Let's free up some more of the "unconditionally available on 64BIT"
space in order-1 folios by letting _folio_nr_pages overlay memcg_data in
the first tail page (second folio page). Consequently, we have the
optimization now whenever we have CONFIG_MEMCG, independent of 64BIT.

We have to make sure that page->memcg on tail pages does not return
"surprises". page_memcg_check() already properly refuses PageTail().
Let's do that earlier in print_page_owner_memcg() to avoid printing
wrong "Slab cache page" information. No other code should touch that
field on tail pages of compound pages.

Reset the "_nr_pages" to 0 when splitting folios, or when freeing them
back to the buddy (to avoid false page->memcg_data "bad page" reports).

Note that in __split_huge_page(), folio_nr_pages() would stop working
already as soon as we start messing with the subpages.

Most kernel configs should have at least CONFIG_MEMCG enabled, even if
disabled at runtime. 64byte "struct memmap" is what we usually have
on 64BIT.

While at it, rename "_folio_nr_pages" to "_nr_pages".

Hopefully memdescs / dynamically allocating "strut folio" in the future
will further clean this up, e.g., making _nr_pages available in all
configs and maybe even in small folios. Doing that should be fairly easy
on top of this change.

Reviewed-by: Kirill A. Shutemov <redacted>
Signed-off-by: David Hildenbrand <redacted>
---
  include/linux/mm.h       |  4 ++--
  include/linux/mm_types.h | 30 ++++++++++++++++++++++--------
  mm/huge_memory.c         | 16 +++++++++++++---
  mm/internal.h            |  4 ++--
  mm/page_alloc.c          |  6 +++++-
  mm/page_owner.c          |  2 +-
  6 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a743321dc1a5d..694704217df8a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h

@@ -1199,10 +1199,10 @@ static inline unsigned int folio_large_order(const struct folio *folio)
  	return folio->_flags_1 & 0xff;
  }
  
-#ifdef CONFIG_64BIT
+#ifdef NR_PAGES_IN_LARGE_FOLIO
  static inline long folio_large_nr_pages(const struct folio *folio)
  {
-	return folio->_folio_nr_pages;
+	return folio->_nr_pages;
  }
  #else
  static inline long folio_large_nr_pages(const struct folio *folio)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 689b2a7461892..e81be20bbabc6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h

@@ -287,6 +287,11 @@ typedef struct {
  	unsigned long val;
  } swp_entry_t;
  
+#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT)
+/* We have some extra room after the refcount in tail pages. */
+#define NR_PAGES_IN_LARGE_FOLIO
+#endif
+
  /**
   * struct folio - Represents a contiguous set of bytes.
   * @flags: Identical to the page flags.

@@ -312,7 +317,7 @@ typedef struct {
   * @_large_mapcount: Do not use directly, call folio_mapcount().
   * @_nr_pages_mapped: Do not use outside of rmap and debug code.
   * @_pincount: Do not use directly, call folio_maybe_dma_pinned().
- * @_folio_nr_pages: Do not use directly, call folio_nr_pages().
+ * @_nr_pages: Do not use directly, call folio_nr_pages().
   * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h.
   * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h.
   * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h.

@@ -377,13 +382,20 @@ struct folio {
  			unsigned long _flags_1;
  			unsigned long _head_1;
  	/* public: */
-			atomic_t _large_mapcount;
-			atomic_t _entire_mapcount;
-			atomic_t _nr_pages_mapped;
-			atomic_t _pincount;
-#ifdef CONFIG_64BIT
-			unsigned int _folio_nr_pages;
-#endif
+			union {
+				struct {
+					atomic_t _large_mapcount;
+					atomic_t _entire_mapcount;
+					atomic_t _nr_pages_mapped;
+					atomic_t _pincount;
+				};
+				unsigned long _usable_1[4];
+			};
+			atomic_t _mapcount_1;
+			atomic_t _refcount_1;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+			unsigned int _nr_pages;
+#endif /* NR_PAGES_IN_LARGE_FOLIO */
  	/* private: the union with struct page is transitional */