Message-ID: <20250224165603.1434404-4-david@redhat.com>
Date: Mon, 24 Feb 2025 17:55:45 +0100
From: David Hildenbrand <david@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: linux-doc@...r.kernel.org,
	cgroups@...r.kernel.org,
	linux-mm@...ck.org,
	linux-fsdevel@...r.kernel.org,
	linux-api@...r.kernel.org,
	David Hildenbrand <david@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	"Matthew Wilcox (Oracle)" <willy@...radead.org>,
	Tejun Heo <tj@...nel.org>,
	Zefan Li <lizefan.x@...edance.com>,
	Johannes Weiner <hannes@...xchg.org>,
	Michal Koutný <mkoutny@...e.com>,
	Jonathan Corbet <corbet@....net>,
	Andy Lutomirski <luto@...nel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	Borislav Petkov <bp@...en8.de>,
	Dave Hansen <dave.hansen@...ux.intel.com>,
	Muchun Song <muchun.song@...ux.dev>,
	"Liam R. Howlett" <Liam.Howlett@...cle.com>,
	Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
	Vlastimil Babka <vbabka@...e.cz>,
	Jann Horn <jannh@...gle.com>,
	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCH v2 03/20] 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.

Reviewed-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Signed-off-by: David Hildenbrand <david@...hat.com>
---
 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 7c5a8fd29cfcd..f6b6373a864dd 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 */
 		};
 		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 1e45064046a0f..13152313e77ce 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3307,9 +3307,10 @@ 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 nr_pages = 1 << old_order;
 	long new_nr_pages = 1 << new_order;
 	long index;
 
@@ -3529,12 +3530,21 @@ 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 b07550db2bfd1..7f6d5def00fa0 100644
--- 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 16dfcf7ade74a..bdfc954dab9aa 100644
--- 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 2d6360eaccbb6..a409e2561a8fd 100644
--- 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)
-- 
2.48.1

Powered by blists - more mailing lists