ip: discard IPv4 datagrams with overlapping segments.

BugLink: https://bugs.launchpad.net/bugs/1818806

commit 7969e5c4 upstream.

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>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
[bwh: Backported to 4.4:
 - s/__IP_INC_STATS/IP_INC_STATS_BH/
 - Deleted code is slightly different]
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Juerg Haefliger <juergh@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

include/uapi/linux/snmp.h

@@ -55,6 +55,7 @@ enum
 	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
 	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
 	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
+	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
 	__IPSTATS_MIB_MAX
 };
 

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;
@@ -357,60 +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;
-		}
-	}
-
-	err = -ENOMEM;
 
-	while (next && next->ip_defrag_offset < end) {
-		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
+	/* Is there an overlap with the previous fragment? */
+	if (prev &&
+	    (prev->ip_defrag_offset + prev->len) > offset)
+		goto discard_qp;
 
-		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;
-			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;
@@ -458,6 +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_BH(net, IPSTATS_MIB_REASM_OVERLAPS);
 err:
 	kfree_skb(skb);
 	return err;

net/ipv4/proc.c

@@ -132,6 +132,7 @@ 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
 };