Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA

[Joonsoo Kim]

On Tue, Aug 30, 2016 at 06:10:46PM +0530, Aneesh Kumar K.V wrote:
> "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx> writes:
> 
> > ....
> >
> >>  static inline void check_highest_zone(enum zone_type k)
> >>  {
> >> -	if (k > policy_zone && k != ZONE_MOVABLE)
> >> +	if (k > policy_zone && k != ZONE_MOVABLE && !is_zone_cma_idx(k))
> >>  		policy_zone = k;
> >>  }
> >>
> >
> >
> > Should we apply policy to allocation from ZONE CMA ?. CMA reserve
> > happens early and may mostly come from one node. Do we want the
> > CMA allocation to fail if we use mbind(MPOL_BIND) with a node mask not
> > including that node on which CMA is reserved, considering CMA memory is
> > going to be used for special purpose.
> 
> Looking at this again, I guess CMA alloc is not going to depend on
> memory policy, but this is for other movable allocation ?

This is for usual file cache or anonymous page allocation. IIUC,
policy_zone is used to determine if mempolicy should be applied or not
and setting policy_zone to ZONE_CMA makes mempolicy less useful.

Thanks.