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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

53 files changed, 1365 insertions, 910 deletions

diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c6d4238ff94a..f83de23a30e7 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -11,7 +11,7 @@ obj-y     := route.o inetpeer.o protocol.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 \
+	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 13a9a3297eae..f3dad1661343 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1602,8 +1602,9 @@ static const struct net_protocol igmp_protocol = {
 };
 #endif
 
-static const struct net_protocol tcp_protocol = {
+static struct net_protocol tcp_protocol = {
 	.early_demux	=	tcp_v4_early_demux,
+	.early_demux_handler =  tcp_v4_early_demux,
 	.handler	=	tcp_v4_rcv,
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
@@ -1611,8 +1612,9 @@ static const struct net_protocol tcp_protocol = {
 	.icmp_strict_tag_validation = 1,
 };
 
-static const struct net_protocol udp_protocol = {
+static struct net_protocol udp_protocol = {
 	.early_demux =	udp_v4_early_demux,
+	.early_demux_handler =	udp_v4_early_demux,
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
@@ -1723,6 +1725,8 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
+	net->ipv4.sysctl_udp_early_demux = 1;
+	net->ipv4.sysctl_tcp_early_demux = 1;
 #ifdef CONFIG_SYSCTL
 	net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
 #endif
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 51b27ae09fbd..0937b34c27ca 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -872,7 +872,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		    skb->pkt_type != PACKET_HOST)
 			state = NUD_STALE;
 		neigh_update(n, sha, state,
-			     override ? NEIGH_UPDATE_F_OVERRIDE : 0);
+			     override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
 		neigh_release(n);
 	}
 
@@ -1033,7 +1033,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 		err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
 				   r->arp_ha.sa_data : NULL, state,
 				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
+				   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 	return err;
@@ -1084,7 +1084,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip)
 		if (neigh->nud_state & ~NUD_NOARP)
 			err = neigh_update(neigh, NULL, NUD_FAILED,
 					   NEIGH_UPDATE_F_OVERRIDE|
-					   NEIGH_UPDATE_F_ADMIN);
+					   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebedd545e5e..df14815a3b8c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -571,7 +571,8 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	return ret;
 }
 
-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -582,7 +583,8 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -752,7 +754,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	struct in_device *in_dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
+			  NULL);
 	if (err < 0)
 		goto errout;
 
@@ -843,7 +846,8 @@ static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
 	return NULL;
 }
 
-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct in_ifaddr *ifa;
@@ -1192,6 +1196,18 @@ out:
 	return done;
 }
 
+static __be32 in_dev_select_addr(const struct in_device *in_dev,
+				 int scope)
+{
+	for_primary_ifa(in_dev) {
+		if (ifa->ifa_scope != RT_SCOPE_LINK &&
+		    ifa->ifa_scope <= scope)
+			return ifa->ifa_local;
+	} endfor_ifa(in_dev);
+
+	return 0;
+}
+
 __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
 {
 	__be32 addr = 0;
@@ -1228,13 +1244,9 @@ no_in_dev:
 	if (master_idx &&
 	    (dev = dev_get_by_index_rcu(net, master_idx)) &&
 	    (in_dev = __in_dev_get_rcu(dev))) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 
 	/* Not loopback addresses on loopback should be preferred
@@ -1249,13 +1261,9 @@ no_in_dev:
 		if (!in_dev)
 			continue;
 
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 out_unlock:
 	rcu_read_unlock();
@@ -1713,7 +1721,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 	if (dev && !__in_dev_get_rtnl(dev))
 		return -EAFNOSUPPORT;
 
-	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy);
+	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1741,7 +1749,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	if (!in_dev)
 		return -EAFNOSUPPORT;
 
-	if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0)
+	if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
 	if (tb[IFLA_INET_CONF]) {
@@ -1798,6 +1806,9 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
+	if (!devconf)
+		goto out;
+
 	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING,
 			IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
@@ -1819,6 +1830,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
 		goto nla_put_failure;
 
+out:
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1827,8 +1839,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				 struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+				 int ifindex, struct ipv4_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -1838,7 +1850,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
 		goto errout;
 
 	err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
-					RTM_NEWNETCONF, 0, type);
+					event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -1861,7 +1873,8 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
-				    struct nlmsghdr *nlh)
+				    struct nlmsghdr *nlh,
+				    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
@@ -1874,7 +1887,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
-			  devconf_ipv4_policy);
+			  devconf_ipv4_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -2017,10 +2030,12 @@ static void inet_forward_change(struct net *net)
 
 	IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
 	IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_ALL,
 				    net->ipv4.devconf_all);
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_DEFAULT,
 				    net->ipv4.devconf_dflt);
 
@@ -2033,7 +2048,8 @@ static void inet_forward_change(struct net *net)
 		in_dev = __in_dev_get_rtnl(dev);
 		if (in_dev) {
 			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    dev->ifindex, &in_dev->cnf);
 		}
 	}
@@ -2078,19 +2094,22 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_RP_FILTER,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_PROXY_NEIGH,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						    ifindex, cnf);
 		}
 	}
@@ -2125,7 +2144,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 					container_of(cnf, struct in_device, cnf);
 				if (*valp)
 					dev_disable_lro(idev->dev);
-				inet_netconf_notify_devconf(net,
+				inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
 							    NETCONFA_FORWARDING,
 							    idev->dev->ifindex,
 							    cnf);
@@ -2133,7 +2152,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 			rtnl_unlock();
 			rt_cache_flush(net);
 		} else
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    NETCONFA_IFINDEX_DEFAULT,
 						    net->ipv4.devconf_dflt);
 	}
@@ -2255,7 +2275,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 
 	p->sysctl = t;
 
-	inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+				    ifindex, p);
 	return 0;
 
 free:
@@ -2264,16 +2285,18 @@ out:
 	return -ENOBUFS;
 }
 
-static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
+static void __devinet_sysctl_unregister(struct net *net,
+					struct ipv4_devconf *cnf, int ifindex)
 {
 	struct devinet_sysctl_table *t = cnf->sysctl;
 
-	if (!t)
-		return;
+	if (t) {
+		cnf->sysctl = NULL;
+		unregister_net_sysctl_table(t->sysctl_header);
+		kfree(t);
+	}
 
-	cnf->sysctl = NULL;
-	unregister_net_sysctl_table(t->sysctl_header);
-	kfree(t);
+	inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
 }
 
 static int devinet_sysctl_register(struct in_device *idev)
@@ -2295,7 +2318,9 @@ static int devinet_sysctl_register(struct in_device *idev)
 
 static void devinet_sysctl_unregister(struct in_device *idev)
 {
-	__devinet_sysctl_unregister(&idev->cnf);
+	struct net *net = dev_net(idev->dev);
+
+	__devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex);
 	neigh_sysctl_unregister(idev->arp_parms);
 }
 
@@ -2370,9 +2395,9 @@ static __net_init int devinet_init_net(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 err_reg_ctl:
-	__devinet_sysctl_unregister(dflt);
+	__devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT);
 err_reg_dflt:
-	__devinet_sysctl_unregister(all);
+	__devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
 err_reg_all:
 	if (tbl != ctl_forward_entry)
 		kfree(tbl);
@@ -2394,8 +2419,10 @@ static __net_exit void devinet_exit_net(struct net *net)
 
 	tbl = net->ipv4.forw_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv4.forw_hdr);
-	__devinet_sysctl_unregister(net->ipv4.devconf_dflt);
-	__devinet_sysctl_unregister(net->ipv4.devconf_all);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_dflt,
+				    NETCONFA_IFINDEX_DEFAULT);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_all,
+				    NETCONFA_IFINDEX_ALL);
 	kfree(tbl);
 #endif
 	kfree(net->ipv4.devconf_dflt);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b1e24446e297..65cc02bd82bc 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -152,21 +152,28 @@ static void esp_output_restore_header(struct sk_buff *skb)
 }
 
 static struct ip_esp_hdr *esp_output_set_extra(struct sk_buff *skb,
+					       struct xfrm_state *x,
 					       struct ip_esp_hdr *esph,
 					       struct esp_output_extra *extra)
 {
-	struct xfrm_state *x = skb_dst(skb)->xfrm;
-
 	/* For ESN we move the header forward by 4 bytes to
 	 * accomodate the high bits.  We will move it back after
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
+		__u32 seqhi;
+		struct xfrm_offload *xo = xfrm_offload(skb);
+
+		if (xo)
+			seqhi = xo->seq.hi;
+		else
+			seqhi = XFRM_SKB_CB(skb)->seq.output.hi;
+
 		extra->esphoff = (unsigned char *)esph -
 				 skb_transport_header(skb);
 		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
 		extra->seqhi = esph->spi;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		esph->seq_no = htonl(seqhi);
 	}
 
 	esph->spi = x->id.spi;
@@ -198,98 +205,56 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
+static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
-	struct esp_output_extra *extra;
-	int err = -ENOMEM;
-	struct ip_esp_hdr *esph;
-	struct crypto_aead *aead;
-	struct aead_request *req;
-	struct scatterlist *sg, *dsg;
-	struct sk_buff *trailer;
-	struct page *page;
-	void *tmp;
-	u8 *iv;
-	u8 *tail;
-	u8 *vaddr;
-	int blksize;
-	int clen;
-	int alen;
-	int plen;
-	int ivlen;
-	int tfclen;
-	int nfrags;
-	int assoclen;
-	int extralen;
-	int tailen;
-	__be64 seqno;
-	__u8 proto = *skb_mac_header(skb);
-
-	/* skb is pure payload to encrypt */
-
-	aead = x->data;
-	alen = crypto_aead_authsize(aead);
-	ivlen = crypto_aead_ivsize(aead);
-
-	tfclen = 0;
-	if (x->tfcpad) {
-		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
-		u32 padto;
-
-		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
-		if (skb->len < padto)
-			tfclen = padto - skb->len;
+	int encap_type;
+	struct udphdr *uh;
+	__be32 *udpdata32;
+	__be16 sport, dport;
+	struct xfrm_encap_tmpl *encap = x->encap;
+	struct ip_esp_hdr *esph = esp->esph;
+
+	spin_lock_bh(&x->lock);
+	sport = encap->encap_sport;
+	dport = encap->encap_dport;
+	encap_type = encap->encap_type;
+	spin_unlock_bh(&x->lock);
+
+	uh = (struct udphdr *)esph;
+	uh->source = sport;
+	uh->dest = dport;
+	uh->len = htons(skb->len + esp->tailen
+		  - skb_transport_offset(skb));
+	uh->check = 0;
+
+	switch (encap_type) {
+	default:
+	case UDP_ENCAP_ESPINUDP:
+		esph = (struct ip_esp_hdr *)(uh + 1);
+		break;
+	case UDP_ENCAP_ESPINUDP_NON_IKE:
+		udpdata32 = (__be32 *)(uh + 1);
+		udpdata32[0] = udpdata32[1] = 0;
+		esph = (struct ip_esp_hdr *)(udpdata32 + 2);
+		break;
 	}
-	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
-	clen = ALIGN(skb->len + 2 + tfclen, blksize);
-	plen = clen - skb->len - tfclen;
-	tailen = tfclen + plen + alen;
-	assoclen = sizeof(*esph);
-	extralen = 0;
 
-	if (x->props.flags & XFRM_STATE_ESN) {
-		extralen += sizeof(*extra);
-		assoclen += sizeof(__be32);
-	}
+	*skb_mac_header(skb) = IPPROTO_UDP;
+	esp->esph = esph;
+}
 
-	*skb_mac_header(skb) = IPPROTO_ESP;
-	esph = ip_esp_hdr(skb);
+int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+{
+	u8 *tail;
+	u8 *vaddr;
+	int nfrags;
+	struct page *page;
+	struct sk_buff *trailer;
+	int tailen = esp->tailen;
 
 	/* this is non-NULL only with UDP Encapsulation */
-	if (x->encap) {
-		struct xfrm_encap_tmpl *encap = x->encap;
-		struct udphdr *uh;
-		__be32 *udpdata32;
-		__be16 sport, dport;
-		int encap_type;
-
-		spin_lock_bh(&x->lock);
-		sport = encap->encap_sport;
-		dport = encap->encap_dport;
-		encap_type = encap->encap_type;
-		spin_unlock_bh(&x->lock);
-
-		uh = (struct udphdr *)esph;
-		uh->source = sport;
-		uh->dest = dport;
-		uh->len = htons(skb->len + tailen
-				- skb_transport_offset(skb));
-		uh->check = 0;
-
-		switch (encap_type) {
-		default:
-		case UDP_ENCAP_ESPINUDP:
-			esph = (struct ip_esp_hdr *)(uh + 1);
-			break;
-		case UDP_ENCAP_ESPINUDP_NON_IKE:
-			udpdata32 = (__be32 *)(uh + 1);
-			udpdata32[0] = udpdata32[1] = 0;
-			esph = (struct ip_esp_hdr *)(udpdata32 + 2);
-			break;
-		}
-
-		*skb_mac_header(skb) = IPPROTO_UDP;
-	}
+	if (x->encap)
+		esp_output_udp_encap(x, skb, esp);
 
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_availroom(skb)) {
@@ -304,6 +269,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 			struct sock *sk = skb->sk;
 			struct page_frag *pfrag = &x->xfrag;
 
+			esp->inplace = false;
+
 			allocsize = ALIGN(tailen, L1_CACHE_BYTES);
 
 			spin_lock_bh(&x->lock);
@@ -320,10 +287,12 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 			tail = vaddr + pfrag->offset;
 
-			esp_output_fill_trailer(tail, tfclen, plen, proto);
+			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
 			kunmap_atomic(vaddr);
 
+			spin_unlock_bh(&x->lock);
+
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -339,107 +308,113 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 			if (sk)
 				atomic_add(tailen, &sk->sk_wmem_alloc);
 
-			skb_push(skb, -skb_network_offset(skb));
-
-			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
-			esph->spi = x->id.spi;
-
-			tmp = esp_alloc_tmp(aead, nfrags + 2, extralen);
-			if (!tmp) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-
-			extra = esp_tmp_extra(tmp);
-			iv = esp_tmp_iv(aead, tmp, extralen);
-			req = esp_tmp_req(aead, iv);
-			sg = esp_req_sg(aead, req);
-			dsg = &sg[nfrags];
-
-			esph = esp_output_set_extra(skb, esph, extra);
-
-			sg_init_table(sg, nfrags);
-			skb_to_sgvec(skb, sg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
-
-			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-
-			skb_shinfo(skb)->nr_frags = 1;
-
-			page = pfrag->page;
-			get_page(page);
-			/* replace page frags in skb with new page */
-			__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
-			pfrag->offset = pfrag->offset + allocsize;
-
-			sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
-			skb_to_sgvec(skb, dsg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			spin_unlock_bh(&x->lock);
-
-			goto skip_cow2;
+			goto out;
 		}
 	}
 
 cow:
-	err = skb_cow_data(skb, tailen, &trailer);
-	if (err < 0)
-		go