Re: [PATCH v2] mm: hugetlb: optionally allocate gigantic hugepages using cma

[Roman Gushchin <guro@fb.com>]

On Tue, Mar 10, 2020 at 06:39:51PM +0100, Michal Hocko wrote:
> On Tue 10-03-20 10:30:56, Roman Gushchin wrote:
> > On Tue, Mar 10, 2020 at 10:01:21AM +0100, Michal Hocko wrote:
> > > On Mon 09-03-20 17:25:24, Roman Gushchin wrote:
> > > [...]
> > > > 2) Run-time allocations of gigantic hugepages are performed using the
> > > >    cma allocator and the dedicated cma area
> > > 
> > > [...]
> > > > @@ -1237,6 +1246,23 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
> > > >  {
> > > >  	unsigned long nr_pages = 1UL << huge_page_order(h);
> > > >  
> > > > +	if (IS_ENABLED(CONFIG_CMA) && hugetlb_cma[0]) {
> > > > +		struct page *page;
> > > > +		int nid;
> > > > +
> > > > +		for_each_node_mask(nid, *nodemask) {
> > > > +			if (!hugetlb_cma[nid])
> > > > +				break;
> > > > +
> > > > +			page = cma_alloc(hugetlb_cma[nid], nr_pages,
> > > > +					 huge_page_order(h), true);
> > > > +			if (page)
> > > > +				return page;
> > > > +		}
> > > > +
> > > > +		return NULL;
> > > 
> > > Is there any strong reason why the alloaction annot fallback to non-CMA
> > > allocator when the cma is depleted?
> > 
> > The reason is that that gigantic pages allocated using cma require
> > a special handling on releasing. It's solvable by using an additional
> > page flag, but because the current code is usually not working except
> > a short time just after the system start, I don't think it's worth it.
> 
> I am not deeply familiar with the cma much TBH but cma_release seems to
> be documented to return false if the area doesn't belong to the area so
> the free patch can try cma_release and fallback to the regular free, no?

Good point! Then the fallback is not adding too much of complexity, so
I'll add it in the next version.

Thanks!