+ mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer.patch added to mm-new branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm: fix ASSERT_EXCLUSIVE_BITS by passing memdesc_flags_t by pointer
has been added to the -mm mm-new branch.  Its filename is
     mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer.patch

This patch will later appear in the mm-new branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Note, mm-new is a provisional staging ground for work-in-progress
patches, and acceptance into mm-new is a notification for others take
notice and to finish up reviews.  Please do not hesitate to respond to
review feedback and post updated versions to replace or incrementally
fixup patches in mm-new.

The mm-new branch of mm.git is not included in linux-next

If a few days of testing in mm-new is successful, the patch will me moved
into mm.git's mm-unstable branch, which is included in linux-next

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Hui Zhu <zhuhui@kylinos.cn>
Subject: mm: fix ASSERT_EXCLUSIVE_BITS by passing memdesc_flags_t by pointer
Date: Tue, 30 Jun 2026 15:08:10 +0800

KCSAN reports a data race between page_to_nid()/folio_pgdat() reading
page->flags and folio_trylock()/folio_lock() concurrently doing
test_and_set_bit_lock(PG_locked, ...) on the same word, e.g.:

  BUG: KCSAN: data-race in __lruvec_stat_mod_folio / shmem_get_folio_gfp

The race is benign: nid/zone bits are set once at page init and never
overlap with PG_locked.  However, ASSERT_EXCLUSIVE_BITS() inside
memdesc_nid/zonenum() was checking a by-value copy of the flags word, not
the live page->flags, so it failed to annotate the real access.

Change memdesc_nid(), memdesc_zonenum(), memdesc_section(), and
memdesc_is_zone_device() to take a const memdesc_flags_t * and update all
callers to pass &page->flags / &folio->flags, so ASSERT_EXCLUSIVE_BITS()
operates on the actual shared word.

Guard the ASSERT_EXCLUSIVE_BITS() calls in memdesc_zonenum() and
memdesc_section() under ZONES_WIDTH != 0 / SECTIONS_WIDTH != 0 to avoid a
zero-mask check on configs where the corresponding field is absent.  Under
CONFIG_NUMA=n, stub out page_to_nid() and folio_nid() as plain "return 0"
instead of reading page->flags when NODES_MASK is 0 and the check can
never fire.

Link: https://lore.kernel.org/20260630070810.470763-1-hui.zhu@linux.dev
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
Co-developed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Kairui Song <kasong@tencent.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/asm-generic/memory_model.h |    2 -
 include/linux/mm.h                 |   42 +++++++++++++++++++++------
 include/linux/mm_inline.h          |    4 +-
 include/linux/mmzone.h             |   26 +++++++++-------
 mm/page_alloc.c                    |    6 +--
 mm/slab.h                          |    2 -
 mm/sparse.c                        |    2 -
 7 files changed, 56 insertions(+), 28 deletions(-)

--- a/include/asm-generic/memory_model.h~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/include/asm-generic/memory_model.h
@@ -53,7 +53,7 @@ static inline int pfn_valid(unsigned lon
  */
 #define __page_to_pfn(pg)					\
 ({	const struct page *__pg = (pg);				\
-	int __sec = memdesc_section(__pg->flags);		\
+	int __sec = memdesc_section(&__pg->flags);		\
 	(unsigned long)(__pg - __section_mem_map_addr(__nr_to_section(__sec)));	\
 })
 
--- a/include/linux/mm.h~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/include/linux/mm.h
@@ -37,6 +37,7 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/iommu-debug-pagealloc.h>
+#include <linux/kcsan-checks.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -2286,23 +2287,45 @@ static inline int page_zone_id(struct pa
 }
 
