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.

Link: https://lkml.kernel.org/r/20250303163014.1128035-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andy Lutomirks^H^Hski <luto@kernel.org>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Michal Koutn <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: tejun heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7c5a8fd29cfcd5b204a7aa9098d9eef3e5c46be6..f6b6373a864dde1a1749ef79fb841445b48ab608 100644 (file)
--- 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 689b2a7461892912963f97947ddde628c7bffc8b..e81be20bbabc628c88f2f0938e2fcba9ac80018a 100644 (file)
--- 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 */
                };
                struct page __page_1;
@@ -435,6 +447,8 @@ 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) ==                     \

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6ac6d468af0d46ecba368e313e5ffe021433087a..07d43ca6db1c66236383ed777b3bf719c97d57af 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3307,10 +3307,11 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
  * It splits @folio into @new_order folios and copies the @folio metadata to
  * all the resulting folios.
  */
-static void __split_folio_to_order(struct folio *folio, int new_order)
+static void __split_folio_to_order(struct folio *folio, int old_order,
+               int new_order)
 {
-       long nr_pages = folio_nr_pages(folio);
        long new_nr_pages = 1 << new_order;
+       long nr_pages = 1 << old_order;
        long index;
 
        /*
@@ -3528,12 +3529,21 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
                        }
                }
 
+               /*
+                * Reset any memcg data overlay in the tail pages.
+                * folio_nr_pages() is unreliable until prep_compound_page()
+                * was called again.
+                */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+               folio->_nr_pages = 0;
+#endif
+
                /* complete memcg works before add pages to LRU */
                split_page_memcg(&folio->page, old_order, split_order);
                split_page_owner(&folio->page, old_order, split_order);
                pgalloc_tag_split(folio, old_order, split_order);
 
-               __split_folio_to_order(folio, split_order);
+               __split_folio_to_order(folio, old_order, split_order);
 
 after_split:
                /*

diff --git a/mm/internal.h b/mm/internal.h
index b07550db2bfd1d152fa90f91b3687b0fa1a9f653..7f6d5def00fa037349afd044a230d5b697b608ff 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -684,8 +684,8 @@ 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
 }
 

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eab307690db8f8e682e015acbf225b78885c705b..e03cf2124b95e0d4276012f8d61e680e6a27c285 100644 (file)
--- a/mm/page_alloc.c
+++ b/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);

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 2d6360eaccbb6ee34bd3654823fa1e687a407a05..a409e2561a8fd91c6c5928cf632ced56a1b3dfa7 100644 (file)
--- a/mm/page_owner.c
+++ b/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)