quoted

If SPARSEMEM is enabled, it won't build page structures for
non-existing pages (holes) within a zone, so provide a more accurate
estimation of pages occupied by memmap if there are bigger holes within
the zone.

And pages for highmem zones' memmap will be allocated from lowmem, so
charge nr_kernel_pages for that.

...

--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c

@@ -4442,6 +4442,26 @@ void __init set_pageblock_order(void)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
+static unsigned long calc_memmap_size(unsigned long spanned_pages,
+				      unsigned long present_pages)
+{
+	unsigned long pages = spanned_pages;
+
+	/*
+	 * Provide a more accurate estimation if there are holes within
+	 * the zone and SPARSEMEM is in use. If there are holes within the
+	 * zone, each populated memory region may cost us one or two extra
+	 * memmap pages due to alignment because memmap pages for each
+	 * populated regions may not naturally algined on page boundary.
+	 * So the (present_pages >> 4) heuristic is a tradeoff for that.
+	 */
+	if (spanned_pages > present_pages + (present_pages >> 4) &&
+	    IS_ENABLED(CONFIG_SPARSEMEM))
+		pages = present_pages;
+
+	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
+}
+

I spose we should do this, although it makes no difference as the
compiler will inline calc_memmap_size() into its caller:

--- a/mm/page_alloc.c~mm-provide-more-accurate-estimation-of-pages-occupied-by-memmap-fix
+++ a/mm/page_alloc.c

@@ -4526,8 +4526,8 @@ void __init set_pageblock_order(void)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-static unsigned long calc_memmap_size(unsigned long spanned_pages,
-				      unsigned long present_pages)
+static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
+						   unsigned long present_pages)
 {
 	unsigned long pages = spanned_pages;
 

.