diff mbox series

[v2,net-next,1/3] ip: discard IPv4 datagrams with overlapping segments.

Message ID 20180802233439.51643-2-posk@google.com
State Accepted, archived
Delegated to: David Miller
Headers show
Series ip: Use rb trees for IP frag queue | expand

Commit Message

Peter Oskolkov Aug. 2, 2018, 11:34 p.m. UTC 
This behavior is required in IPv6, and there is little need
to tolerate overlapping fragments in IPv4. This change
simplifies the code and eliminates potential DDoS attack vectors.

Tested: ran ip_defrag selftest (not yet available uptream).

Suggested-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>

---
 include/uapi/linux/snmp.h |  1 +
 net/ipv4/ip_fragment.c    | 75 ++++++++++-----------------------------
 net/ipv4/proc.c           |  1 +
 3 files changed, 21 insertions(+), 56 deletions(-)

Comments

Stephen Hemminger Aug. 3, 2018, 12:09 a.m. UTC | #1 
On Thu,  2 Aug 2018 23:34:37 +0000
Peter Oskolkov <posk@google.com> wrote:

> This behavior is required in IPv6, and there is little need
> to tolerate overlapping fragments in IPv4. This change
> simplifies the code and eliminates potential DDoS attack vectors.
> 
> Tested: ran ip_defrag selftest (not yet available uptream).
> 
> Suggested-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Peter Oskolkov <posk@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Florian Westphal <fw@strlen.de>

There are a couple of relevant RFC's

RFC 1858 - Security Considerations for IP Fragment Filtering
RFC 2460 - Handling of Overlapping IPv6 Fragments

Acked-by: Stephen Hemminger <stephen@networkplumber.org>
diff mbox series

Patch

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index e5ebc83827ab..f80135e5feaa 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -56,6 +56,7 @@  enum
 	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
 	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
 	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
+	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
 	__IPSTATS_MIB_MAX
 };
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d14d741fb05e..960bf5eab59f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -277,6 +277,7 @@  static int ip_frag_reinit(struct ipq *qp)
 /* 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 sk_buff *prev, *next;
 	struct net_device *dev;
 	unsigned int fragsize;
@@ -357,65 +358,23 @@  static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	}
 
 found:
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
+	/* 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.
 	 */
-	if (prev) {
-		int i = (prev->ip_defrag_offset + prev->len) - offset;
 
-		if (i > 0) {
-			offset += i;
-			err = -EINVAL;
-			if (end <= offset)
-				goto err;
-			err = -ENOMEM;
-			if (!pskb_pull(skb, i))
-				goto err;
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
+	/* Is there an overlap with the previous fragment? */
+	if (prev &&
+	    (prev->ip_defrag_offset + prev->len) > offset)
+		goto discard_qp;
 
-	err = -ENOMEM;
-
-	while (next && next->ip_defrag_offset < end) {
-		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
-
-		if (i < next->len) {
-			int delta = -next->truesize;
-
-			/* Eat head of the next overlapped fragment
-			 * and leave the loop. The next ones cannot overlap.
-			 */
-			if (!pskb_pull(next, i))
-				goto err;
-			delta += next->truesize;
-			if (delta)
-				add_frag_mem_limit(qp->q.net, delta);
-			next->ip_defrag_offset += i;
-			qp->q.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
-				qp->q.fragments = next;
-
-			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(qp->q.net, free_it->truesize);
-			kfree_skb(free_it);
-		}
-	}
+	/* Is there an overlap with the next fragment? */
+	if (next && next->ip_defrag_offset < end)
+		goto discard_qp;
 
 	/* Note : skb->ip_defrag_offset and skb->dev share the same location */
 	dev = skb->dev;
@@ -463,6 +422,10 @@  static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	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;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index b46e4cf9a55a..70289682a670 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -119,6 +119,7 @@  static const struct snmp_mib snmp4_ipextstats_list[] = {
 	SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
 	SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
 	SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
+	SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
 	SNMP_MIB_SENTINEL
 };