From 4b3b45edba9222e518a1ec72df841eba3609fe34 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 9 Mar 2017 13:56:46 +0300 Subject: udp: avoid ufo handling on IP payload compression packets commit c146066ab802 ("ipv4: Don't use ufo handling on later transformed packets") and commit f89c56ce710a ("ipv6: Don't use ufo handling on later transformed packets") added a check that 'rt->dst.header_len' isn't zero in order to skip UFO, but it doesn't include IPcomp in transport mode where it equals zero. Packets, after payload compression, may not require further fragmentation, and if original length exceeds MTU, later compressed packets will be transmitted incorrectly. This can be reproduced with LTP udp_ipsec.sh test on veth device with enabled UFO, MTU is 1500 and UDP payload is 2000: * IPv4 case, offset is wrong + unnecessary fragmentation udp_ipsec.sh -p comp -m transport -s 2000 & tcpdump -ni ltp_ns_veth2 ... IP (tos 0x0, ttl 64, id 45203, offset 0, flags [+], proto Compressed IP (108), length 49) 10.0.0.2 > 10.0.0.1: IPComp(cpi=0x1000) IP (tos 0x0, ttl 64, id 45203, offset 1480, flags [none], proto UDP (17), length 21) 10.0.0.2 > 10.0.0.1: ip-proto-17 * IPv6 case, sending small fragments udp_ipsec.sh -6 -p comp -m transport -s 2000 & tcpdump -ni ltp_ns_veth2 ... IP6 (flowlabel 0x6b9ba, hlim 64, next-header Compressed IP (108) payload length: 37) fd00::2 > fd00::1: IPComp(cpi=0x1000) IP6 (flowlabel 0x6b9ba, hlim 64, next-header Compressed IP (108) payload length: 21) fd00::2 > fd00::1: IPComp(cpi=0x1000) Fix it by checking 'rt->dst.xfrm' pointer to 'xfrm_state' struct, skip UFO if xfrm is set. So the new check will include both cases: IPcomp and IPsec. Fixes: c146066ab802 ("ipv4: Don't use ufo handling on later transformed packets") Fixes: f89c56ce710a ("ipv6: Don't use ufo handling on later transformed packets") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6/ip6_output.c') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 528b3c1f3fde..df42096e1f04 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1385,7 +1385,7 @@ emsgsize: if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, -- cgit From 79e49503efe53a8c51d8b695bedc8a346c5e4a87 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 13 Mar 2017 16:24:28 +0100 Subject: ipv6: avoid write to a possibly cloned skb ip6_fragment, in case skb has a fraglist, checks if the skb is cloned. If it is, it will move to the 'slow path' and allocates new skbs for each fragment. However, right before entering the slowpath loop, it updates the nexthdr value of the last ipv6 extension header to NEXTHDR_FRAGMENT, to account for the fragment header that will be inserted in the new ipv6-fragment skbs. In case original skb is cloned this munges nexthdr value of another skb. Avoid this by doing the nexthdr update for each of the new fragment skbs separately. This was observed with tcpdump on a bridge device where netfilter ipv6 reassembly is active: tcpdump shows malformed fragment headers as the l4 header (icmpv6, tcp, etc). is decoded as a fragment header. Cc: Hannes Frederic Sowa Reported-by: Andreas Karis Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/ipv6/ip6_output.c') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index df42096e1f04..58f6288e9ba5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -768,13 +768,14 @@ slow_path: * Fragment the datagram. */ - *prevhdr = NEXTHDR_FRAGMENT; troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while (left > 0) { + u8 *fragnexthdr_offset; + len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) @@ -819,6 +820,10 @@ slow_path: */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + /* * Build fragment header. */ -- cgit