912 lines · 22.1 KB · C
RawDownload
/* *	Linux NET3:	IP/IP protocol decoder. * *	Authors: *		Sam Lantinga (slouken@cs.ucdavis.edu)  02/01/95 * *	Fixes: *		Alan Cox	:	Merged and made usable non modular (its so tiny its silly as *					a module taking up 2 pages). *		Alan Cox	: 	Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph) *					to keep ip_forward happy. *		Alan Cox	:	More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8). *		Kai Schulte	:	Fixed #defines for IP_FIREWALL->FIREWALL *              David Woodhouse :       Perform some basic ICMP handling. *                                      IPIP Routing without decapsulation. *              Carlos Picoto   :       GRE over IP support *		Alexey Kuznetsov:	Reworked. Really, now it is truncated version of ipv4/ip_gre.c. *					I do not want to merge them together. * *	This program is free software; you can redistribute it and/or *	modify it under the terms of the GNU General Public License *	as published by the Free Software Foundation; either version *	2 of the License, or (at your option) any later version. * */ /* tunnel.c: an IP tunnel driver 	The purpose of this driver is to provide an IP tunnel through	which you can tunnel network traffic transparently across subnets. 	This was written by looking at Nick Holloway's dummy driver	Thanks for the great code! 		-Sam Lantinga	(slouken@cs.ucdavis.edu)  02/01/95 	Minor tweaks:		Cleaned up the code a little and added some pre-1.3.0 tweaks.		dev->hard_header/hard_header_len changed to use no headers.		Comments/bracketing tweaked.		Made the tunnels use dev->name not tunnel: when error reporting.		Added tx_dropped stat 		-Alan Cox	(alan@lxorguk.ukuu.org.uk) 21 March 95 	Reworked:		Changed to tunnel to destination gateway in addition to the			tunnel's pointopoint address		Almost completely rewritten		Note:  There is currently no firewall or ICMP handling done. 		-Sam Lantinga	(slouken@cs.ucdavis.edu) 02/13/96 */ /* Things I wish I had known when writing the tunnel driver: 	When the tunnel_xmit() function is called, the skb contains the	packet to be sent (plus a great deal of extra info), and dev	contains the tunnel device that _we_ are. 	When we are passed a packet, we are expected to fill in the	source address with our source IP address. 	What is the proper way to allocate, copy and free a buffer?	After you allocate it, it is a "0 length" chunk of memory	starting at zero.  If you want to add headers to the buffer	later, you'll have to call "skb_reserve(skb, amount)" with	the amount of memory you want reserved.  Then, you call	"skb_put(skb, amount)" with the amount of space you want in	the buffer.  skb_put() returns a pointer to the top (#0) of	that buffer.  skb->len is set to the amount of space you have	"allocated" with skb_put().  You can then write up to skb->len	bytes to that buffer.  If you need more, you can call skb_put()	again with the additional amount of space you need.  You can	find out how much more space you can allocate by calling	"skb_tailroom(skb)".	Now, to add header space, call "skb_push(skb, header_len)".	This creates space at the beginning of the buffer and returns	a pointer to this new space.  If later you need to strip a	header from a buffer, call "skb_pull(skb, header_len)".	skb_headroom() will return how much space is left at the top	of the buffer (before the main data).  Remember, this headroom	space must be reserved before the skb_put() function is called.	*/ /*   This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c    For comments look at net/ipv4/ip_gre.c --ANK */  #include <linux/capability.h>#include <linux/module.h>#include <linux/types.h>#include <linux/kernel.h>#include <linux/slab.h>#include <asm/uaccess.h>#include <linux/skbuff.h>#include <linux/netdevice.h>#include <linux/in.h>#include <linux/tcp.h>#include <linux/udp.h>#include <linux/if_arp.h>#include <linux/mroute.h>#include <linux/init.h>#include <linux/netfilter_ipv4.h>#include <linux/if_ether.h> #include <net/sock.h>#include <net/ip.h>#include <net/icmp.h>#include <net/ipip.h>#include <net/inet_ecn.h>#include <net/xfrm.h>#include <net/net_namespace.h>#include <net/netns/generic.h> #define