Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

34 files changed, 768 insertions, 249 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 03381f3e12ba..fc816b187170 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -180,8 +180,8 @@ config NET_IPIP
 config NET_IPGRE_DEMUX
 	tristate "IP: GRE demultiplexer"
 	help
-	 This is helper module to demultiplex GRE packets on GRE version field criteria.
-	 Required by ip_gre and pptp modules.
+	  This is helper module to demultiplex GRE packets on GRE version field criteria.
+	  Required by ip_gre and pptp modules.
 
 config NET_IP_TUNNEL
 	tristate
@@ -459,200 +459,200 @@ config TCP_CONG_BIC
 	tristate "Binary Increase Congestion (BIC) control"
 	default m
 	---help---
-	BIC-TCP is a sender-side only change that ensures a linear RTT
-	fairness under large windows while offering both scalability and
-	bounded TCP-friendliness. The protocol combines two schemes
-	called additive increase and binary search increase. When the
-	congestion window is large, additive increase with a large
-	increment ensures linear RTT fairness as well as good
-	scalability. Under small congestion windows, binary search
-	increase provides TCP friendliness.
-	See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
+	  BIC-TCP is a sender-side only change that ensures a linear RTT
+	  fairness under large windows while offering both scalability and
+	  bounded TCP-friendliness. The protocol combines two schemes
+	  called additive increase and binary search increase. When the
+	  congestion window is large, additive increase with a large
+	  increment ensures linear RTT fairness as well as good
+	  scalability. Under small congestion windows, binary search
+	  increase provides TCP friendliness.
+	  See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
 
 config TCP_CONG_CUBIC
 	tristate "CUBIC TCP"
 	default y
 	---help---
-	This is version 2.0 of BIC-TCP which uses a cubic growth function
-	among other techniques.
-	See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
+	  This is version 2.0 of BIC-TCP which uses a cubic growth function
+	  among other techniques.
+	  See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
 
 config TCP_CONG_WESTWOOD
 	tristate "TCP Westwood+"
 	default m
 	---help---
-	TCP Westwood+ is a sender-side only modification of the TCP Reno
-	protocol stack that optimizes the performance of TCP congestion
-	control. It is based on end-to-end bandwidth estimation to set
-	congestion window and slow start threshold after a congestion
-	episode. Using this estimation, TCP Westwood+ adaptively sets a
-	slow start threshold and a congestion window which takes into
-	account the bandwidth used  at the time congestion is experienced.
-	TCP Westwood+ significantly increases fairness wrt TCP Reno in
-	wired networks and throughput over wireless links.
+	  TCP Westwood+ is a sender-side only modification of the TCP Reno
+	  protocol stack that optimizes the performance of TCP congestion
+	  control. It is based on end-to-end bandwidth estimation to set
+	  congestion window and slow start threshold after a congestion
+	  episode. Using this estimation, TCP Westwood+ adaptively sets a
+	  slow start threshold and a congestion window which takes into
+	  account the bandwidth used  at the time congestion is experienced.
+	  TCP Westwood+ significantly increases fairness wrt TCP Reno in
+	  wired networks and throughput over wireless links.
 
 config TCP_CONG_HTCP
 	tristate "H-TCP"
 	default m
 	---help---
-	H-TCP is a send-side only modifications of the TCP Reno
-	protocol stack that optimizes the performance of TCP
-	congestion control for high speed network links. It uses a
-	modeswitch to change the alpha and beta parameters of TCP Reno
-	based on network conditions and in a way so as to be fair with
-	other Reno and H-TCP flows.
+	  H-TCP is a send-side only modifications of the TCP Reno
+	  protocol stack that optimizes the performance of TCP
+	  congestion control for high speed network links. It uses a
+	  modeswitch to change the alpha and beta parameters of TCP Reno
+	  based on network conditions and in a way so as to be fair with
+	  other Reno and H-TCP flows.
 
 config TCP_CONG_HSTCP
 	tristate "High Speed TCP"
 	default n
 	---help---
-	Sally Floyd's High Speed TCP (RFC 3649) congestion control.
-	A modification to TCP's congestion control mechanism for use
-	with large congestion windows. A table indicates how much to
-	increase the congestion window by when an ACK is received.
- 	For more detail	see http://www.icir.org/floyd/hstcp.html
+	  Sally Floyd's High Speed TCP (RFC 3649) congestion control.
+	  A modification to TCP's congestion control mechanism for use
+	  with large congestion windows. A table indicates how much to
+	  increase the congestion window by when an ACK is received.
+	  For more detail see http://www.icir.org/floyd/hstcp.html
 
 config TCP_CONG_HYBLA
 	tristate "TCP-Hybla congestion control algorithm"
 	default n
 	---help---
-	TCP-Hybla is a sender-side only change that eliminates penalization of
-	long-RTT, large-bandwidth connections, like when satellite legs are
-	involved, especially when sharing a common bottleneck with normal
-	terrestrial connections.
+	  TCP-Hybla is a sender-side only change that eliminates penalization of
+	  long-RTT, large-bandwidth connections, like when satellite legs are
+	  involved, especially when sharing a common bottleneck with normal
+	  terrestrial connections.
 
 config TCP_CONG_VEGAS
 	tristate "TCP Vegas"
 	default n
 	---help---
-	TCP Vegas is a sender-side only change to TCP that anticipates
-	the onset of congestion by estimating the bandwidth. TCP Vegas
-	adjusts the sending rate by modifying the congestion
-	window. TCP Vegas should provide less packet loss, but it is
-	not as aggressive as TCP Reno.
+	  TCP Vegas is a sender-side only change to TCP that anticipates
+	  the onset of congestion by estimating the bandwidth. TCP Vegas
+	  adjusts the sending rate by modifying the congestion
+	  window. TCP Vegas should provide less packet loss, but it is
+	  not as aggressive as TCP Reno.
 
 config TCP_CONG_NV
-       tristate "TCP NV"
-       default n
-       ---help---
-       TCP NV is a follow up to TCP Vegas. It has been modified to deal with
-       10G networks, measurement noise introduced by LRO, GRO and interrupt
-       coalescence. In addition, it will decrease its cwnd multiplicatively
-       instead of linearly.
+	tristate "TCP NV"
+	default n
+	---help---
+	  TCP NV is a follow up to TCP Vegas. It has been modified to deal with
+	  10G networks, measurement noise introduced by LRO, GRO and interrupt
+	  coalescence. In addition, it will decrease its cwnd multiplicatively
+	  instead of linearly.
 
-       Note that in general congestion avoidance (cwnd decreased when # packets
-       queued grows) cannot coexist with congestion control (cwnd decreased only
-       when there is packet loss) due to fairness issues. One scenario when they
-       can coexist safely is when the CA flows have RTTs << CC flows RTTs.
+	  Note that in general congestion avoidance (cwnd decreased when # packets
+	  queued grows) cannot coexist with congestion control (cwnd decreased only
+	  when there is packet loss) due to fairness issues. One scenario when they
+	  can coexist safely is when the CA flows have RTTs << CC flows RTTs.
 
