[PATCH v2 08/17] mm/sparse-vmemmap: support section-based vmemmap optimization

[Muchun Song]

Teach sparse-vmemmap population code to use the compound page order
when deciding whether a vmemmap page can be optimized.

With this information, the common sparse-vmemmap population path can
allocate or reuse shared tail vmemmap pages directly instead of relying
on HugeTLB-specific handling.

This centralizes vmemmap optimization logic in the sparse-vmemmap code,
based on section metadata, and prepares for sharing the same mechanism
across different users of vmemmap optimization, including HugeTLB and
DAX.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
v2:
- Keep vmemmap accounting and population logic in sparse-vmemmap.c
  (suggested by Mike Rapoport)
- Move vmemmap_get_tail() before its first use instead of adding only a
  forward declaration in the previous patch (suggested by Mike Rapoport)
- Simplify the PMD path handling for HVO-covered sections
---
 mm/sparse-vmemmap.c | 36 ++++++++++++++++++++++++++++++------
 mm/sparse.c         |  4 ++--
 mm/sparse.h         |  7 +++++++
 3 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index b770fe2428fd..e818b4109777 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -186,6 +186,11 @@ static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *
 
 	return tail;
 }
+#else
+static inline struct page *vmemmap_get_tail(unsigned int order, struct zone *zone)
+{
+	return NULL;
+}
 #endif
 
 static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
@@ -193,12 +198,24 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 				       unsigned long ptpfn, unsigned long flags)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
+	unsigned long pfn = page_to_pfn((struct page *)addr);
+
 	if (pte_none(ptep_get(pte))) {
 		pte_t entry;
-		void *p;
+
+		if (pfn_vmemmap_optimizable(pfn) && ptpfn == (unsigned long)-1) {
+			unsigned int order = section_order(__pfn_to_section(pfn));
+			struct zone *zone = pfn_to_zone(pfn, node);
+			struct page *page = vmemmap_get_tail(order, zone);
+
+			if (!page)
+				return NULL;
+			ptpfn = page_to_pfn(page);
+		}
 
 		if (ptpfn == (unsigned long)-1) {
-			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+			void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+
 			if (!p)
 				return NULL;
 			ptpfn = PHYS_PFN(__pa(p));
@@ -217,7 +234,8 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 		}
 		entry = pfn_pte(ptpfn, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
-	}
+	} else if (WARN_ON_ONCE(pfn_vmemmap_optimizable(pfn)))
+		return NULL;
 	return pte;
 }
 
@@ -406,6 +424,9 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
 	pmd_t *pmd;
 
 	for (addr = start; addr < end; addr = next) {
+		unsigned long pfn = page_to_pfn((struct page *)addr);
+		const struct mem_section *ms = __pfn_to_section(pfn);
+
 		next = pmd_addr_end(addr, end);
 
 		pgd = vmemmap_pgd_populate(addr, node);
@@ -421,7 +442,7 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
 			return -ENOMEM;
 
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(pmdp_get(pmd))) {
+		if (pmd_none(pmdp_get(pmd)) && !section_vmemmap_optimizable(ms)) {
 			void *p;
 
 			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
@@ -439,8 +460,11 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
 				 */
 				return -ENOMEM;
 			}
-		} else if (vmemmap_check_pmd(pmd, node, addr, next))
+		} else if (vmemmap_check_pmd(pmd, node, addr, next)) {
+			if (WARN_ON_ONCE(section_vmemmap_optimizable(ms)))
+				return -ENOTSUPP;
 			continue;
+		}
 		if (vmemmap_populate_basepages(addr, next, node, altmap))
 			return -ENOMEM;
 	}
@@ -648,7 +672,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 	}
 }
 
-static int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+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);
diff --git a/mm/sparse.c b/mm/sparse.c
index ca9875f568d3..24555a32a5d9 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -315,8 +315,8 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 							nid, NULL, NULL);
 			if (!map)
 				panic("Failed to allocate memmap for section %lu\n", pnum);
-			memmap_boot_pages_add(DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
-							   PAGE_SIZE));
+			memmap_boot_pages_add(section_nr_vmemmap_pages(pfn, PAGES_PER_SECTION,
+								       NULL, NULL));
 			sparse_init_early_section(nid, map, pnum, 0);
 		}
 	}
diff --git a/mm/sparse.h b/mm/sparse.h
index 1e9fcea10181..4377b097dc8d 100644
--- a/mm/sparse.h
+++ b/mm/sparse.h
@@ -87,8 +87,15 @@ static inline bool section_vmemmap_optimizable(const struct mem_section *section
  */
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 void sparse_init_subsection_map(void);
+int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
 #else
 static inline void sparse_init_subsection_map(void) {}
+static inline int section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 #endif /* __MM_SPARSE_H */
-- 
2.54.0