mm: let _folio_nr_pages overlay memcg_data in first tail page

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.

[[email protected]: make "make htmldoc" happy]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: David Hildenbrand <[email protected]>
Reviewed-by: Kirill A. Shutemov <[email protected]>
Cc: Andy Lutomirks^H^Hski <[email protected]>
Cc: Borislav Betkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Lance Yang <[email protected]>
Cc: Liam Howlett <[email protected]>
Cc: Lorenzo Stoakes <[email protected]>
Cc: Matthew Wilcow (Oracle) <[email protected]>
Cc: Michal Koutn <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: tejun heo <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Zefan Li <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: davidhildenbrand

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)

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.
@@ -376,14 +381,23 @@ struct folio {
 		struct {
 			unsigned long _flags_1;
 			unsigned long _head_1;
+			union {
+				struct {
 	/* 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
+					atomic_t _large_mapcount;
+					atomic_t _entire_mapcount;
+					atomic_t _nr_pages_mapped;
+					atomic_t _pincount;
+	/* private: the union with struct page is transitional */
+				};
+				unsigned long _usable_1[4];
+			};
+			atomic_t _mapcount_1;
+			atomic_t _refcount_1;
+	/* public: */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+			unsigned int _nr_pages;
+#endif /* NR_PAGES_IN_LARGE_FOLIO */
 	/* private: the union with struct page is transitional */
 		};
 		struct page __page_1;
@@ -435,6 +449,8 @@ FOLIO_MATCH(_last_cpupid, _last_cpupid);
 			offsetof(struct page, pg) + sizeof(struct page))
 FOLIO_MATCH(flags, _flags_1);
 FOLIO_MATCH(compound_head, _head_1);
+FOLIO_MATCH(_mapcount, _mapcount_1);
+FOLIO_MATCH(_refcount, _refcount_1);
 #undef FOLIO_MATCH
 #define FOLIO_MATCH(pg, fl)						\
 	static_assert(offsetof(struct folio, fl) ==			\

mm/huge_memory.c

@@ -3399,6 +3399,14 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	int order = folio_order(folio);
 	unsigned int nr = 1 << order;
 
+	/*
+	 * Reset any memcg data overlay in the tail pages. folio_nr_pages()
+	 * is unreliable after this point.
+	 */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+	folio->_nr_pages = 0;
+#endif
+
 	/* complete memcg works before add pages to LRU */
 	split_page_memcg(head, order, new_order);
 

mm/internal.h

@@ -725,8 +725,8 @@ static inline void folio_set_order(struct folio *folio, unsigned int order)
 		return;
 
 	folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
-#ifdef CONFIG_64BIT
-	folio->_folio_nr_pages = 1U << order;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+	folio->_nr_pages = 1U << order;
 #endif
 }
 

mm/page_alloc.c

@@ -1174,8 +1174,12 @@ __always_inline bool free_pages_prepare(struct page *page,
 	if (unlikely(order)) {
 		int i;
 
-		if (compound)
+		if (compound) {
 			page[1].flags &= ~PAGE_FLAGS_SECOND;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+			folio->_nr_pages = 0;
+#endif
+		}
 		for (i = 1; i < (1 << order); i++) {
 			if (compound)
 				bad += free_tail_page_prepare(page, page + i);

mm/page_owner.c

@@ -507,7 +507,7 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
 
 	rcu_read_lock();
 	memcg_data = READ_ONCE(page->memcg_data);
-	if (!memcg_data)
+	if (!memcg_data || PageTail(page))
 		goto out_unlock;
 
 	if (memcg_data & MEMCG_DATA_OBJEXTS)