On Mon, Jun 08, 2026 at 04:36:02AM -0400, Michael S. Tsirkin wrote: > folio_zero_user() is defined in mm/memory.c under > CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS. A subsequent patch > will call it from post_alloc_hook() for all user page zeroing, so > configs without THP or HUGETLBFS will need a stub. > > Add a stub that uses clear_user_highpages() with aligned > addr_hint.
It's not a stub? You're doing default behaviour for !THP || hugetlbfs? > > Without THP/HUGETLBFS, only order-0 user pages are allocated, so > the locality optimization in the real folio_zero_user() (zero near > the faulting address last) is not needed. The 'real' folio_zero_user()? But they're both real? In what sense is this unreal? This commit message is pretty confusing. > This also matches what vma_alloc_zeroed_movable_folio currently does. You're also not explaining why we need a random new file just for a single define, this is really weird? And please don't add new files without adding an entry to MAINTAINERS. While we're here, can we just move this function somewhere else? memory.c is like the junkyard of mm. Maybe util.c. Anyway this seems like it belongs in mm/internal.h. > > Signed-off-by: Michael S. Tsirkin <[email protected]> > Assisted-by: Claude:claude-opus-4-6 > Assisted-by: cursor-agent:GPT-5.4-xhigh > --- > mm/folio_zero.h | 18 ++++++++++++++++++ > mm/page_alloc.c | 1 + > 2 files changed, 19 insertions(+) > create mode 100644 mm/folio_zero.h > > diff --git a/mm/folio_zero.h b/mm/folio_zero.h > new file mode 100644 > index 000000000000..c135b3a34da8 > --- /dev/null > +++ b/mm/folio_zero.h > @@ -0,0 +1,18 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +#ifndef MM_FOLIO_ZERO_H > +#define MM_FOLIO_ZERO_H > + > +#include <linux/highmem.h> > + > +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) > +void folio_zero_user(struct folio *folio, unsigned long addr_hint); > +#else No comment explaining what this does in comparison to the THP/hugetlbfs version? Let's have a kdoc comment here. > +static inline void folio_zero_user(struct folio *folio, unsigned long > addr_hint) So we have a folio (physical metadata) and an adress hint? > +{ > + unsigned long base = ALIGN_DOWN(addr_hint, folio_size(folio)); const please. > + > + clear_user_highpages(&folio->page, base, folio_nr_pages(folio)); > +} > +#endif > + > +#endif /* MM_FOLIO_ZERO_H */ > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 6d3f284c607d..0943ab724032 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -17,6 +17,7 @@ > #include <linux/stddef.h> > #include <linux/mm.h> > #include <linux/highmem.h> > +#include "folio_zero.h" > #include <linux/interrupt.h> > #include <linux/jiffies.h> > #include <linux/compiler.h> > -- > MST > Thanks, Lorenzo
