EINVAL;
+		}
+	}
+
+	family = inner_mode->afinfo->family;
 
 	skb->mark = be32_to_cpu(tunnel->parms.i_key);
 	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2625332..5f006e1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2076,6 +2076,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	struct rta_mfc_stats mfcs;
 	struct nlattr *mp_attr;
 	struct rtnexthop *nhp;
+	unsigned long lastuse;
 	int ct;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
@@ -2105,12 +2106,14 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 	nla_nest_end(skb, mp_attr);
 
+	lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+	lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
 	mfcs.mfcs_packets = c->mfc_un.res.pkt;
 	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
 	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
 	if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
-	    nla_put_u64_64bit(skb, RTA_EXPIRES,
-			      jiffies_to_clock_t(c->mfc_un.res.lastuse),
+	    nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
 			      RTA_PAD))
 		return -EMSGSIZE;
 
@@ -2120,7 +2123,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 int ipmr_get_route(struct net *net, struct sk_buff *skb,
 		   __be32 saddr, __be32 daddr,
-		   struct rtmsg *rtm, int nowait)
+		   struct rtmsg *rtm, int nowait, u32 portid)
 {
 	struct mfc_cache *cache;
 	struct mr_table *mrt;
@@ -2165,6 +2168,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			return -ENOMEM;
 		}
 
+		NETLINK_CB(skb2).portid = portid;
 		skb_push(skb2, sizeof(struct iphdr));
 		skb_reset_network_header(skb2);
 		iph = ip_hdr(skb2);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f993545..7c00ce9 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -156,7 +156,7 @@ static struct nf_loginfo trace_loginfo = {
 	.u = {
 		.log = {
 			.level = 4,
-			.logflags = NF_LOG_MASK,
+			.logflags = NF_LOG_DEFAULT_MASK,
 		},
 	},
 };
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 870aebd..713c09a 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -110,7 +110,7 @@ static unsigned int ipv4_helper(void *priv,
 	if (!help)
 		return NF_ACCEPT;
 
-	/* rcu_read_lock()ed by nf_hook_slow */
+	/* rcu_read_lock()ed by nf_hook_thresh */
 	helper = rcu_dereference(help->helper);
 	if (!helper)
 		return NF_ACCEPT;
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 4b5904b..d075b3c 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -149,7 +149,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 		return -NF_ACCEPT;
 	}
 
-	/* rcu_read_lock()ed by nf_hook_slow */
+	/* rcu_read_lock()ed by nf_hook_thresh */
 	innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum);
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index 8945c26..b24795e 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -30,7 +30,7 @@ static struct nf_loginfo default_loginfo = {
 	.u = {
 		.log = {
 			.level	  = LOGLEVEL_NOTICE,
-			.logflags = NF_LOG_MASK,
+			.logflags = NF_LOG_DEFAULT_MASK,
 		},
 	},
 };
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 20f2255..8566489 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -29,7 +29,7 @@ static struct nf_loginfo default_loginfo = {
 	.u = {
 		.log = {
 			.level	  = LOGLEVEL_NOTICE,
-			.logflags = NF_LOG_MASK,
+			.logflags = NF_LOG_DEFAULT_MASK,
 		},
 	},
 };
@@ -46,7 +46,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m,
 	if (info->type == NF_LOG_TYPE_LOG)
 		logflags = info->u.log.logflags;
 	else
-		logflags = NF_LOG_MASK;
+		logflags = NF_LOG_DEFAULT_MASK;
 
 	ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph);
 	if (ih == NULL) {
@@ -76,7 +76,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m,
 	if (ntohs(ih->frag_off) & IP_OFFSET)
 		nf_log_buf_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET);
 
-	if ((logflags & XT_LOG_IPOPT) &&
+	if ((logflags & NF_LOG_IPOPT) &&
 	    ih->ihl * 4 > sizeof(struct iphdr)) {
 		const unsigned char *op;
 		unsigned char _opt[4 * 15 - sizeof(struct iphdr)];
@@ -250,7 +250,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m,
 	}
 
 	/* Max length: 15 "UID=4294967295 " */
-	if ((logflags & XT_LOG_UID) && !iphoff)
+	if ((logflags & NF_LOG_UID) && !iphoff)
 		nf_log_dump_sk_uid_gid(m, skb->sk);
 
 	/* Max length: 16 "MARK=0xFFFFFFFF " */
@@ -282,7 +282,7 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m,
 	if (info->type == NF_LOG_TYPE_LOG)
 		logflags = info->u.log.logflags;
 
-	if (!(logflags & XT_LOG_MACDECODE))
+	if (!(logflags & NF_LOG_MACDECODE))
 		goto fallback;
 
 	switch (dev->type) {
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index 9414923..edf0500 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -88,8 +88,8 @@ gre_manip_pkt(struct sk_buff *skb,
 	      const struct nf_conntrack_tuple *tuple,
 	      enum nf_nat_manip_type maniptype)
 {
-	const struct gre_hdr *greh;
-	struct gre_hdr_pptp *pgreh;
+	const struct gre_base_hdr *greh;
+	struct pptp_gre_header *pgreh;
 
 	/* pgreh includes two optional 32bit fields which are not required
 	 * to be there.  That's where the magic '8' comes from */
@@ -97,18 +97,19 @@ gre_manip_pkt(struct sk_buff *skb,
 		return false;
 
 	greh = (void *)skb->data + hdroff;
-	pgreh = (struct gre_hdr_pptp *)greh;
+	pgreh = (struct pptp_gre_header *)greh;
 
 	/* we only have destination manip of a packet, since 'source key'
 	 * is not present in the packet itself */
 	if (maniptype != NF_NAT_MANIP_DST)
 		return true;
-	switch (greh->version) {
-	case GRE_VERSION_1701:
+
+	switch (greh->flags & GRE_VERSION) {
+	case GRE_VERSION_0:
 		/* We do not currently NAT any GREv0 packets.
 		 * Try to behave like "nf_nat_proto_unknown" */
 		break;
-	case GRE_VERSION_PPTP:
+	case GRE_VERSION_1:
 		pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key));
 		pgreh->call_id = tuple->dst.u.gre.key;
 		break;
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index cd84d42..805c8dd 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -21,7 +21,7 @@ nft_do_chain_arp(void *priv,
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_unspec(&pkt, skb, state);
 
 	return nft_do_chain(&pkt, priv);
 }
@@ -80,7 +80,10 @@ static int __init nf_tables_arp_init(void)
 {
 	int ret;
 
-	nft_register_chain_type(&filter_arp);
+	ret = nft_register_chain_type(&filter_arp);
+	if (ret < 0)
+		return ret;
+
 	ret = register_pernet_subsys(&nf_tables_arp_net_ops);
 	if (ret < 0)
 		nft_unregister_chain_type(&filter_arp);
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index e44ba3b..2840a29 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -103,7 +103,10 @@ static int __init nf_tables_ipv4_init(void)
 {
 	int ret;
 
-	nft_register_chain_type(&filter_ipv4);
+	ret = nft_register_chain_type(&filter_ipv4);
+	if (ret < 0)
+		return ret;
+
 	ret = register_pernet_subsys(&nf_tables_ipv4_net_ops);
 	if (ret < 0)
 		nft_unregister_chain_type(&filter_ipv4);
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 2375b0a..30493be 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv,
 	__be32 saddr, daddr;
 	u_int8_t tos;
 	const struct iphdr *iph;
+	int err;
 
 	/* root is playing with raw sockets. */
 	if (skb->len < sizeof(struct iphdr) ||
@@ -46,15 +47,17 @@ static unsigned int nf_route_table_hook(void *priv,
 	tos = iph->tos;
 
 	ret = nft_do_chain(&pkt, priv);
-	if (ret != NF_DROP && ret != NF_QUEUE) {
+	if (ret != NF_DROP && ret != NF_STOLEN) {
 		iph = ip_hdr(skb);
 
 		if (iph->saddr != saddr ||
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
-		    iph->tos != tos)
-			if (ip_route_me_harder(state->net, skb, RTN_UNSPEC))
-				ret = NF_DROP;
+		    iph->tos != tos) {
+			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
 	}
 	return ret;
 }
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 1ed015e..7143ca1 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -46,6 +46,8 @@
 #include <net/sock.h>
 #include <net/raw.h>
 
+#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX)
+
 /*
  *	Report socket allocation statistics [mea@utu.fi]
  */
@@ -356,22 +358,22 @@ static void icmp_put(struct seq_file *seq)
 	atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
 
 	seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors");
-	for (i = 0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name; i++)
 		seq_printf(seq, " In%s", icmpmibmap[i].name);
 	seq_puts(seq, " OutMsgs OutErrors");
-	for (i = 0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name; i++)
 		seq_printf(seq, " Out%s", icmpmibmap[i].name);
 	seq_printf(seq, "\nIcmp: %lu %lu %lu",
 		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS),
 		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS),
 		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
-	for (i = 0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + icmpmibmap[i].index));
 	seq_printf(seq, " %lu %lu",
 		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
 		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
-	for (i = 0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
 }
@@ -379,14 +381,16 @@ static void icmp_put(struct seq_file *seq)
 /*
  *	Called from the PROCfs module. This outputs /proc/net/snmp.
  */
-static int snmp_seq_show(struct seq_file *seq, void *v)
+static int snmp_seq_show_ipstats(struct seq_file *seq, void *v)
 {
-	int i;
 	struct net *net = seq->private;
+	u64 buff64[IPSTATS_MIB_MAX];
+	int i;
 
-	seq_puts(seq, "Ip: Forwarding DefaultTTL");
+	memset(buff64, 0, IPSTATS_MIB_MAX * sizeof(u64));
 
