On Thu, 10 Mar 2022 20:06:40 +0100 Toke Høiland-Jørgensen wrote: > >> So this always clones the skb if it has frags? Is that really needed? > > > > if we look at skb_cow_data(), paged area is always considered not writable > > Ah, right, did not know that. Seems a bit odd, but OK. Yeah, I think I pointed that out, I may well be wrong. AFAICT frags which are not writable are not marked in any clear way. We have SKBFL_SHARED_FRAG which seems pretty close but its documented as an indication that the frag can be written under our feet, not that we can't write to it. Subtly different. And (as documented) it's only used when doing SW csums, as far as I can grep. Maybe someone else knows the semantics.
