ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK

UFO as well as UDP_CORK do not respect IP_PMTUDISC_DO and
IP_PMTUDISC_PROBE well enough.

UFO enabled packet delivery just appends all frags to the cork and hands
it over to the network card. So we just deliver non-DF udp fragments
(DF-flag may get overwritten by hardware or virtual UFO enabled
interface).

UDP_CORK does enqueue the data until the cork is disengaged. At this
point it sets the correct IP_DF and local_df flags and hands it over to
ip_fragment which in this case will generate an icmp error which gets
appended to the error socket queue. This is not reflected in the syscall
error (of course, if UFO is enabled this also won't happen).

Improve this by checking the pmtudisc flags before appending data to the
socket and if we still can fit all data in one packet when IP_PMTUDISC_DO
or IP_PMTUDISC_PROBE is set, only then proceed.

We use (mtu-fragheaderlen) to check for the maximum length because we
ensure not to generate a fragment and non-fragmented data does not need
to have its length aligned on 64 bit boundaries. Also the passed in
ip_options are already aligned correctly.

Maybe, we can relax some other checks around ip_fragment. This needs
more research.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8fbac7de1e1b731e14aa485e75c1212618cace55..51be64e18e32e92ffaf898351142f01d9c9c42ec 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -810,7 +810,7 @@ static int __ip_append_data(struct sock *sk,
        int copy;
        int err;
        int offset = 0;
-       unsigned int maxfraglen, fragheaderlen;
+       unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
        int csummode = CHECKSUM_NONE;
        struct rtable *rt = (struct rtable *)cork->dst;
 
@@ -823,8 +823,10 @@ static int __ip_append_data(struct sock *sk,
 
        fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
        maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+       maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+                        mtu : 0xFFFF;
 
-       if (cork->length + length > 0xFFFF - fragheaderlen) {
+       if (cork->length + length > maxnonfragsize - fragheaderlen) {
                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
                               mtu-exthdrlen);
                return -EMSGSIZE;
@@ -1122,7 +1124,7 @@ ssize_t   ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
        int mtu;
        int len;
        int err;
-       unsigned int maxfraglen, fragheaderlen, fraggap;
+       unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
 
        if (inet->hdrincl)
                return -EPERM;
@@ -1146,8 +1148,10 @@ ssize_t  ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
        fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
        maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+       maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+                        mtu : 0xFFFF;
 
-       if (cork->length + size > 0xFFFF - fragheaderlen) {
+       if (cork->length + size > maxnonfragsize - fragheaderlen) {
                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
                return -EMSGSIZE;
        }