-	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
+	seq_puts(seq, "Ip: Forwarding DefaultTTL");
+	for (i = 0; snmp4_ipstats_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_ipstats_list[i].name);
 
 	seq_printf(seq, "\nIp: %d %d",
@@ -394,57 +398,77 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		   net->ipv4.sysctl_ip_default_ttl);
 
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
-	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
-		seq_printf(seq, " %llu",
-			   snmp_fold_field64(net->mib.ip_statistics,
-					     snmp4_ipstats_list[i].entry,
-					     offsetof(struct ipstats_mib, syncp)));
+	snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list,
+				   net->mib.ip_statistics,
+				   offsetof(struct ipstats_mib, syncp));
+	for (i = 0; snmp4_ipstats_list[i].name; i++)
+		seq_printf(seq, " %llu", buff64[i]);
 
-	icmp_put(seq);	/* RFC 2011 compatibility */
-	icmpmsg_put(seq);
+	return 0;
+}
+
+static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v)
+{
+	unsigned long buff[TCPUDP_MIB_MAX];
+	struct net *net = seq->private;
+	int i;
+
+	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
 
 	seq_puts(seq, "\nTcp:");
-	for (i = 0; snmp4_tcp_list[i].name != NULL; i++)
+	for (i = 0; snmp4_tcp_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_tcp_list[i].name);
 
 	seq_puts(seq, "\nTcp:");
-	for (i = 0; snmp4_tcp_list[i].name != NULL; i++) {
+	snmp_get_cpu_field_batch(buff, snmp4_tcp_list,
+				 net->mib.tcp_statistics);
+	for (i = 0; snmp4_tcp_list[i].name; i++) {
 		/* MaxConn field is signed, RFC 2012 */
 		if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
-			seq_printf(seq, " %ld",
-				   snmp_fold_field(net->mib.tcp_statistics,
-						   snmp4_tcp_list[i].entry));
+			seq_printf(seq, " %ld", buff[i]);
 		else
-			seq_printf(seq, " %lu",
-				   snmp_fold_field(net->mib.tcp_statistics,
-						   snmp4_tcp_list[i].entry));
+			seq_printf(seq, " %lu", buff[i]);
 	}
 
+	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
+
+	snmp_get_cpu_field_batch(buff, snmp4_udp_list,
+				 net->mib.udp_statistics);
 	seq_puts(seq, "\nUdp:");
-	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
+	for (i = 0; snmp4_udp_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_udp_list[i].name);
-
 	seq_puts(seq, "\nUdp:");
-	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.udp_statistics,
-					   snmp4_udp_list[i].entry));
+	for (i = 0; snmp4_udp_list[i].name; i++)
+		seq_printf(seq, " %lu", buff[i]);
+
+	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
 
 	/* the UDP and UDP-Lite MIBs are the same */
 	seq_puts(seq, "\nUdpLite:");
-	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
+	snmp_get_cpu_field_batch(buff, snmp4_udp_list,
+				 net->mib.udplite_statistics);
+	for (i = 0; snmp4_udp_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_udp_list[i].name);
-
 	seq_puts(seq, "\nUdpLite:");
-	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field(net->mib.udplite_statistics,
-					   snmp4_udp_list[i].entry));
+	for (i = 0; snmp4_udp_list[i].name; i++)
+		seq_printf(seq, " %lu", buff[i]);
 
 	seq_putc(seq, '\n');
 	return 0;
 }
 
+static int snmp_seq_show(struct seq_file *seq, void *v)
+{
+	snmp_seq_show_ipstats(seq, v);
+
+	icmp_put(seq);	/* RFC 2011 compatibility */
+	icmpmsg_put(seq);
+
+	snmp_seq_show_tcp_udp(seq, v);
+
+	return 0;
+}
+
 static int snmp_seq_open(struct inode *inode, struct file *file)
 {
 	return single_open_net(inode, file, snmp_seq_show);
@@ -469,21 +493,21 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	struct net *net = seq->private;
 
 	seq_puts(seq, "TcpExt:");
-	for (i = 0; snmp4_net_list[i].name != NULL; i++)
+	for (i = 0; snmp4_net_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_net_list[i].name);
 
 	seq_puts(seq, "\nTcpExt:");
-	for (i = 0; snmp4_net_list[i].name != NULL; i++)
+	for (i = 0; snmp4_net_list[i].name; i++)
 		seq_printf(seq, " %lu",
 			   snmp_fold_field(net->mib.net_statistics,
 					   snmp4_net_list[i].entry));
 
 	seq_puts(seq, "\nIpExt:");
-	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
+	for (i = 0; snmp4_ipextstats_list[i].name; i++)
 		seq_printf(seq, " %s", snmp4_ipextstats_list[i].name);
 
 	seq_puts(seq, "\nIpExt:");
-	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
+	for (i = 0; snmp4_ipextstats_list[i].name; i++)
 		seq_printf(seq, " %llu",
 			   snmp_fold_field64(net->mib.ip_statistics,
 					     snmp4_ipextstats_list[i].entry,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b52496f..f2be689 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -476,12 +476,18 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = ACCESS_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 delta = 0;
+	u32 new, delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	return atomic_add_return(segs + delta, p_id) - segs;
+	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
+	do {
+		old = (u32)atomic_read(p_id);
+		new = old + delta + segs;
+	} while (atomic_cmpxchg(p_id, old, new) != old);
+
+	return new - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
@@ -2494,7 +2500,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 		    IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
 			int err = ipmr_get_route(net, skb,
 						 fl4->saddr, fl4->daddr,
-						 r, nowait);
+						 r, nowait, portid);
+
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7dae800..f253e50 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
-	tp->rtt_min[0].rtt = ~0U;
+	minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U);
 
 	/* So many TCP implementations out there (incorrectly) count the
 	 * initial SYN frame in their delayed-ACK and congestion control
@@ -396,6 +396,9 @@ void tcp_init_sock(struct sock *sk)
 	 */
 	tp->snd_cwnd = TCP_INIT_CWND;
 
+	/* There's a bubble in the pipe until at least the first ACK. */
+	tp->app_limited = ~0U;
+
 	/* See draft-stevens-tcpca-spec-01 for discussion of the
 	 * initialization of these values.
 	 */
@@ -1014,6 +1017,9 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 					flags);
 
 	lock_sock(sk);
+
+	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
+
 	res = do_tcp_sendpages(sk, page, offset, size, flags);
 	release_sock(sk);
 	return res;
@@ -1115,6 +1121,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
+	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
+
 	/* Wait for a connection to finish. One exception is TCP Fast Open
 	 * (passive side) where data is allowed to be sent before a connection
 	 * is fully established.
@@ -2704,7 +2712,7 @@ 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 = tcp_time_stamp;
+	u32 now = tcp_time_stamp, intv;
 	unsigned int start;
 	int notsent_bytes;
 	u64 rate64;
@@ -2794,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_min_rtt = tcp_min_rtt(tp);
 	info->tcpi_data_segs_in = tp->data_segs_in;
 	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);
+		put_unaligned(rate64, &info->tcpi_delivery_rate);
+	}
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -3261,11 +3278,12 @@ static void __init tcp_init_mem(void)
 
 void __init tcp_init(void)
 {
-	unsigned long limit;
 	int max_rshare, max_wshare, cnt;
+	unsigned long limit;
 	unsigned int i;
 
