nf_conntrack_reasm.c

linux 内核源代码

/*
 * IPv6 fragment reassembly for connection tracking
 *
 * Copyright (C)2004 USAGI/WIDE Project
 *
 * Author:
 *	Yasuyuki Kozakai @USAGI <[e-mail]>
 *
 * Based on: net/ipv6/reassembly.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.
 */

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

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/kernel.h>
#include <linux/module.h>

#define NF_CT_FRAG6_HIGH_THRESH 262144 /* == 256*1024 */
#define NF_CT_FRAG6_LOW_THRESH 196608  /* == 192*1024 */
#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT

struct nf_ct_frag6_skb_cb
{
	struct inet6_skb_parm	h;
	int			offset;
	struct sk_buff		*orig;
};

#define NFCT_FRAG6_CB(skb)	((struct nf_ct_frag6_skb_cb*)((skb)->cb))

struct nf_ct_frag6_queue
{
	struct inet_frag_queue	q;

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

	unsigned int		csum;
	__u16			nhoffset;
};

struct inet_frags_ctl nf_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 nf_frags;

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 += nf_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 nf_hashfn(struct inet_frag_queue *q)
{
	struct nf_ct_frag6_queue *nq;

	nq = container_of(q, struct nf_ct_frag6_queue, q);
	return ip6qhashfn(nq->id, &nq->saddr, &nq->daddr);
}

static void nf_skb_free(struct sk_buff *skb)
{
	if (NFCT_FRAG6_CB(skb)->orig)
		kfree_skb(NFCT_FRAG6_CB(skb)->orig);
}

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

/* Destruction primitives. */

static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
{
	inet_frag_put(&fq->q, &nf_frags);
}

/* Kill fq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static __inline__ void fq_kill(struct nf_ct_frag6_queue *fq)
{
	inet_frag_kill(&fq->q, &nf_frags);
}

static void nf_ct_frag6_evictor(void)
{
	inet_frag_evictor(&nf_frags);
}

static void nf_ct_frag6_expire(unsigned long data)
{
	struct nf_ct_frag6_queue *fq;

	fq = container_of((struct inet_frag_queue *)data,
			struct nf_ct_frag6_queue, q);

	spin_lock(&fq->q.lock);

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

	fq_kill(fq);

out:
	spin_unlock(&fq->q.lock);
	fq_put(fq);
}

/* Creation primitives. */

static __inline__ struct nf_ct_frag6_queue *
fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst)
{
	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(&nf_frags, &arg, hash);
	if (q == NULL)
		goto oom;

	return container_of(q, struct nf_ct_frag6_queue, q);

oom:
	pr_debug("Can't alloc new queue\n");
	return NULL;
}


static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
			     struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	int offset, end;

	if (fq->q.last_in & COMPLETE) {
		pr_debug("Allready completed\n");
		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) {
		pr_debug("offset is too large.\n");
		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)) {
			pr_debug("already received last fragment\n");
			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
			 */
			pr_debug("end of fragment not rounded to 8 bytes.\n");
			return -1;
		}
		if (end > fq->q.len) {
			/* Some bits beyond end -> corruption. */
			if (fq->q.last_in & LAST_IN) {
				pr_debug("last packet already reached.\n");
				goto err;
			}
			fq->q.len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) {
		pr_debug("queue: message is too short.\n");
		goto err;
	}
	if (pskb_trim_rcsum(skb, end - offset)) {
		pr_debug("Can't trim\n");
		goto err;
	}

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = NULL;
	for (next = fq->q.fragments; next != NULL; next = next->next) {
		if (NFCT_FRAG6_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

	/* We found where to put this one.  Check for overlap with
	 * preceding fragment, and, if needed, align things so that
	 * any overlaps are eliminated.
	 */
	if (prev) {
		int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset) {
				pr_debug("overlap\n");
				goto err;
			}
			if (!pskb_pull(skb, i)) {
				pr_debug("Can't pull\n");
				goto err;
			}
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
	}

	/* Look for overlap with succeeding segments.
	 * If we can merge fragments, do it.
	 */
	while (next && NFCT_FRAG6_CB(next)->offset < end) {
		/* overlap is 'i' bytes */
		int i = end - NFCT_FRAG6_CB(next)->offset;

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			pr_debug("Eat head of the overlapped parts.: %d", i);
			if (!pskb_pull(next, i))
				goto err;

			/* next fragment */
			NFCT_FRAG6_CB(next)->offset += i;
			fq->q.meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragmnet is completely overridden with
			 * new one drop it.
			 */
			next = next->next;

			if (prev)
				prev->next = next;
			else
				fq->q.fragments = next;

			fq->q.meat -= free_it->len;
			frag_kfree_skb(free_it, NULL);
		}
	}

	NFCT_FRAG6_CB(skb)->offset = offset;

	/* Insert this fragment in the chain of fragments. */
	skb->next = next;
	if (prev)
		prev->next = skb;
	else