[PATCH v7 4/6] mm/sparse-vmemmap: Fix DAX vmemmap accounting with optimization

[Muchun Song]

When vmemmap optimization is enabled for DAX, the nr_memmap_pages
counter in /proc/vmstat is incorrect. The current code always accounts
for the full, non-optimized vmemmap size, but vmemmap optimization
reduces the actual number of vmemmap pages by reusing tail pages. This
causes the system to overcount vmemmap usage, leading to inaccurate
page statistics in /proc/vmstat.

Fix this by introducing section_nr_vmemmap_pages(), which returns the exact
vmemmap page count for a given pfn range based on whether optimization
is in effect.

Fixes: 15995a352474 ("mm: report per-page metadata information")
Cc: sta...@vger.kernel.org
Signed-off-by: Muchun Song <songmuc...@bytedance.com>
Acked-by: Mike Rapoport (Microsoft) <r...@kernel.org>
Acked-by: Oscar Salvador <osalva...@suse.de>
---
v6 -> v7:
- Refine the alignment assertions in section_nr_vmemmap_pages().
---
 mm/sparse-vmemmap.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 3340f6d30b01..01f448607bad 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -652,6 +652,31 @@ 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,
+               struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+       const unsigned int order = pgmap ? pgmap->vmemmap_shift : 0;
+       const unsigned long pages_per_compound = 1UL << order;
+
+       VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION));
+
+       if (!vmemmap_can_optimize(altmap, pgmap))
+               return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
+
+       if (order < PFN_SECTION_SHIFT) {
+               VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, 
pages_per_compound));
+               return VMEMMAP_RESERVE_NR * nr_pages / pages_per_compound;
+       }
+
+       VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION));
+       VM_WARN_ON_ONCE(nr_pages > PAGES_PER_SECTION);
+
+       if (IS_ALIGNED(pfn, pages_per_compound))
+               return VMEMMAP_RESERVE_NR;
+
+       return 0;
+}
+
 static struct page * __meminit populate_section_memmap(unsigned long pfn,
                unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
                struct dev_pagemap *pgmap)
@@ -659,7 +684,7 @@ static struct page * __meminit 
populate_section_memmap(unsigned long pfn,
        struct page *page = __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_nr_vmemmap_pages(pfn, nr_pages, altmap, 
pgmap));
 
        return page;
 }
@@ -670,7 +695,7 @@ static void depopulate_section_memmap(unsigned long pfn, 
unsigned long nr_pages,
        unsigned long start = (unsigned long) pfn_to_page(pfn);
        unsigned long end = start + nr_pages * sizeof(struct page);
 
-       memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), 
PAGE_SIZE)));
+       memmap_pages_add(-section_nr_vmemmap_pages(pfn, nr_pages, altmap, 
pgmap));
        vmemmap_free(start, end, altmap);
 }
 
@@ -678,9 +703,10 @@ static void free_map_bootmem(struct page *memmap)
 {
        unsigned long start = (unsigned long)memmap;
        unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+       unsigned long pfn = page_to_pfn(memmap);
 
-       memmap_boot_pages_add(-1L * (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));
        vmemmap_free(start, end, NULL);
 }
 
-- 
2.20.1