-	sock_skb_cb_check_size(sizeof(struct tcp_skb_cb));
+	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
+		     FIELD_SIZEOF(struct sk_buff, cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
new file mode 100644
index 0000000..0ea66c2
--- /dev/null
+++ b/net/ipv4/tcp_bbr.c
@@ -0,0 +1,896 @@
+/* Bottleneck Bandwidth and RTT (BBR) congestion control
+ *
+ * BBR congestion control computes the sending rate based on the delivery
+ * rate (throughput) estimated from ACKs. In a nutshell:
+ *
+ *   On each ACK, update our model of the network path:
+ *      bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips)
+ *      min_rtt = windowed_min(rtt, 10 seconds)
+ *   pacing_rate = pacing_gain * bottleneck_bandwidth
+ *   cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4)
+ *
+ * The core algorithm does not react directly to packet losses or delays,
+ * although BBR may adjust the size of next send per ACK when loss is
+ * observed, or adjust the sending rate if it estimates there is a
+ * traffic policer, in order to keep the drop rate reasonable.
+ *
+ * BBR is described in detail in:
+ *   "BBR: Congestion-Based Congestion Control",
+ *   Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
+ *   Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016.
+ *
+ * There is a public e-mail list for discussing BBR development and testing:
+ *   https://groups.google.com/forum/#!forum/bbr-dev
+ *
+ * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled,
+ * since pacing is integral to the BBR design and implementation.
+ * BBR without pacing would not function properly, and may incur unnecessary
+ * high packet loss rates.
+ */
+#include <linux/module.h>
+#include <net/tcp.h>
+#include <linux/inet_diag.h>
+#include <linux/inet.h>
+#include <linux/random.h>
+#include <linux/win_minmax.h>
+
+/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth
+ * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps.
+ * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32.
+ * Since the minimum window is >=4 packets, the lower bound isn't
+ * an issue. The upper bound isn't an issue with existing technologies.
+ */
+#define BW_SCALE 24
+#define BW_UNIT (1 << BW_SCALE)
+
+#define BBR_SCALE 8	/* scaling factor for fractions in BBR (e.g. gains) */
+#define BBR_UNIT (1 << BBR_SCALE)
+
+/* BBR has the following modes for deciding how fast to send: */
+enum bbr_mode {
+	BBR_STARTUP,	/* ramp up sending rate rapidly to fill pipe */
+	BBR_DRAIN,	/* drain any queue created during startup */
+	BBR_PROBE_BW,	/* discover, share bw: pace around estimated bw */
+	BBR_PROBE_RTT,	/* cut cwnd to min to probe min_rtt */
+};
+
+/* BBR congestion control block */
+struct bbr {
+	u32	min_rtt_us;	        /* min RTT in min_rtt_win_sec window */
+	u32	min_rtt_stamp;	        /* timestamp of min_rtt_us */
+	u32	probe_rtt_done_stamp;   /* end time for BBR_PROBE_RTT mode */
+	struct minmax bw;	/* Max recent delivery rate in pkts/uS << 24 */
+	u32	rtt_cnt;	    /* count of packet-timed rounds elapsed */
+	u32     next_rtt_delivered; /* scb->tx.delivered at end of round */
+	struct skb_mstamp cycle_mstamp;  /* time of this cycle phase start */
+	u32     mode:3,		     /* current bbr_mode in state machine */
+		prev_ca_state:3,     /* CA state on previous ACK */
+		packet_conservation:1,  /* use packet conservation? */
+		restore_cwnd:1,	     /* decided to revert cwnd to old value */
+		round_start:1,	     /* start of packet-timed tx->ack round? */
+		tso_segs_goal:7,     /* segments we want in each skb we send */
+		idle_restart:1,	     /* restarting after idle? */
+		probe_rtt_round_done:1,  /* a BBR_PROBE_RTT round at 4 pkts? */
+		unused:5,
+		lt_is_sampling:1,    /* taking long-term ("LT") samples now? */
+		lt_rtt_cnt:7,	     /* round trips in long-term interval */
+		lt_use_bw:1;	     /* use lt_bw as our bw estimate? */
+	u32	lt_bw;		     /* LT est delivery rate in pkts/uS << 24 */
+	u32	lt_last_delivered;   /* LT intvl start: tp->delivered */
+	u32	lt_last_stamp;	     /* LT intvl start: tp->delivered_mstamp */
+	u32	lt_last_lost;	     /* LT intvl start: tp->lost */
+	u32	pacing_gain:10,	/* current gain for setting pacing rate */
+		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;
+	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
+	u32	full_bw;	/* recent bw, to estimate if pipe is full */
+};
+
+#define CYCLE_LEN	8	/* number of phases in a pacing gain cycle */
+
+/* Window length of bw filter (in rounds): */
+static const int bbr_bw_rtts = CYCLE_LEN + 2;
+/* Window length of min_rtt filter (in sec): */
+static const u32 bbr_min_rtt_win_sec = 10;
+/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */
+static const u32 bbr_probe_rtt_mode_ms = 200;
+/* Skip TSO below the following bandwidth (bits/sec): */
+static const int bbr_min_tso_rate = 1200000;
+
+/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain
+ * that will allow a smoothly increasing pacing rate that will double each RTT
+ * and send the same number of packets per RTT that an un-paced, slow-starting
+ * Reno or CUBIC flow would:
+ */
+static const int bbr_high_gain  = BBR_UNIT * 2885 / 1000 + 1;
+/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain
+ * the queue created in BBR_STARTUP in a single round:
+ */
+static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885;
+/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */
+static const int bbr_cwnd_gain  = BBR_UNIT * 2;
+/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */
+static const int bbr_pacing_gain[] = {
+	BBR_UNIT * 5 / 4,	/* probe for more available bw */
+	BBR_UNIT * 3 / 4,	/* drain queue and/or yield bw to other flows */
+	BBR_UNIT, BBR_UNIT, BBR_UNIT,	/* cruise at 1.0*bw to utilize pipe, */
+	BBR_UNIT, BBR_UNIT, BBR_UNIT	/* without creating excess queue... */
+};
+/* Randomize the starting gain cycling phase over N phases: */
+static const u32 bbr_cycle_rand = 7;
+
+/* Try to keep at least this many packets in flight, if things go smoothly. For
+ * smooth functioning, a sliding window protocol ACKing every other packet
+ * needs at least 4 packets in flight:
+ */
+static const u32 bbr_cwnd_min_target = 4;
+
+/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */
+/* If bw has increased significantly (1.25x), there may be more bw available: */
+static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4;
+/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */
+static const u32 bbr_full_bw_cnt = 3;
+
+/* "long-term" ("LT") bandwidth estimator parameters... */
+/* The minimum number of rounds in an LT bw sampling interval: */
+static const u32 bbr_lt_intvl_min_rtts = 4;
+/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */
+static const u32 bbr_lt_loss_thresh = 50;
+/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */
+static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8;
+/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */
+static const u32 bbr_lt_bw_diff = 4000 / 8;
+/* If we estimate we're policed, use lt_bw for this many round trips: */
+static const u32 bbr_lt_bw_max_rtts = 48;
+
+/* Do we estimate that STARTUP filled the pipe? */
+static bool bbr_full_bw_reached(const struct sock *sk)
+{
+	const struct bbr *bbr = inet_csk_ca(sk);
+
+	return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+}
+
+/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
+static u32 bbr_max_bw(const struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	return minmax_get(&bbr->bw);
+}
+
+/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */
+static u32 bbr_bw(const struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk);
+}
+
+/* Return rate in bytes per second, optionally with a gain.
+ * The order here is chosen carefully to avoid overflow of u64. This should
+ * work for input rates of up to 2.9Tbit/sec and gain of 2.89x.
+ */
+static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
+{
+	rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache);
+	rate *= gain;
+	rate >>= BBR_SCALE;
+	rate *= USEC_PER_SEC;
+	return rate >> BW_SCALE;
+}
+
+/* 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
+ * estimated bandwidth. This is an important aspect of the design. In this
+ * implementation this slightly lower pacing rate is achieved implicitly by not
+ * including link-layer headers in the packet size used for the pacing rate.
+ */
+static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+	u64 rate = bw;
+
+	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)
+		sk->sk_pacing_rate = rate;
+}
+
+/* Return count of segments we want in the skbs we send, or 0 for default. */
+static u32 bbr_tso_segs_goal(struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	return bbr->tso_segs_goal;
+}
+
+static void bbr_set_tso_segs_goal(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 min_segs;
+
+	min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2;
+	bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs),
+				 0x7FU);
+}
+
+/* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */
+static void bbr_save_cwnd(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT)
+		bbr->prior_cwnd = tp->snd_cwnd;  /* this cwnd is good enough */
+	else  /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */
+		bbr->prior_cwnd = max(bbr->prior_cwnd, tp->snd_cwnd);
+}
+
+static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	if (event == CA_EVENT_TX_START && tp->app_limited) {
+		bbr->idle_restart = 1;
+		/* Avoid pointless buffer overflows: pace at est. bw if we don't
+		 * need more speed (we're restarting from idle and app-limited).
+		 */
+		if (bbr->mode == BBR_PROBE_BW)
+			bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT);
+	}
+}
+
+/* Find target cwnd. Right-size the cwnd based on min RTT and the
+ * estimated bottleneck bandwidth:
+ *
+ * cwnd = bw * min_rtt * gain = BDP * gain
+ *
+ * The key factor, gain, controls the amount of queue. While a small gain
+ * builds a smaller queue, it becomes more vulnerable to noise in RTT
+ * measurements (e.g., delayed ACKs or other ACK compression effects). This
+ * noise may cause BBR to under-estimate the rate.
+ *
+ * To achieve full performance in high-speed paths, we budget enough cwnd to
+ * fit full-sized skbs in-flight on both end hosts to fully utilize the path:
+ *   - one skb in sending host Qdisc,
+ *   - one skb in sending host TSO/GSO engine