 #ifdef NODE_NOT_IN_PAGE_FLAGS
-int memdesc_nid(memdesc_flags_t mdf);
+int memdesc_nid(const memdesc_flags_t *mdf);
 #else
-static inline int memdesc_nid(memdesc_flags_t mdf)
+#ifdef CONFIG_NUMA
+static inline int memdesc_nid(const memdesc_flags_t *mdf)
 {
-	return (mdf.f >> NODES_PGSHIFT) & NODES_MASK;
+	ASSERT_EXCLUSIVE_BITS(mdf->f, NODES_MASK << NODES_PGSHIFT);
+	return (mdf->f >> NODES_PGSHIFT) & NODES_MASK;
+}
+#else
+static inline int memdesc_nid(const memdesc_flags_t *mdf)
+{
+	return 0;
 }
 #endif
+#endif
+
+#ifdef CONFIG_NUMA
+static inline int page_to_nid(const struct page *page)
+{
+	const struct page *p = PF_POISONED_CHECK(page);
 
+	return memdesc_nid(&p->flags);
+}
+
+static inline int folio_nid(const struct folio *folio)
+{
+	return memdesc_nid(&folio->flags);
+}
+#else
 static inline int page_to_nid(const struct page *page)
 {
-	return memdesc_nid(PF_POISONED_CHECK(page)->flags);
+	return 0;
 }
 
 static inline int folio_nid(const struct folio *folio)
 {
-	return memdesc_nid(folio->flags);
+	return 0;
 }
+#endif
 
 #ifdef CONFIG_NUMA_BALANCING
 /* page access time bits needs to hold at least 4 seconds */
@@ -2541,12 +2564,15 @@ static inline void set_page_section(stru
 	page->flags.f |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
 }
 
-static inline unsigned long memdesc_section(memdesc_flags_t mdf)
+static inline unsigned long memdesc_section(const memdesc_flags_t *mdf)
 {
-	return (mdf.f >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
+#if SECTIONS_WIDTH != 0
+	ASSERT_EXCLUSIVE_BITS(mdf->f, SECTIONS_MASK << SECTIONS_PGSHIFT);
+#endif
+	return (mdf->f >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
 }
 #else /* !SECTION_IN_PAGE_FLAGS */
-static inline unsigned long memdesc_section(memdesc_flags_t mdf)
+static inline unsigned long memdesc_section(const memdesc_flags_t *mdf)
 {
 	return 0;
 }
--- a/include/linux/mm_inline.h~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/include/linux/mm_inline.h
@@ -650,7 +650,7 @@ static inline bool vma_has_recency(const
 static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages)
 {
 	struct page *cur_page = pages[0];
-	unsigned long section = memdesc_section(cur_page->flags);
+	unsigned long section = memdesc_section(&cur_page->flags);
 	size_t i;
 
 	for (i = 1; i < nr_pages; i++) {
@@ -660,7 +660,7 @@ static inline size_t num_pages_contiguou
 		 * In unproblematic kernel configs, page_to_section() == 0 and
 		 * the whole check will get optimized out.
 		 */
-		if (memdesc_section(cur_page->flags) != section)
+		if (memdesc_section(&cur_page->flags) != section)
 			break;
 	}
 
--- a/include/linux/mmzone.h~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/include/linux/mmzone.h
@@ -1272,31 +1272,33 @@ static inline bool zone_is_empty(const s
 #define KASAN_TAG_MASK		((1UL << KASAN_TAG_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
-static inline enum zone_type memdesc_zonenum(memdesc_flags_t flags)
+static inline enum zone_type memdesc_zonenum(const memdesc_flags_t *flags)
 {
-	ASSERT_EXCLUSIVE_BITS(flags.f, ZONES_MASK << ZONES_PGSHIFT);
-	return (flags.f >> ZONES_PGSHIFT) & ZONES_MASK;
+#if ZONES_WIDTH != 0
+	ASSERT_EXCLUSIVE_BITS(flags->f, ZONES_MASK << ZONES_PGSHIFT);
+#endif
+	return (flags->f >> ZONES_PGSHIFT) & ZONES_MASK;
 }
 
