Re: [PATCH 6/7] mm/gup: Accelerate thp gup even for "pages != NULL"

[Peter Xu <peterx@redhat.com>]

On Wed, Jun 14, 2023 at 03:58:34PM +0100, Matthew Wilcox wrote:
> On Tue, Jun 13, 2023 at 05:53:45PM -0400, Peter Xu wrote:
> > +			if (page_increm > 1)
> > +				WARN_ON_ONCE(
> > +				    try_grab_folio(compound_head(page),
> 
> You don't need to call compound_head() here; try_grab_folio() works
> on tail pages just fine.

I did it with caution because two things I'm not sure: either
is_pci_p2pdma_page() or is_longterm_pinnable_page() inside, both calls
is_zone_device_page() on the page*.

But I just noticed try_grab_folio() is also used in gup_pte_range() where
the thp can be pte mapped, so I assume we at least need that to handle tail
page well.

Do we perhaps need the compound_head() in try_grab_folio() as a separate
patch?  Or maybe I was wrong on is_zone_device_page()?

> 
> > +						   page_increm - 1,
> > +						   foll_flags) == NULL);
> > +
> > +			for (j = 0; j < page_increm; j++) {
> > +				subpage = nth_page(page, j);
> > +				pages[i+j] = subpage;
> > +				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
> > +				flush_dcache_page(subpage);
> 
> You're better off calling flush_dcache_folio() right at the end.

Will do.

Thanks,

-- 
Peter Xu