mm/mglru: fix potential generation folio number leak

Each generation of MGLRU accounts anon and file folio numbers separately,
and the page table walker updates each generation's counters in batch once
the walk is done.  The walker promotes a folio's generation with a cmpxchg
on folio->flags, and update_batch_size() then reads the live flags again
to pick the anon/file column to charge.  The walk holds neither the lruvec
lock nor the folio lock, so the type can flip between the cmpxchg and that
read: the lazyfree path clears PG_swapbacked, and reclaim sets it back on
a dirty lazyfree folio.  The batched delta pair is then recorded in the
wrong type column.  Nothing reconciles it afterwards, permanently skewing
lrugen->nr_pages and the reclaim budgets derived from it.

Fix it by capturing the type from the flags snapshot the cmpxchg
linearized against: folio_update_gen() returns the type of the state it
transitioned from, and update_batch_size() accounts with that.

A folio's type only changes while it is off the LRU list, inside a del/add
pair under the lruvec lock, with the gen bits cleared in between.  The
generation and PG_swapbacked sit in the same folio->flags word, so the
cmpxchg snapshot captures them together.  Let G be the generation that
snapshot captured (old_gen) and G' the one it wrote (new_gen); the CAS can
land in only three places:

  - before the del: the folio is anon at G; the batch records anon
    G -> G', and the del later removes the folio from the anon
    counters;
  - between del and add: gen == -1, so folio_update_gen() returns -1
    without touching the flags and no batch is recorded; the del/add
    pair accounts for the move alone;
  - after the add: the folio is file at the fresh generation the add
    charged; the batch records file, that gen -> G', matching that
    charge.

Unlike the drift of lazy promotions, which sort_folio() repairs under the
lruvec lock, the phantom deltas from before this fix land in a column the
folio never occupies again, so nothing ever repairs them.

Link: https://lore.kernel.org/20260906-mglru-flags-cleanup-v6-6-9aacbd77d4ca@tencent.com
Fixes: bd74fdaea1 ("mm: multi-gen LRU: support page table walks")
Signed-off-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <baoquan.he@linux.dev>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lian Wang <lianux.mm@gmail.com>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <qi.zheng@linux.dev>
Cc: Ridong Chen <ridong.chen@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>

include/linux/mm_inline.h

@@ -30,6 +30,17 @@ static inline int folio_is_file_lru(const struct folio *folio)
 	return !folio_test_swapbacked(folio);
 }
 
+/**
+ * folio_flags_is_file_lru - Should the folio be on a file LRU or anon LRU?
+ * @flags: The folio's flags.
+ *
+ * Just like folio_is_file_lru but take the folio flags directly instead.
+ */
+static inline int folio_flags_is_file_lru(const unsigned long *flags)
+{
+	return !test_bit(PG_swapbacked, flags);
+}
+
 static __always_inline void __update_lru_size(struct lruvec *lruvec,
 				enum lru_list lru, enum zone_type zid,
 				long nr_pages)

mm/vmscan.c

@@ -3294,7 +3294,8 @@ static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
  ******************************************************************************/
 
 /* promote pages accessed through page tables */
-static int folio_update_gen(struct folio *folio, int new_gen, const vma_flags_t *vma_flags)
+static int folio_update_gen(struct folio *folio, int new_gen, int *type,
+			    const vma_flags_t *vma_flags)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(*folio_flags(folio, 0));
 	int old_gen;
@@ -3323,6 +3324,7 @@ static int folio_update_gen(struct folio *folio, int new_gen, const vma_flags_t
 		new_flags |= BIT(PG_workingset);
 	} while (!try_cmpxchg(folio_flags(folio, 0), &old_flags, new_flags));
 
+	*type = folio_flags_is_file_lru(&old_flags);
 	return old_gen;
 }
 
@@ -3368,9 +3370,8 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio)
 }
 
 static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio,
-			      int old_gen, int new_gen)
+			      int old_gen, int new_gen, int type)
 {
-	int type = folio_is_file_lru(folio);
 	int zone = folio_zonenum(folio);
 	int delta = folio_nr_pages(folio);
 
@@ -3559,7 +3560,7 @@ static bool suitable_to_scan(int total, int young)
 static void walk_update_folio(struct lru_gen_mm_walk *walk, struct vm_area_struct *vma,
 		struct lruvec *lruvec, struct folio *folio, bool dirty)
 {
-	int new_gen, old_gen;
+	int new_gen, old_gen, type;
 
 	if (!folio)
 		return;
@@ -3572,9 +3573,9 @@ static void walk_update_folio(struct lru_gen_mm_walk *walk, struct vm_area_struc
 		folio_mark_dirty(folio);
 
 	if (walk) {
-		old_gen = folio_update_gen(folio, new_gen, &vma->flags);
+		old_gen = folio_update_gen(folio, new_gen, &type, &vma->flags);
 		if (old_gen >= 0 && old_gen != new_gen)
-			update_batch_size(walk, folio, old_gen, new_gen);
+			update_batch_size(walk, folio, old_gen, new_gen, type);
 	} else if (lru_gen_set_refs(folio, &vma->flags)) {
 		old_gen = folio_lru_gen(folio);
 		if (old_gen >= 0 && old_gen != new_gen)