 static inline enum zone_type page_zonenum(const struct page *page)
 {
-	return memdesc_zonenum(page->flags);
+	return memdesc_zonenum(&page->flags);
 }
 
 static inline enum zone_type folio_zonenum(const struct folio *folio)
 {
-	return memdesc_zonenum(folio->flags);
+	return memdesc_zonenum(&folio->flags);
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-static inline bool memdesc_is_zone_device(memdesc_flags_t mdf)
+static inline bool memdesc_is_zone_device(const memdesc_flags_t *mdf)
 {
 	return memdesc_zonenum(mdf) == ZONE_DEVICE;
 }
 
 static inline struct dev_pagemap *page_pgmap(const struct page *page)
 {
-	VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(page->flags), page);
+	VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(&page->flags), page);
 	return page_folio(page)->pgmap;
 }
 
@@ -1311,9 +1313,9 @@ static inline struct dev_pagemap *page_p
 static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
 						     const struct page *b)
 {
-	if (memdesc_is_zone_device(a->flags) != memdesc_is_zone_device(b->flags))
+	if (memdesc_is_zone_device(&a->flags) != memdesc_is_zone_device(&b->flags))
 		return false;
-	if (!memdesc_is_zone_device(a->flags))
+	if (!memdesc_is_zone_device(&a->flags))
 		return true;
 	return page_pgmap(a) == page_pgmap(b);
 }
@@ -1321,7 +1323,7 @@ static inline bool zone_device_pages_hav
 extern void memmap_init_zone_device(struct zone *, unsigned long,
 				    unsigned long, struct dev_pagemap *);
 #else
-static inline bool memdesc_is_zone_device(memdesc_flags_t mdf)
+static inline bool memdesc_is_zone_device(const memdesc_flags_t *mdf)
 {
 	return false;
 }
@@ -1338,12 +1340,12 @@ static inline struct dev_pagemap *page_p
 
 static inline bool is_zone_device_page(const struct page *page)
 {
-	return memdesc_is_zone_device(page->flags);
+	return memdesc_is_zone_device(&page->flags);
 }
 
 static inline bool folio_is_zone_device(const struct folio *folio)
 {
-	return memdesc_is_zone_device(folio->flags);
+	return memdesc_is_zone_device(&folio->flags);
 }
 
 static inline bool is_zone_movable_page(const struct page *page)
--- a/mm/page_alloc.c~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/mm/page_alloc.c
@@ -6913,15 +6913,15 @@ static void __free_contig_range_common(u
 			continue;
 		}
 
-		if (start && memdesc_section(page->flags) != start_sec) {
+		if (start && memdesc_section(&page->flags) != start_sec) {
 			free_prepared_contig_range(start, i - nr_start);
 			start = page;
 			nr_start = i;
-			start_sec = memdesc_section(page->flags);
+			start_sec = memdesc_section(&page->flags);
 		} else if (!start) {
 			start = page;
 			nr_start = i;
-			start_sec = memdesc_section(page->flags);
+			start_sec = memdesc_section(&page->flags);
 		}
 	}
 
--- a/mm/slab.h~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/mm/slab.h
@@ -179,7 +179,7 @@ static inline void *slab_address(const s
 
 static inline int slab_nid(const struct slab *slab)
 {
-	return memdesc_nid(slab->flags);
+	return memdesc_nid(&slab->flags);
 }
 
 static inline pg_data_t *slab_pgdat(const struct slab *slab)
--- a/mm/sparse.c~mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer
+++ a/mm/sparse.c
@@ -43,7 +43,7 @@ static u8 section_to_node_table[NR_MEM_S
 static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
 #endif
 
-int memdesc_nid(memdesc_flags_t mdf)
+int memdesc_nid(const memdesc_flags_t *mdf)
 {
 	return section_to_node_table[memdesc_section(mdf)];
 }
_

Patches currently in -mm which might be from zhuhui@kylinos.cn are

mm-fix-assert_exclusive_bits-by-passing-memdesc_flags_t-by-pointer.patch