diff mbox

[net-next] ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK

Message ID 20131025194003.GG15744@order.stressinduktion.org
State Superseded, archived
Delegated to: David Miller
Headers show

Commit Message

Hannes Frederic Sowa Oct. 25, 2013, 7:40 p.m. UTC 
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.

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

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
 net/ipv4/ip_output.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

Comments

Hannes Frederic Sowa Oct. 27, 2013, 2:37 p.m. UTC | #1 
On Fri, Oct 25, 2013 at 09:40:03PM +0200, Hannes Frederic Sowa wrote:
>  	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
>  	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
> +	maxmsgsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
> +		     maxfraglen : 0xFFFF;

Oops, sorry. I just realized that the check is too strict. The 64
bit boundary restricton is solely used if we are actually generating
fragments. So I should have used mtu directly instead of maxfraglen.

This should only matter in case of some unusual MTUs but I will send a
corrected patch as soon as I am at home.

Greetings,

  Hannes

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8fbac7d..27dc1b3 100644
--- 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, maxmsgsize;
 	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;
+	maxmsgsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+		     maxfraglen : 0xFFFF;
 
-	if (cork->length + length > 0xFFFF - fragheaderlen) {
+	if (cork->length + length > maxmsgsize - 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, maxmsgsize;
 
 	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;
+	maxmsgsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+		     maxfraglen : 0xFFFF;
 
-	if (cork->length + size > 0xFFFF - fragheaderlen) {
+	if (cork->length + size > maxmsgsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
 		return -EMSGSIZE;
 	}