On Mon, Jul 20, 2026 at 03:34:26PM +0800, Gregory Price wrote: > Collapse can move base pages across nodes. The khugepaged daemon does > this transparently, while MADV_COLLAPSE is a userland construct. > > Isolate private nodes from khugepaged exactly like ZONE_DEVICE. > Never collapse private node folios silently (the owner may not > support migration). > > MADV_COLLAPSE is user-initiated, so it is allowed on a private node > opted into CAP_USER_NUMA, consistent with other userspace interfaces. > > folio_allows_collapse() encodes this: false for khugepaged on a private > node, CAP_USER_NUMA for MADV_COLLAPSE. > > Signed-off-by: Gregory Price <[email protected]> > --- > mm/internal.h | 26 ++++++++++++++++++++++++++ > mm/khugepaged.c | 16 +++++++++++++--- > 2 files changed, 39 insertions(+), 3 deletions(-) > > diff --git a/mm/internal.h b/mm/internal.h > index 9621eb127c28c..9dbc5752cd3fe 100644 > --- a/mm/internal.h > +++ b/mm/internal.h > @@ -136,6 +136,32 @@ static inline bool folio_allows_numa_balance(struct > folio *folio) > node_allows_numa_balancing(folio_nid(folio)); > } > > +/* > + * folio_allows_collapse() - may collapse fold this folio into a THP? > + * @is_khugepaged: true for the khugepaged, false for MADV_COLLAPSE. > + * > + * Collapse is a residency operation gated by the actor calling it: > + * - khugepaged never operates on private-node folios (like ZONE_DEVICE) > + * - MADV_COLLAPSE is gated by CAP_USER_NUMA > + * > + * Never true for ZONE_DEVICE. > + */ > +static inline bool folio_allows_collapse(struct folio *folio, bool > is_khugepaged) > +{ > + int nid = folio_nid(folio); > + > + if (folio_is_zone_device(folio)) > + return false; > + if (is_khugepaged) > + return !node_is_private(nid); > + return node_allows_user_numa(nid); > +} > + > +static inline bool page_allows_collapse(struct page *page, bool > is_khugepaged) > +{ > + return folio_allows_collapse(page_folio(page), is_khugepaged); > +} > + > /* > * folio_allows_longterm_pin() - may this folio be long-term GUP-pinned? > * > diff --git a/mm/khugepaged.c b/mm/khugepaged.c > index fb4378cc17b10..5f20839857738 100644 > --- a/mm/khugepaged.c > +++ b/mm/khugepaged.c > @@ -700,7 +700,8 @@ static enum scan_result > __collapse_huge_page_isolate(struct vm_area_struct *vma, > goto out; > } > page = vm_normal_page(vma, addr, pteval); > - if (unlikely(!page) || unlikely(page_is_private_managed(page))) > { > + if (unlikely(!page) || > + unlikely(!page_allows_collapse(page, cc->is_khugepaged))) { > result = SCAN_PAGE_NULL; > goto out; > } > @@ -1241,9 +1242,17 @@ static enum scan_result alloc_charge_folio(struct > folio **foliop, struct mm_stru > gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : > GFP_TRANSHUGE); > int node = collapse_find_target_node(cc); > + unsigned int aflags; > struct folio *folio; > + bool allow; > > - folio = __folio_alloc(gfp, order, node, &cc->alloc_nmask, > ALLOC_DEFAULT); > + /* Private node access: khugepaged never, madvise with CAP_USER_NUMA */ > + allow = cc->is_khugepaged ? !node_is_private(node) > + : node_allows_user_numa(node); > + aflags = (allow && node_is_private(node)) ? > + ALLOC_ZONELIST_PRIVATE : ALLOC_DEFAULT; > + > + folio = __folio_alloc(gfp, order, node, &cc->alloc_nmask, aflags); > if (!folio) { > *foliop = NULL; > if (is_pmd_order(order)) > @@ -1687,7 +1696,8 @@ static enum scan_result collapse_scan_pmd(struct > mm_struct *mm, > } > > page = vm_normal_page(vma, addr, pteval); > - if (unlikely(!page) || unlikely(page_is_private_managed(page))) > { > + if (unlikely(!page) || > + unlikely(!page_allows_collapse(page, cc->is_khugepaged))) {
I think collapse_scan_file() need something like folio_allows_collapse() check as well. --Richard > result = SCAN_PAGE_NULL; > goto out_unmap; > } > -- > 2.53.0-Meta > >
