[PATCH v8] mm: fix ASSERT_EXCLUSIVE_BITS by passing memdesc_flags_t by pointer

[Hui Zhu <hui.zhu@linux.dev>]

From: Hui Zhu <zhuhui@kylinos.cn>

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.

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>
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
Changelog:
v8:
According to the comments of Andrew, include kcsan-checks.h in mm.h.
Incorporate David's patch that switch memdesc_nid(), memdesc_zonenum(),
memdesc_section() and memdesc_is_zone_device() to take a const
memdesc_flags_t * instead of using a per-accessor macro/call-site hack.
Update all callers accordingly and extend the same exclusive-bits check
to memdesc_section() and memdesc_is_zone_device(), guarded by
SECTIONS_WIDTH != 0 / reusing ZONES_WIDTH != 0 to avoid zero-mask checks
on configs without the corresponding field.
v7:
According to the comments of Sashiko, restrict the memdesc_nid() macro
to CONFIG_NUMA, keeping a plain "return 0" static inline stub otherwise,
and re-add a local page pointer in page_to_nid() to avoid evaluating
PF_POISONED_CHECK(page) twice.
v6:
According to the comments of David, turn memdesc_nid() from a static
inline function into a macro so ASSERT_EXCLUSIVE_BITS() can check the
caller's page->flags/folio->flags directly.
v5:
According to the comments of Sashiko, guard the ASSERT_EXCLUSIVE_BITS()
calls with #ifndef NODE_NOT_IN_PAGE_FLAGS (for nid) and #if
ZONES_WIDTH != 0 (for zonenum).
According to the comments of David, avoid calling
PF_POISONED_CHECK(page) twice in page_to_nid().
According to the warning of lkp, switch the CONFIG_NUMA=n
page_to_nid()/folio_nid() stubs from macros to static inline functions.
v4:
According to the comments of Andrew and Sashiko, set
page_to_nid()/folio_nid() as static inline stubs returning 0
under CONFIG_NUMA=n.
v3:
According to the comments of Andrew and Sashiko, move
ASSERT_EXCLUSIVE_BITS out of memdesc_nid()/memdesc_zonenum()
into the page/folio call sites.
v2:
According to the comments of David, remove useless comments and use
ASSERT_EXCLUSIVE_BITS() in memdesc_nid() instead of data_race() in
page_to_nid().

 include/asm-generic/memory_model.h |  2 +-
 include/linux/mm.h                 | 40 ++++++++++++++++++++++++------
 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, 54 insertions(+), 28 deletions(-)

diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index efa6610acbc7..f8404bc7773c 100644
--- a/include/asm-generic/memory_model.h
+++ b/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)));	\
 })
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 485df9c2dbdd..315d8917f8e7 100644
--- a/include/linux/mm.h
+++ b/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 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
 
+#ifdef CONFIG_NUMA
 static inline int page_to_nid(const struct page *page)
 {
-	return memdesc_nid(PF_POISONED_CHECK(page)->flags);
+	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);
+	return memdesc_nid(&folio->flags);
 }
+#else
+static inline int page_to_nid(const struct page *page)
+{
+	return 0;
+}
+
+static inline int folio_nid(const struct folio *folio)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_NUMA_BALANCING
 /* page access time bits needs to hold at least 4 seconds */
@@ -2541,12 +2564,13 @@ 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;
 }
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index a8430a7ae054..efcddb9925ad 100644
--- a/include/linux/mm_inline.h
+++ b/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;
 	}
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ca2712187147..e60dad546ca6 100644
--- a/include/linux/mmzone.h
+++ b/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)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ee902a468c2f..020a97ca018e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6904,15 +6904,15 @@ 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);
 		}
 	}
 
diff --git a/mm/slab.h b/mm/slab.h
index 281a65233795..9ded319495a0 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -179,7 +179,7 @@ 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)
diff --git a/mm/sparse.c b/mm/sparse.c
index 16ac6df3c89f..8e3847764513 100644
--- a/mm/sparse.c
+++ b/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)];
 }
-- 
2.43.0