+ *   - one skb being received by receiver host LRO/GRO/delayed-ACK engine
+ * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because
+ * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets,
+ * which allows 2 outstanding 2-packet sequences, to try to keep pipe
+ * full even with ACK-every-other-packet delayed ACKs.
+ */
+static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 cwnd;
+	u64 w;
+
+	/* If we've never had a valid RTT sample, cap cwnd at the initial
+	 * default. This should only happen when the connection is not using TCP
+	 * timestamps and has retransmitted all of the SYN/SYNACK/data packets
+	 * ACKed so far. In this case, an RTO can cut cwnd to 1, in which
+	 * case we need to slow-start up toward something safe: TCP_INIT_CWND.
+	 */
+	if (unlikely(bbr->min_rtt_us == ~0U))	 /* no valid RTT samples yet? */
+		return TCP_INIT_CWND;  /* be safe: cap at default initial cwnd*/
+
+	w = (u64)bw * bbr->min_rtt_us;
+
+	/* Apply a gain to the given value, then remove the BW_SCALE shift. */
+	cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT;
+
+	/* Allow enough full-sized skbs in flight to utilize end systems. */
+	cwnd += 3 * bbr->tso_segs_goal;
+
+	/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
+	cwnd = (cwnd + 1) & ~1U;
+
+	return cwnd;
+}
+
+/* An optimization in BBR to reduce losses: On the first round of recovery, we
+ * follow the packet conservation principle: send P packets per P packets acked.
+ * After that, we slow-start and send at most 2*P packets per P packets acked.
+ * After recovery finishes, or upon undo, we restore the cwnd we had when
+ * recovery started (capped by the target cwnd based on estimated BDP).
+ *
+ * TODO(ycheng/ncardwell): implement a rate-based approach.
+ */
+static bool bbr_set_cwnd_to_recover_or_restore(
+	struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state;
+	u32 cwnd = tp->snd_cwnd;
+
+	/* An ACK for P pkts should release at most 2*P packets. We do this
+	 * in two steps. First, here we deduct the number of lost packets.
+	 * Then, in bbr_set_cwnd() we slow start up toward the target cwnd.
+	 */
+	if (rs->losses > 0)
+		cwnd = max_t(s32, cwnd - rs->losses, 1);
+
+	if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) {
+		/* Starting 1st round of Recovery, so do packet conservation. */
+		bbr->packet_conservation = 1;
+		bbr->next_rtt_delivered = tp->delivered;  /* start round now */
+		/* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */
+		cwnd = tcp_packets_in_flight(tp) + acked;
+	} else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) {
+		/* Exiting loss recovery; restore cwnd saved before recovery. */
+		bbr->restore_cwnd = 1;
+		bbr->packet_conservation = 0;
+	}
+	bbr->prev_ca_state = state;
+
+	if (bbr->restore_cwnd) {
+		/* Restore cwnd after exiting loss recovery or PROBE_RTT. */
+		cwnd = max(cwnd, bbr->prior_cwnd);
+		bbr->restore_cwnd = 0;
+	}
+
+	if (bbr->packet_conservation) {
+		*new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked);
+		return true;	/* yes, using packet conservation */
+	}
+	*new_cwnd = cwnd;
+	return false;
+}
+
+/* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss
+ * has drawn us down below target), or snap down to target if we're above it.
+ */
+static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
+			 u32 acked, u32 bw, int gain)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 cwnd = 0, target_cwnd = 0;
+
+	if (!acked)
+		return;
+
+	if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd))
+		goto done;
+
+	/* If we're below target cwnd, slow start cwnd toward target cwnd. */
+	target_cwnd = bbr_target_cwnd(sk, bw, gain);
+	if (bbr_full_bw_reached(sk))  /* only cut cwnd if we filled the pipe */
+		cwnd = min(cwnd + acked, target_cwnd);
+	else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND)
+		cwnd = cwnd + acked;
+	cwnd = max(cwnd, bbr_cwnd_min_target);
+
+done:
+	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);	/* apply global cap */
+	if (bbr->mode == BBR_PROBE_RTT)  /* drain queue, refresh min_rtt */
+		tp->snd_cwnd = min(tp->snd_cwnd, bbr_cwnd_min_target);
+}
+
+/* End cycle phase if it's time and/or we hit the phase's in-flight target. */
+static bool bbr_is_next_cycle_phase(struct sock *sk,
+				    const struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	bool is_full_length =
+		skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) >
+		bbr->min_rtt_us;
+	u32 inflight, bw;
+
+	/* The pacing_gain of 1.0 paces at the estimated bw to try to fully
+	 * use the pipe without increasing the queue.
+	 */
+	if (bbr->pacing_gain == BBR_UNIT)
+		return is_full_length;		/* just use wall clock time */
+
+	inflight = rs->prior_in_flight;  /* what was in-flight before ACK? */
+	bw = bbr_max_bw(sk);
+
+	/* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at
+	 * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is
+	 * small (e.g. on a LAN). We do not persist if packets are lost, since
+	 * a path with small buffers may not hold that much.
+	 */
+	if (bbr->pacing_gain > BBR_UNIT)
+		return is_full_length &&
+			(rs->losses ||  /* perhaps pacing_gain*BDP won't fit */
+			 inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain));
+
+	/* A pacing_gain < 1.0 tries to drain extra queue we added if bw
+	 * probing didn't find more bw. If inflight falls to match BDP then we
+	 * estimate queue is drained; persisting would underutilize the pipe.
+	 */
+	return is_full_length ||
+		inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT);
+}
+
+static void bbr_advance_cycle_phase(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
+	bbr->cycle_mstamp = tp->delivered_mstamp;
+	bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx];
+}
+
+/* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
+static void bbr_update_cycle_phase(struct sock *sk,
+				   const struct rate_sample *rs)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw &&
+	    bbr_is_next_cycle_phase(sk, rs))
+		bbr_advance_cycle_phase(sk);
+}
+
+static void bbr_reset_startup_mode(struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->mode = BBR_STARTUP;
+	bbr->pacing_gain = bbr_high_gain;
+	bbr->cwnd_gain	 = bbr_high_gain;
+}
+
+static void bbr_reset_probe_bw_mode(struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->mode = BBR_PROBE_BW;
+	bbr->pacing_gain = BBR_UNIT;
+	bbr->cwnd_gain = bbr_cwnd_gain;
+	bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand);
+	bbr_advance_cycle_phase(sk);	/* flip to next phase of gain cycle */
+}
+
+static void bbr_reset_mode(struct sock *sk)
+{
+	if (!bbr_full_bw_reached(sk))
+		bbr_reset_startup_mode(sk);
+	else
+		bbr_reset_probe_bw_mode(sk);
+}
+
+/* Start a new long-term sampling interval. */
+static void bbr_reset_lt_bw_sampling_interval(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies;
+	bbr->lt_last_delivered = tp->delivered;
+	bbr->lt_last_lost = tp->lost;
+	bbr->lt_rtt_cnt = 0;
+}
+
+/* Completely reset long-term bandwidth sampling. */
+static void bbr_reset_lt_bw_sampling(struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->lt_bw = 0;
+	bbr->lt_use_bw = 0;
+	bbr->lt_is_sampling = false;
+	bbr_reset_lt_bw_sampling_interval(sk);
+}
+
+/* Long-term bw sampling interval is done. Estimate whether we're policed. */
+static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 diff;
+
+	if (bbr->lt_bw) {  /* do we have bw from a previous interval? */
+		/* Is new bw close to the lt_bw from the previous interval? */
+		diff = abs(bw - bbr->lt_bw);
+		if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) ||
+		    (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <=
+		     bbr_lt_bw_diff)) {
+			/* All criteria are met; estimate we're policed. */
+			bbr->lt_bw = (bw + bbr->lt_bw) >> 1;  /* avg 2 intvls */
+			bbr->lt_use_bw = 1;
+			bbr->pacing_gain = BBR_UNIT;  /* try to avoid drops */
+			bbr->lt_rtt_cnt = 0;
+			return;
+		}
+	}
+	bbr->lt_bw = bw;
+	bbr_reset_lt_bw_sampling_interval(sk);
+}
+
+/* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of
+ * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and
+ * explicitly models their policed rate, to reduce unnecessary losses. We
+ * estimate that we're policed if we see 2 consecutive sampling intervals with
+ * consistent throughput and high packet loss. If we think we're being policed,
+ * set lt_bw to the "long-term" average delivery rate from those 2 intervals.
+ */
+static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 lost, delivered;
+	u64 bw;
+	s32 t;
+
+	if (bbr->lt_use_bw) {	/* already using long-term rate, lt_bw? */
+		if (bbr->mode == BBR_PROBE_BW && bbr->round_start &&
+		    ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) {
+			bbr_reset_lt_bw_sampling(sk);    /* stop using lt_bw */
+			bbr_reset_probe_bw_mode(sk);  /* restart gain cycling */
+		}
+		return;
+	}
+
+	/* Wait for the first loss before sampling, to let the policer exhaust
+	 * its tokens and estimate the steady-state rate allowed by the policer.
+	 * Starting samples earlier includes bursts that over-estimate the bw.
+	 */
+	if (!bbr->lt_is_sampling) {
+		if (!rs->losses)
+			return;
+		bbr_reset_lt_bw_sampling_interval(sk);
+		bbr->lt_is_sampling = true;
+	}
+
+	/* To avoid underestimates, reset sampling if we run out of data. */
+	if (rs->is_app_limited) {
+		bbr_reset_lt_bw_sampling(sk);
+		return;
+	}
+
+	if (bbr->round_start)
+		bbr->lt_rtt_cnt++;	/* count round trips in this interval */
+	if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts)
+		return;		/* sampling interval needs to be longer */
+	if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) {
+		bbr_reset_lt_bw_sampling(sk);  /* interval is too long */
+		return;
+	}
+
+	/* End sampling interval when a packet is lost, so we estimate the
+	 * policer tokens were exhausted. Stopping the sampling before the
+	 * tokens are exhausted under-estimates the policed rate.
+	 */
+	if (!rs->losses)
+		return;
+
+	/* Calculate packets lost and delivered in sampling interval. */
+	lost = tp->lost - bbr->lt_last_lost;
+	delivered = tp->delivered - bbr->lt_last_delivered;
+	/* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */
+	if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered)
+		return;
+
+	/* Find average delivery rate in this sampling interval. */
+	t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp);
