reassembly.c

linux 内核源代码

/*
 *	IPv6 fragment reassembly
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
 *
 *	Based on: net/ipv4/ip_fragment.c
 *
 *	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.
 */

/*
 *	Fixes:
 *	Andi Kleen	Make it work with multiple hosts.
 *			More RFC compliance.
 *
 *      Horst von Brand Add missing #include <linux/string.h>
 *	Alexey Kuznetsov	SMP races, threading, cleanup.
 *	Patrick McHardy		LRU queue of frag heads for evictor.
 *	Mitsuru KANDA @USAGI	Register inet6_protocol{}.
 *	David Stevens and
 *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
 *				calculate ICV correctly.
 */
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/net.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/skbuff.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>

struct ip6frag_skb_cb
{
	struct inet6_skb_parm	h;
	int			offset;
};

#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))


/*
 *	Equivalent of ipv4 struct ipq
 */

struct frag_queue
{
	struct inet_frag_queue	q;

	__be32			id;		/* fragment id		*/
	struct in6_addr		saddr;
	struct in6_addr		daddr;

	int			iif;
	unsigned int		csum;
	__u16			nhoffset;
};

struct inet_frags_ctl ip6_frags_ctl __read_mostly = {
	.high_thresh 	 = 256 * 1024,
	.low_thresh	 = 192 * 1024,
	.timeout	 = IPV6_FRAG_TIMEOUT,
	.secret_interval = 10 * 60 * HZ,
};

static struct inet_frags ip6_frags;

int ip6_frag_nqueues(void)
{
	return ip6_frags.nqueues;
}

int ip6_frag_mem(void)
{
	return atomic_read(&ip6_frags.mem);
}

static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
			  struct net_device *dev);

/*
 * callers should be careful not to use the hash value outside the ipfrag_lock
 * as doing so could race with ipfrag_hash_rnd being recalculated.
 */
static unsigned int ip6qhashfn(__be32 id, struct in6_addr *saddr,
			       struct in6_addr *daddr)
{
	u32 a, b, c;

	a = (__force u32)saddr->s6_addr32[0];
	b = (__force u32)saddr->s6_addr32[1];
	c = (__force u32)saddr->s6_addr32[2];

	a += JHASH_GOLDEN_RATIO;
	b += JHASH_GOLDEN_RATIO;
	c += ip6_frags.rnd;
	__jhash_mix(a, b, c);

	a += (__force u32)saddr->s6_addr32[3];
	b += (__force u32)daddr->s6_addr32[0];
	c += (__force u32)daddr->s6_addr32[1];
	__jhash_mix(a, b, c);

	a += (__force u32)daddr->s6_addr32[2];
	b += (__force u32)daddr->s6_addr32[3];
	c += (__force u32)id;
	__jhash_mix(a, b, c);

	return c & (INETFRAGS_HASHSZ - 1);
}

static unsigned int ip6_hashfn(struct inet_frag_queue *q)
{
	struct frag_queue *fq;

	fq = container_of(q, struct frag_queue, q);
	return ip6qhashfn(fq->id, &fq->saddr, &fq->daddr);
}

int ip6_frag_match(struct inet_frag_queue *q, void *a)
{
	struct frag_queue *fq;
	struct ip6_create_arg *arg = a;

	fq = container_of(q, struct frag_queue, q);
	return (fq->id == arg->id &&
			ipv6_addr_equal(&fq->saddr, arg->src) &&
			ipv6_addr_equal(&fq->daddr, arg->dst));
}
EXPORT_SYMBOL(ip6_frag_match);

/* Memory Tracking Functions. */
static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
{
	if (work)
		*work -= skb->truesize;
	atomic_sub(skb->truesize, &ip6_frags.mem);
	kfree_skb(skb);
}

void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
	struct frag_queue *fq = container_of(q, struct frag_queue, q);
	struct ip6_create_arg *arg = a;

	fq->id = arg->id;
	ipv6_addr_copy(&fq->saddr, arg->src);
	ipv6_addr_copy(&fq->daddr, arg->dst);
}
EXPORT_SYMBOL(ip6_frag_init);

/* Destruction primitives. */

static __inline__ void fq_put(struct frag_queue *fq)
{
	inet_frag_put(&fq->q, &ip6_frags);
}

/* Kill fq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static __inline__ void fq_kill(struct frag_queue *fq)
{
	inet_frag_kill(&fq->q, &ip6_frags);
}

static void ip6_evictor(struct inet6_dev *idev)
{
	int evicted;

	evicted = inet_frag_evictor(&ip6_frags);
	if (evicted)
		IP6_ADD_STATS_BH(idev, IPSTATS_MIB_REASMFAILS, evicted);
}

static void ip6_frag_expire(unsigned long data)
{
	struct frag_queue *fq;
	struct net_device *dev = NULL;

	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);

	spin_lock(&fq->q.lock);

	if (fq->q.last_in & COMPLETE)
		goto out;

	fq_kill(fq);

	dev = dev_get_by_index(&init_net, fq->iif);
	if (!dev)
		goto out;

	rcu_read_lock();
	IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
	IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
	rcu_read_unlock();

	/* Don't send error if the first segment did not arrive. */
	if (!(fq->q.last_in&FIRST_IN) || !fq->q.fragments)
		goto out;

	/*
	   But use as source device on which LAST ARRIVED
	   segment was received. And do not use fq->dev
	   pointer directly, device might already disappeared.
	 */
	fq->q.fragments->dev = dev;
	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev);
out:
	if (dev)
		dev_put(dev);
	spin_unlock(&fq->q.lock);
	fq_put(fq);
}

static __inline__ struct frag_queue *
fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst,
	struct inet6_dev *idev)
{
	struct inet_frag_queue *q;
	struct ip6_create_arg arg;
	unsigned int hash;

	arg.id = id;
	arg.src = src;
	arg.dst = dst;
	hash = ip6qhashfn(id, src, dst);

	q = inet_frag_find(&ip6_frags, &arg, hash);
	if (q == NULL)
		goto oom;

	return container_of(q, struct frag_queue, q);

oom:
	IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS);
	return NULL;
}

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int offset, end;

	if (fq->q.last_in & COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((u8 *)&fhdr->frag_off -
				   skb_network_header(skb)));
		return -1;
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		const unsigned char *nh = skb_network_header(skb);
		skb->csum = csum_sub(skb->csum,
				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
						  0));
	}

	/* Is this the final fragment? */
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < fq->q.len ||
		    ((fq->q.last_in & LAST_IN) && end != fq->q.len))
			goto err;
		fq->q.last_in |= LAST_IN;
		fq->q.len = end;
	} else {
		/* Check if the fragment is rounded to 8 bytes.
		 * Required by the RFC.
		 */
		if (end & 0x7) {
			/* RFC2460 says always send parameter problem in
			 * this case. -DaveM
			 */
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  offsetof(struct ipv6hdr, payload_len));
			return -1;
		}
		if (end > fq->q.len) {
			/* Some bits beyond end -> corruption. */
			if (fq->q.last_in & LAST_IN)
				goto err;
			fq->q.len = end;