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 big holes within
the zone.

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

Signed-off-by: Jiang Liu <redacted>
---
  mm/page_alloc.c |   22 ++++++++++++++++++++--
  1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5b327d7..eb25679 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c

@@ -4435,6 +4435,22 @@ 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 big holes within
+	 * the zone and SPARSEMEM is in use.
+	 */
+	if (spanned_pages > present_pages + (present_pages >> 4) &&
+	    IS_ENABLED(CONFIG_SPARSEMEM))
+		pages = present_pages;
+
+	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
+}
+
  /*
   * Set up the zone data structures:
   *   - mark all pages reserved

@@ -4469,8 +4485,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
  		 * is used by this zone for memmap. This affects the watermark
  		 * and per-cpu initialisations
  		 */
-		memmap_pages =
-			PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
+		memmap_pages = calc_memmap_size(size, realsize);
  		if (freesize >= memmap_pages) {
  			freesize -= memmap_pages;
  			if (memmap_pages)

@@ -4491,6 +4506,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
  
  		if (!is_highmem_idx(j))
  			nr_kernel_pages += freesize;
+		/* Charge for highmem memmap if there are enough kernel pages */
+		else if (nr_kernel_pages > memmap_pages * 2)
+			nr_kernel_pages -= memmap_pages;