[PATCH v5 10/12] mm/sparse-vmemmap: drop the extra tail page from device DAX reservation

[Muchun Song <songmuchun@bytedance.com>]

The device DAX vmemmap population still reserves one extra tail vmemmap
page after the head page.

Drop that extra reservation and let the shared tail page cover all tail
vmemmap pages after the head page, so DAX follows the same reservation
model as HugeTLB.

This reduces the reserved vmemmap pages for optimized DAX mappings to
one and removes the now-unneeded first-tail population from the generic
and powerpc paths to simplify the code as well.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
---
v3:
- Collect Acked-by from Qi Zheng
---
 arch/powerpc/mm/book3s64/radix_pgtable.c | 46 ++----------------------
 include/linux/mm.h                       |  4 +--
 mm/mm_init.c                             |  2 +-
 mm/sparse-vmemmap.c                      | 13 ++-----
 4 files changed, 8 insertions(+), 57 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index ee068f24a79f..9ca28e4a610a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1218,39 +1218,6 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 	return 0;
 }
 
-static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node,
-							 struct vmem_altmap *altmap,
-							 struct page *reuse)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	pgd = pgd_offset_k(addr);
-	p4d = p4d_offset(pgd, addr);
-	pud = vmemmap_pud_alloc(p4d, node, addr);
-	if (!pud)
-		return NULL;
-	pmd = vmemmap_pmd_alloc(pud, node, addr);
-	if (!pmd)
-		return NULL;
-	if (pmd_leaf(*pmd))
-		/*
-		 * The second page is mapped as a hugepage due to a nearby request.
-		 * Force our mapping to page size without deduplication
-		 */
-		return NULL;
-	pte = vmemmap_pte_alloc(pmd, node, addr);
-	if (!pte)
-		return NULL;
-	radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
-	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
-
-	return pte;
-}
-
 int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 					      unsigned long start,
 					      unsigned long end, int node,
@@ -1297,7 +1264,7 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		if (!pte_none(*pte)) {
 			/*
 			 * This could be because we already have a compound
-			 * page whose VMEMMAP_RESERVE_NR pages were mapped and
+			 * page whose retained vmemmap page was mapped and
 			 * this request fall in those pages.
 			 */
 			next = addr + PAGE_SIZE;
@@ -1318,16 +1285,7 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 					return -ENOMEM;
 				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
 
-				/*
-				 * Populate the tail pages vmemmap page
-				 * It can fall in different pmd, hence
-				 * vmemmap_populate_address()
-				 */
-				pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL);
-				if (!pte)
-					return -ENOMEM;
-
-				next = addr + 2 * PAGE_SIZE;
+				next = addr + PAGE_SIZE;
 				continue;
 			}
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 070ce27e9cd3..30a3365bca82 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -38,6 +38,7 @@
 #include <linux/bitops.h>
 #include <linux/iommu-debug-pagealloc.h>
 #include <linux/kcsan-checks.h>
+#include <linux/vmemmap-optimization.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -5167,7 +5168,6 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 }
 #endif
 
-#define VMEMMAP_RESERVE_NR	2
 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
 static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
 					  struct dev_pagemap *pgmap)
@@ -5187,7 +5187,7 @@ static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
 	 * For vmemmap optimization with DAX we need minimum 2 vmemmap
 	 * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
 	 */
-	return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
+	return !altmap && (nr_vmemmap_pages > VMEMMAP_OPTIMIZATION_PAGES);
 }
 /*
  * If we don't have an architecture override, use the generic rule
diff --git a/mm/mm_init.c b/mm/mm_init.c
index efffa8609b85..56bb4567a494 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1056,7 +1056,7 @@ static inline unsigned long compound_nr_pages(unsigned long pfn,
 	if (!section_vmemmap_optimizable(ms))
 		return pgmap_vmemmap_nr(pgmap);
 
-	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
+	return VMEMMAP_OPTIMIZATION_PAGES * (PAGE_SIZE / sizeof(struct page));
 }
 
 static void __ref memmap_init_compound(struct page *head,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 4309f8b626f5..b6378826b9a2 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -136,7 +136,6 @@ int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages
 {
 	const struct mem_section *ms = __pfn_to_section(pfn);
 	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));
@@ -147,13 +146,13 @@ int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages
 
 	if (order < PFN_SECTION_SHIFT) {
 		VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, pages_per_compound));
-		return vmemmap_pages * nr_pages / pages_per_compound;
+		return VMEMMAP_OPTIMIZATION_PAGES * nr_pages / pages_per_compound;
 	}
 
 	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION));
 
 	if (IS_ALIGNED(pfn, pages_per_compound))
-		return vmemmap_pages;
+		return VMEMMAP_OPTIMIZATION_PAGES;
 
 	return 0;
 }
@@ -550,17 +549,11 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		if (!pte)
 			return -ENOMEM;
 
-		/* Populate the tail pages vmemmap page */
-		next = addr + PAGE_SIZE;
-		pte = vmemmap_populate_address(next, node, NULL, -1, flags);
-		if (!pte)
-			return -ENOMEM;
-
 		/*
 		 * Reuse the shared page for the rest of tail pages
 		 * See layout diagram in Documentation/mm/vmemmap_dedup.rst
 		 */
-		next += PAGE_SIZE;
+		next = addr + PAGE_SIZE;
 		rc = vmemmap_populate_range(next, last, node, NULL,
 					    page_to_pfn(page), flags);
 		if (rc)
-- 
2.54.0