mm: provide more accurate estimation of pages occupied by memmap

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.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Maciej Rutecki <maciej.rutecki@gmail.com>
Cc: Chris Clayton <chris2553@googlemail.com>
Cc: "Rafael J . Wysocki" <rjw@sisk.pl>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0f945af223d2202c79059a632cd4033f79d546cb..7dc5ccc19f2eef0225a0215ded09f66867d1b271 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4542,6 +4542,26 @@ 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;
+}
+
 /*
  * Set up the zone data structures:
  *   - mark all pages reserved
@@ -4576,8 +4596,7 @@ 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)
@@ -4598,6 +4617,9 @@ 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;
                nr_all_pages += freesize;
 
                zone->spanned_pages = size;