Ejemplo n.º 1
0
/* Process an incoming IP datagram fragment. */
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
	int vif = l3mdev_master_ifindex_rcu(dev);
	struct ipq *qp;

	__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
	skb_orphan(skb);

	/* Lookup (or create) queue header */
	qp = ip_find(net, ip_hdr(skb), user, vif);
	if (qp) {
		int ret;

		spin_lock(&qp->q.lock);

		ret = ip_frag_queue(qp, skb);

		spin_unlock(&qp->q.lock);
		ipq_put(qp);
		return ret;
	}

	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -ENOMEM;
}
Ejemplo n.º 2
0
/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(unsigned long arg)
{
	struct ipq *qp;
	struct net *net;

	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	spin_lock(&qp->q.lock);

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);

	if (!inet_frag_evicting(&qp->q)) {
		struct sk_buff *head = qp->q.fragments;
		const struct iphdr *iph;
		int err;

		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);

		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
			goto out;

		rcu_read_lock();
		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out_rcu_unlock;

		/* skb has no dst, perform route lookup again */
		iph = ip_hdr(head);
		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
					   iph->tos, head->dev);
		if (err)
			goto out_rcu_unlock;

		/* Only an end host needs to send an ICMP
		 * "Fragment Reassembly Timeout" message, per RFC792.
		 */
		if (frag_expire_skip_icmp(qp->user) &&
		    (skb_rtable(head)->rt_type != RTN_LOCAL))
			goto out_rcu_unlock;

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
		rcu_read_unlock();
	}
out:
	spin_unlock(&qp->q.lock);
	ipq_put(qp);
}
Ejemplo n.º 3
0
/* Is the fragment too far ahead to be part of ipq? */
static int ip_frag_too_far(struct ipq *qp)
{
	struct inet_peer *peer = qp->peer;
	unsigned int max = qp->q.net->max_dist;
	unsigned int start, end;

	int rc;

	if (!peer || !max)
		return 0;

	start = qp->rid;
	end = atomic_inc_return(&peer->rid);
	qp->rid = end;

	rc = qp->q.fragments && (end - start) > max;

	if (rc) {
		struct net *net;

		net = container_of(qp->q.net, struct net, ipv4.frags);
		__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	}

	return rc;
}
Ejemplo n.º 4
0
static int br_validate_ipv4(struct net *net, struct sk_buff *skb)
{
	const struct iphdr *iph;
	u32 len;

	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto inhdr_error;

	iph = ip_hdr(skb);

	/* Basic sanity checks */
	if (iph->ihl < 5 || iph->version != 4)
		goto inhdr_error;

	if (!pskb_may_pull(skb, iph->ihl*4))
		goto inhdr_error;

	iph = ip_hdr(skb);
	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto inhdr_error;

	len = ntohs(iph->tot_len);
	if (skb->len < len) {
		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
		goto drop;
	} else if (len < (iph->ihl*4))
		goto inhdr_error;

	if (pskb_trim_rcsum(skb, len)) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
	/* We should really parse IP options here but until
	 * somebody who actually uses IP options complains to
	 * us we'll just silently ignore the options because
	 * we're lazy!
	 */
	return 0;

inhdr_error:
	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
	return -1;
}
Ejemplo n.º 5
0
static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct ip_options *opt	= &(IPCB(skb)->opt);

	__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
	__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);

	if (unlikely(opt->optlen))
		ip_forward_options(skb);

	return dst_output(net, sk, skb);
}
Ejemplo n.º 6
0
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
			 struct net_device *dev)
{
	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
	struct iphdr *iph;
	struct sk_buff *fp, *head = qp->q.fragments;
	int len;
	int ihlen;
	int err;
	u8 ecn;

	ipq_kill(qp);

	ecn = ip_frag_ecn_table[qp->ecn];
	if (unlikely(ecn == 0xff)) {
		err = -EINVAL;
		goto out_fail;
	}
	/* Make the one we just received the head. */
	if (prev) {
		head = prev->next;
		fp = skb_clone(head, GFP_ATOMIC);
		if (!fp)
			goto out_nomem;

		fp->next = head->next;
		if (!fp->next)
			qp->q.fragments_tail = fp;
		prev->next = fp;

		skb_morph(head, qp->q.fragments);
		head->next = qp->q.fragments->next;

		consume_skb(qp->q.fragments);
		qp->q.fragments = head;
	}

	WARN_ON(!head);
	WARN_ON(FRAG_CB(head)->offset != 0);

