Hi, On Fri, 26 Aug 2016 13:45:56 -0700 Alexander Duyck <alexander.du...@gmail.com> wrote: > > However, if TSO is off, but GSO is on, who takes care of further > > splitting these skbs according to their gso_size? > > I believe the patch resolves it via the net_gso_ok check. This is > used to verify if the lower device could segment it if we split out > the buffers from skb->frag_list.
Thanks, got it. > > And another question: > > Can this be utilized in any way to solve the problem described in [1] ? > > > > [1] https://patchwork.ozlabs.org/patch/661419/ > > I don't think so. This solution is to only do part of the software > offload and still make use of an existing hardware offload. Sorry, I wasn't too clear. When attempting to reduce gso_size in order to avoid segmentation+fragmentation, problem I'm hitting is: http://lists.openwall.net/netdev/2016/08/25/35 Actually, the idea of yours hinted me to a new direction, will pursue that. Thanks, Shmulik
