Bug in sbsndptr()

[Lawrence Stewart]

Hi Andre,

A colleague and I spent a very frustrating day tracing an accounting bug
in the multipath TCP patch we're working on at CAIA to a bug in
sbsndptr(). I haven't tested it with regular TCP yet, but I believe the
following patch fixes the bug (proposed commit log message is at the top
of the patch):

http://people.freebsd.org/~lstewart/patches/misctcp/sbsndptr_mnext_10.x.r247314.diff

The patch should have no tangible effect to operation other than to
ensure the function delivers on the promise to return the closest mbuf
in the chain for the given offset.

I would appreciate a review and any thoughts.

Cheers,
Lawrence