ipv6/netfilter: Discard first fragment not including all headers

Packets are processed even though the first fragment don't include all
headers through the upper layer header. This breaks TAHI IPv6 Core
Conformance Test v6LC.1.3.6.

Referring to RFC8200 SECTION 4.5: "If the first fragment does not include
all headers through an Upper-Layer header, then that fragment should be
discarded and an ICMP Parameter Problem, Code 3, message should be sent to
the source of the fragment, with the Pointer field set to zero."

The fragment needs to be validated the same way it is done in
commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't
include all headers") for ipv6. Wrap the validation into a common function,
ipv6_frag_thdr_truncated() to check for truncation in the upper layer
header. This validation does not fullfill all aspects of RFC 8200,
section 4.5, but is at the moment sufficient to pass mentioned TAHI test.

In netfilter, utilize the fragment offset returned by find_prev_fhdr() to
let ipv6_frag_thdr_truncated() start it's traverse from the fragment
header.

Return 0 to drop the fragment in the netfilter. This is the same behaviour
as used on other protocol errors in this function, e.g. when
nf_ct_frag6_queue() returns -EPROTO. The Fragment will later be picked up
by ipv6_frag_rcv() in reassembly.c. ipv6_frag_rcv() will then send an
appropriate ICMP Parameter Problem message back to the source.

References commit 2efdaaaf883a ("IPv6: reply ICMP error if the first
fragment don't include all headers")

Signed-off-by: Georg Kohmann <geokohma@cisco.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://lore.kernel.org/r/20201111115025.28879-1-geokohma@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index bd1f396cc9c729d734fbf9132335266dfddec5f9..637cc6dd12b7d6613dffbfa02f42dd2b99d5b021 100644 (file)
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1064,6 +1064,8 @@ int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp,
 
 bool ipv6_ext_hdr(u8 nexthdr);
 
+bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp);
+
 enum {
        IP6_FH_F_FRAG           = (1 << 0),
        IP6_FH_F_AUTH           = (1 << 1),

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 054d287eb13d031b908efe154376d8e033d41b44..b9cc0b330dbef06a310914e3f80fda2658437f18 100644 (file)
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -440,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
 int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 {
        u16 savethdr = skb->transport_header;
+       u8 nexthdr = NEXTHDR_FRAGMENT;
        int fhoff, nhoff, ret;
        struct frag_hdr *fhdr;
        struct frag_queue *fq;
@@ -455,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
        if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
                return 0;
 
+       /* Discard the first fragment if it does not include all headers
+        * RFC 8200, Section 4.5
+        */
+       if (ipv6_frag_thdr_truncated(skb, fhoff, &nexthdr)) {
+               pr_debug("Drop incomplete fragment\n");
+               return 0;
+       }
+
        if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
                return -ENOMEM;
 

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index c8cf1bbad74a241f8867ca41328406bcd06e0c35..e3869bac9c886218c47b802940e35cfd255387f5 100644 (file)
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -318,15 +318,43 @@ out_fail:
        return -1;
 }
 
+/* Check if the upper layer header is truncated in the first fragment. */
+bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp)
+{
+       u8 nexthdr = *nexthdrp;
+       __be16 frag_off;
+       int offset;
+
+       offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off);
+       if (offset < 0 || (frag_off & htons(IP6_OFFSET)))
+               return false;
+       switch (nexthdr) {
+       case NEXTHDR_TCP:
+               offset += sizeof(struct tcphdr);
+               break;
+       case NEXTHDR_UDP:
+               offset += sizeof(struct udphdr);
+               break;
+       case NEXTHDR_ICMP:
+               offset += sizeof(struct icmp6hdr);
+               break;
+       default:
+               offset += 1;
+       }
+       if (offset > skb->len)
+               return true;
+       return false;
+}
+EXPORT_SYMBOL(ipv6_frag_thdr_truncated);
+
 static int ipv6_frag_rcv(struct sk_buff *skb)
 {
        struct frag_hdr *fhdr;
        struct frag_queue *fq;
        const struct ipv6hdr *hdr = ipv6_hdr(skb);
        struct net *net = dev_net(skb_dst(skb)->dev);
-       __be16 frag_off;
-       int iif, offset;
        u8 nexthdr;
+       int iif;
 
        if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
                goto fail_hdr;
@@ -362,24 +390,11 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
         * the source of the fragment, with the Pointer field set to zero.
         */
        nexthdr = hdr->nexthdr;
-       offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off);
-       if (offset >= 0) {
-               /* Check some common protocols' header */
-               if (nexthdr == IPPROTO_TCP)
-                       offset += sizeof(struct tcphdr);
-               else if (nexthdr == IPPROTO_UDP)
-                       offset += sizeof(struct udphdr);
-               else if (nexthdr == IPPROTO_ICMPV6)
-                       offset += sizeof(struct icmp6hdr);
-               else
-                       offset += 1;
-
-               if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) {
-                       __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
-                                       IPSTATS_MIB_INHDRERRORS);
-                       icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
-                       return -1;
-               }
+       if (ipv6_frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
+               __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+                               IPSTATS_MIB_INHDRERRORS);
+               icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+               return -1;
        }
 
        iif = skb->dev ? skb->dev->ifindex : 0;