nf_conntrack_reasm.c

linux-2.6.15.6

			 */
			DEBUGP("the end of this fragment is not rounded to 8 bytes.\n");
			return -1;
		}
		if (end > fq->len) {
			/* Some bits beyond end -> corruption. */
			if (fq->last_in & LAST_IN) {
				DEBUGP("last packet already reached.\n");
				goto err;
			}
			fq->len = end;
		}
	}

	if (end == offset)
		goto err;

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

	/* 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->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) {
				DEBUGP("overlap\n");
				goto err;
			}
			if (!pskb_pull(skb, i)) {
				DEBUGP("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.
			 */
			DEBUGP("Eat head of the overlapped parts.: %d", i);
			if (!pskb_pull(next, i))
				goto err;

			/* next fragment */
			NFCT_FRAG6_CB(next)->offset += i;
			fq->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->fragments = next;

			fq->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
		fq->fragments = skb;

	skb->dev = NULL;
	skb_get_timestamp(skb, &fq->stamp);
	fq->meat += skb->len;
	atomic_add(skb->truesize, &nf_ct_frag6_mem);

	/* The first fragment.
	 * nhoffset is obtained from the first fragment, of course.
	 */
	if (offset == 0) {
		fq->nhoffset = nhoff;
		fq->last_in |= FIRST_IN;
	}
	write_lock(&nf_ct_frag6_lock);
	list_move_tail(&fq->lru_list, &nf_ct_frag6_lru_list);
	write_unlock(&nf_ct_frag6_lock);
	return 0;

err:
	return -1;
}

/*
 *	Check if this packet is complete.
 *	Returns NULL on failure by any reason, and pointer
 *	to current nexthdr field in reassembled frame.
 *
 *	It is called with locked fq, and caller must check that
 *	queue is eligible for reassembly i.e. it is not COMPLETE,
 *	the last and the first frames arrived and all the bits are here.
 */
static struct sk_buff *
nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
{
	struct sk_buff *fp, *op, *head = fq->fragments;
	int    payload_len;

	fq_kill(fq);

	BUG_TRAP(head != NULL);
	BUG_TRAP(NFCT_FRAG6_CB(head)->offset == 0);

	/* Unfragmented part is taken from the first segment. */
	payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
	if (payload_len > IPV6_MAXPLEN) {
		DEBUGP("payload len is too large.\n");
		goto out_oversize;
	}

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) {
		DEBUGP("skb is cloned but can't expand head");
		goto out_oom;
	}

	/* If the first fragment is fragmented itself, we split
	 * it to two chunks: the first with data and paged part
	 * and the second, holding only fragments. */
	if (skb_shinfo(head)->frag_list) {
		struct sk_buff *clone;
		int i, plen = 0;

		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) {
			DEBUGP("Can't alloc skb\n");
			goto out_oom;
		}
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_shinfo(head)->frag_list = NULL;
		for (i=0; i<skb_shinfo(head)->nr_frags; i++)
			plen += skb_shinfo(head)->frags[i].size;
		clone->len = clone->data_len = head->data_len - plen;
		head->data_len -= clone->len;
		head->len -= clone->len;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;

		NFCT_FRAG6_CB(clone)->orig = NULL;
		atomic_add(clone->truesize, &nf_ct_frag6_mem);
	}

	/* We have to remove fragment header from datagram and to relocate
	 * header in order to calculate ICV correctly. */
	head->nh.raw[fq->nhoffset] = head->h.raw[0];
	memmove(head->head + sizeof(struct frag_hdr), head->head, 
		(head->data - head->head) - sizeof(struct frag_hdr));
	head->mac.raw += sizeof(struct frag_hdr);
	head->nh.raw += sizeof(struct frag_hdr);

	skb_shinfo(head)->frag_list = head->next;
	head->h.raw = head->data;
	skb_push(head, head->data - head->nh.raw);
	atomic_sub(head->truesize, &nf_ct_frag6_mem);

	for (fp=head->next; fp; fp = fp->next) {
		head->data_len += fp->len;
		head->len += fp->len;
		if (head->ip_summed != fp->ip_summed)
			head->ip_summed = CHECKSUM_NONE;
		else if (head->ip_summed == CHECKSUM_HW)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
		atomic_sub(fp->truesize, &nf_ct_frag6_mem);
	}

	head->next = NULL;
	head->dev = dev;
	skb_set_timestamp(head, &fq->stamp);
	head->nh.ipv6h->payload_len = htons(payload_len);

	/* Yes, and fold redundant checksum back. 8) */
	if (head->ip_summed == CHECKSUM_HW)
		head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);

	fq->fragments = NULL;

	/* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
	fp = skb_shinfo(head)->frag_list;
	if (NFCT_FRAG6_CB(fp)->orig == NULL)
		/* at above code, head skb is divided into two skbs. */
		fp = fp->next;

	op = NFCT_FRAG6_CB(head)->orig;
	for (; fp; fp = fp->next) {
		struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig;

		op->next = orig;
		op = orig;
		NFCT_FRAG6_CB(fp)->orig = NULL;
	}

	return head;

out_oversize:
	if (net_ratelimit())
		printk(KERN_DEBUG "nf_ct_frag6_reasm: payload len = %d\n", payload_len);
	goto out_fail;
out_oom:
	if (net_ratelimit())
		printk(KERN_DEBUG "nf_ct_frag6_reasm: no memory for reassembly\n");
out_fail:
	return NULL;
}