	/* Allocate a new buffer for the datagram. */
	ihlen = ip_hdrlen(head);
	len = ihlen + qp->q.len;

	err = -E2BIG;
	if (len > 65535)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_unclone(head, 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_has_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		clone = alloc_skb(0, GFP_ATOMIC);
		if (!clone)
			goto out_nomem;
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_frag_list_init(head);
		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
		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;
		add_frag_mem_limit(qp->q.net, clone->truesize);
	}

	skb_shinfo(head)->frag_list = head->next;
	skb_push(head, head->data - skb_network_header(head));

	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_COMPLETE)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
	}
	sub_frag_mem_limit(qp->q.net, head->truesize);

	head->next = NULL;
	head->dev = dev;
	head->tstamp = qp->q.stamp;
	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

	iph = ip_hdr(head);
	iph->tot_len = htons(len);
	iph->tos |= ecn;

	/* When we set IP_DF on a refragmented skb we must also force a
	 * call to ip_fragment to avoid forwarding a DF-skb of size s while
	 * original sender only sent fragments of size f (where f < s).
	 *
	 * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
	 * frag seen to avoid sending tiny DF-fragments in case skb was built
	 * from one very small df-fragment and one large non-df frag.
	 */
	if (qp->max_df_size == qp->q.max_size) {
		IPCB(head)->flags |= IPSKB_FRAG_PMTU;
		iph->frag_off = htons(IP_DF);
	} else {
		iph->frag_off = 0;
	}

	ip_send_check(iph);

	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
	qp->q.fragments = NULL;
	qp->q.fragments_tail = NULL;
	return 0;

out_nomem:
	net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
	err = -ENOMEM;
	goto out_fail;
out_oversize:
	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	return err;
}
Ejemplo n.º 7
0
int ip_forward(struct sk_buff *skb)
{
	u32 mtu;
	struct iphdr *iph;	/* Our header */
	struct rtable *rt;	/* Route we use */
	struct ip_options *opt	= &(IPCB(skb)->opt);
	struct net *net;

	/* that should never happen */
	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	if (unlikely(skb->sk))
		goto drop;

	if (skb_warn_if_lro(skb))
		goto drop;

	if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
		goto drop;

	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
		return NET_RX_SUCCESS;

	skb_forward_csum(skb);
	net = dev_net(skb->dev);

	/*
	 *	According to the RFC, we must first decrease the TTL field. If
	 *	that reaches zero, we must reply an ICMP control message telling
	 *	that the packet's lifetime expired.
	 */
	if (ip_hdr(skb)->ttl <= 1)
		goto too_many_hops;

	if (!xfrm4_route_forward(skb))
		goto drop;

	rt = skb_rtable(skb);

	if (opt->is_strictroute && rt->rt_uses_gateway)
		goto sr_failed;

	IPCB(skb)->flags |= IPSKB_FORWARDED;
	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
	if (ip_exceeds_mtu(skb, mtu)) {
		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			  htonl(mtu));
		goto drop;
	}

	/* We are about to mangle packet. Copy it! */
	if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len))
		goto drop;
	iph = ip_hdr(skb);

	/* Decrease ttl after skb cow done */
	ip_decrease_ttl(iph);

	/*
	 *	We now generate an ICMP HOST REDIRECT giving the route
	 *	we calculated.
	 */
	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
	    !skb_sec_path(skb))
		ip_rt_send_redirect(skb);

	skb->priority = rt_tos2priority(iph->tos);

