On Wed, 17 Dec 2008, Herbert Xu wrote:

Ilpo J??rvinen [off-list ref] wrote:

quoted

I should have noticed this earlier... :-) The previous solution
to URG+GSO/TSO will cause SACK block tcp_fragment to do zig-zig
patterns, or even worse, a steep downward slope into packet
counting because each skb pcount would be truncated to pcount
of 2 and then the following fragments of the later portion would
restore the window again.

How about just handling it, URG isn't that hard.  If anyone is
bored you can do this for GRO as well.

tcp: Add GSO support for urgent data

When segmenting packets with urgent data we need to clear the
urgent flag/pointer once we move past the end of the urgent data.
This was not handled correctly in GSO or (presumably) in existing
hardware.

This patch adds a new GSO flag for TCP urgent data and also fixes
its handling in GSO.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

This is certainly nice and possible but as mention earlier, the harder 
problem is that the urg_ptr is only 16-bits so there will be still be 
problem if the urgent seq-64k mark is within a super-skb as tail segments 
need urg while the head ones won't. I think we would need out-of-band 
means to communicate the extra bit (17th) from tcp if we want to solve 
that one. It would be rather easy to change TCP to only do splitting for 
that particular skb though and keep everything else intact.

...The same consideration applies to gro as well.


-- 
 i.