[PATCH] mm/huge_memory: prevent losing PG_waiters in __split_folio_to_order()

[Zi Yan]

__split_folio_to_order() calls prep_compound_page() on each new head page
to create a compound page after clear_compound_head(). prep_compound_page()
uses non atomic __SetPageHead(). It is mostly OK, since the folio is locked
and frozen and no one else is supposed to modify the folio's flags.

However, code calling migration_entry_wait() can reach the folio by PFN,
then access its flags. It is because softleaf_entry_wait_on_locked() used
by migration_entry_wait() sets PG_waiters concurrently without taking a
reference and the frozen refcount during split cannot block it. Meanwhile,
__SetPageHead() does a plain read and write, so PG_waiters atomically set
by softleaf_entry_wait_on_locked() will be lost if the set happens after
__SetPageHead()'s read and before its write.

One example code interleaving:

CPU0: __split_folio_to_order(new_order>0)  CPU1: do_swap_page()

1. clear_compound_head(new_head)
   new_head->compound_info = 0
   (page_folio(new_head) == new_head now)

                                           2. migration_entry_wait()
                                             softleaf_to_folio(entry)
                                             page_folio() -> new_head
                                             (not the old head any more)

3. prep_compound_page(new_head, new_order)
     __SetPageHead(new_head)
       tmp = new_head->flags.f  <-- load; PG_waiters == 0 in tmp

                                           4. folio_set_waiters(new_head)
                                             set_bit(PG_waiters, &flags.f)
                                             enqueue on waitqueue, sleep

5.     new_head->flags.f = tmp | (1UL << PG_head)
       <-- store; overwrites step 4, PG_waiters == 0 again

Later, folio_unlock(new_folio) sees no PG_waiters, skips folio_wake_bit(),
and CPU1 can remain blocked indefinitely.

Fix it by adding the atomic version SetPageHead() and
prep_compound_page_atomic() using it. __split_folio_to_order() uses
prep_compound_page_atomic() to avoid the issue without adding an atomic ops
to other prep_compound_page() users.

Reported-by: David Hildenbrand <david@xxxxxxxxxx>
Closes: https://lore.kernel.org/all/DMHE8BEEER1H.2BIY52NXATPIA@xxxxxxxxxx/
Fixes: c010d47f107f6 ("mm: thp: split huge page to any lower order pages")
Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
The issue was raised by David when reviewing Ye Liu's "mm/huge_memory: use
READ_ONCE() when cloning folio flags during split" [1].

[1] https://lore.kernel.org/all/20261029-data_race_huge_mem-v1-1-112e331291c1@xxxxxxxxx/
---
 include/linux/page-flags.h |  1 +
 mm/huge_memory.c           | 10 +++++++++-
 mm/internal.h              |  2 ++
 mm/page_alloc.c            | 20 ++++++++++++++++++--
 4 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b0ddc652e76cc..08492ab3da895 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -854,6 +854,7 @@ static __always_inline int PageHead(const struct page *page)
 	return test_bit(PG_head, &page->flags.f);
 }
 
+SETPAGEFLAG(Head, head, PF_ANY)
 __SETPAGEFLAG(Head, head, PF_ANY)
 __CLEARPAGEFLAG(Head, head, PF_ANY)
 CLEARPAGEFLAG(Head, head, PF_ANY)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bd44d58e86845..319b038eba89d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3779,7 +3779,15 @@ static void __split_folio_to_order(struct folio *folio, int old_order,
 		 */
 		clear_compound_head(new_head);
 		if (new_order) {
-			prep_compound_page(new_head, new_order);
+			/*
+			 * new_head is recognized as a folio after
+			 * clear_compound_head().
+			 * softleaf_entry_wait_on_locked() can set PG_waiters
+			 * on it without taking a reference, so its frozen state
+			 * cannot prevent it. Use the atomic version to avoid
+			 * losing a concurrently set PG_waiters.
+			 */
+			prep_compound_page_atomic(new_head, new_order);
 			folio_set_large_rmappable(new_folio);
 		}
 
diff --git a/mm/internal.h b/mm/internal.h
index aeebb3e49ed11..9b8864a8540aa 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -807,6 +807,8 @@ static inline void prep_compound_tail(struct page *tail,
 	VM_WARN_ON_ONCE(tail->private);
 }
 
+void prep_compound_page_atomic(struct page *page, unsigned int order);
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 143776e671abb..ace1359468046 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -682,18 +682,34 @@ static inline bool pcp_allowed_order(unsigned int order)
  * This usage means that zero-order pages may not be compound.
  */
 
-void prep_compound_page(struct page *page, unsigned int order)
+static void __prep_compound_head_and_tail(struct page *page, unsigned int order)
 {
 	int i;
 	int nr_pages = 1 << order;
 
-	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++)
 		prep_compound_tail(page + i, page, order);
 
 	prep_compound_head(page, order);
 }
 
+void prep_compound_page(struct page *page, unsigned int order)
+{
+	__SetPageHead(page);
+	__prep_compound_head_and_tail(page, order);
+}
+
+/*
+ * PG_head is set atomically whereas the other metadata is set with plain stores.
+ * It should be used when @page's flags can be modified concurrently,
+ * e.g., in __split_folio_to_order().
+ */
+void prep_compound_page_atomic(struct page *page, unsigned int order)
+{
+	SetPageHead(page);
+	__prep_compound_head_and_tail(page, order);
+}
+
 static inline void set_buddy_order(struct page *page, unsigned int order)
 {
 	set_page_private(page, order);

---
base-commit: d865f2677c44cb2171b833d6775cf692756fa8be
change-id: 20261029-fix-split_folio_to_order-race-087a2a9fbf7c

Best regards,
--  
Yan, Zi