ip_fragment.c

Linux Kernel 2.6.9 for OMAP1710

	return qp;
}

/* Add an entry to the 'ipq' queue for a newly received IP datagram. */
static struct ipq *ip_frag_create(unsigned hash, struct iphdr *iph)
{
	struct ipq *qp;

	if ((qp = frag_alloc_queue()) == NULL)
		goto out_nomem;

	qp->protocol = iph->protocol;
	qp->last_in = 0;
	qp->id = iph->id;
	qp->saddr = iph->saddr;
	qp->daddr = iph->daddr;
	qp->len = 0;
	qp->meat = 0;
	qp->fragments = NULL;
	qp->iif = 0;

	/* Initialize a timer for this entry. */
	init_timer(&qp->timer);
	qp->timer.data = (unsigned long) qp;	/* pointer to queue	*/
	qp->timer.function = ip_expire;		/* expire function	*/
	qp->lock = SPIN_LOCK_UNLOCKED;
	atomic_set(&qp->refcnt, 1);

	return ip_frag_intern(hash, qp);

out_nomem:
	NETDEBUG(if (net_ratelimit()) printk(KERN_ERR "ip_frag_create: no memory left !\n"));
	return NULL;
}

/* Find the correct entry in the "incomplete datagrams" queue for
 * this IP datagram, and create new one, if nothing is found.
 */
static inline struct ipq *ip_find(struct iphdr *iph)
{
	__u16 id = iph->id;
	__u32 saddr = iph->saddr;
	__u32 daddr = iph->daddr;
	__u8 protocol = iph->protocol;
	unsigned int hash = ipqhashfn(id, saddr, daddr, protocol);
	struct ipq *qp;

	read_lock(&ipfrag_lock);
	for(qp = ipq_hash[hash]; qp; qp = qp->next) {
		if(qp->id == id		&&
		   qp->saddr == saddr	&&
		   qp->daddr == daddr	&&
		   qp->protocol == protocol) {
			atomic_inc(&qp->refcnt);
			read_unlock(&ipfrag_lock);
			return qp;
		}
	}
	read_unlock(&ipfrag_lock);

	return ip_frag_create(hash, iph);
}

/* Add new segment to existing queue. */
static void ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
	struct sk_buff *prev, *next;
	int flags, offset;
	int ihl, end;

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

 	offset = ntohs(skb->nh.iph->frag_off);
	flags = offset & ~IP_OFFSET;
	offset &= IP_OFFSET;
	offset <<= 3;		/* offset is in 8-byte chunks */
 	ihl = skb->nh.iph->ihl * 4;

	/* Determine the position of this fragment. */
 	end = offset + skb->len - ihl;

	/* Is this the final fragment? */
	if ((flags & IP_MF) == 0) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrrupted.
		 */
		if (end < qp->len ||
		    ((qp->last_in & LAST_IN) && end != qp->len))
			goto err;
		qp->last_in |= LAST_IN;
		qp->len = end;
	} else {
		if (end&7) {
			end &= ~7;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
		if (end > qp->len) {
			/* Some bits beyond end -> corruption. */
			if (qp->last_in & LAST_IN)
				goto err;
			qp->len = end;
		}
	}
	if (end == offset)
		goto err;

	if (pskb_pull(skb, ihl) == NULL)
		goto err;
	if (pskb_trim(skb, end-offset))
		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 = qp->fragments; next != NULL; next = next->next) {
		if (FRAG_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 = (FRAG_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;
		}
	}

	while (next && FRAG_CB(next)->offset < end) {
		int i = end - FRAG_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;
			FRAG_CB(next)->offset += i;
			qp->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
				qp->fragments = next;

			qp->meat -= free_it->len;
			frag_kfree_skb(free_it, NULL);
		}
	}

	FRAG_CB(skb)->offset = offset;

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

 	if (skb->dev)
 		qp->iif = skb->dev->ifindex;
	skb->dev = NULL;
	qp->stamp = skb->stamp;
	qp->meat += skb->len;
	atomic_add(skb->truesize, &ip_frag_mem);
	if (offset == 0)
		qp->last_in |= FIRST_IN;

	write_lock(&ipfrag_lock);
	list_move_tail(&qp->lru_list, &ipq_lru_list);
	write_unlock(&ipfrag_lock);

	return;

err:
	kfree_skb(skb);
}


/* Build a new IP datagram from all its fragments. */

static struct sk_buff *ip_frag_reasm(struct ipq *qp, struct net_device *dev)
{
	struct iphdr *iph;
	struct sk_buff *fp, *head = qp->fragments;
	int len;
	int ihlen;

	ipq_kill(qp);

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

	/* Allocate a new buffer for the datagram. */
	ihlen = head->nh.iph->ihl*4;
	len = ihlen + qp->len;

	if(len > 65535)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
		goto out_nomem;

	/* 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_nomem;
		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, &ip_frag_mem);
	}

	skb_shinfo(head)->frag_list = head->next;
	skb_push(head, head->data - head->nh.raw);
	atomic_sub(head->truesize, &ip_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, &ip_frag_mem);
	}

	head->next = NULL;
	head->dev = dev;
	head->stamp = qp->stamp;

	iph = head->nh.iph;
	iph->frag_off = 0;
	iph->tot_len = htons(len);
	IP_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
	qp->fragments = NULL;
	return head;

out_nomem:
 	NETDEBUG(if (net_ratelimit())
	         printk(KERN_ERR 
			"IP: queue_glue: no memory for gluing queue %p\n",
			qp));
	goto out_fail;
out_oversize:
	if (net_ratelimit())
		printk(KERN_INFO
			"Oversized IP packet from %d.%d.%d.%d.\n",
			NIPQUAD(qp->saddr));
out_fail:
	IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	return NULL;
}

/* Process an incoming IP datagram fragment. */
struct sk_buff *ip_defrag(struct sk_buff *skb)
{
	struct iphdr *iph = skb->nh.iph;
	struct ipq *qp;
	struct net_device *dev;
	
	IP_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);

	/* Start by cleaning up the memory. */
	if (atomic_read(&ip_frag_mem) > sysctl_ipfrag_high_thresh)
		ip_evictor();

	dev = skb->dev;

	/* Lookup (or create) queue header */
	if ((qp = ip_find(iph)) != NULL) {
		struct sk_buff *ret = NULL;

		spin_lock(&qp->lock);

		ip_frag_queue(qp, skb);

		if (qp->last_in == (FIRST_IN|LAST_IN) &&
		    qp->meat == qp->len)
			ret = ip_frag_reasm(qp, dev);

		spin_unlock(&qp->lock);
		ipq_put(qp, NULL);
		return ret;
	}

	IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return NULL;
}

void ipfrag_init(void)
{
	ipfrag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
				 (jiffies ^ (jiffies >> 6)));

	init_timer(&ipfrag_secret_timer);
	ipfrag_secret_timer.function = ipfrag_secret_rebuild;
	ipfrag_secret_timer.expires = jiffies + sysctl_ipfrag_secret_interval;
	add_timer(&ipfrag_secret_timer);
}

void ipfrag_flush(void)
{
	__ip_evictor(0);
}

EXPORT_SYMBOL(ip_defrag);
EXPORT_SYMBOL(ipfrag_flush);