+ mm-sparse-vmemmap-set-compound-page-order-for-device-dax.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm/sparse-vmemmap: set compound page order for device DAX
has been added to the -mm mm-unstable branch.  Its filename is
     mm-sparse-vmemmap-set-compound-page-order-for-device-dax.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-sparse-vmemmap-set-compound-page-order-for-device-dax.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Muchun Song <muchun.song@linux.dev>
Subject: mm/sparse-vmemmap: set compound page order for device DAX
Date: Sun, 27 Sep 2026 10:54:35 +0800

Device DAX can use vmemmap optimization only when a full section is
populated with a compound-page geometry. Record that geometry as the
compound page order in section metadata before populating the section, so
later vmemmap accounting and population decisions can use the section state
directly.

Clear the compound page order when the section becomes empty again. Also
reject partial additions to a section that already has optimized vmemmap
mappings. compound_nr_pages() determines how many struct pages to
initialize with a section as the smallest granularity. A section therefore
cannot safely mix optimized and ordinary vmemmap layouts.

Partial additions continue to use ordinary vmemmap population, so they do
not save vmemmap memory. Such additions are uncommon, and the lost saving
is negligible.

Link: https://lore.kernel.org/20260927025441.741633-7-songmuchun@bytedance.com
Signed-off-by: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
Cc: David Hildenbrand <david@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <chleroy@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Lance Yang <lance.yang@linux.dev>
---

 mm/mm_init.c        |   15 +++++----------
 mm/sparse-vmemmap.c |   16 ++++++++++++----
 2 files changed, 17 insertions(+), 14 deletions(-)

--- a/mm/mm_init.c~mm-sparse-vmemmap-set-compound-page-order-for-device-dax
+++ a/mm/mm_init.c
@@ -1049,16 +1049,11 @@ static void zone_device_page_init_from_t
  * of an altmap. See vmemmap_populate_compound_pages().
  */
 static inline unsigned long compound_nr_pages(unsigned long pfn,
-					      struct vmem_altmap *altmap,
 					      struct dev_pagemap *pgmap)
 {
-	/*
-	 * If DAX memory is hot-plugged into an unoccupied subsection
-	 * of an early section, the unoptimized boot memmap is reused.
-	 * See section_activate().
-	 */
-	if (early_section(__pfn_to_section(pfn)) ||
-	    !vmemmap_can_optimize(altmap, pgmap))
+	const struct mem_section *ms = __pfn_to_section(pfn);
+
+	if (!section_vmemmap_optimizable(ms))
 		return pgmap_vmemmap_nr(pgmap);
 
 	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
@@ -1144,7 +1139,7 @@ void __ref memmap_init_zone_device(struc
 	memcpy(&template, page, sizeof(*page));
 	if (pfns_per_compound != 1)
 		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
-				     compound_nr_pages(pfn, altmap, pgmap));
+				     compound_nr_pages(pfn, pgmap));
 	pfn += pfns_per_compound;
 
 	/* Initialize the remaining head pages from template. */
@@ -1160,7 +1155,7 @@ void __ref memmap_init_zone_device(struc
 			continue;
 
 		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
-				     compound_nr_pages(pfn, altmap, pgmap));
+				     compound_nr_pages(pfn, pgmap));
 	}
 
 	pageblock_migratetype_init_range(start_pfn, nr_pages, MIGRATE_MOVABLE,
--- a/mm/sparse-vmemmap.c~mm-sparse-vmemmap-set-compound-page-order-for-device-dax
+++ a/mm/sparse-vmemmap.c
@@ -135,14 +135,14 @@ int __meminit section_nr_vmemmap_pages(u
 		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
 	const struct mem_section *ms = __pfn_to_section(pfn);
-	const int order = pgmap ? pgmap->vmemmap_shift : section_compound_order(ms);
+	const int order = section_compound_order(ms);
 	const int vmemmap_pages = pgmap ? VMEMMAP_RESERVE_NR : VMEMMAP_OPTIMIZATION_PAGES;
 	const unsigned long pages_per_compound = 1UL << order;
 
 	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION));
 	VM_WARN_ON_ONCE(nr_pages > PAGES_PER_SECTION);
 
-	if (!vmemmap_can_optimize(altmap, pgmap) && !section_vmemmap_optimizable(ms))
+	if (!section_vmemmap_optimizable(ms))
 		return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
 
 	if (order < PFN_SECTION_SHIFT) {
@@ -608,7 +608,7 @@ struct page * __meminit __populate_secti
 		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
 		return NULL;
 
-	if (vmemmap_can_optimize(altmap, pgmap))
+	if (pgmap && section_vmemmap_optimizable(__pfn_to_section(pfn)))
 		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
 	else
 		r = vmemmap_populate(start, end, nid, altmap);
@@ -827,8 +827,10 @@ static void section_deactivate(unsigned
 	else if (memmap)
 		free_map_bootmem(memmap);
 
-	if (empty)
+	if (empty) {
 		ms->section_mem_map = (unsigned long)NULL;
+		section_set_compound_order(ms, 0);
+	}
 }
 
 static struct page * __meminit section_activate(int nid, unsigned long pfn,
@@ -838,8 +840,13 @@ static struct page * __meminit section_a
 	struct mem_section *ms = __pfn_to_section(pfn);
 	struct mem_section_usage *usage = NULL;
 	struct page *memmap;
+	unsigned int order;
 	int rc;
 
+	order = vmemmap_can_optimize(altmap, pgmap) ? pgmap->vmemmap_shift : 0;
+	if (nr_pages < PAGES_PER_SECTION && section_compound_order(ms))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (!ms->usage) {
 		usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
 		if (!usage)
@@ -865,6 +872,7 @@ static struct page * __meminit section_a
 	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
 		return pfn_to_page(pfn);
 
+	section_set_compound_order_range(pfn, nr_pages, order);
 	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 	if (!memmap) {
 		section_deactivate(pfn, nr_pages, altmap, pgmap);
_

Patches currently in -mm which might be from muchun.song@linux.dev are

mm-sparse-vmemmap-factor-out-shared-vmemmap-tail-page-allocation.patch
mm-sparse-vmemmap-allocate-shared-tail-page-array-dynamically.patch
mm-sparse-vmemmap-introduce-config_vmemmap_optimization.patch
mm-sparse-vmemmap-open-code-init_compound_tail.patch
mm-sparse-vmemmap-prepare-dax-vmemmap-population-for-compound-page-orders.patch
mm-sparse-vmemmap-set-compound-page-order-for-device-dax.patch
mm-sparse-vmemmap-switch-device-dax-to-shared-tail-vmemmap-pages.patch
mm-sparse-vmemmap-move-vmemmap-optimization-helpers-to-a-public-header.patch
powerpc-mm-switch-device-dax-to-shared-tail-vmemmap-pages.patch
mm-sparse-vmemmap-drop-the-extra-tail-page-from-device-dax-reservation.patch
mm-sparse-vmemmap-drop-unused-section_nr_vmemmap_pages-arguments.patch
documentation-mm-update-dax-vmemmap-deduplication-docs.patch