	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
		       net, NULL, skb, skb->dev, rt->dst.dev,
		       ip_forward_finish);

sr_failed:
	/*
	 *	Strict routing permits no gatewaying
	 */
	 icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
	 goto drop;

too_many_hops:
	/* Tell the sender its packet died... */
	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
	icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}
Ejemplo n.º 8
0
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
			 struct sk_buff *prev_tail, struct net_device *dev)
{
	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
	struct iphdr *iph;
	struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
	struct sk_buff **nextp; /* To build frag_list. */
	struct rb_node *rbn;
	int len;
	int ihlen;
	int err;
	u8 ecn;

	ipq_kill(qp);

	ecn = ip_frag_ecn_table[qp->ecn];
	if (unlikely(ecn == 0xff)) {
		err = -EINVAL;
		goto out_fail;
	}
	/* Make the one we just received the head. */
	if (head != skb) {
		fp = skb_clone(skb, GFP_ATOMIC);
		if (!fp)
			goto out_nomem;
		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
		if (RB_EMPTY_NODE(&skb->rbnode))
			FRAG_CB(prev_tail)->next_frag = fp;
		else
			rb_replace_node(&skb->rbnode, &fp->rbnode,
					&qp->q.rb_fragments);
		if (qp->q.fragments_tail == skb)
			qp->q.fragments_tail = fp;
		skb_morph(skb, head);
		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
		rb_replace_node(&head->rbnode, &skb->rbnode,
				&qp->q.rb_fragments);
		consume_skb(head);
		head = skb;
	}

	WARN_ON(head->ip_defrag_offset != 0);

	/* Allocate a new buffer for the datagram. */
	ihlen = ip_hdrlen(head);
	len = ihlen + qp->q.len;

	err = -E2BIG;
	if (len > 65535)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_unclone(head, 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_has_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		clone = alloc_skb(0, GFP_ATOMIC);
		if (!clone)
			goto out_nomem;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_frag_list_init(head);
		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
		clone->len = clone->data_len = head->data_len - plen;
		head->truesize += clone->truesize;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;
		add_frag_mem_limit(qp->q.net, clone->truesize);
		skb_shinfo(head)->frag_list = clone;
		nextp = &clone->next;
	} else {
		nextp = &skb_shinfo(head)->frag_list;
	}

	skb_push(head, head->data - skb_network_header(head));

	/* Traverse the tree in order, to build frag_list. */
	fp = FRAG_CB(head)->next_frag;
	rbn = rb_next(&head->rbnode);
	rb_erase(&head->rbnode, &qp->q.rb_fragments);
	while (rbn || fp) {
		/* fp points to the next sk_buff in the current run;
		 * rbn points to the next run.
		 */
		/* Go through the current run. */
		while (fp) {
			*nextp = fp;
			nextp = &fp->next;
			fp->prev = NULL;
			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
			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_COMPLETE)
				head->csum = csum_add(head->csum, fp->csum);
			head->truesize += fp->truesize;
			fp = FRAG_CB(fp)->next_frag;
		}
		/* Move to the next run. */
		if (rbn) {
			struct rb_node *rbnext = rb_next(rbn);

			fp = rb_to_skb(rbn);
			rb_erase(rbn, &qp->q.rb_fragments);
			rbn = rbnext;
		}
	}
	sub_frag_mem_limit(qp->q.net, head->truesize);

	*nextp = NULL;
	head->next = NULL;
	head->prev = NULL;
	head->dev = dev;
	head->tstamp = qp->q.stamp;
	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

	iph = ip_hdr(head);
	iph->tot_len = htons(len);
	iph->tos |= ecn;

	/* When we set IP_DF on a refragmented skb we must also force a
	 * call to ip_fragment to avoid forwarding a DF-skb of size s while
	 * original sender only sent fragments of size f (where f < s).
	 *
	 * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
	 * frag seen to avoid sending tiny DF-fragments in case skb was built
	 * from one very small df-fragment and one large non-df frag.
	 */
	if (qp->max_df_size == qp->q.max_size) {
		IPCB(head)->flags |= IPSKB_FRAG_PMTU;
		iph->frag_off = htons(IP_DF);
	} else {
		iph->frag_off = 0;
	}

	ip_send_check(iph);

	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
	qp->q.fragments = NULL;
	qp->q.rb_fragments = RB_ROOT;
	qp->q.fragments_tail = NULL;
	qp->q.last_run_head = NULL;
	return 0;

out_nomem:
	net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
	err = -ENOMEM;
	goto out_fail;
out_oversize:
	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	return err;
}
Ejemplo n.º 9
0
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
	struct rb_node **rbn, *parent;
	struct sk_buff *skb1, *prev_tail;
	struct net_device *dev;
	unsigned int fragsize;
	int flags, offset;
	int ihl, end;
	int err = -ENOENT;
	u8 ecn;