-       For further details see http://www.brakmo.org/networking/tcp-nv/
+	  For further details see http://www.brakmo.org/networking/tcp-nv/
 
 config TCP_CONG_SCALABLE
 	tristate "Scalable TCP"
 	default n
 	---help---
-	Scalable TCP is a sender-side only change to TCP which uses a
-	MIMD congestion control algorithm which has some nice scaling
-	properties, though is known to have fairness issues.
-	See http://www.deneholme.net/tom/scalable/
+	  Scalable TCP is a sender-side only change to TCP which uses a
+	  MIMD congestion control algorithm which has some nice scaling
+	  properties, though is known to have fairness issues.
+	  See http://www.deneholme.net/tom/scalable/
 
 config TCP_CONG_LP
 	tristate "TCP Low Priority"
 	default n
 	---help---
-	TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
-	to utilize only the excess network bandwidth as compared to the
-	``fair share`` of bandwidth as targeted by TCP.
-	See http://www-ece.rice.edu/networks/TCP-LP/
+	  TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
+	  to utilize only the excess network bandwidth as compared to the
+	  ``fair share`` of bandwidth as targeted by TCP.
+	  See http://www-ece.rice.edu/networks/TCP-LP/
 
 config TCP_CONG_VENO
 	tristate "TCP Veno"
 	default n
 	---help---
-	TCP Veno is a sender-side only enhancement of TCP to obtain better
-	throughput over wireless networks. TCP Veno makes use of state
-	distinguishing to circumvent the difficult judgment of the packet loss
-	type. TCP Veno cuts down less congestion window in response to random
-	loss packets.
-	See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
+	  TCP Veno is a sender-side only enhancement of TCP to obtain better
+	  throughput over wireless networks. TCP Veno makes use of state
+	  distinguishing to circumvent the difficult judgment of the packet loss
+	  type. TCP Veno cuts down less congestion window in response to random
+	  loss packets.
+	  See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
 
 config TCP_CONG_YEAH
 	tristate "YeAH TCP"
 	select TCP_CONG_VEGAS
 	default n
 	---help---
-	YeAH-TCP is a sender-side high-speed enabled TCP congestion control
-	algorithm, which uses a mixed loss/delay approach to compute the
-	congestion window. It's design goals target high efficiency,
-	internal, RTT and Reno fairness, resilience to link loss while
-	keeping network elements load as low as possible.
+	  YeAH-TCP is a sender-side high-speed enabled TCP congestion control
+	  algorithm, which uses a mixed loss/delay approach to compute the
+	  congestion window. It's design goals target high efficiency,
+	  internal, RTT and Reno fairness, resilience to link loss while
+	  keeping network elements load as low as possible.
 
-	For further details look here:
-	  http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
+	  For further details look here:
+	    http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
 
 config TCP_CONG_ILLINOIS
 	tristate "TCP Illinois"
 	default n
 	---help---
-	TCP-Illinois is a sender-side modification of TCP Reno for
-	high speed long delay links. It uses round-trip-time to
-	adjust the alpha and beta parameters to achieve a higher average
-	throughput and maintain fairness.
+	  TCP-Illinois is a sender-side modification of TCP Reno for
+	  high speed long delay links. It uses round-trip-time to
+	  adjust the alpha and beta parameters to achieve a higher average
+	  throughput and maintain fairness.
 
-	For further details see:
-	  http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
+	  For further details see:
+	    http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
 
 config TCP_CONG_DCTCP
 	tristate "DataCenter TCP (DCTCP)"
 	default n
 	---help---
-	DCTCP leverages Explicit Congestion Notification (ECN) in the network to
-	provide multi-bit feedback to the end hosts. It is designed to provide:
+	  DCTCP leverages Explicit Congestion Notification (ECN) in the network to
+	  provide multi-bit feedback to the end hosts. It is designed to provide:
 
-	- High burst tolerance (incast due to partition/aggregate),
-	- Low latency (short flows, queries),
-	- High throughput (continuous data updates, large file transfers) with
-	  commodity, shallow-buffered switches.
+	  - High burst tolerance (incast due to partition/aggregate),
+	  - Low latency (short flows, queries),
+	  - High throughput (continuous data updates, large file transfers) with
+	    commodity, shallow-buffered switches.
 
-	All switches in the data center network running DCTCP must support
-	ECN marking and be configured for marking when reaching defined switch
-	buffer thresholds. The default ECN marking threshold heuristic for
-	DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
-	(~100KB) at 10Gbps, but might need further careful tweaking.
+	  All switches in the data center network running DCTCP must support
+	  ECN marking and be configured for marking when reaching defined switch
+	  buffer thresholds. The default ECN marking threshold heuristic for
+	  DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
+	  (~100KB) at 10Gbps, but might need further careful tweaking.
 
-	For further details see:
-	  http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+	  For further details see:
+	    http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
 
 config TCP_CONG_CDG
 	tristate "CAIA Delay-Gradient (CDG)"
 	default n
 	---help---
-	CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
-	the TCP sender in order to:
+	  CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
+	  the TCP sender in order to:
 
 	  o Use the delay gradient as a congestion signal.
 	  o Back off with an average probability that is independent of the RTT.
 	  o Coexist with flows that use loss-based congestion control.
 	  o Tolerate packet loss unrelated to congestion.
 
-	For further details see:
-	  D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
-	  delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
+	  For further details see:
+	    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.
+	  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"
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 70f92aaca411..53de8e00990e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -208,7 +208,7 @@ int inet_listen(struct socket *sock, int backlog)
 	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		goto out;
 
-	sk->sk_max_ack_backlog = backlog;
+	WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
 	/* Really, if the socket is already in listen state
 	 * we can only allow the backlog to be adjusted.
 	 */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 71c78d223dfd..577db1d50a24 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -70,11 +70,6 @@ fail:
 	fib_free_table(main_table);
 	return -ENOMEM;
 }
-
-static bool fib4_has_custom_rules(struct net *net)
-{
-	return false;
-}
 #else
 
 struct fib_table *fib_new_table(struct net *net, u32 id)
@@ -131,11 +126,6 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 	}
 	return NULL;
 }
-
-static bool fib4_has_custom_rules(struct net *net)
-{
-	return net->ipv4.fib_has_custom_rules;
-}
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 static void fib_replace_table(struct net *net, struct fib_table *old,
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
index b804ccbdb241..0c28bd469a68 100644
--- a/net/ipv4/fib_notifier.c
+++ b/net/ipv4/fib_notifier.c
@@ -9,12 +9,12 @@
 #include <net/netns/ipv4.h>
 #include <net/ip_fib.h>
 
-int call_fib4_notifier(struct notifier_block *nb, struct net *net,
+int call_fib4_notifier(struct notifier_block *nb,
 		       enum fib_event_type event_type,
 		       struct fib_notifier_info *info)
 {
 	info->family = AF_INET;
-	return call_fib_notifier(nb, net, event_type, info);
+	return call_fib_notifier(nb, event_type, info);
 }
 
 int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
@@ -34,17 +34,16 @@ static unsigned int fib4_seq_read(struct net *net)
 	return net->ipv4.fib_seq + fib4_rules_seq_read(net);
 }
 
-static int fib4_dump(struct net *net, struct notifier_block *nb)
+static int fib4_dump(struct net *net, struct notifier_block *nb,
+		     struct netlink_ext_ack *extack)
 {
 	int err;
 
-	err = fib4_rules_dump(net, nb);
+	err = fib4_rules_dump(net, nb, extack);
 	if (err)
 		return err;
 
