On Thu, 2022-06-16 at 10:08 +0300, Leon Romanovsky wrote: > On Mon, Jun 06, 2022 at 12:38:36PM -0700, Gerd Rausch wrote: > > Unlike with IPv[46], where "ip_finish_output2" triggers > > a refresh of STALE neighbour entries via "neigh_output", > > "rdma_resolve_addr" never triggers an update. > > > > If a wrong STALE entry ever enters the cache, it'll remain > > wrong forever (unless refreshed via TCP/IP, or otherwise). > > > > Let the cache inconsistency resolve itself by triggering > > an update from "rdma_resolve_addr". > > > > Signed-off-by: Gerd Rausch <gerd.rausch@xxxxxxxxxx> > > --- > > drivers/infiniband/core/addr.c | 40 ++++++++++++++++++++++++++++++++++ > > 1 file changed, 40 insertions(+) > > Gerd, > > Do you plan to resubmit the patch? > There is a complain from kbuild robot. > > Hi Leon, The kbuild robot complained about a __be32 passed as u32. I'll simply add a "(__force u32)" cast as is done in other places. I didn't want to make a lot of noise by re-submitting for such a simple change, but I can certainly re-submit, and will do so. Thanks, Gerd