+	if (t < 1)
+		return;		/* interval is less than one jiffy, so wait */
+	t = jiffies_to_usecs(t);
+	/* Interval long enough for jiffies_to_usecs() to return a bogus 0? */
+	if (t < 1) {
+		bbr_reset_lt_bw_sampling(sk);  /* interval too long; reset */
+		return;
+	}
+	bw = (u64)delivered * BW_UNIT;
+	do_div(bw, t);
+	bbr_lt_bw_interval_done(sk, bw);
+}
+
+/* Estimate the bandwidth based on how fast packets are delivered */
+static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u64 bw;
+
+	bbr->round_start = 0;
+	if (rs->delivered < 0 || rs->interval_us <= 0)
+		return; /* Not a valid observation */
+
+	/* See if we've reached the next RTT */
+	if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) {
+		bbr->next_rtt_delivered = tp->delivered;
+		bbr->rtt_cnt++;
+		bbr->round_start = 1;
+		bbr->packet_conservation = 0;
+	}
+
+	bbr_lt_bw_sampling(sk, rs);
+
+	/* Divide delivered by the interval to find a (lower bound) bottleneck
+	 * bandwidth sample. Delivered is in packets and interval_us in uS and
+	 * ratio will be <<1 for most connections. So delivered is first scaled.
+	 */
+	bw = (u64)rs->delivered * BW_UNIT;
+	do_div(bw, rs->interval_us);
+
+	/* If this sample is application-limited, it is likely to have a very
+	 * low delivered count that represents application behavior rather than
+	 * the available network rate. Such a sample could drag down estimated
+	 * bw, causing needless slow-down. Thus, to continue to send at the
+	 * last measured network rate, we filter out app-limited samples unless
+	 * they describe the path bw at least as well as our bw model.
+	 *
+	 * So the goal during app-limited phase is to proceed with the best
+	 * network rate no matter how long. We automatically leave this
+	 * phase when app writes faster than the network can deliver :)
+	 */
+	if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) {
+		/* Incorporate new sample into our max bw filter. */
+		minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw);
+	}
+}
+
+/* Estimate when the pipe is full, using the change in delivery rate: BBR
+ * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by
+ * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited
+ * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the
+ * higher rwin, 3: we get higher delivery rate samples. Or transient
+ * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar
+ * design goal, but uses delay and inter-ACK spacing instead of bandwidth.
+ */
+static void bbr_check_full_bw_reached(struct sock *sk,
+				      const struct rate_sample *rs)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 bw_thresh;
+
+	if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited)
+		return;
+
+	bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE;
+	if (bbr_max_bw(sk) >= bw_thresh) {
+		bbr->full_bw = bbr_max_bw(sk);
+		bbr->full_bw_cnt = 0;
+		return;
+	}
+	++bbr->full_bw_cnt;
+}
+
+/* If pipe is probably full, drain the queue and then enter steady-state. */
+static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) {
+		bbr->mode = BBR_DRAIN;	/* drain queue we created */
+		bbr->pacing_gain = bbr_drain_gain;	/* pace slow to drain */
+		bbr->cwnd_gain = bbr_high_gain;	/* maintain cwnd */
+	}	/* fall through to check if in-flight is already small: */
+	if (bbr->mode == BBR_DRAIN &&
+	    tcp_packets_in_flight(tcp_sk(sk)) <=
+	    bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT))
+		bbr_reset_probe_bw_mode(sk);  /* we estimate queue is drained */
+}
+
+/* The goal of PROBE_RTT mode is to have BBR flows cooperatively and
+ * periodically drain the bottleneck queue, to converge to measure the true
+ * min_rtt (unloaded propagation delay). This allows the flows to keep queues
+ * small (reducing queuing delay and packet loss) and achieve fairness among
+ * BBR flows.
+ *
+ * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires,
+ * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets.
+ * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed
+ * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and
+ * re-enter the previous mode. BBR uses 200ms to approximately bound the
+ * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s).
+ *
+ * Note that flows need only pay 2% if they are busy sending over the last 10
+ * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have
+ * natural silences or low-rate periods within 10 seconds where the rate is low
+ * enough for long enough to drain its queue in the bottleneck. We pick up
+ * these min RTT measurements opportunistically with our min_rtt filter. :-)
+ */
+static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	bool filter_expired;
+
+	/* Track min RTT seen in the min_rtt_win_sec filter window: */
+	filter_expired = after(tcp_time_stamp,
+			       bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
+	if (rs->rtt_us >= 0 &&
+	    (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) {
+		bbr->min_rtt_us = rs->rtt_us;
+		bbr->min_rtt_stamp = tcp_time_stamp;
+	}
+
+	if (bbr_probe_rtt_mode_ms > 0 && filter_expired &&
+	    !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) {
+		bbr->mode = BBR_PROBE_RTT;  /* dip, drain queue */
+		bbr->pacing_gain = BBR_UNIT;
+		bbr->cwnd_gain = BBR_UNIT;
+		bbr_save_cwnd(sk);  /* note cwnd so we can restore it */
+		bbr->probe_rtt_done_stamp = 0;
+	}
+
+	if (bbr->mode == BBR_PROBE_RTT) {
+		/* Ignore low rate samples during this mode. */
+		tp->app_limited =
+			(tp->delivered + tcp_packets_in_flight(tp)) ? : 1;
+		/* Maintain min packets in flight for max(200 ms, 1 round). */
+		if (!bbr->probe_rtt_done_stamp &&
+		    tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) {
+			bbr->probe_rtt_done_stamp = tcp_time_stamp +
+				msecs_to_jiffies(bbr_probe_rtt_mode_ms);
+			bbr->probe_rtt_round_done = 0;
+			bbr->next_rtt_delivered = tp->delivered;
+		} else if (bbr->probe_rtt_done_stamp) {
+			if (bbr->round_start)
+				bbr->probe_rtt_round_done = 1;
+			if (bbr->probe_rtt_round_done &&
+			    after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) {
+				bbr->min_rtt_stamp = tcp_time_stamp;
+				bbr->restore_cwnd = 1;  /* snap to prior_cwnd */
+				bbr_reset_mode(sk);
+			}
+		}
+	}
+	bbr->idle_restart = 0;
+}
+
+static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
+{
+	bbr_update_bw(sk, rs);
+	bbr_update_cycle_phase(sk, rs);
+	bbr_check_full_bw_reached(sk, rs);
+	bbr_check_drain(sk, rs);
+	bbr_update_min_rtt(sk, rs);
+}
+
+static void bbr_main(struct sock *sk, const struct rate_sample *rs)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+	u32 bw;
+
+	bbr_update_model(sk, rs);
+
+	bw = bbr_bw(sk);
+	bbr_set_pacing_rate(sk, bw, bbr->pacing_gain);
+	bbr_set_tso_segs_goal(sk);
+	bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain);
+}
+
+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 */
+	bbr->rtt_cnt = 0;
+	bbr->next_rtt_delivered = 0;
+	bbr->prev_ca_state = TCP_CA_Open;
+	bbr->packet_conservation = 0;
+
+	bbr->probe_rtt_done_stamp = 0;
+	bbr->probe_rtt_round_done = 0;
+	bbr->min_rtt_us = tcp_min_rtt(tp);
+	bbr->min_rtt_stamp = tcp_time_stamp;
+
+	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->restore_cwnd = 0;
+	bbr->round_start = 0;
+	bbr->idle_restart = 0;
+	bbr->full_bw = 0;
+	bbr->full_bw_cnt = 0;
+	bbr->cycle_mstamp.v64 = 0;
+	bbr->cycle_idx = 0;
+	bbr_reset_lt_bw_sampling(sk);
+	bbr_reset_startup_mode(sk);
+}
+
+static u32 bbr_sndbuf_expand(struct sock *sk)
+{
+	/* Provision 3 * cwnd since BBR may slow-start even during recovery. */
+	return 3;
+}
+
+/* In theory BBR does not need to undo the cwnd since it does not
+ * always reduce cwnd on losses (see bbr_main()). Keep it for now.
+ */
+static u32 bbr_undo_cwnd(struct sock *sk)
+{
+	return tcp_sk(sk)->snd_cwnd;
+}
+
+/* Entering loss recovery, so save cwnd for when we exit or undo recovery. */
+static u32 bbr_ssthresh(struct sock *sk)
+{
+	bbr_save_cwnd(sk);
+	return TCP_INFINITE_SSTHRESH;	 /* BBR does not use ssthresh */
+}
+
+static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr,
+			   union tcp_cc_info *info)
+{
+	if (ext & (1 << (INET_DIAG_BBRINFO - 1)) ||
+	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
+		struct tcp_sock *tp = tcp_sk(sk);
+		struct bbr *bbr = inet_csk_ca(sk);
+		u64 bw = bbr_bw(sk);
+
+		bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE;
+		memset(&info->bbr, 0, sizeof(info->bbr));
+		info->bbr.bbr_bw_lo		= (u32)bw;
+		info->bbr.bbr_bw_hi		= (u32)(bw >> 32);
+		info->bbr.bbr_min_rtt		= bbr->min_rtt_us;
+		info->bbr.bbr_pacing_gain	= bbr->pacing_gain;
+		info->bbr.bbr_cwnd_gain		= bbr->cwnd_gain;
+		*attr = INET_DIAG_BBRINFO;
+		return sizeof(info->bbr);
+	}
+	return 0;
+}
+
+static void bbr_set_state(struct sock *sk, u8 new_state)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	if (new_state == TCP_CA_Loss) {
+		struct rate_sample rs = { .losses = 1 };
+
+		bbr->prev_ca_state = TCP_CA_Loss;
+		bbr->full_bw = 0;
+		bbr->round_start = 1;	/* treat RTO like end of a round */
+		bbr_lt_bw_sampling(sk, &rs);
+	}
+}
+
+static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
+	.flags		= TCP_CONG_NON_RESTRICTED,
+	.name		= "bbr",
+	.owner		= THIS_MODULE,
+	.init		= bbr_init,
+	.cong_control	= bbr_main,
+	.sndbuf_expand	= bbr_sndbuf_expand,
+	.undo_cwnd	= bbr_undo_cwnd,
+	.cwnd_event	= bbr_cwnd_event,
+	.ssthresh	= bbr_ssthresh,
+	.tso_segs_goal	= bbr_tso_segs_goal,
+	.get_info	= bbr_get_info,
+	.set_state	= bbr_set_state,
+};
+
+static int __init bbr_register(void)
+{
+	BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE);
+	return tcp_register_congestion_control(&tcp_bbr_cong_ops);
+}
+
+static void __exit bbr_unregister(void)
+{
+	tcp_unregister_congestion_control(&tcp_bbr_cong_ops);
+}
+
+module_init(bbr_register);
+module_exit(bbr_unregister);
+
+MODULE_AUTHOR("Van Jacobson <vanj@google.com>");
+MODULE_AUTHOR("Neal Cardwell <ncardwell@google.com>");
+MODULE_AUTHOR("Yuchung Cheng <ycheng@google.com>");
+MODULE_AUTHOR("Soheil Hassas Yeganeh <soheil@google.com>");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)");
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 03725b2..35b2803 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -56,7 +56,7 @@ MODULE_PARM_DESC(use_shadow, "use shadow window heuristic");
 module_param(use_tolerance, bool, 0644);
 MODULE_PARM_DESC(use_tolerance, "use loss tolerance heuristic");
 