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto err;

	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
	    unlikely(ip_frag_too_far(qp)) &&
	    unlikely(err = ip_frag_reinit(qp))) {
		ipq_kill(qp);
		goto err;
	}

	ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
	offset = ntohs(ip_hdr(skb)->frag_off);
	flags = offset & ~IP_OFFSET;
	offset &= IP_OFFSET;
	offset <<= 3;		/* offset is in 8-byte chunks */
	ihl = ip_hdrlen(skb);

	/* Determine the position of this fragment. */
	end = offset + skb->len - skb_network_offset(skb) - ihl;
	err = -EINVAL;

	/* 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 corrupted.
		 */
		if (end < qp->q.len ||
		    ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
			goto err;
		qp->q.flags |= INET_FRAG_LAST_IN;
		qp->q.len = end;
	} else {
		if (end&7) {
			end &= ~7;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
		if (end > qp->q.len) {
			/* Some bits beyond end -> corruption. */
			if (qp->q.flags & INET_FRAG_LAST_IN)
				goto err;
			qp->q.len = end;
		}
	}
	if (end == offset)
		goto err;

	err = -ENOMEM;
	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
		goto err;

	err = pskb_trim_rcsum(skb, end - offset);
	if (err)
		goto err;

	/* Note : skb->rbnode and skb->dev share the same location. */
	dev = skb->dev;
	/* Makes sure compiler wont do silly aliasing games */
	barrier();

	/* RFC5722, Section 4, amended by Errata ID : 3089
	 *                          When reassembling an IPv6 datagram, if
	 *   one or more its constituent fragments is determined to be an
	 *   overlapping fragment, the entire datagram (and any constituent
	 *   fragments) MUST be silently discarded.
	 *
	 * We do the same here for IPv4 (and increment an snmp counter).
	 */

	/* Find out where to put this fragment.  */
	prev_tail = qp->q.fragments_tail;
	if (!prev_tail)
		ip4_frag_create_run(&qp->q, skb);  /* First fragment. */
	else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
		/* This is the common case: skb goes to the end. */
		/* Detect and discard overlaps. */
		if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
			goto discard_qp;
		if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
			ip4_frag_append_to_last_run(&qp->q, skb);
		else
			ip4_frag_create_run(&qp->q, skb);
	} else {
		/* Binary search. Note that skb can become the first fragment,
		 * but not the last (covered above).
		 */
		rbn = &qp->q.rb_fragments.rb_node;
		do {
			parent = *rbn;
			skb1 = rb_to_skb(parent);
			if (end <= skb1->ip_defrag_offset)
				rbn = &parent->rb_left;
			else if (offset >= skb1->ip_defrag_offset +
						FRAG_CB(skb1)->frag_run_len)
				rbn = &parent->rb_right;
			else /* Found an overlap with skb1. */
				goto discard_qp;
		} while (*rbn);
		/* Here we have parent properly set, and rbn pointing to
		 * one of its NULL left/right children. Insert skb.
		 */
		ip4_frag_init_run(skb);
		rb_link_node(&skb->rbnode, parent, rbn);
		rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
	}

	if (dev)
		qp->iif = dev->ifindex;
	skb->ip_defrag_offset = offset;

	qp->q.stamp = skb->tstamp;
	qp->q.meat += skb->len;
	qp->ecn |= ecn;
	add_frag_mem_limit(qp->q.net, skb->truesize);
	if (offset == 0)
		qp->q.flags |= INET_FRAG_FIRST_IN;

	fragsize = skb->len + ihl;

	if (fragsize > qp->q.max_size)
		qp->q.max_size = fragsize;

