reassembly.c

Linux Kernel 2.6.9 for OMAP1710

	init_timer(&fq->timer);
	fq->timer.function = ip6_frag_expire;
	fq->timer.data = (long) fq;
	fq->lock = SPIN_LOCK_UNLOCKED;
	atomic_set(&fq->refcnt, 1);

	return ip6_frag_intern(hash, fq);

oom:
	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	return NULL;
}

static __inline__ struct frag_queue *
fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
{
	struct frag_queue *fq;
	unsigned int hash = ip6qhashfn(id, src, dst);

	read_lock(&ip6_frag_lock);
	for(fq = ip6_frag_hash[hash]; fq; fq = fq->next) {
		if (fq->id == id && 
		    !ipv6_addr_cmp(src, &fq->saddr) &&
		    !ipv6_addr_cmp(dst, &fq->daddr)) {
			atomic_inc(&fq->refcnt);
			read_unlock(&ip6_frag_lock);
			return fq;
		}
	}
	read_unlock(&ip6_frag_lock);

	return ip6_frag_create(hash, id, src, dst);
}


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

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

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
			((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
 		icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw);
 		return;
	}

 	if (skb->ip_summed == CHECKSUM_HW)
 		skb->csum = csum_sub(skb->csum,
 				     csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 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->len ||
		    ((fq->last_in & LAST_IN) && end != fq->len))
			goto err;
		fq->last_in |= LAST_IN;
		fq->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(IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, 
					  offsetof(struct ipv6hdr, payload_len));
			return;
		}
		if (end > fq->len) {
			/* Some bits beyond end -> corruption. */
			if (fq->last_in & LAST_IN)
				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))
		goto err;
	if (end-offset < skb->len) {
		if (pskb_trim(skb, end - offset))
			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 (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 = (FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset)
				goto err;
			if (!pskb_pull(skb, i))
				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 && FRAG6_CB(next)->offset < end) {
		int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			if (!pskb_pull(next, i))
				goto err;
			FRAG6_CB(next)->offset += i;	/* next fragment */
			fq->meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragment 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);
		}
	}

	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;

	if (skb->dev)
		fq->iif = skb->dev->ifindex;
	skb->dev = NULL;
	fq->stamp = skb->stamp;
	fq->meat += skb->len;
	atomic_add(skb->truesize, &ip6_frag_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(&ip6_frag_lock);
	list_move_tail(&fq->lru_list, &ip6_frag_lru_list);
	write_unlock(&ip6_frag_lock);
	return;

err:
	IP6_INC_STATS(IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
}

/*
 *	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 int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
			  unsigned int *nhoffp,
			  struct net_device *dev)
{
	struct sk_buff *fp, *head = fq->fragments;
	int    payload_len;
	unsigned int nhoff;

	fq_kill(fq);

	BUG_TRAP(head != NULL);
	BUG_TRAP(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)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
		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)
			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;
		atomic_add(clone->truesize, &ip6_frag_mem);
	}

	/* We have to remove fragment header from datagram and to relocate
	 * header in order to calculate ICV correctly. */
	nhoff = fq->nhoffset;
	head->nh.raw[nhoff] = 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, &ip6_frag_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, &ip6_frag_mem);
	}

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

	*skb_in = head;

	/* 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);

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
	fq->fragments = NULL;
	*nhoffp = nhoff;
	return 1;

out_oversize:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
	goto out_fail;
out_oom:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	return -1;
}

static int ipv6_frag_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
{
	struct sk_buff *skb = *skbp; 
	struct net_device *dev = skb->dev;
	struct frag_hdr *fhdr;
	struct frag_queue *fq;
	struct ipv6hdr *hdr;

	hdr = skb->nh.ipv6h;

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);

	/* Jumbo payload inhibits frag. header */
	if (hdr->payload_len==0) {
		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
		return -1;
	}
	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
		return -1;
	}

	hdr = skb->nh.ipv6h;
	fhdr = (struct frag_hdr *)skb->h.raw;

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		/* It is not a fragmented frame */
		skb->h.raw += sizeof(struct frag_hdr);
		IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);

		*nhoffp = (u8*)fhdr - skb->nh.raw;
		return 1;
	}

	if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
		ip6_evictor();

	if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) {
		int ret = -1;

		spin_lock(&fq->lock);

		ip6_frag_queue(fq, skb, fhdr, *nhoffp);

		if (fq->last_in == (FIRST_IN|LAST_IN) &&
		    fq->meat == fq->len)
			ret = ip6_frag_reasm(fq, skbp, nhoffp, dev);

		spin_unlock(&fq->lock);
		fq_put(fq, NULL);
		return ret;
	}

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -1;
}

static struct inet6_protocol frag_protocol =
{
	.handler	=	ipv6_frag_rcv,
	.flags		=	INET6_PROTO_NOPOLICY,
};

void __init ipv6_frag_init(void)
{
	if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
		printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n");

	ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
				   (jiffies ^ (jiffies >> 6)));

	init_timer(&ip6_frag_secret_timer);
	ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
	ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
	add_timer(&ip6_frag_secret_timer);
}