-struct minmax {
+struct cdg_minmax {
 	union {
 		struct {
 			s32 min;
@@ -74,10 +74,10 @@ enum cdg_state {
 };
 
 struct cdg {
-	struct minmax rtt;
-	struct minmax rtt_prev;
-	struct minmax *gradients;
-	struct minmax gsum;
+	struct cdg_minmax rtt;
+	struct cdg_minmax rtt_prev;
+	struct cdg_minmax *gradients;
+	struct cdg_minmax gsum;
 	bool gfilled;
 	u8  tail;
 	u8  state;
@@ -353,7 +353,7 @@ static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev)
 {
 	struct cdg *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct minmax *gradients;
+	struct cdg_minmax *gradients;
 
 	switch (ev) {
 	case CA_EVENT_CWND_RESTART:
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 882caa4..1294af4 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -69,7 +69,7 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
 	int ret = 0;
 
 	/* all algorithms must implement ssthresh and cong_avoid ops */
-	if (!ca->ssthresh || !ca->cong_avoid) {
+	if (!ca->ssthresh || !(ca->cong_avoid || ca->cong_control)) {
 		pr_err("%s does not implement required ops\n", ca->name);
 		return -EINVAL;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dad3e7e..a27b9c0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -289,6 +289,7 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
 static void tcp_sndbuf_expand(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	int sndmem, per_mss;
 	u32 nr_segs;
 
@@ -309,7 +310,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	 * Cubic needs 1.7 factor, rounded to 2 to include
 	 * extra cushion (application might react slowly to POLLOUT)
 	 */
-	sndmem = 2 * nr_segs * per_mss;
+	sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
+	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
 		sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
@@ -899,12 +901,29 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 		tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
 }
 
+/* Sum the number of packets on the wire we have marked as lost.
+ * There are two cases we care about here:
+ * a) Packet hasn't been marked lost (nor retransmitted),
+ *    and this is the first loss.
+ * b) Packet has been marked both lost and retransmitted,
+ *    and this means we think it was lost again.
+ */
+static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	__u8 sacked = TCP_SKB_CB(skb)->sacked;
+
+	if (!(sacked & TCPCB_LOST) ||
+	    ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS)))
+		tp->lost += tcp_skb_pcount(skb);
+}
+
 static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
 		tcp_verify_retransmit_hint(tp, skb);
 
 		tp->lost_out += tcp_skb_pcount(skb);
+		tcp_sum_lost(tp, skb);
 		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
 	}
 }
@@ -913,6 +932,7 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	tcp_verify_retransmit_hint(tp, skb);
 
+	tcp_sum_lost(tp, skb);
 	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
 		tp->lost_out += tcp_skb_pcount(skb);
 		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
@@ -1094,6 +1114,7 @@ struct tcp_sacktag_state {
 	 */
 	struct skb_mstamp first_sackt;
 	struct skb_mstamp last_sackt;
+	struct rate_sample *rate;
 	int	flag;
 };
 
@@ -1261,6 +1282,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
 			start_seq, end_seq, dup_sack, pcount,
 			&skb->skb_mstamp);
+	tcp_rate_skb_delivered(sk, skb, state->rate);
 
 	if (skb == tp->lost_skb_hint)
 		tp->lost_cnt_hint += pcount;
@@ -1311,6 +1333,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 		tcp_advance_highest_sack(sk, skb);
 
 	tcp_skb_collapse_tstamp(prev, skb);
+	if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64))
+		TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0;
+
 	tcp_unlink_write_queue(skb, sk);
 	sk_wmem_free_skb(sk, skb);
 
@@ -1540,6 +1565,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						dup_sack,
 						tcp_skb_pcount(skb),
 						&skb->skb_mstamp);
+			tcp_rate_skb_delivered(sk, skb, state->rate);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -1622,8 +1648,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 
 	found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
 					 num_sacks, prior_snd_una);
-	if (found_dup_sack)
+	if (found_dup_sack) {
 		state->flag |= FLAG_DSACKING_ACK;
+		tp->delivered++; /* A spurious retransmission is delivered */
+	}
 
 	/* Eliminate too old ACKs, but take into
 	 * account more or less fresh ones, they can
@@ -1890,6 +1918,7 @@ void tcp_enter_loss(struct sock *sk)
 	struct sk_buff *skb;
 	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
+	bool mark_lost;
 
 	/* Reduce ssthresh if it has not yet been made inside this window. */
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
@@ -1923,8 +1952,12 @@ void tcp_enter_loss(struct sock *sk)
 		if (skb == tcp_send_head(sk))
 			break;
 
+		mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
+			     is_reneg);
+		if (mark_lost)
+			tcp_sum_lost(tp, skb);
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
-		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) {
+		if (mark_lost) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
 			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
 			tp->lost_out += tcp_skb_pcount(skb);
@@ -2329,10 +2362,9 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
 			 msg,
-			 &np->daddr, ntohs(inet->inet_dport),
+			 &sk->sk_v6_daddr, ntohs(inet->inet_dport),
 			 tp->snd_cwnd, tcp_left_out(tp),
 			 tp->snd_ssthresh, tp->prior_ssthresh,
 			 tp->packets_out);
@@ -2503,6 +2535,9 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	if (inet_csk(sk)->icsk_ca_ops->cong_control)
+		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)) {
@@ -2879,67 +2914,13 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 	*rexmit = REXMIT_LOST;
 }
 
-/* Kathleen Nichols' algorithm for tracking the minimum value of
- * a data stream over some fixed time interval. (E.g., the minimum
- * RTT over the past five minutes.) It uses constant space and constant
- * time per update yet almost always delivers the same minimum as an
- * implementation that has to keep all the data in the window.
- *
- * The algorithm keeps track of the best, 2nd best & 3rd best min
- * values, maintaining an invariant that the measurement time of the
- * n'th best >= n-1'th best. It also makes sure that the three values
- * are widely separated in the time window since that bounds the worse
- * case error when that data is monotonically increasing over the window.
- *
- * Upon getting a new min, we can forget everything earlier because it
- * has no value - the new min is <= everything else in the window by
- * definition and it's the most recent. So we restart fresh on every new min
- * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd
- * best.
- */
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
-	const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
-	struct rtt_meas *m = tcp_sk(sk)->rtt_min;
-	struct rtt_meas rttm = {
-		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
-		.ts = now,
-	};
-	u32 elapsed;
-
-	/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
-	if (unlikely(rttm.rtt <= m[0].rtt))
-		m[0] = m[1] = m[2] = rttm;
-	else if (rttm.rtt <= m[1].rtt)
-		m[1] = m[2] = rttm;
-	else if (rttm.rtt <= m[2].rtt)
-		m[2] = rttm;
-
-	elapsed = now - m[0].ts;
-	if (unlikely(elapsed > wlen)) {
-		/* Passed entire window without a new min so make 2nd choice
-		 * the new min & 3rd choice the new 2nd. So forth and so on.
-		 */
-		m[0] = m[1];
-		m[1] = m[2];
-		m[2] = rttm;
-		if (now - m[0].ts > wlen) {
-			m[0] = m[1];
-			m[1] = rttm;
-			if (now - m[0].ts > wlen)
-				m[0] = rttm;
-		}
-	} else if (m[1].ts == m[0].ts && elapsed > wlen / 4) {
-		/* Passed a quarter of the window without a new min so
-		 * take 2nd choice from the 2nd quarter of the window.
-		 */
-		m[2] = m[1] = rttm;
-	} else if (m[2].ts == m[1].ts && elapsed > wlen / 2) {
-		/* Passed half the window without a new min so take the 3rd
-		 * choice from the last half of the window.
-		 */
-		m[2] = rttm;
-	}
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;
+
+	minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp,
+			   rtt_us ? : jiffies_to_usecs(1));
 }
 
 static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
@@ -3102,10 +3083,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
  */
 static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			       u32 prior_snd_una, int *acked,
-			       struct tcp_sacktag_state *sack)
+			       struct tcp_sacktag_state *sack,
+			       struct skb_mstamp *now)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct skb_mstamp first_ackt, last_ackt, now;
+	struct skb_mstamp first_ackt, last_ackt;
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 prior_sacked = tp->sacked_out;
 	u32 reord = tp->packets_out;
@@ -3137,7 +3119,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			acked_pcount = tcp_tso_acked(sk, skb);
 			if (!acked_pcount)
 				break;
-
 			fully_acked = false;
 		} else {
 			/* Speedup tcp_unlink_write_queue() and next loop */
@@ -3173,6 +3154,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 		tp->packets_out -= acked_pcount;
 		pkts_acked += acked_pcount;
+		tcp_rate_skb_delivered(sk, skb, sack->rate);
 
 		/* Initial outgoing SYN's get put onto the write_queue
 		 * just like anything else we transmit.  It is not
@@ -3205,16 +3187,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 		flag |= FLAG_SACK_RENEGING;
 
-	skb_mstamp_get(&now);
 	if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
-		seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
-		ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+		seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt);
+		ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt);
 	}
 	if (sack->first_sackt.v64) {
-		sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt);
-		ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt);
+		sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt);
+		ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt);
 	}
-
+	sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */
 	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us,
 					ca_rtt_us);
 
@@ -3242,7 +3223,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		tp->fackets_out -= min(pkts_acked, tp->fackets_out);
 