-	fib_notify(net, nb);
-
-	return 0;
+	return fib_notify(net, nb, extack);
 }
 
 static const struct fib_notifier_ops fib4_notifier_ops_template = {
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index b43a7ba5c6a4..f99e3bac5cab 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -65,9 +65,10 @@ bool fib4_rule_default(const struct fib_rule *rule)
 }
 EXPORT_SYMBOL_GPL(fib4_rule_default);
 
-int fib4_rules_dump(struct net *net, struct notifier_block *nb)
+int fib4_rules_dump(struct net *net, struct notifier_block *nb,
+		    struct netlink_ext_ack *extack)
 {
-	return fib_rules_dump(net, nb, AF_INET);
+	return fib_rules_dump(net, nb, AF_INET, extack);
 }
 
 unsigned int fib4_rules_seq_read(struct net *net)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1ab2fb6bb37d..b9df9c09b84e 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -74,11 +74,13 @@
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
-static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
+static int call_fib_entry_notifier(struct notifier_block *nb,
 				   enum fib_event_type event_type, u32 dst,
-				   int dst_len, struct fib_alias *fa)
+				   int dst_len, struct fib_alias *fa,
+				   struct netlink_ext_ack *extack)
 {
 	struct fib_entry_notifier_info info = {
+		.info.extack = extack,
 		.dst = dst,
 		.dst_len = dst_len,
 		.fi = fa->fa_info,
@@ -86,7 +88,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 		.type = fa->fa_type,
 		.tb_id = fa->tb_id,
 	};
-	return call_fib4_notifier(nb, net, event_type, &info.info);
+	return call_fib4_notifier(nb, event_type, &info.info);
 }
 
 static int call_fib_entry_notifiers(struct net *net,
@@ -2015,10 +2017,12 @@ void fib_info_notify_update(struct net *net, struct nl_info *info)
 	}
 }
 
-static void fib_leaf_notify(struct net *net, struct key_vector *l,
-			    struct fib_table *tb, struct notifier_block *nb)
+static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb,
+			   struct notifier_block *nb,
+			   struct netlink_ext_ack *extack)
 {
 	struct fib_alias *fa;
+	int err;
 
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
 		struct fib_info *fi = fa->fa_info;
@@ -2032,39 +2036,53 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 		if (tb->tb_id != fa->tb_id)
 			continue;
 
-		call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
-					KEYLENGTH - fa->fa_slen, fa);
+		err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key,
+					      KEYLENGTH - fa->fa_slen,
+					      fa, extack);
+		if (err)
+			return err;
 	}
+	return 0;
 }
 
-static void fib_table_notify(struct net *net, struct fib_table *tb,
-			     struct notifier_block *nb)
+static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb,
+			    struct netlink_ext_ack *extack)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *l, *tp = t->kv;
 	t_key key = 0;
+	int err;
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		fib_leaf_notify(net, l, tb, nb);
+		err = fib_leaf_notify(l, tb, nb, extack);
+		if (err)
+			return err;
 
 		key = l->key + 1;
 		/* stop in case of wrap around */
 		if (key < l->key)
 			break;
 	}
+	return 0;
 }
 
-void fib_notify(struct net *net, struct notifier_block *nb)
+int fib_notify(struct net *net, struct notifier_block *nb,
+	       struct netlink_ext_ack *extack)
 {
 	unsigned int h;
+	int err;
 
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
 		struct fib_table *tb;
 
-		hlist_for_each_entry_rcu(tb, head, tb_hlist)
-			fib_table_notify(net, tb, nb);
+		hlist_for_each_entry_rcu(tb, head, tb_hlist) {
+			err = fib_table_notify(tb, nb, extack);
+			if (err)
+				return err;
+		}
 	}
+	return 0;
 }
 
 static void __trie_free_rcu(struct rcu_head *head)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4298aae74e0e..18068ed42f25 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -249,10 +249,11 @@ bool icmp_global_allow(void)
 	bool rc = false;
 
 	/* Check if token bucket is empty and cannot be refilled
-	 * without taking the spinlock.
+	 * without taking the spinlock. The READ_ONCE() are paired
+	 * with the following WRITE_ONCE() in this same function.
 	 */
-	if (!icmp_global.credit) {
-		delta = min_t(u32, now - icmp_global.stamp, HZ);
+	if (!READ_ONCE(icmp_global.credit)) {
+		delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
 		if (delta < HZ / 50)
 			return false;
 	}
@@ -262,14 +263,14 @@ bool icmp_global_allow(void)
 	if (delta >= HZ / 50) {
 		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
 		if (incr)
-			icmp_global.stamp = now;
+			WRITE_ONCE(icmp_global.stamp, now);
 	}
 	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
 	if (credit) {
 		credit--;
 		rc = true;
 	}
-	icmp_global.credit = credit;
+	WRITE_ONCE(icmp_global.credit, credit);
 	spin_unlock(&icmp_global.lock);
 	return rc;
 }
@@ -682,7 +683,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
 
 		if (dev)
-			saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
+			saddr = inet_select_addr(dev, iph->saddr,
+						 RT_SCOPE_LINK);
 		else
 			saddr = 0;
 		rcu_read_unlock();
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 480d0b22db1a..3b9c7a2725a9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1563,7 +1563,7 @@ static int ip_mc_check_igmp_msg(struct sk_buff *skb)
 	}
 }
 
-static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb)
+static __sum16 ip_mc_validate_checksum(struct sk_buff *skb)
 {
 	return skb_checksum_simple_validate(skb);
 }
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index eb30fc1770de..e4c6e8b40490 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -716,7 +716,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 	 * ones are about to clog our table.
 	 */
 	qlen = reqsk_queue_len(queue);
-	if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
+	if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
 		int young = reqsk_queue_len_young(queue) << 1;
 
 		while (thresh > 2) {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7dc79b973e6e..af154977904c 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -226,17 +226,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		r->idiag_timer = 1;
 		r->idiag_retrans = icsk->icsk_retransmits;
 		r->idiag_expires =
-			jiffies_to_msecs(icsk->icsk_timeout - jiffies);
+			jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		r->idiag_timer = 4;
 		r->idiag_retrans = icsk->icsk_probes_out;
 		r->idiag_expires =
-			jiffies_to_msecs(icsk->icsk_timeout - jiffies);
+			jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
 	} else if (timer_pending(&sk->sk_timer)) {
 		r->idiag_timer = 2;
 		r->idiag_retrans = icsk->icsk_probes_out;
 		r->idiag_expires =
-			jiffies_to_msecs(sk->sk_timer.expires - jiffies);
+			jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
 	} else {
 		r->idiag_timer = 0;
 		r->idiag_expires = 0;
@@ -342,16 +342,13 @@ static int inet_twsk_diag_fill(struct sock *sk,
 	r = nlmsg_data(nlh);
 	BUG_ON(tw->tw_state != TCP_TIME_WAIT);
 
-	tmo = tw->tw_timer.expires - jiffies;
-	if (tmo < 0)
-		tmo = 0;
-
 	inet_diag_msg_common_fill(r, sk);
 	r->idiag_retrans      = 0;
 
