Re: [RFC-PATCH 2/4] mm: Add __rcu_alloc_page_lockless() func.

[Michal Hocko]

On Fri 02-10-20 09:50:14, Mel Gorman wrote:
> On Fri, Oct 02, 2020 at 09:11:23AM +0200, Michal Hocko wrote:
> > On Thu 01-10-20 21:26:26, Uladzislau Rezki wrote:
> > > > 
> > > > No, I meant going back to idea of new gfp flag, but adjust the implementation in
> > > > the allocator (different from what you posted in previous version) so that it
> > > > only looks at the flag after it tries to allocate from pcplist and finds out
> > > > it's empty. So, no inventing of new page allocator entry points or checks such
> > > > as the one you wrote above, but adding the new gfp flag in a way that it doesn't
> > > > affect existing fast paths.
> > > >
> > > OK. Now i see. Please have a look below at the patch, so we fully understand
> > > each other. If that is something that is close to your view or not:
> > > 
> > > <snip>
> > > t a/include/linux/gfp.h b/include/linux/gfp.h
> > > index c603237e006c..7e613560a502 100644
> > > --- a/include/linux/gfp.h
> > > +++ b/include/linux/gfp.h
> > > @@ -39,8 +39,9 @@ struct vm_area_struct;
> > >  #define ___GFP_HARDWALL                0x100000u
> > >  #define ___GFP_THISNODE                0x200000u
> > >  #define ___GFP_ACCOUNT         0x400000u
> > > +#define ___GFP_NO_LOCKS                0x800000u
> > 
> > Even if a new gfp flag gains a sufficient traction and support I am
> > _strongly_ opposed against consuming another flag for that. Bit space is
> > limited. 
> 
> That is definitely true. I'm not happy with the GFP flag at all, the
> comment is at best a damage limiting move. It still would be better for
> a memory pool to be reserved and sized for critical allocations.

Completely agreed. The only existing usecase is so special cased that a
dedicated pool is not only easier to maintain but it should be also much
better tuned for the specific workload. Something not really feasible
with the allocator.

> > Besides that we certainly do not want to allow craziness like
> > __GFP_NO_LOCK | __GFP_RECLAIM (and similar), do we?
> 
> That would deserve to be taken to a dumpster and set on fire. The flag
> combination could be checked in the allocator but the allocator path fast
> paths are bad enough already.

If a new allocation/gfp mode is absolutely necessary then I believe that
the most reasoanble way forward would be
#define GFP_NO_LOCK	((__force gfp_t)0)

and explicitly document it as a final flag to use without any further
modifiers. Yeah there are some that could be used potentially - e.g. zone
specifiers, __GFP_ZERO and likely few others. But support for those can
be added when there is an actual and reasonable demand.

I would also strongly argue against implementation alowing to fully
consume pcp free pages.
-- 
Michal Hocko
SUSE Labs