[PATCH v2 3/6] mm/sparse-vmemmap: Fix DAX vmemmap accounting with optimization

[Mike Rapoport]

On Wed, Apr 15, 2026 at 07:14:09PM +0800, Muchun Song wrote:
> 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_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")
> Signed-off-by: Muchun Song <songmuchun at bytedance.com>

Acked-by: Mike Rapoport (Microsoft) <rppt at kernel.org>

> ---
>  mm/sparse-vmemmap.c | 32 ++++++++++++++++++++++++++++----
>  1 file changed, 28 insertions(+), 4 deletions(-)
> 
> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
> index 40290fbc1db4..05e3e2b94e32 100644
> --- a/mm/sparse-vmemmap.c
> +++ b/mm/sparse-vmemmap.c
> @@ -652,6 +652,29 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
>  	}
>  }
>  
> +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_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, min(pages_per_compound,
> +							PAGES_PER_SECTION)));
> +	VM_WARN_ON_ONCE(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;
> +}
> +
>  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 +682,7 @@ 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_vmemmap_pages(pfn, nr_pages, altmap, pgmap));
>  
>  	return page;
>  }
> @@ -670,7 +693,7 @@ 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_vmemmap_pages(pfn, nr_pages, altmap, pgmap));
>  	vmemmap_free(start, end, altmap);
>  }
>  
> @@ -679,9 +702,10 @@ static void free_map_bootmem(struct page *memmap, struct vmem_altmap *altmap,
>  {
>  	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_vmemmap_pages(pfn, PAGES_PER_SECTION,
> +						     altmap, pgmap));
>  	vmemmap_free(start, end, NULL);
>  }
>  
> -- 
> 2.20.1
> 

-- 
Sincerely yours,
Mike.