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
-	r->idiag_expires      = jiffies_to_msecs(tmo);
+	tmo = tw->tw_timer.expires - jiffies;
+	r->idiag_expires      = jiffies_delta_to_msecs(tmo);
 	r->idiag_rqueue	      = 0;
 	r->idiag_wqueue	      = 0;
 	r->idiag_uid	      = 0;
@@ -385,7 +382,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
 		     offsetof(struct sock, sk_cookie));
 
 	tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
-	r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
+	r->idiag_expires = jiffies_delta_to_msecs(tmo);
 	r->idiag_rqueue	= 0;
 	r->idiag_wqueue	= 0;
 	r->idiag_uid	= 0;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index be778599bfed..ff327a62c9ce 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -160,7 +160,12 @@ static void inet_peer_gc(struct inet_peer_base *base,
 					base->total / inet_peer_threshold * HZ;
 	for (i = 0; i < gc_cnt; i++) {
 		p = gc_stack[i];
-		delta = (__u32)jiffies - p->dtime;
+
+		/* The READ_ONCE() pairs with the WRITE_ONCE()
+		 * in inet_putpeer()
+		 */
+		delta = (__u32)jiffies - READ_ONCE(p->dtime);
+
 		if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
 			gc_stack[i] = NULL;
 	}
@@ -237,7 +242,10 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
 
 void inet_putpeer(struct inet_peer *p)
 {
-	p->dtime = (__u32)jiffies;
+	/* The WRITE_ONCE() pairs with itself (we run lockless)
+	 * and the READ_ONCE() in inet_peer_gc()
+	 */
+	WRITE_ONCE(p->dtime, (__u32)jiffies);
 
 	if (refcount_dec_and_test(&p->refcnt))
 		call_rcu(&p->rcu, inetpeer_free_rcu);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 10636fb6093e..572b6307a2df 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -340,6 +340,8 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 				  iph->saddr, iph->daddr, tpi->key);
 
 	if (tunnel) {
+		const struct iphdr *tnl_params;
+
 		if (__iptunnel_pull_header(skb, hdr_len, tpi->proto,
 					   raw_proto, false) < 0)
 			goto drop;
@@ -348,7 +350,9 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 			skb_pop_mac_header(skb);
 		else
 			skb_reset_mac_header(skb);
-		if (tunnel->collect_md) {
+
+		tnl_params = &tunnel->parms.iph;
+		if (tunnel->collect_md || tnl_params->daddr == 0) {
 			__be16 flags;
 			__be64 tun_id;
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index c59a78a267c3..aa438c6758a7 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -302,16 +302,31 @@ drop:
 	return true;
 }
 
+static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
+			    const struct sk_buff *hint)
+{
+	return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr &&
+	       ip_hdr(hint)->tos == iph->tos;
+}
+
 INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *));
 INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *));
 static int ip_rcv_finish_core(struct net *net, struct sock *sk,
-			      struct sk_buff *skb, struct net_device *dev)
+			      struct sk_buff *skb, struct net_device *dev,
+			      const struct sk_buff *hint)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
 	struct rtable *rt;
 	int err;
 
+	if (ip_can_use_hint(skb, iph, hint)) {
+		err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
+					dev, hint);
+		if (unlikely(err))
+			goto drop_error;
+	}
+
 	if (net->ipv4.sysctl_ip_early_demux &&
 	    !skb_dst(skb) &&
 	    !skb->sk &&
@@ -408,7 +423,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_SUCCESS;
 
-	ret = ip_rcv_finish_core(net, sk, skb, dev);
+	ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -535,11 +550,20 @@ static void ip_sublist_rcv_finish(struct list_head *head)
 	}
 }
 
+static struct sk_buff *ip_extract_route_hint(const struct net *net,
+					     struct sk_buff *skb, int rt_type)
+{
+	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+		return NULL;
+
+	return skb;
+}
+
 static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 			       struct list_head *head)
 {
+	struct sk_buff *skb, *next, *hint = NULL;
 	struct dst_entry *curr_dst = NULL;
-	struct sk_buff *skb, *next;
 	struct list_head sublist;
 
 	INIT_LIST_HEAD(&sublist);
@@ -554,11 +578,14 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		skb = l3mdev_ip_rcv(skb);
 		if (!skb)
 			continue;
-		if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
+		if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP)
 			continue;
 
 		dst = skb_dst(skb);
 		if (curr_dst != dst) {
+			hint = ip_extract_route_hint(net, skb,
+					       ((struct rtable *)dst)->rt_type);
+
 			/* dispatch old sublist */
 			if (!list_empty(&sublist))
 				ip_sublist_rcv_finish(&sublist);
@@ -611,5 +638,6 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 		list_add_tail(&skb->list, &sublist);
 	}
 	/* dispatch final sublist */
-	ip_sublist_rcv(&sublist, curr_dev, curr_net);
+	if (!list_empty(&sublist))
+		ip_sublist_rcv(&sublist, curr_dev, curr_net);
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3d8baaaf7086..9d83cb320dcb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,7 +422,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb_dst(skb)->dev;
+	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
 
 	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
 
@@ -430,7 +430,7 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	skb->protocol = htons(ETH_P_IP);
 
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-			    net, sk, skb, NULL, dev,
+			    net, sk, skb, indev, dev,
 			    ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 1452a97914a0..47f8b947eef1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -34,6 +34,9 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/dst_metadata.h>
+#include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
 
 const struct ip_tunnel_encap_ops __rcu *
 		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
@@ -126,15 +129,14 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 
 	if (!md || md->type != METADATA_IP_TUNNEL ||
 	    md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
-
 		return NULL;
 
-	res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
+	src = &md->u.tun_info;
+	res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags);
 	if (!res)
 		return NULL;
 
 	dst = &res->u.tun_info;
-	src = &md->u.tun_info;
 	dst->key.tun_id = src->key.tun_id;
 	if (src->mode & IP_TUNNEL_INFO_IPV6)
 		memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
@@ -143,6 +145,8 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 		dst->key.u.ipv4.dst = src->key.u.ipv4.src;
 	dst->key.tun_flags = src->key.tun_flags;
 	dst->mode = src->mode | IP_TUNNEL_INFO_TX;
+	ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
+				src->options_len, 0);
 
 	return res;
 }
@@ -211,30 +215,243 @@ void ip_tunnel_get_stats64(struct net_device *dev,
 EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
 
 static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
+	[LWTUNNEL_IP_UNSPEC]	= { .strict_start_type = LWTUNNEL_IP_OPTS },
 	[LWTUNNEL_IP_ID]	= { .type = NLA_U64 },
 	[LWTUNNEL_IP_DST]	= { .type = NLA_U32 },
 	[LWTUNNEL_IP_SRC]	= { .type = NLA_U32 },
 	[LWTUNNEL_IP_TTL]	= { .type = NLA_U8 },
 	[LWTUNNEL_IP_TOS]	= { .type = NLA_U8 },
 	[LWTUNNEL_IP_FLAGS]	= { .type = NLA_U16 },
+	[LWTUNNEL_IP_OPTS]	= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = {
+	[LWTUNNEL_IP_OPTS_GENEVE]	= { .type = NLA_NESTED },
+	[LWTUNNEL_IP_OPTS_VXLAN]	= { .type = NLA_NESTED },
+	[LWTUNNEL_IP_OPTS_ERSPAN]	= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
+	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
+	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
+	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+};
+
+static const struct nla_policy
+vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = {
+	[LWTUNNEL_IP_OPT_VXLAN_GBP]	= { .type = NLA_U32 },
 };
 
+static const struct nla_policy
+erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = {
+	[LWTUNNEL_IP_OPT_ERSPAN_VER]	= { .type = NLA_U8 },
+	[LWTUNNEL_IP_OPT_ERSPAN_INDEX]	= { .type = NLA_U32 },
+	[LWTUNNEL_IP_OPT_ERSPAN_DIR]	= { .type = NLA_U8 },
+	[LWTUNNEL_IP_OPT_ERSPAN_HWID]	= { .type = NLA_U8 },
+};
+
+static int ip_tun_parse_opts_geneve(struct nlattr *attr,
+				    struct ip_tunnel_info *info, int opts_len,
+				    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1];
+	int data_len, err;
+
+	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr,
+			       geneve_opt_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] ||
+	    !tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] ||
+	    !tb[LWTUNNEL_IP_OPT_GENEVE_DATA])
+		return -EINVAL;
+
+	attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA];
+	data_len = nla_len(attr);
+	if (data_len % 4)
+		return -EINVAL;
+
+	if (info) {
+		struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len;
+
+		memcpy(opt->opt_data, nla_data(attr), data_len);
+		opt->length = data_len / 4;
+		attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS];
+		opt->opt_class = nla_get_be16(attr);
+		attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
+		opt->type = nla_get_u8(attr);
+		info->key.tun_flags |= TUNNEL_GENEVE_OPT;
+	}
+
+	return sizeof(struct geneve_opt) + data_len;
+}
+
+static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
+				   struct ip_tunnel_info *info, int opts_len,
+				   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr,
+			       vxlan_opt_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP])
+		return -EINVAL;
+
+	if (info) {
+		struct vxlan_metadata *md =
+			ip_tunnel_info_opts(info) + opts_len;
+
+		attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
+		md->gbp = nla_get_u32(attr);
+		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+	}
+
+	return sizeof(struct vxlan_metadata);
+}
+
+static int ip_tun_parse_opts_erspan(struct nlattr *attr,
+				    struct ip_tunnel_info *info, int opts_len,
+				    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1];
+	int err;
+	u8 ver;
+
+	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr,
+			       erspan_opt_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER])
+		return -EINVAL;
+
+	ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]);
+	if (ver == 1) {
+		if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX])
+			return -EINVAL;
+	} else if (ver == 2) {
+		if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] ||
+		    !tb[LWTUNNEL_IP_OPT_ERSPAN_HWID])
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	if (info) {
+		struct erspan_metadata *md =
+			ip_tunnel_info_opts(info) + opts_len;
+
+		md->version = ver;
+		if (ver == 1) {
+			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX];
+			md->u.index = nla_get_be32(attr);
+		} else {
+			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR];
+			md->u.md2.dir = nla_get_u8(attr);
+			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID];
+			set_hwid(&md->u.md2, nla_get_u8(attr));
+		}
+
+		info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+	}
+
+	return sizeof(struct erspan_metadata);
+}
+
+static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
+			     struct netlink_ext_ack *extack)
+{
+	int err, rem, opt_len, opts_len = 0, type = 0;
+	struct nlattr *nla;
+
+	if (!attr)
+		return 0;
+
+	err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX,
+			   ip_opts_policy, extack);
+	if (err)
+		return err;
+
+	nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) {
+		switch (nla_type(nla)) {
+		case LWTUNNEL_IP_OPTS_GENEVE:
+			if (type && type != TUNNEL_GENEVE_OPT)
+				return -EINVAL;
+			opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len,
+							   extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			if (opts_len > IP_TUNNEL_OPTS_MAX)
+				return -EINVAL;
+			type = TUNNEL_GENEVE_OPT;
+			break;
+		case LWTUNNEL_IP_OPTS_VXLAN:
+			if (type)
+				return -EINVAL;
+			opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len,
+							  extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_VXLAN_OPT;
+			break;
+		case LWTUNNEL_IP_OPTS_ERSPAN:
+			if (type)
+				return -EINVAL;
+			opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len,
+							   extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_ERSPAN_OPT;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return opts_len;
+}
+
+static int ip_tun_get_optlen(struct nlattr *attr,
+			     struct netlink_ext_ack *extack)
+{
+	return ip_tun_parse_opts(attr, NULL, extack);
+}
+
+static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
+			   struct netlink_ext_ack *extack)
+{
+	return ip_tun_parse_opts(attr, info, extack);
+}
+
 static int ip_tun_build_state(struct nlattr *attr,
 			      unsigned int family, const void *cfg,
 			      struct lwtunnel_state **ts,
 			      struct netlink_ext_ack *extack)
 {
-	struct ip_tunnel_info *tun_info;
-	struct lwtunnel_state *new_state;
 	struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
-	int err;
+	struct lwtunnel_state *new_state;
+	struct ip_tunnel_info *tun_info;
+	int err, opt_len;
 
 	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
 					  ip_tun_policy, extack);
 	if (err < 0)
 		return err;
 
-	new_state = lwtunnel_state_alloc(sizeof(*tun_info));
+	opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack);
+	if (opt_len < 0)
+		return opt_len;
+
+	new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
 	if (!new_state)
 		return -ENOMEM;
 
@@ -242,6 +459,12 @@ static int ip_tun_build_state(struct nlattr *attr,
 
 	tun_info = lwt_tun_info(new_state);
 
+	err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack);
+	if (err < 0) {
+		lwtstate_free(new_state);
+		return err;
+	}
+
 #ifdef CONFIG_DST_CACHE
 	err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
 	if (err) {
@@ -266,10 +489,12 @@ static int ip_tun_build_state(struct nlattr *attr,
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
 
 	if (tb[LWTUNNEL_IP_FLAGS])
-		tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]);
+		tun_info->key.tun_flags |=
+				(nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) &
+				 ~TUNNEL_OPTIONS_PRESENT);
 
 	tun_info->mode = IP_TUNNEL_INFO_TX;
-	tun_info->options_len = 0;
+	tun_info->options_len = opt_len;
 
 	*ts = new_state;
 
@@ -285,6 +510,114 @@ static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
 #endif
 }
 
+static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb,
+					 struct ip_tunnel_info *tun_info)
+{
+	struct geneve_opt *opt;
+	struct nlattr *nest;
+	int offset = 0;
+
+	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE);
+	if (!nest)
+		return -ENOMEM;
+
+	while (tun_info->options_len > offset) {
+		opt = ip_tunnel_info_opts(tun_info) + offset;
+		if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS,
+				 opt->opt_class) ||
+		    nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) ||
+		    nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4,
+			    opt->opt_data)) {
+			nla_nest_cancel(skb, nest);
+			return -ENOMEM;
+		}
+		offset += sizeof(*opt) + opt->length * 4;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+}
+
+static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb,
+					struct ip_tunnel_info *tun_info)
+{
+	struct vxlan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN);
+	if (!nest)
+		return -ENOMEM;
+
+	md = ip_tunnel_info_opts(tun_info);
+	if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) {
+		nla_nest_cancel(skb, nest);
+		return -ENOMEM;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+}
+
+static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb,
+					 struct ip_tunnel_info *tun_info)
+{
+	struct erspan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN);
+	if (!nest)
+		return -ENOMEM;
+
+	md = ip_tunnel_info_opts(tun_info);
+	if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version))
+		goto err;
+
+	if (md->version == 1 &&
+	    nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index))
+		goto err;
+
+	if (md->version == 2 &&
+	    (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) ||
+	     nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID,
+			get_hwid(&md->u.md2))))
+		goto err;
+
+	nla_nest_end(skb, nest);
+	return 0;
+err:
+	nla_nest_cancel(skb, nest);
+	return -ENOMEM;
+}
+
+static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
+				  struct ip_tunnel_info *tun_info)
+{
+	struct nlattr *nest;
+	int err = 0;
+
+	if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+		return 0;
+
+	nest = nla_nest_start_noflag(skb, type);
+	if (!nest)
+		return -ENOMEM;
+
+	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT)
+		err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
+	else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT)
+		err = ip_tun_fill_encap_opts_vxlan(skb, tun_info);
+	else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)
+		err = ip_tun_fill_encap_opts_erspan(skb, tun_info);
+
+	if (err) {
+		nla_nest_cancel(skb, nest);
+		return err;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+}
+
 static int ip_tun_fill_encap_info(struct sk_buff *skb,
 				  struct lwtunnel_state *lwtstate)
 {
@@ -296,12 +629,52 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
-	    nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags))
+	    nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) ||
+	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
 		return -ENOMEM;
 