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
-		   sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
+		   sack_rtt_us > skb_mstamp_us_delta(now, &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.
@@ -3333,8 +3314,15 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
  * information. All transmission or retransmission are delayed afterwards.
  */
 static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
-			     int flag)
+			     int flag, const struct rate_sample *rs)
 {
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ca_ops->cong_control) {
+		icsk->icsk_ca_ops->cong_control(sk, rs);
+		return;
+	}
+
 	if (tcp_in_cwnd_reduction(sk)) {
 		/* Reduce cwnd if state mandates */
 		tcp_cwnd_reduction(sk, acked_sacked, flag);
@@ -3579,17 +3567,21 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_sacktag_state sack_state;
+	struct rate_sample rs = { .prior_delivered = 0 };
 	u32 prior_snd_una = tp->snd_una;
 	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 prior_delivered = tp->delivered;
+	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 */
+	struct skb_mstamp now;
 
 	sack_state.first_sackt.v64 = 0;
+	sack_state.rate = &rs;
 
 	/* We very likely will need to access write queue head. */
 	prefetchw(sk->sk_write_queue.next);
@@ -3612,6 +3604,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, tp->snd_nxt))
 		goto invalid_ack;
 
+	skb_mstamp_get(&now);
+
 	if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
@@ -3622,6 +3616,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	}
 
 	prior_fackets = tp->fackets_out;
+	rs.prior_in_flight = tcp_packets_in_flight(tp);
 
 	/* ts_recent update must be made after we are sure that the packet
 	 * is in window.
@@ -3677,7 +3672,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	/* 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);
+				    &sack_state, &now);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
@@ -3694,7 +3689,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
 		tcp_schedule_loss_probe(sk);
-	tcp_cong_control(sk, ack, tp->delivered - prior_delivered, flag);
+	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
+	lost = tp->lost - lost;			/* freshly marked lost */
+	tcp_rate_gen(sk, delivered, lost, &now, &rs);
+	tcp_cong_control(sk, ack, delivered, flag, &rs);
 	tcp_xmit_recovery(sk, rexmit);
 	return 1;
 
@@ -5951,7 +5949,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		 * so release it.
 		 */
 		if (req) {
-			tp->total_retrans = req->num_retrans;
+			inet_csk(sk)->icsk_retransmits = 0;
 			reqsk_fastopen_remove(sk, req, false);
 		} else {
 			/* Make sure socket is routed, for correct metrics. */
@@ -5993,7 +5991,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		} else
 			tcp_init_metrics(sk);
 
-		tcp_update_pacing_rate(sk);
+		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
+			tcp_update_pacing_rate(sk);
 
 		/* Prevent spurious tcp_cwnd_restart() on first data packet */
 		tp->lsndtime = tcp_time_stamp;
@@ -6326,6 +6325,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
+	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;
 
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
 	inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 04b9893..7ac37c3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1196,7 +1196,6 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->no_srccheck = inet_sk(sk_listener)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
 }
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f63c73d..6234eba 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -464,7 +464,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 		newtp->srtt_us = 0;
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
-		newtp->rtt_min[0].rtt = ~0U;
+		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
 
 		newtp->packets_out = 0;
@@ -487,6 +487,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
+		/* There's a bubble in the pipe until at least the first ACK. */
+		newtp->app_limited = ~0U;
+
 		tcp_init_xmit_timers(newsk);
 		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 5c59649..bc68da3 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -90,12 +90,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
-	/* GSO partial only requires splitting the frame into an MSS
-	 * multiple and possibly a remainder.  So update the mss now.
-	 */
-	if (features & NETIF_F_GSO_PARTIAL)
-		mss = skb->len - (skb->len % mss);
-
 	copy_destructor = gso_skb->destructor == tcp_wfree;
 	ooo_okay = gso_skb->ooo_okay;
 	/* All segments but the first should have ooo_okay cleared */
@@ -108,6 +102,13 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	/* Only first segment might have ooo_okay set */
 	segs->ooo_okay = ooo_okay;
 
+	/* GSO partial and frag_list segmentation only requires splitting
+	 * the frame into an MSS multiple and possibly a remainder, both
+	 * cases return a GSO skb. So update the mss now.
+	 */
+	if (skb_is_gso(segs))
+		mss *= skb_shinfo(segs)->gso_segs;
+
 	delta = htonl(oldlen + (thlen + mss));
 
 	skb = segs;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8b45794..896e9df 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -734,9 +734,16 @@ static void tcp_tsq_handler(struct sock *sk)
 {
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
-	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK)) {
+		struct tcp_sock *tp = tcp_sk(sk);
+
+		if (tp->lost_out > tp->retrans_out &&
+		    tp->snd_cwnd > tcp_packets_in_flight(tp))
+			tcp_xmit_retransmit_queue(sk);
+
+		tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
 			       0, GFP_ATOMIC);
+	}
 }
 /*
  * One tasklet per cpu tries to send more skbs.
@@ -918,6 +925,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int 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);
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -1213,6 +1221,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	tcp_set_skb_tso_segs(skb, mss_now);
 	tcp_set_skb_tso_segs(buff, mss_now);
 
+	/* Update delivered info for the new segment */
+	TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx;
+
 	/* If this packet has been sent out already, we must
 	 * adjust the various packet counters.
 	 */
@@ -1358,6 +1369,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
 	}
 	return mtu;
 }
+EXPORT_SYMBOL(tcp_mss_to_mtu);
 
 /* MTU probing init per socket */
 void tcp_mtup_init(struct sock *sk)
@@ -1545,7 +1557,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 /* Return how many segs we'd like on a TSO packet,
  * to send one TSO packet per ms
  */
-static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
+u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+		     int min_tso_segs)
 {
 	u32 bytes, segs;
 
@@ -1557,10 +1570,23 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
 	 * This preserves ACK clocking and is consistent
 	 * with tcp_tso_should_defer() heuristic.
 	 */
-	segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs);
+	segs = max_t(u32, bytes / mss_now, min_tso_segs);
 
 	return min_t(u32, segs, sk->sk_gso_max_segs);
 }
+EXPORT_SYMBOL(tcp_tso_autosize);
+
+/* Return the number of segments we want in the skb we are transmitting.
+ * See if congestion control module wants to decide; otherwise, autosize.
+ */
+static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
+{
+	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
+	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);
+}
 
 /* Returns the portion of skb which can be sent right away */
 static unsigned int tcp_mss_split_point(const struct sock *sk,
@@ -1966,12 +1992,14 @@ static int tcp_mtu_probe(struct sock *sk)
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
 		copy = min_t(int, skb->len, probe_size - len);
-		if (nskb->ip_summed)
+		if (nskb->ip_summed) {
 			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
-		else
-			nskb->csum = skb_copy_and_csum_bits(skb, 0,
-							    skb_put(nskb, copy),
-							    copy, nskb->csum);
+		} else {
+			__wsum csum = skb_copy_and_csum_bits(skb, 0,
+							     skb_put(nskb, copy),
+							     copy, 0);
+			nskb->csum = csum_block_add(nskb->csum, csum, len);
+		}
 
 		if (skb->len <= copy) {
 			/* We've eaten all the data from this skb.
@@ -2020,6 +2048,39 @@ static int tcp_mtu_probe(struct sock *sk)
 	return -1;
 }
 
+/* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * (These limits are doubled for retransmits)
+ * This allows for :
+ *  - better RTT estimation and ACK scheduling
+ *  - faster recovery
+ *  - high rates
+ * Alas, some drivers / subsystems require a fair amount
+ * of queued bytes to ensure line rate.
+ * One example is wifi aggregation (802.11 AMPDU)
+ */
+static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
+				  unsigned int factor)
+{
+	unsigned int limit;
+
+	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
+	limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
+	limit <<= factor;
+
+	if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+		set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags);
+		/* It is possible TX completion already happened
+		 * before we set TSQ_THROTTLED, so we must
+		 * test again the condition.
+		 */
+		smp_mb__after_atomic();
+		if (atomic_read(&sk->sk_wmem_alloc) > limit)
+			return true;
+	}
+	return false;
+}
+
 /* This routine writes packets to the network.  It advances the
  * send_head.  This happens as incoming acks open up the remote
  * window for us.
@@ -2057,7 +2118,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 	}
 
-	max_segs = tcp_tso_autosize(sk, mss_now);
+	max_segs = tcp_tso_segs(sk, mss_now);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -2106,29 +2167,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
 			break;
 
-		/* TCP Small Queues :
-		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
-		 * This allows for :
-		 *  - better RTT estimation and ACK scheduling
-		 *  - faster recovery
-		 *  - high rates
-		 * Alas, some drivers / subsystems require a fair amount
-		 * of queued bytes to ensure line rate.
-		 * One example is wifi aggregation (802.11 AMPDU)
-		 */
-		limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
-		limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
-
-		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
-			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			/* It is possible TX completion already happened
-			 * before we set TSQ_THROTTLED, so we must
-			 * test again the condition.
-			 */
-			smp_mb__after_atomic();
-			if (atomic_read(&sk->sk_wmem_alloc) > limit)
-				break;
-		}
+		if (tcp_small_queue_check(sk, skb, 0))
+			break;
 
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
@@ -2605,7 +2645,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	 * copying overhead: fragmentation, tunneling, mangling etc.
 	 */
 	if (atomic_read(&sk->sk_wmem_alloc) >
-	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+	    min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+		  sk->sk_sndbuf))
 		return -EAGAIN;
 
 	if (skb_still_in_host_queue(sk, skb))
@@ -2774,7 +2815,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		last_lost = tp->snd_una;
 	}
 
-	max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
+	max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
 	tcp_for_write_queue_from(skb, sk) {
 		__u8 sacked;
 		int segs;
@@ -2828,10 +2869,13 @@ begin_fwd:
 		if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
 			continue;
 
