[PATCH v5 06/12] mm/sparse-vmemmap: set compound page order for device DAX

[Muchun Song <songmuchun@bytedance.com>]

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.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
---
v3:
- Update the subject and commit message to use compound page order
  terminology
- Use EOPNOTSUPP instead of ENOTSUPP

v2:
- Explain why optimized and ordinary layouts cannot share a section
  (suggested by Qi Zheng)
- Collect Acked-by from Qi Zheng
---
 mm/mm_init.c        | 15 +++++----------
 mm/sparse-vmemmap.c | 16 ++++++++++++----
 2 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 97e0158d2aca..efffa8609b85 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1049,16 +1049,11 @@ static void zone_device_page_init_from_template(struct page *page,
  * 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(struct zone *zone,
 	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(struct zone *zone,
 			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,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 2457ea2c6dca..ca2470e96a74 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -135,14 +135,14 @@ int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages
 		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_section_memmap(unsigned long pfn,
 		!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 long pfn, unsigned long nr_pages,
 	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_activate(int nid, unsigned long pfn,
 	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_activate(int nid, unsigned long pfn,
 	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);
-- 
2.54.0