[PATCH 03/49] mm/sparse: fix vmemmap page accounting for HVOed DAX

[Muchun Song]

When HVO is enabled for DAX, the vmemmap page accounting is wrong since
it only accounts for non-HVO case.

Fix the accounting by introducing section_vmemmap_pages() that returns
the exact number of vmemmap pages needed for the given pfn range.

Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Muchun Song <songmuchun at bytedance.com>
---
 mm/sparse-vmemmap.c | 30 ++++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 7aa9a97498eb..0ef96b1afbcc 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -724,6 +724,27 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
 	return rc;
 }
 
+static int __meminit section_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+					   struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	unsigned int order = pgmap ? pgmap->vmemmap_shift : 0;
+	unsigned long pages_per_compound = 1L << order;
+
+	VM_BUG_ON(!IS_ALIGNED(pfn | nr_pages, min(pages_per_compound, PAGES_PER_SECTION)));
+	VM_BUG_ON(pfn_to_section_nr(pfn) != pfn_to_section_nr(pfn + nr_pages - 1));
+
+	if (!vmemmap_can_optimize(altmap, pgmap))
+		return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
+
+	if (order < PFN_SECTION_SHIFT)
+		return VMEMMAP_RESERVE_NR * nr_pages / pages_per_compound;
+
+	if (IS_ALIGNED(pfn, pages_per_compound))
+		return VMEMMAP_RESERVE_NR;
+
+	return 0;
+}
+
 /*
  * To deactivate a memory region, there are 3 cases to handle:
  *
@@ -775,11 +796,12 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	 * section_activate() and pfn_valid() .
 	 */
 	if (!section_is_early) {
-		memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
+		memmap_pages_add(-section_vmemmap_pages(pfn, nr_pages, altmap,
+							pgmap));
 		depopulate_section_memmap(pfn, nr_pages, altmap);
 	} else if (memmap) {
-		memmap_boot_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page),
-							  PAGE_SIZE)));
+		memmap_pages_add(-section_vmemmap_pages(pfn, nr_pages, altmap,
+							pgmap));
 		free_map_bootmem(memmap);
 	}
 
@@ -822,7 +844,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 		return pfn_to_page(pfn);
 
 	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
-	memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
+	memmap_pages_add(section_vmemmap_pages(pfn, nr_pages, altmap, pgmap));
 	if (!memmap) {
 		section_deactivate(pfn, nr_pages, altmap, pgmap);
 		return ERR_PTR(-ENOMEM);
-- 
2.20.1