This patch allows VIRTIO_NET_F_HASH_REPORT feature to the adapter whose backend does not have a virtio header and does not have offload features that depend on it. The migration between such different systems is very problematic even if it seems successful, such setups are not performance-oriented and especially supporting the hash delivery for them is (IMHO) redundant, it just requires more testing and does not bring any advantage.
On Fri, Oct 27, 2023 at 11:07 AM Akihiko Odaki <akihiko.od...@daynix.com> wrote: > On 2023/10/27 16:14, Jason Wang wrote: > > On Tue, Oct 17, 2023 at 12:14 PM Akihiko Odaki <akihiko.od...@daynix.com> > wrote: > >> > >> virtio-net can report hash values even if the peer does not have a > >> virtio-net header. > > > > Do we need a compat flag for this? > > I don't think so. This change actually fixes the migration from a system > with tap devices that support virtio-net headers to a system with tap > devices that do not support virtio-net headers. Such a compatibility > flag will revert the fix. > > Regards, > Akihiko Odaki >
