mm: fix ASSERT_EXCLUSIVE_BITS by passing memdesc_flags_t by pointer

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() call in memdesc_zonenum() under
ZONES_WIDTH != 0 to avoid a zero-mask check on configs where the zone
field is absent.  memdesc_section() needs no such guard, since
SECTIONS_WIDTH is never 0 wherever SECTION_IN_PAGE_FLAGS is defined. 
Under CONFIG_NUMA=n, memdesc_nid() itself is stubbed to "return 0" instead
of reading page->flags, since NODES_MASK is 0 and the check can never
fire; page_to_nid()/folio_nid() now just call memdesc_nid()
unconditionally and rely on that stub, instead of duplicating the
CONFIG_NUMA split at each call site.

[zhuhui@kylinos.cn: v11]
  Link: https://lore.kernel.org/20260708083308.747930-1-hui.zhu@linux.dev
[ziy@nvidia.com: build fix]
  Link: https://lore.kernel.org/DJSGLP9VFLRI.355AAWR2VHIEL@nvidia.com
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>
Acked-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

@@ -53,7 +53,7 @@ static inline int pfn_valid(unsigned long pfn)
  */
 #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)));	\
 })
 

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;
@@ -2286,22 +2287,30 @@ static inline int page_zone_id(struct page *page)
 }
 
 #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
 
 static inline int page_to_nid(const struct page *page)
 {
-	return memdesc_nid(PF_POISONED_CHECK(page)->flags);
+	return memdesc_nid(&(PF_POISONED_CHECK(page)->flags));
 }
 
 static inline int folio_nid(const struct folio *folio)
 {
-	return memdesc_nid(folio->flags);
+	return memdesc_nid(&folio->flags);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -2541,12 +2550,13 @@ static inline void set_page_section(struct page *page, unsigned long section)
 	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;
+	ASSERT_EXCLUSIVE_BITS(mdf->f, SECTIONS_MASK << SECTIONS_PGSHIFT);
+	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;
 }

include/linux/mm_inline.h

@@ -650,7 +650,7 @@ static inline bool vma_has_recency(const struct vm_area_struct *vma)
 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_contiguous(struct page **pages, size_t nr_pages)
 		 * 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;
 	}
 

include/linux/mmzone.h

@@ -1272,31 +1272,33 @@ static inline bool zone_is_empty(const struct zone *zone)
 #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_pgmap(const struct page *page)
 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_have_same_pgmap(const struct page *a,
 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_pgmap(const struct page *page)
 
 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)

mm/page_alloc.c

@@ -6913,15 +6913,15 @@ static void __free_contig_range_common(unsigned long pfn, unsigned long nr_pages
 			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);
 		}
 	}
 

mm/page_owner.c

@@ -815,7 +815,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 			 */
 			if (page_flags.f == PAGE_POISON_PATTERN)
 				goto ext_put_continue;
-			nid = memdesc_nid(page_flags);
+			nid = memdesc_nid(&page_flags);
 			if (!node_isset(nid, state->nid_filter))
 				goto ext_put_continue;
 		}

mm/slab.h

@@ -180,7 +180,7 @@ static inline void *slab_address(const struct slab *slab)
 
 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)

mm/sparse.c

@@ -43,7 +43,7 @@ static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
 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)];
 }