/*
 * find the header just before Fragment Header.
 *
 * if success return 0 and set ...
 * (*prevhdrp): the value of "Next Header Field" in the header
 *		just before Fragment Header.
 * (*prevhoff): the offset of "Next Header Field" in the header
 *		just before Fragment Header.
 * (*fhoff)   : the offset of Fragment Header.
 *
 * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c
 *
 */
static int
find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
{
        u8 nexthdr = skb->nh.ipv6h->nexthdr;
	u8 prev_nhoff = (u8 *)&skb->nh.ipv6h->nexthdr - skb->data;
	int start = (u8 *)(skb->nh.ipv6h+1) - skb->data;
	int len = skb->len - start;
	u8 prevhdr = NEXTHDR_IPV6;

        while (nexthdr != NEXTHDR_FRAGMENT) {
                struct ipv6_opt_hdr hdr;
                int hdrlen;

		if (!ipv6_ext_hdr(nexthdr)) {
			return -1;
		}
                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
			DEBUGP("too short\n");
			return -1;
		}
                if (nexthdr == NEXTHDR_NONE) {
			DEBUGP("next header is none\n");
			return -1;
		}
                if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
                        BUG();
                if (nexthdr == NEXTHDR_AUTH)
                        hdrlen = (hdr.hdrlen+2)<<2;
                else
                        hdrlen = ipv6_optlen(&hdr);

		prevhdr = nexthdr;
		prev_nhoff = start;

                nexthdr = hdr.nexthdr;
                len -= hdrlen;
                start += hdrlen;
        }

	if (len < 0)
		return -1;

	*prevhdrp = prevhdr;
	*prevhoff = prev_nhoff;
	*fhoff = start;

	return 0;
}

struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
{
	struct sk_buff *clone; 
	struct net_device *dev = skb->dev;
	struct frag_hdr *fhdr;
	struct nf_ct_frag6_queue *fq;
	struct ipv6hdr *hdr;
	int fhoff, nhoff;
	u8 prevhdr;
	struct sk_buff *ret_skb = NULL;

	/* Jumbo payload inhibits frag. header */
	if (skb->nh.ipv6h->payload_len == 0) {
		DEBUGP("payload len = 0\n");
		return skb;
	}

	if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
		return skb;

	clone = skb_clone(skb, GFP_ATOMIC);
	if (clone == NULL) {
		DEBUGP("Can't clone skb\n");
		return skb;
	}

	NFCT_FRAG6_CB(clone)->orig = skb;

	if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) {
		DEBUGP("message is too short.\n");
		goto ret_orig;
	}

	clone->h.raw = clone->data + fhoff;
	hdr = clone->nh.ipv6h;
	fhdr = (struct frag_hdr *)clone->h.raw;

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		DEBUGP("Invalid fragment offset\n");
		/* It is not a fragmented frame */
		goto ret_orig;
	}

	if (atomic_read(&nf_ct_frag6_mem) > nf_ct_frag6_high_thresh)
		nf_ct_frag6_evictor();

	fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr);
	if (fq == NULL) {
		DEBUGP("Can't find and can't create new queue\n");
		goto ret_orig;
	}

	spin_lock(&fq->lock);

	if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
		spin_unlock(&fq->lock);
		DEBUGP("Can't insert skb to queue\n");
		fq_put(fq, NULL);
		goto ret_orig;
	}

	if (fq->last_in == (FIRST_IN|LAST_IN) && fq->meat == fq->len) {
		ret_skb = nf_ct_frag6_reasm(fq, dev);
		if (ret_skb == NULL)
			DEBUGP("Can't reassemble fragmented packets\n");
	}
	spin_unlock(&fq->lock);

	fq_put(fq, NULL);
	return ret_skb;

ret_orig:
	kfree_skb(clone);
	return skb;
}

void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
			struct net_device *in, struct net_device *out,
			int (*okfn)(struct sk_buff *))
{
	struct sk_buff *s, *s2;

	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
		nf_conntrack_put_reasm(s->nfct_reasm);
		nf_conntrack_get_reasm(skb);
		s->nfct_reasm = skb;

		s2 = s->next;
		NF_HOOK_THRESH(PF_INET6, hooknum, s, in, out, okfn,
			       NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
		s = s2;
	}
	nf_conntrack_put_reasm(skb);
}

int nf_ct_frag6_kfree_frags(struct sk_buff *skb)
{
	struct sk_buff *s, *s2;

	for (s = NFCT_FRAG6_CB(skb)->orig; s; s = s2) {

		s2 = s->next;
		kfree_skb(s);
	}

	kfree_skb(skb);

	return 0;
}

int nf_ct_frag6_init(void)
{
	nf_ct_frag6_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
				   (jiffies ^ (jiffies >> 6)));

	init_timer(&nf_ct_frag6_secret_timer);
	nf_ct_frag6_secret_timer.function = nf_ct_frag6_secret_rebuild;
	nf_ct_frag6_secret_timer.expires = jiffies
					   + nf_ct_frag6_secret_interval;
	add_timer(&nf_ct_frag6_secret_timer);

	return 0;
}

void nf_ct_frag6_cleanup(void)
{
	del_timer(&nf_ct_frag6_secret_timer);
	nf_ct_frag6_low_thresh = 0;
	nf_ct_frag6_evictor();
}