+		if (tcp_small_queue_check(sk, skb, 1))
+			return;
+
 		if (tcp_retransmit_skb(sk, skb, segs))
 			return;
 
-		NET_INC_STATS(sock_net(sk), mib_idx);
+		NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb));
 
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += tcp_skb_pcount(skb);
@@ -3568,6 +3612,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	if (!res) {
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+		if (unlikely(tcp_passive_fastopen(sk)))
+			tcp_sk(sk)->total_retrans++;
 	}
 	return res;
 }
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
new file mode 100644
index 0000000..9be1581
--- /dev/null
+++ b/net/ipv4/tcp_rate.c
@@ -0,0 +1,186 @@
+#include <net/tcp.h>
+
+/* The bandwidth estimator estimates the rate at which the network
+ * can currently deliver outbound data packets for this flow. At a high
+ * level, it operates by taking a delivery rate sample for each ACK.
+ *
+ * A rate sample records the rate at which the network delivered packets
+ * for this flow, calculated over the time interval between the transmission
+ * of a data packet and the acknowledgment of that packet.
+ *
+ * Specifically, over the interval between each transmit and corresponding ACK,
+ * the estimator generates a delivery rate sample. Typically it uses the rate
+ * at which packets were acknowledged. However, the approach of using only the
+ * acknowledgment rate faces a challenge under the prevalent ACK decimation or
+ * compression: packets can temporarily appear to be delivered much quicker
+ * than the bottleneck rate. Since it is physically impossible to do that in a
+ * sustained fashion, when the estimator notices that the ACK rate is faster
+ * than the transmit rate, it uses the latter:
+ *
+ *    send_rate = #pkts_delivered/(last_snd_time - first_snd_time)
+ *    ack_rate  = #pkts_delivered/(last_ack_time - first_ack_time)
+ *    bw = min(send_rate, ack_rate)
+ *
+ * Notice the estimator essentially estimates the goodput, not always the
+ * network bottleneck link rate when the sending or receiving is limited by
+ * other factors like applications or receiver window limits.  The estimator
+ * deliberately avoids using the inter-packet spacing approach because that
+ * approach requires a large number of samples and sophisticated filtering.
+ *
+ * TCP flows can often be application-limited in request/response workloads.
+ * The estimator marks a bandwidth sample as application-limited if there
+ * was some moment during the sampled window of packets when there was no data
+ * ready to send in the write queue.
+ */
+
+/* Snapshot the current delivery information in the skb, to generate
+ * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered().
+ */
+void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	 /* In general we need to start delivery rate samples from the
+	  * time we received the most recent ACK, to ensure we include
+	  * the full time the network needs to deliver all in-flight
+	  * packets. If there are no packets in flight yet, then we
+	  * know that any ACKs after now indicate that the network was
+	  * able to deliver those packets completely in the sampling
+	  * interval between now and the next ACK.
+	  *
+	  * Note that we use packets_out instead of tcp_packets_in_flight(tp)
+	  * because the latter is a guess based on RTO and loss-marking
+	  * heuristics. We don't want spurious RTOs or loss markings to cause
+	  * a spuriously small time interval, causing a spuriously high
+	  * bandwidth estimate.
+	  */
+	if (!tp->packets_out) {
+		tp->first_tx_mstamp  = skb->skb_mstamp;
+		tp->delivered_mstamp = skb->skb_mstamp;
+	}
+
+	TCP_SKB_CB(skb)->tx.first_tx_mstamp	= tp->first_tx_mstamp;
+	TCP_SKB_CB(skb)->tx.delivered_mstamp	= tp->delivered_mstamp;
+	TCP_SKB_CB(skb)->tx.delivered		= tp->delivered;
+	TCP_SKB_CB(skb)->tx.is_app_limited	= tp->app_limited ? 1 : 0;
+}
+
+/* When an skb is sacked or acked, we fill in the rate sample with the (prior)
+ * delivery information when the skb was last transmitted.
+ *
+ * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is
+ * called multiple times. We favor the information from the most recently
+ * sent skb, i.e., the skb with the highest prior_delivered count.
+ */
+void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
+			    struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+
+	if (!scb->tx.delivered_mstamp.v64)
+		return;
+
+	if (!rs->prior_delivered ||
+	    after(scb->tx.delivered, rs->prior_delivered)) {
+		rs->prior_delivered  = scb->tx.delivered;
+		rs->prior_mstamp     = scb->tx.delivered_mstamp;
+		rs->is_app_limited   = scb->tx.is_app_limited;
+		rs->is_retrans	     = scb->sacked & TCPCB_RETRANS;
+
+		/* Find the duration of the "send phase" of this window: */
+		rs->interval_us      = skb_mstamp_us_delta(
+						&skb->skb_mstamp,
+						&scb->tx.first_tx_mstamp);
+
+		/* Record send time of most recently ACKed packet: */
+		tp->first_tx_mstamp  = skb->skb_mstamp;
+	}
+	/* Mark off the skb delivered once it's sacked to avoid being
+	 * used again when it's cumulatively acked. For acked packets
+	 * we don't need to reset since it'll be freed soon.
+	 */
+	if (scb->sacked & TCPCB_SACKED_ACKED)
+		scb->tx.delivered_mstamp.v64 = 0;
+}
+
+/* Update the connection delivery information and generate a rate sample. */
+void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
+		  struct skb_mstamp *now, struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 snd_us, ack_us;
+
+	/* Clear app limited if bubble is acked and gone. */
+	if (tp->app_limited && after(tp->delivered, tp->app_limited))
+		tp->app_limited = 0;
+
+	/* TODO: there are multiple places throughout tcp_ack() to get
+	 * current time. Refactor the code using a new "tcp_acktag_state"
+	 * to carry current time, flags, stats like "tcp_sacktag_state".
+	 */
+	if (delivered)
+		tp->delivered_mstamp = *now;
+
+	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
+	rs->losses = lost;		/* freshly marked lost */
+	/* Return an invalid sample if no timing information is available. */
+	if (!rs->prior_mstamp.v64) {
+		rs->delivered = -1;
+		rs->interval_us = -1;
+		return;
+	}
+	rs->delivered   = tp->delivered - rs->prior_delivered;
+
+	/* Model sending data and receiving ACKs as separate pipeline phases
+	 * for a window. Usually the ACK phase is longer, but with ACK
+	 * compression the send phase can be longer. To be safe we use the
+	 * longer phase.
+	 */
+	snd_us = rs->interval_us;				/* send phase */
+	ack_us = skb_mstamp_us_delta(now, &rs->prior_mstamp);	/* ack phase */
+	rs->interval_us = max(snd_us, ack_us);
+
+	/* Normally we expect interval_us >= min-rtt.
+	 * Note that rate may still be over-estimated when a spuriously
+	 * retransmistted skb was first (s)acked because "interval_us"
+	 * is under-estimated (up to an RTT). However continuously
+	 * measuring the delivery rate during loss recovery is crucial
+	 * for connections suffer heavy or prolonged losses.
+	 */
+	if (unlikely(rs->interval_us < tcp_min_rtt(tp))) {
+		if (!rs->is_retrans)
+			pr_debug("tcp rate: %ld %d %u %u %u\n",
+				 rs->interval_us, rs->delivered,
+				 inet_csk(sk)->icsk_ca_state,
+				 tp->rx_opt.sack_ok, tcp_min_rtt(tp));
+		rs->interval_us = -1;
+		return;
+	}
+
+	/* Record the last non-app-limited or the highest app-limited bw */
+	if (!rs->is_app_limited ||
+	    ((u64)rs->delivered * tp->rate_interval_us >=
+	     (u64)tp->rate_delivered * rs->interval_us)) {
+		tp->rate_delivered = rs->delivered;
+		tp->rate_interval_us = rs->interval_us;
+		tp->rate_app_limited = rs->is_app_limited;
+	}
+}
+
+/* If a gap is detected between sends, mark the socket application-limited. */
+void tcp_rate_check_app_limited(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (/* We have less than one packet to send. */
+	    tp->write_seq - tp->snd_nxt < tp->mss_cache &&
+	    /* Nothing in sending host's qdisc queues or NIC tx queue. */
+	    sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) &&
+	    /* We are not limited by CWND. */
+	    tcp_packets_in_flight(tp) < tp->snd_cwnd &&
+	    /* All lost packets have been retransmitted. */
+	    tp->lost_out <= tp->retrans_out)
+		tp->app_limited =
+			(tp->delivered + tcp_packets_in_flight(tp)) ? : 1;
+}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d84930b..3ea1cf8 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -192,6 +192,8 @@ static int tcp_write_timeout(struct sock *sk)
 			if (tp->syn_data && icsk->icsk_retransmits == 1)
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+		} else if (!tp->syn_data && !tp->syn_fastopen) {
+			sk_rethink_txhash(sk);
 		}
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
 		syn_set = true;
@@ -213,6 +215,8 @@ static int tcp_write_timeout(struct sock *sk)
 			tcp_mtu_probing(icsk, sk);
 
 			dst_negative_advice(sk);
+		} else {
+			sk_rethink_txhash(sk);
 		}
 
 		retry_until = net->ipv4.sysctl_tcp_retries2;
@@ -384,6 +388,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	 */
 	inet_rtx_syn_ack(sk, req);
 	req->num_timeout++;
+	icsk->icsk_retransmits++;
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 			  TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 81f253b..f9333c9 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;
+	bool remcsum, need_csum, offload_csum, ufo, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct udphdr *uh = udp_hdr(skb);
 	u16 mac_offset = skb->mac_header;
@@ -88,6 +88,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	outer_hlen = skb_tnl_header_len(skb);
 	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
@@ -117,7 +119,7 @@ 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 (skb_is_gso(skb)) {
+		if (gso_partial) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);