HASH_SIZE  16#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) static int ipip_net_id __read_mostly;struct ipip_net {	struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];	struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];	struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];	struct ip_tunnel __rcu *tunnels_wc[1];	struct ip_tunnel __rcu **tunnels[4]; 	struct net_device *fb_tunnel_dev;}; static int ipip_tunnel_init(struct net_device *dev);static void ipip_tunnel_setup(struct net_device *dev);static void ipip_dev_free(struct net_device *dev); /* * Locking : hash tables are protected by RCU and RTNL */ #define for_each_ip_tunnel_rcu(start) \	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /* often modified stats are per cpu, other are shared (netdev->stats) */struct pcpu_tstats {	unsigned long	rx_packets;	unsigned long	rx_bytes;	unsigned long	tx_packets;	unsigned long	tx_bytes;}; static struct net_device_stats *ipip_get_stats(struct net_device *dev){	struct pcpu_tstats sum = { 0 };	int i; 	for_each_possible_cpu(i) {		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); 		sum.rx_packets += tstats->rx_packets;		sum.rx_bytes   += tstats->rx_bytes;		sum.tx_packets += tstats->tx_packets;		sum.tx_bytes   += tstats->tx_bytes;	}	dev->stats.rx_packets = sum.rx_packets;	dev->stats.rx_bytes   = sum.rx_bytes;	dev->stats.tx_packets = sum.tx_packets;	dev->stats.tx_bytes   = sum.tx_bytes;	return &dev->stats;} static struct ip_tunnel * ipip_tunnel_lookup(struct net *net,		__be32 remote, __be32 local){	unsigned int h0 = HASH(remote);	unsigned int h1 = HASH(local);	struct ip_tunnel *t;	struct ipip_net *ipn = net_generic(net, ipip_net_id); 	for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])		if (local == t->parms.iph.saddr &&		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))			return t; 	for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))			return t; 	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))			return t; 	t = rcu_dereference(ipn->tunnels_wc[0]);	if (t && (t->dev->flags&IFF_UP))		return t;	return NULL;} static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,		struct ip_tunnel_parm *parms){	__be32 remote = parms->iph.daddr;	__be32 local = parms->iph.saddr;	unsigned int h = 0;	int prio = 0; 	if (remote) {		prio |= 2;		h ^= HASH(remote);	}	if (local) {		prio |= 1;		h ^= HASH(local);	}	return &ipn->tunnels[prio][h];} static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,		struct ip_tunnel *t){	return __ipip_bucket(ipn, &t->parms);} static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t){	struct ip_tunnel __rcu **tp;	struct ip_tunnel *iter; 	for (tp = ipip_bucket(ipn, t);	     (iter = rtnl_dereference(*tp)) != NULL;	     tp = &iter->next) {		if (t == iter) {			RCU_INIT_POINTER(*tp, t->next);			break;		}	}} static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t){	struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t); 	RCU_INIT_POINTER(t->next, rtnl_dereference(*tp));	RCU_INIT_POINTER(*tp, t);} static struct ip_tunnel * ipip_tunnel_locate(struct net *net,		struct ip_tunnel_parm *parms, int create){	__be32 remote = parms->iph.daddr;	__be32 local = parms->iph.saddr;	struct ip_tunnel *t, *nt;	struct ip_tunnel __rcu **tp;	struct net_device *dev;	char name[IFNAMSIZ];	struct ipip_net *ipn = net_generic(net, ipip_net_id); 	for (tp = __ipip_bucket(ipn, parms);		 (t = rtnl_dereference(*tp)) != NULL;		 tp = &t->next) {		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)			return t;	}	if (!create)		return NULL; 	if (parms->name[0])		strlcpy(name, parms->name, IFNAMSIZ);	else		strcpy(name, "tunl%d"); 	dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);	if (dev == NULL)		return NULL; 	dev_net_set(dev, net); 	nt = netdev_priv(dev);	nt->parms = *parms; 	if (ipip_tunnel_init(dev) < 0)		goto failed_free; 	if (register_netdevice(dev) < 0)		goto failed_free; 	strcpy(nt->parms.name, dev->name); 	dev_hold(dev);	ipip_tunnel_link(ipn, nt);	return nt; failed_free:	ipip_dev_free(dev);	return NULL;} /* called with RTNL */static void ipip_tunnel_uninit(struct net_device *dev){	struct net *net = dev_net(dev);	struct ipip_net *ipn = net_generic(net, ipip_net_id); 	if (dev == ipn->fb_tunnel_dev)		RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);	else		ipip_tunnel_unlink(ipn, netdev_priv(dev));	dev_put(dev);} static int ipip_err(struct sk_buff *skb, u32 info){ /* All the routers (except for Linux) return only   8 bytes of packet payload. It means, that precise relaying of   ICMP in the real Internet is absolutely infeasible. */	const struct iphdr *iph = (const struct iphdr *)skb->data;	const int type = icmp_hdr(skb)->type;	const int code = icmp_hdr(skb)->code;	struct ip_tunnel *t;	int err; 	switch (type) {	default:	case ICMP_PARAMETERPROB:		return 0; 	case ICMP_DEST_UNREACH:		switch (code) {		case ICMP_SR_FAILED:		case ICMP_PORT_UNREACH:			/* Impossible event. */			return 0;		case ICMP_FRAG_NEEDED:			/* Soft state for pmtu is maintained by IP core. */			return 0;		default:			/* All others are translated to HOST_UNREACH.			   rfc2003 contains "deep thoughts" about NET_UNREACH,			   I believe they are just ether pollution. --ANK			 */			break;		}		break;	case ICMP_TIME_EXCEEDED:		if (code != ICMP_EXC_TTL)			return 0;		break;	} 	err = -ENOENT; 	rcu_read_lock();	t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);	if (t == NULL || t->parms.iph.daddr == 0)		goto out; 	err = 0;	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)		goto out; 	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))		t->err_count++;	else		t->err_count = 1;	t->err_time = jiffies;out:	rcu_read_unlock();	return err;} static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph,					struct sk_buff *skb){	struct iphdr *inner_iph = ip_hdr(skb); 	if (INET_ECN_is_ce(outer_iph->tos))		IP_ECN_set_ce(inner_iph);} static int ipip_rcv(struct sk_buff *skb){	struct ip_tunnel *tunnel;	const struct iphdr *iph = ip_hdr(skb); 	rcu_read_lock();	tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);	if (tunnel != NULL) {		struct pcpu_tstats *tstats; 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {			rcu_read_unlock();			kfree_skb(skb);			return 0;		} 		secpath_reset(skb); 		skb->mac_header = skb->network_header;		skb_reset_network_header(skb);		skb->protocol = htons(ETH_P_IP);		skb->pkt_type = PACKET_HOST; 		tstats = this_cpu_ptr(tunnel->dev->tstats);		tstats->rx_packets++;		tstats->rx_bytes += skb->len; 		__skb_tunnel_rx(skb, tunnel->dev); 		ipip_ecn_decapsulate(iph, skb); 		netif_rx(skb); 		rcu_read_unlock();		return 0;	}	rcu_read_unlock(); 	return -1;} /* *	This function assumes it is being called from dev_queue_xmit() *	and that skb is filled properly by that function. */ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev){	struct ip_tunnel *tunnel = netdev_priv(dev);	struct pcpu_tstats *tstats;	const struct iphdr  *tiph = &tunnel->parms.iph;	u8     tos = tunnel->parms.iph.tos;	__be16 df = tiph->frag_off;	struct rtable *rt;     			/* Route to the other host */	struct net_device *tdev;		/* Device to other host */	const struct iphdr  *old_iph = ip_hdr(skb);	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; 	if (skb->protocol != htons(ETH_P_IP))		goto tx_error; 	if (tos & 1)		tos = old_iph->tos; 	if (!dst) {		/* NBMA tunnel */		if ((rt = skb_rtable(skb)) == NULL) {			dev->stats.tx_fifo_errors++;			goto tx_error;		}		if ((dst = rt->rt_gateway) == 0)			goto tx_error_icmp;	} 	rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,				   dst, tiph->saddr,				   0, 0,				   IPPROTO_IPIP, RT_TOS(tos),				   tunnel->parms.link);	if (IS_ERR(rt)) {		dev->stats.tx_carrier_errors++;		goto tx_error_icmp;	}	tdev = rt->dst.dev; 	if (tdev == dev) {		ip_rt_put(rt);		dev->stats.collisions++;		goto tx_error;	} 	df |= old_iph->frag_off & htons(IP_DF); 	if (df) {		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); 		if (mtu < 68) {			dev->stats.collisions++;			ip_rt_put(rt);			goto tx_error;		} 		if (skb_dst(skb))			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); 		if ((old_iph->frag_off & htons(IP_DF)) &&		    mtu < ntohs(old_iph->tot_len)) {			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,				  htonl(mtu));			ip_rt_put(rt);			goto tx_error;		}	} 

Lines 1–500 of 912.

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t