 	return 0;
 }
 
+static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
+{
+	int opt_len;
+
+	if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+		return 0;
+
+	opt_len = nla_total_size(0);		/* LWTUNNEL_IP_OPTS */
+	if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+		struct geneve_opt *opt;
+		int offset = 0;
+
+		opt_len += nla_total_size(0);	/* LWTUNNEL_IP_OPTS_GENEVE */
+		while (info->options_len > offset) {
+			opt = ip_tunnel_info_opts(info) + offset;
+			opt_len += nla_total_size(2)	/* OPT_GENEVE_CLASS */
+				   + nla_total_size(1)	/* OPT_GENEVE_TYPE */
+				   + nla_total_size(opt->length * 4);
+							/* OPT_GENEVE_DATA */
+			offset += sizeof(*opt) + opt->length * 4;
+		}
+	} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_VXLAN */
+			   + nla_total_size(4);	/* OPT_VXLAN_GBP */
+	} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+		struct erspan_metadata *md = ip_tunnel_info_opts(info);
+
+		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_ERSPAN */
+			   + nla_total_size(1)	/* OPT_ERSPAN_VER */
+			   + (md->version == 1 ? nla_total_size(4)
+						/* OPT_ERSPAN_INDEX (v1) */
+					       : nla_total_size(1) +
+						 nla_total_size(1));
+						/* OPT_ERSPAN_DIR + HWID (v2) */
+	}
+
+	return opt_len;
+}
+
 static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
 {
 	return nla_total_size_64bit(8)	/* LWTUNNEL_IP_ID */
@@ -309,13 +682,21 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
 		+ nla_total_size(4)	/* LWTUNNEL_IP_SRC */
 		+ nla_total_size(1)	/* LWTUNNEL_IP_TOS */
 		+ nla_total_size(1)	/* LWTUNNEL_IP_TTL */
-		+ nla_total_size(2);	/* LWTUNNEL_IP_FLAGS */
+		+ nla_total_size(2)	/* LWTUNNEL_IP_FLAGS */
+		+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
+					/* LWTUNNEL_IP_OPTS */
 }
 
 static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
 {
-	return memcmp(lwt_tun_info(a), lwt_tun_info(b),
-		      sizeof(struct ip_tunnel_info));
+	struct ip_tunnel_info *info_a = lwt_tun_info(a);
+	struct ip_tunnel_info *info_b = lwt_tun_info(b);
+
+	return memcmp(info_a, info_b, sizeof(info_a->key)) ||
+	       info_a->mode != info_b->mode ||
+	       info_a->options_len != info_b->options_len ||
+	       memcmp(ip_tunnel_info_opts(info_a),
+		      ip_tunnel_info_opts(info_b), info_a->options_len);
 }
 
 static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
@@ -328,12 +709,14 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
 };
 
 static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
+	[LWTUNNEL_IP6_UNSPEC]	= { .strict_start_type = LWTUNNEL_IP6_OPTS },
 	[LWTUNNEL_IP6_ID]		= { .type = NLA_U64 },
 	[LWTUNNEL_IP6_DST]		= { .len = sizeof(struct in6_addr) },
 	[LWTUNNEL_IP6_SRC]		= { .len = sizeof(struct in6_addr) },
 	[LWTUNNEL_IP6_HOPLIMIT]		= { .type = NLA_U8 },
 	[LWTUNNEL_IP6_TC]		= { .type = NLA_U8 },
 	[LWTUNNEL_IP6_FLAGS]		= { .type = NLA_U16 },
+	[LWTUNNEL_IP6_OPTS]		= { .type = NLA_NESTED },
 };
 
 static int ip6_tun_build_state(struct nlattr *attr,
@@ -341,17 +724,21 @@ static int ip6_tun_build_state(struct nlattr *attr,
 			       struct lwtunnel_state **ts,
 			       struct netlink_ext_ack *extack)
 {
-	struct ip_tunnel_info *tun_info;
-	struct lwtunnel_state *new_state;
 	struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
-	int err;
+	struct lwtunnel_state *new_state;
+	struct ip_tunnel_info *tun_info;
+	int err, opt_len;
 
 	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
 					  ip6_tun_policy, extack);
 	if (err < 0)
 		return err;
 
-	new_state = lwtunnel_state_alloc(sizeof(*tun_info));
+	opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack);
+	if (opt_len < 0)
+		return opt_len;
+
+	new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
 	if (!new_state)
 		return -ENOMEM;
 
@@ -359,6 +746,12 @@ static int ip6_tun_build_state(struct nlattr *attr,
 
 	tun_info = lwt_tun_info(new_state);
 
+	err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack);
+	if (err < 0) {
+		lwtstate_free(new_state);
+		return err;
+	}
+
 	if (tb[LWTUNNEL_IP6_ID])
 		tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
 
@@ -375,10 +768,12 @@ static int ip6_tun_build_state(struct nlattr *attr,
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
 
 	if (tb[LWTUNNEL_IP6_FLAGS])
-		tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
+		tun_info->key.tun_flags |=
+				(nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) &
+				 ~TUNNEL_OPTIONS_PRESENT);
 
 	tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
-	tun_info->options_len = 0;
+	tun_info->options_len = opt_len;
 
 	*ts = new_state;
 
@@ -396,7 +791,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
-	    nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
+	    nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) ||
+	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
 		return -ENOMEM;
 
 	return 0;
@@ -409,7 +805,9 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
 		+ nla_total_size(16)	/* LWTUNNEL_IP6_SRC */
 		+ nla_total_size(1)	/* LWTUNNEL_IP6_HOPLIMIT */
 		+ nla_total_size(1)	/* LWTUNNEL_IP6_TC */
-		+ nla_total_size(2);	/* LWTUNNEL_IP6_FLAGS */
+		+ nla_total_size(2)	/* LWTUNNEL_IP6_FLAGS */
+		+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
+					/* LWTUNNEL_IP6_OPTS */
 }
 
 static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 9bcca08efec9..f35308ff84c3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1412,6 +1412,9 @@ static int __init wait_for_devices(void)
 		struct net_device *dev;
 		int found = 0;
 
+		/* make sure deferred device probes are finished */
+		wait_for_device_probe();
+
 		rtnl_lock();
 		for_each_netdev(&init_net, dev) {
 			if (ic_is_init_dev(dev)) {
@@ -1483,10 +1486,10 @@ static int __init ip_auto_config(void)
 	 * missing values.
 	 */
 	if (ic_myaddr == NONE ||
-#ifdef CONFIG_ROOT_NFS
+#if defined(CONFIG_ROOT_NFS) || defined(CONFIG_CIFS_ROOT)
 	    (root_server_addr == NONE &&
 	     ic_servaddr == NONE &&
-	     ROOT_DEV == Root_NFS) ||
+	     (ROOT_DEV == Root_NFS || ROOT_DEV == Root_CIFS)) ||
 #endif
 	    ic_first_dev->next) {
 #ifdef IPCONFIG_DYNAMIC
@@ -1513,6 +1516,12 @@ static int __init ip_auto_config(void)
 				goto try_try_again;
 			}
 #endif
+#ifdef CONFIG_CIFS_ROOT
+			if (ROOT_DEV == Root_CIFS) {
+				pr_err("IP-Config: Retrying forever (CIFS root)...\n");
+				goto try_try_again;
+			}
+#endif
 
 			if (--retries) {
 				pr_err("IP-Config: Reopening network devices...\n");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 58007439cffd..6e68def66822 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -278,9 +278,10 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	rtnl_unlock();
 }
 
-static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb,
+			   struct netlink_ext_ack *extack)
 {
-	return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack);
 }
 
 static unsigned int ipmr_rules_seq_read(struct net *net)
@@ -336,7 +337,8 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	rtnl_unlock();
 }
 
-static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb,
+			   struct netlink_ext_ack *extack)
 {
 	return 0;
 }
@@ -3041,10 +3043,11 @@ static unsigned int ipmr_seq_read(struct net *net)
 	return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
 }
 
-static int ipmr_dump(struct net *net, struct notifier_block *nb)
+static int ipmr_dump(struct net *net, struct notifier_block *nb,
+		     struct netlink_ext_ack *extack)
 {
 	return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump,
-		       ipmr_mr_table_iter, &mrt_lock);
+		       ipmr_mr_table_iter, &mrt_lock, extack);
 }
 
 static const struct fib_notifier_ops ipmr_notifier_ops_template = {
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index ea48bd15a575..aa8738a91210 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -386,15 +386,17 @@ EXPORT_SYMBOL(mr_rtm_dumproute);
 
 int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
 	    int (*rules_dump)(struct net *net,
-			      struct notifier_block *nb),
+			      struct notifier_block *nb,
+			      struct netlink_ext_ack *extack),
 	    struct mr_table *(*mr_iter)(struct net *net,
 					struct mr_table *mrt),
-	    rwlock_t *mrt_lock)
+	    rwlock_t *mrt_lock,
+	    struct netlink_ext_ack *extack)
 {
 	struct mr_table *mrt;
 	int err;
 
-	err = rules_dump(net, nb);
+	err = rules_dump(net, nb, extack);
 	if (err)
 		return err;
 
@@ -409,17 +411,25 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
 			if (!v->dev)
 				continue;
 
-			mr_call_vif_notifier(nb, net, family,
-					     FIB_EVENT_VIF_ADD,
-					     v, vifi, mrt->id);
+			err = mr_call_vif_notifier(nb, family,
+						   FIB_EVENT_VIF_ADD,
+						   v, vifi, mrt->id, extack);
+			if (err)
+				break;
 		}
 		read_unlock(mrt_lock);
 
+		if (err)
+			return err;
+
 		/* Notify on table MFC entries */
-		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
-			mr_call_mfc_notifier(nb, net, family,
-					     FIB_EVENT_ENTRY_ADD,
-					     mfc, mrt->id);
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+			err = mr_call_mfc_notifier(nb, family,
+						   FIB_EVENT_ENTRY_ADD,
+						   mfc, mrt->id, extack);
+			if (err)
+				return err;
+		}
 	}
 
 	return 0;
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 012c4047c788..e32e41b99f0f 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -9,6 +9,8 @@
 static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,
 	.init		= nf_flow_table_init,
+	.setup		= nf_flow_table_offload_setup,
+	.action		= nf_flow_rule_route_ipv4,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ip_hook,
 	.owner		= THIS_MODULE,
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index 36a28d46149c..c94445b44d8c 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -31,16 +31,8 @@ extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol,
 	if (icmph == NULL)
 		return 1;
 
-	switch (icmph->type) {
-	case ICMP_DEST_UNREACH:
-	case ICMP_SOURCE_QUENCH:
-	case ICMP_REDIRECT:
-	case ICMP_TIME_EXCEEDED:
-	case ICMP_PARAMETERPROB:
-		break;
-	default:
+	if (!icmp_is_err(icmph->type))
 		return 1;
-	}
 
 	inside_iph = skb_header_pointer(skb, outside_hdrlen +
 					sizeof(struct icmphdr),
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fc34fd1668d6..511eaa94e2d1 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -23,7 +23,6 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS)
 
 static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
-	[NHA_UNSPEC]		= { .strict_start_type = NHA_UNSPEC + 1 },
 	[NHA_ID]		= { .type = NLA_U32 },
 	[NHA_GROUP]		= { .type = NLA_BINARY },
 	[NHA_GROUP_TYPE]	= { .type = NLA_U16 },
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 621f83434b24..f88c93c38f11 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1894,10 +1894,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
 	if (!icmph)
 		goto out;
 
-	if (icmph->type != ICMP_DEST_UNREACH &&
-	    icmph->type != ICMP_REDIRECT &&
-	    icmph->type != ICMP_TIME_EXCEEDED &&
-	    icmph->type != ICMP_PARAMETERPROB)
+	if (!icmp_is_err(icmph->type))
 		goto out;
 
 	inner_iph = skb_header_pointer(skb,
@@ -2022,10 +2019,52 @@ static int ip_mkroute_input(struct sk_buff *skb,
 	return __mkroute_input(skb, res, in_dev, daddr, saddr, tos);
 }
 
+/* Implements all the saddr-related checks as ip_route_input_slow(),
+ * assuming daddr is valid and the destination is not a local broadcast one.
+ * Uses the provided hint instead of performing a route lookup.
+ */
+int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+		      u8 tos, struct net_device *dev,
+		      const struct sk_buff *hint)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	struct rtable *rt = (struct rtable *)hint;
+	struct net *net = dev_net(dev);
+	int err = -EINVAL;
+	u32 tag = 0;
+
+	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
+		goto martian_source;
+
+	if (ipv4_is_zeronet(saddr))
+		goto martian_source;
+
+	if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
+		goto martian_source;
+
+	if (rt->rt_type != RTN_LOCAL)
+		goto skip_validate_source;
+
+	tos &= IPTOS_RT_MASK;
+	err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
+	if (err < 0)
+		goto martian_source;
+
+skip_validate_source:
+	skb_dst_copy(skb, hint);
+	return 0;
+
+martian_source:
+	ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
+	return err;
+}
+
 /*
  *	NOTE. We drop all the packets that has local source
  *	addresses, because every properly looped back packet
  *	must have correct destination already attached by output routine.
+ *	Changes in the enforced policies must be applied also to
+ *	ip_route_use_hint().
  *
  *	Such approach solves two big problems:
  *	1. Not simplex devices are handled properly.
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 535b69326f66..345b2b0ff618 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -62,10 +62,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
  * Since subsequent timestamps use the normal tcp_time_stamp value, we
  * must make sure that the resulting initial timestamp is <= tcp_time_stamp.
  */
-u64 cookie_init_timestamp(struct request_sock *req)
+u64 cookie_init_timestamp(struct request_sock *req, u64 now)
 {
 	struct inet_request_sock *ireq;
-	u32 ts, ts_now = tcp_time_stamp_raw();
+	u32 ts, ts_now = tcp_ns_to_ts(now);
 	u32 options = 0;
 
