On Mon, 2016-05-09 at 10:22 -0700, Alexander Duyck wrote: > One thought that just occurred to me based on this would be to > configure inner headers on the way up, and to configure the outer > headers on the way down. Then that way we could go through and be > guaranteed that the inner headers represent the inner most set of > header offsets, and the outer ones represent the outer-most set > regardless of the total number of headers present and there would be > no need to call into the reset_headers function since all the headers > would already be set. > > I was also looking at possibly dropping the inner transport offset as > from what I can tell it and the csum_offset should always be the same > value since csum_offset will always point to the inner transport > header when any kind of offload is enabled which is the criteria for > skb->encapsulation being set anyway.
Ideally nothing should be changed in the source skb while doing gso_segment() calls. As we did in gro_complete() when adding nhoff argument, we probably could pass the current offset and not touch skb->data and various header offsets. Presumably gso state should be stored in a separate structure. I meant, gso_segment() is not a 'please sanity fix this skb'. Only DODGY thing might need to ?