	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
	    fragsize > qp->max_df_size)
		qp->max_df_size = fragsize;

	if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
	    qp->q.meat == qp->q.len) {
		unsigned long orefdst = skb->_skb_refdst;

		skb->_skb_refdst = 0UL;
		err = ip_frag_reasm(qp, skb, prev_tail, dev);
		skb->_skb_refdst = orefdst;
		return err;
	}

	skb_dst_drop(skb);
	return -EINPROGRESS;

discard_qp:
	inet_frag_kill(&qp->q);
	err = -EINVAL;
	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
err:
	kfree_skb(skb);
	return err;
}
Ejemplo n.º 10
0
/* Find the correct entry in the "incomplete datagrams" queue for
 * this IP datagram, and create new one, if nothing is found.
 */
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
			   u32 user, int vif)
{
	struct frag_v4_compare_key key = {
		.saddr = iph->saddr,
		.daddr = iph->daddr,
		.user = user,
		.vif = vif,
		.id = iph->id,
		.protocol = iph->protocol,
	};
	struct inet_frag_queue *q;

	q = inet_frag_find(&net->ipv4.frags, &key);
	if (!q)
		return NULL;

	return container_of(q, struct ipq, q);
}

/* Is the fragment too far ahead to be part of ipq? */
static int ip_frag_too_far(struct ipq *qp)
{
	struct inet_peer *peer = qp->peer;
	unsigned int max = qp->q.net->max_dist;
	unsigned int start, end;

	int rc;

	if (!peer || !max)
		return 0;

	start = qp->rid;
	end = atomic_inc_return(&peer->rid);
	qp->rid = end;

	rc = qp->q.fragments_tail && (end - start) > max;

	if (rc) {
		struct net *net;

		net = container_of(qp->q.net, struct net, ipv4.frags);
		__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	}

	return rc;
}

static int ip_frag_reinit(struct ipq *qp)
{
	unsigned int sum_truesize = 0;

	if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
		refcount_inc(&qp->q.refcnt);
		return -ETIMEDOUT;
	}

	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments);
	sub_frag_mem_limit(qp->q.net, sum_truesize);

	qp->q.flags = 0;
	qp->q.len = 0;
	qp->q.meat = 0;
	qp->q.fragments = NULL;
	qp->q.rb_fragments = RB_ROOT;
	qp->q.fragments_tail = NULL;
	qp->q.last_run_head = NULL;
	qp->iif = 0;
	qp->ecn = 0;

	return 0;
}
Ejemplo n.º 11
0
/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(struct timer_list *t)
{
	struct inet_frag_queue *frag = from_timer(frag, t, timer);
	const struct iphdr *iph;
	struct sk_buff *head = NULL;
	struct net *net;
	struct ipq *qp;
	int err;

	qp = container_of(frag, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	rcu_read_lock();
	spin_lock(&qp->q.lock);

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);

	if (!(qp->q.flags & INET_FRAG_FIRST_IN))
		goto out;

	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
	 * pull the head out of the tree in order to be able to
	 * deal with head->dev.
	 */
	if (qp->q.fragments) {
		head = qp->q.fragments;
		qp->q.fragments = head->next;
	} else {
		head = skb_rb_first(&qp->q.rb_fragments);
		if (!head)
			goto out;
		if (FRAG_CB(head)->next_frag)
			rb_replace_node(&head->rbnode,
					&FRAG_CB(head)->next_frag->rbnode,
					&qp->q.rb_fragments);
		else
			rb_erase(&head->rbnode, &qp->q.rb_fragments);
		memset(&head->rbnode, 0, sizeof(head->rbnode));
		barrier();
	}
	if (head == qp->q.fragments_tail)
		qp->q.fragments_tail = NULL;

	sub_frag_mem_limit(qp->q.net, head->truesize);

	head->dev = dev_get_by_index_rcu(net, qp->iif);
	if (!head->dev)
		goto out;


	/* skb has no dst, perform route lookup again */
	iph = ip_hdr(head);
	err = ip_route_input_noref(head, iph->daddr, iph->saddr,
					   iph->tos, head->dev);
	if (err)
		goto out;

	/* Only an end host needs to send an ICMP
	 * "Fragment Reassembly Timeout" message, per RFC792.
	 */
	if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
	    (skb_rtable(head)->rt_type != RTN_LOCAL))
		goto out;

	spin_unlock(&qp->q.lock);
	icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
	goto out_rcu_unlock;

out:
	spin_unlock(&qp->q.lock);
out_rcu_unlock:
	rcu_read_unlock();
	if (head)
		kfree_skb(head);
	ipq_put(qp);
}