 	ireq = inet_rsk(req);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0902cb32bbad..fcb2cd167f64 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -340,6 +340,10 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 				user_key[i * 4 + 1],
 				user_key[i * 4 + 2],
 				user_key[i * 4 + 3]);
+
+		if (WARN_ON_ONCE(off >= tbl.maxlen - 1))
+			break;
+
 		if (i + 1 < n_keys)
 			off += snprintf(tbl.data + off, tbl.maxlen - off, ",");
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d8876f0e9672..9b48aec29aca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1741,8 +1741,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				struct tcp_zerocopy_receive *zc)
 {
 	unsigned long address = (unsigned long)zc->address;
+	u32 length = 0, seq, offset, zap_len;
 	const skb_frag_t *frags = NULL;
-	u32 length = 0, seq, offset;
 	struct vm_area_struct *vma;
 	struct sk_buff *skb = NULL;
 	struct tcp_sock *tp;
@@ -1769,12 +1769,12 @@ static int tcp_zerocopy_receive(struct sock *sk,
 	seq = tp->copied_seq;
 	inq = tcp_inq(sk);
 	zc->length = min_t(u32, zc->length, inq);
-	zc->length &= ~(PAGE_SIZE - 1);
-	if (zc->length) {
-		zap_page_range(vma, address, zc->length);
+	zap_len = zc->length & ~(PAGE_SIZE - 1);
+	if (zap_len) {
+		zap_page_range(vma, address, zap_len);
 		zc->recv_skip_hint = 0;
 	} else {
-		zc->recv_skip_hint = inq;
+		zc->recv_skip_hint = zc->length;
 	}
 	ret = 0;
 	while (length + PAGE_SIZE <= zc->length) {
@@ -1958,8 +1958,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 	struct scm_timestamping_internal tss;
-	bool has_tss = false;
-	bool has_cmsg;
+	int cmsg_flags;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -1974,7 +1973,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	has_cmsg = tp->recvmsg_inq;
+	cmsg_flags = tp->recvmsg_inq ? 1 : 0;
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2047,7 +2046,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 
 		/* Well, if we have backlog, try to process it now yet. */
 
-		if (copied >= target && !sk->sk_backlog.tail)
+		if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
 			break;
 
 		if (copied) {
@@ -2157,8 +2156,7 @@ skip_copy:
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
-			has_tss = true;
-			has_cmsg = true;
+			cmsg_flags |= 2;
 		}
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
@@ -2183,10 +2181,10 @@ found_fin_ok:
 
 	release_sock(sk);
 
-	if (has_cmsg) {
-		if (has_tss)
+	if (cmsg_flags) {
+		if (cmsg_flags & 2)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (tp->recvmsg_inq) {
+		if (cmsg_flags & 1) {
 			inq = tcp_inq_hint(sk);
 			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
 		}
@@ -2666,6 +2664,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
 	inet->defer_connect = 0;
+	tp->fastopen_client_fail = 0;
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
@@ -3224,8 +3223,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		 * tcpi_unacked -> Number of children ready for accept()
 		 * tcpi_sacked  -> max backlog
 		 */
-		info->tcpi_unacked = sk->sk_ack_backlog;
-		info->tcpi_sacked = sk->sk_max_ack_backlog;
+		info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog);
+		info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog);
 		return;
 	}
 
@@ -3305,6 +3304,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_reord_seen = tp->reord_seen;
 	info->tcpi_rcv_ooopack = tp->rcv_ooopack;
 	info->tcpi_snd_wnd = tp->snd_wnd;
+	info->tcpi_fastopen_client_fail = tp->fastopen_client_fail;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c445a81d144e..3737ec096650 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -256,6 +256,9 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen)
 		offs += snprintf(buf + offs, maxlen - offs,
 				 "%s%s",
 				 offs == 0 ? "" : " ", ca->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
 	}
 	rcu_read_unlock();
 }
@@ -285,6 +288,9 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
 		offs += snprintf(buf + offs, maxlen - offs,
 				 "%s%s",
 				 offs == 0 ? "" : " ", ca->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
 	}
 	rcu_read_unlock();
 }
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 549506162dde..0d08f9e2d8d0 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -21,8 +21,8 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	struct tcp_info *info = _info;
 
 	if (inet_sk_state_load(sk) == TCP_LISTEN) {
-		r->idiag_rqueue = sk->sk_ack_backlog;
-		r->idiag_wqueue = sk->sk_max_ack_backlog;
+		r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog);
+		r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog);
 	} else if (sk->sk_type == SOCK_STREAM) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index a915ade0c818..19ad9586c720 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -422,7 +422,10 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		cookie->len = -1;
 		return true;
 	}
-	return cookie->len > 0;
+	if (cookie->len > 0)
+		return true;
+	tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE;
+	return false;
 }
 
 /* This function checks if we want to defer sending SYN until the first
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a2e52ad7cdab..88b987ca9ebb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5814,6 +5814,10 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
+		if (tp->total_retrans)
+			tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED;
+		else
+			tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
 		skb_rbtree_walk_from(data) {
 			if (__tcp_retransmit_skb(sk, data, 1))
 				break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 67b2dc7a1727..92282f98dc82 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -121,11 +121,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
 			if (ipv6_addr_loopback(&tw->tw_v6_daddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_daddr) &&
-			     (tw->tw_v6_daddr.s6_addr[12] == 127)) ||
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) ||
 			    ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) ||
-			    (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) &&
-			     (tw->tw_v6_rcv_saddr.s6_addr[12] == 127)))
+			    ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr))
 				loopback = true;
 		} else
 #endif
@@ -2453,7 +2451,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
-		rx_queue = sk->sk_ack_backlog;
+		rx_queue = READ_ONCE(sk->sk_ack_backlog);
 	else
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0488607c5cd3..be6d22b8190f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3290,7 +3290,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	now = tcp_clock_ns();
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(req->cookie_ts))
-		skb->skb_mstamp_ns = cookie_init_timestamp(req);
+		skb->skb_mstamp_ns = cookie_init_timestamp(req, now);
 	else
 #endif
 	{
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 4849edb62d52..12ab5db2b71c 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -92,6 +92,9 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
 		offs += snprintf(buf + offs, maxlen - offs,
 				 "%s%s",
 				 offs == 0 ? "" : " ", ulp_ops->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
 	}
 	rcu_read_unlock();
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 447defbfccdd..4da5758cc718 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2551,9 +2551,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 	case UDP_ENCAP:
 		switch (val) {
 		case 0:
+#ifdef CONFIG_XFRM
 		case UDP_ENCAP_ESPINUDP:
 		case UDP_ENCAP_ESPINUDP_NON_IKE:
 			up->encap_rcv = xfrm4_udp_encap_rcv;
+#endif
 			/* FALLTHROUGH */
 		case UDP_ENCAP_L2TPINUDP:
 			up->encap_type = val;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index ecff3fce9807..89ba7c87de5d 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -92,7 +92,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-			    net, sk, skb, NULL, skb_dst(skb)->dev,
+			    net, sk, skb, skb->dev, skb_dst(skb)->dev,
 			    __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }