ip_tunnels: extend iptunnel_xmit()

Refactor various ip tunnels xmit functions and extend iptunnel_xmit()
so that there is more code sharing.

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vxlan.c

@@ -1021,7 +1021,6 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct rtable *rt;
 	const struct iphdr *old_iph;
-	struct iphdr *iph;
 	struct vxlanhdr *vxh;
 	struct udphdr *uh;
 	struct flowi4 fl4;
@@ -1030,6 +1029,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
         u32 vni;
 	__be16 df = 0;
 	__u8 tos, ttl;
+	int err;
 
 	dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
 	vni = rdst->remote_vni;
@@ -1097,13 +1097,6 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		vxlan_encap_bypass(skb, vxlan, dst_vxlan);
 		return NETDEV_TX_OK;
 	}
-
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
 	vxh->vx_vni = htonl(vni << 8);
@@ -1118,27 +1111,18 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	uh->len = htons(skb->len);
 	uh->check = 0;
 
-	__skb_push(skb, sizeof(*iph));
-	skb_reset_network_header(skb);
-	iph		= ip_hdr(skb);
-	iph->version	= 4;
-	iph->ihl	= sizeof(struct iphdr) >> 2;
-	iph->frag_off	= df;
-	iph->protocol	= IPPROTO_UDP;
-	iph->tos	= ip_tunnel_ecn_encap(tos, old_iph, skb);
-	iph->daddr	= dst;
-	iph->saddr	= fl4.saddr;
-	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);
-	tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
-	nf_reset(skb);
-
 	vxlan_set_owner(dev, skb);
 
 	if (handle_offloads(skb))
 		goto drop;
 
-	iptunnel_xmit(skb, dev);
+	tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+	ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+	err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, dst,
+			    IPPROTO_UDP, tos, ttl, df);
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+
 	return NETDEV_TX_OK;
 
 drop:

include/net/ip_tunnels.h

@@ -155,23 +155,27 @@ static inline void tunnel_ip_select_ident(struct sk_buff *skb,
 				  (skb_shinfo(skb)->gso_segs ?: 1) - 1);
 }
 
-static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+int iptunnel_xmit(struct net *net, struct rtable *rt,
+		  struct sk_buff *skb,
+		  __be32 src, __be32 dst, __u8 proto,
+		  __u8 tos, __u8 ttl, __be16 df);
+
+static inline void iptunnel_xmit_stats(int err,
+				       struct net_device_stats *err_stats,
+				       struct pcpu_tstats __percpu *stats)
 {
-	int err;
-	int pkt_len = skb->len - skb_transport_offset(skb);
-	struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
+	if (err > 0) {
+		struct pcpu_tstats *tstats = this_cpu_ptr(stats);
 
-	nf_reset(skb);
-
-	err = ip_local_out(skb);
-	if (likely(net_xmit_eval(err) == 0)) {
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += pkt_len;
+		tstats->tx_bytes += err;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+	} else if (err < 0) {
+		err_stats->tx_errors++;
+		err_stats->tx_aborted_errors++;
 	} else {
-		dev->stats.tx_errors++;
-		dev->stats.tx_aborted_errors++;
+		err_stats->tx_dropped++;
 	}
 }
 #endif /* __NET_IP_TUNNELS_H */

net/ipv4/Makefile

@@ -11,7 +11,7 @@ obj-y     := route.o inetpeer.o protocol.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 \
-	     inet_fragment.o ping.o
+	     inet_fragment.o ping.o ip_tunnel_core.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o

net/ipv4/ip_tunnel.c

@@ -491,19 +491,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *inner_iph;
-	struct iphdr *iph;
 	struct flowi4 fl4;
 	u8     tos, ttl;
 	__be16 df;
 	struct rtable *rt;		/* Route to the other host */
-	struct net_device *tdev;	/* Device to other host */
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int mtu;
+	int err;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -571,14 +569,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		dev->stats.tx_carrier_errors++;
 		goto tx_error;
 	}
-	tdev = rt->dst.dev;
-
-	if (tdev == dev) {
+	if (rt->dst.dev == dev) {
 		ip_rt_put(rt);
 		dev->stats.collisions++;
 		goto tx_error;
 	}
-
 	df = tnl_params->frag_off;
 
 	if (df)
@@ -596,6 +591,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		if (!skb_is_gso(skb) &&
 		    (inner_iph->frag_off&htons(IP_DF)) &&
 		     mtu < ntohs(inner_iph->tot_len)) {
+			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			ip_rt_put(rt);
 			goto tx_error;
@@ -646,8 +642,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
-					       + rt->dst.header_len;
+	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+			+ rt->dst.header_len;
 	if (max_headroom > dev->needed_headroom) {
 		dev->needed_headroom = max_headroom;
 		if (skb_cow_head(skb, dev->needed_headroom)) {
@@ -657,27 +653,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-
-	/* Push down and install the IP header. */
-	skb_push(skb, sizeof(struct iphdr));
-	skb_reset_network_header(skb);
-
-	iph = ip_hdr(skb);
-	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	err = iptunnel_xmit(dev_net(dev), rt, skb,
+			    fl4.saddr, fl4.daddr, protocol,
+			    ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df);
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 
-	iph->version	=	4;
-	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
-	iph->protocol	=	protocol;
-	iph->tos	=	ip_tunnel_ecn_encap(tos, inner_iph, skb);
-	iph->daddr	=	fl4.daddr;
-	iph->saddr	=	fl4.saddr;
-	iph->ttl	=	ttl;
-	tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
-
-	iptunnel_xmit(skb, dev);
 	return;
 
 #if IS_ENABLED(CONFIG_IPV6)

net/ipv4/ip_tunnel_core.c

@@ -0,0 +1,88 @@
+/*
+ * Copyright (c) 2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/if_arp.h>
+#include <linux/mroute.h>
+#include <linux/init.h>
+#include <linux/in6.h>
+#include <linux/inetdevice.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+#include <net/ip_tunnels.h>
+#include <net/arp.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+
+int iptunnel_xmit(struct net *net, struct rtable *rt,
+		  struct sk_buff *skb,
+		  __be32 src, __be32 dst, __u8 proto,
+		  __u8 tos, __u8 ttl, __be16 df)
+{
+	int pkt_len = skb->len;
+	struct iphdr *iph;
+	int err;
+
+	nf_reset(skb);
+	secpath_reset(skb);
+	skb->rxhash = 0;
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+	/* Push down and install the IP header. */
+	__skb_push(skb, sizeof(struct iphdr));
+	skb_reset_network_header(skb);
+
+	iph = ip_hdr(skb);
+
+	iph->version	=	4;
+	iph->ihl	=	sizeof(struct iphdr) >> 2;
+	iph->frag_off	=	df;
+	iph->protocol	=	proto;
+	iph->tos	=	tos;
+	iph->daddr	=	dst;
+	iph->saddr	=	src;
+	iph->ttl	=	ttl;
+	tunnel_ip_select_ident(skb,
+			       (const struct iphdr *)skb_inner_network_header(skb),
+			       &rt->dst);
+
+	err = ip_local_out(skb);
+	if (unlikely(net_xmit_eval(err)))
+		pkt_len = 0;
+	return pkt_len;
+}
+EXPORT_SYMBOL_GPL(iptunnel_xmit);

net/ipv6/sit.c

@@ -723,13 +723,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	__be16 df = tiph->frag_off;
 	struct rtable *rt;     			/* Route to the other host */
 	struct net_device *tdev;		/* Device to other host */
-	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	struct flowi4 fl4;
 	int    mtu;
 	const struct in6_addr *addr6;
 	int addr_type;
+	u8 ttl;
+	int err;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto tx_error;
@@ -872,34 +873,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		skb = new_skb;
 		iph6 = ipv6_hdr(skb);
 	}
-
-	skb->transport_header = skb->network_header;
-	skb_push(skb, sizeof(struct iphdr));
-	skb_reset_network_header(skb);
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags = 0;
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-
-	/*
-	 *	Push down and install the IPIP header.
-	 */
-
-	iph 			=	ip_hdr(skb);
-	iph->version		=	4;
-	iph->ihl		=	sizeof(struct iphdr)>>2;
-	iph->frag_off		=	df;
-	iph->protocol		=	IPPROTO_IPV6;
-	iph->tos		=	INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
-	iph->daddr		=	fl4.daddr;
-	iph->saddr		=	fl4.saddr;
-
-	if ((iph->ttl = tiph->ttl) == 0)
-		iph->ttl	=	iph6->hop_limit;
-
-	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(iph, skb_dst(skb), NULL);
-	iptunnel_xmit(skb, dev);
+	ttl = tiph->ttl;
+	if (ttl == 0)
+		ttl = iph6->hop_limit;
+	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
+
+	err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, fl4.daddr,
+			    IPPROTO_IPV6, tos, ttl, df);
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
 
 tx_error_icmp: