On Thu 27-05-21 21:05:01, Feng Tang wrote: > On Thu, May 27, 2021 at 09:30:00AM +0200, Michal Hocko wrote: [...] > > Until now this was not a real problem even for OOM context because > > alloc_page_interleave is always used for the interleaving policy > > and that one doesn't use any node mask so the code is not really > > exercised. With your MPOL_PREFERRED this would no longer be the case. > > Given the 'interleave' task may have memory allocated from all nodes, > shouldn't the mempolicy_nodemask_intersects() return true for 'interleave'? > or I'm still missing something? Well, if you go with the renaming then it should be quite obvious that any policies which are not a hard binding should return true. -- Michal Hocko SUSE Labs
