path: root/net/mpls/af_mpls.c

#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/sysctl.h>
#include <linux/net.h>
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/vmalloc.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include "internal.h"

#define LABEL_NOT_SPECIFIED (1<<20)
#define MAX_NEW_LABELS 2

/* This maximum ha length copied from the definition of struct neighbour */
#define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long)))

struct mpls_route { /* next hop label forwarding entry */
	struct net_device __rcu *rt_dev;
	struct rcu_head		rt_rcu;
	u32			rt_label[MAX_NEW_LABELS];
	u8			rt_protocol; /* routing protocol that set this entry */
	u8			rt_labels;
	u8			rt_via_alen;
	u8			rt_via_table;
	u8			rt_via[0];
};

static int zero = 0;
static int label_limit = (1 << 20) - 1;

static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
		       struct nlmsghdr *nlh, struct net *net, u32 portid,
		       unsigned int nlm_flags);

static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
{
	struct mpls_route *rt = NULL;

	if (index < net->mpls.platform_labels) {
		struct mpls_route __rcu **platform_label =
			rcu_dereference(net->mpls.platform_label);
		rt = rcu_dereference(platform_label[index]);
	}
	return rt;
}

static bool mpls_output_possible(const struct net_device *dev)
{
	return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
}

static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
{
	/* The size of the layer 2.5 labels to be added for this route */
	return rt->rt_labels * sizeof(struct mpls_shim_hdr);
}

static unsigned int mpls_dev_mtu(const struct net_device *dev)
{
	/* The amount of data the layer 2 frame can hold */
	return dev->mtu;
}

static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
	if (skb->len <= mtu)
		return false;

	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
		return false;

	return true;
}

static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
			struct mpls_entry_decoded dec)
{
	/* RFC4385 and RFC5586 encode other packets in mpls such that
	 * they don't conflict with the ip version number, making
	 * decoding by examining the ip version correct in everything
	 * except for the strangest cases.
	 *
	 * The strange cases if we choose to support them will require
	 * manual configuration.
	 */
	struct iphdr *hdr4;
	bool success = true;

	/* The IPv4 code below accesses through the IPv4 header
	 * checksum, which is 12 bytes into the packet.
	 * The IPv6 code below accesses through the IPv6 hop limit
	 * which is 8 bytes into the packet.
	 *
	 * For all supported cases there should always be at least 12
	 * bytes of packet data present.  The IPv4 header is 20 bytes
	 * without options and the IPv6 header is always 40 bytes
	 * long.
	 */
	if (!pskb_may_pull(skb, 12))
		return false;

	/* Use ip_hdr to find the ip protocol version */
	hdr4 = ip_hdr(skb);
	if (hdr4->version == 4) {
		skb->protocol = htons(ETH_P_IP);
		csum_replace2(&hdr4->check,
			      htons(hdr4->ttl << 8),
			      htons(dec.ttl << 8));
		hdr4->ttl = dec.ttl;
	}
	else if (hdr4->version == 6) {
		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
		skb->protocol = htons(ETH_P_IPV6);
		hdr6->hop_limit = dec.ttl;
	}
	else
		/* version 0 and version 1 are used by pseudo wires */
		success = false;
	return success;
}

static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
			struct packet_type *pt, struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);
	struct mpls_shim_hdr *hdr;
	struct mpls_route *rt;
	struct mpls_entry_decoded dec;
	struct net_device *out_dev;
	unsigned int hh_len;
	unsigned int new_header_size;
	unsigned int mtu;
	int err;

	/* Careful this entire function runs inside of an rcu critical section */

	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
		goto drop;

	if (!pskb_may_pull(skb, sizeof(*hdr)))
		goto drop;

	/* Read and decode the label */
	hdr = mpls_hdr(skb);
	dec = mpls_entry_decode(hdr);

	/* Pop the label */
	skb_pull(skb, sizeof(*hdr));
	skb_reset_network_header(skb);

	skb_orphan(skb);

	rt = mpls_route_input_rcu(net, dec.label);
	if (!rt)
		goto drop;

	/* Find the output device */
	out_dev = rcu_dereference(rt->rt_dev);
	if (!mpls_output_possible(out_dev))
		goto drop;

	if (skb_warn_if_lro(skb))
		goto drop;

	skb_forward_csum(skb);

	/* Verify ttl is valid */
	if (dec.ttl <= 1)
		goto drop;
	dec.ttl -= 1;

	/* Verify the destination can hold the packet */
	new_header_size = mpls_rt_header_size(rt);
	mtu = mpls_dev_mtu(