mm/mglru: reset page lru tier bits when activating

When a folio is activated, lru_gen_add_folio() moves the folio to the
youngest generation.  But unlike folio_update_gen()/folio_inc_gen(),
lru_gen_add_folio() doesn't reset the folio lru tier bits (LRU_REFS_MASK |
LRU_REFS_FLAGS).  This inconsistency can affect how pages are aged via
folio_mark_accessed() (e.g.  fd accesses), though no user visible impact
related to this has been detected yet.

Note that lru_gen_add_folio() cannot clear PG_workingset if the activation
is due to workingset refault, otherwise PSI accounting will be skipped. 
So fix lru_gen_add_folio() to clear the lru tier bits other than
PG_workingset when activating a folio, and also clear all the lru tier
bits when a folio is activated via folio_activate() in
lru_gen_look_around().

Link: https://lkml.kernel.org/r/[email protected]
Fixes: 018ee47 ("mm: multi-gen LRU: exploit locality in rmap")
Signed-off-by: Wei Xu <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: Brian Geffon <[email protected]>
Cc: Jan Alexander Steffens <[email protected]>
Cc: Suleiman Souhlal <[email protected]>
Cc: Yu Zhao <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: weixugc

include/linux/mm_inline.h

@@ -155,6 +155,11 @@ static inline int folio_lru_refs(struct folio *folio)
 	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
 }
 
+static inline void folio_clear_lru_refs(struct folio *folio)
+{
+	set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
+}
+
 static inline int folio_lru_gen(struct folio *folio)
 {
 	unsigned long flags = READ_ONCE(folio->flags);
@@ -222,6 +227,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 {
 	unsigned long seq;
 	unsigned long flags;
+	unsigned long mask;
 	int gen = folio_lru_gen(folio);
 	int type = folio_is_file_lru(folio);
 	int zone = folio_zonenum(folio);
@@ -257,7 +263,14 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
 	/* see the comment on MIN_NR_GENS about PG_active */
-	set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);
+	mask = LRU_GEN_MASK;
+	/*
+	 * Don't clear PG_workingset here because it can affect PSI accounting
+	 * if the activation is due to workingset refault.
+	 */
+	if (folio_test_active(folio))
+		mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active);
+	set_mask_bits(&folio->flags, mask, flags);
 
 	lru_gen_update_size(lruvec, folio, -1, gen);
 	/* for folio_rotate_reclaimable() */

include/linux/mmzone.h

@@ -403,6 +403,8 @@ enum {
 	NR_LRU_GEN_CAPS
 };
 
+#define LRU_REFS_FLAGS		(BIT(PG_referenced) | BIT(PG_workingset))
+
 #define MIN_LRU_BATCH		BITS_PER_LONG
 #define MAX_LRU_BATCH		(MIN_LRU_BATCH * 64)
 

mm/vmscan.c

@@ -2603,8 +2603,6 @@ static bool should_clear_pmd_young(void)
  *                          shorthand helpers
  ******************************************************************************/
 
-#define LRU_REFS_FLAGS	(BIT(PG_referenced) | BIT(PG_workingset))
-
 #define DEFINE_MAX_SEQ(lruvec)						\
 	unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq)
 
@@ -4142,8 +4140,10 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		old_gen = folio_lru_gen(folio);
 		if (old_gen < 0)
 			folio_set_referenced(folio);
-		else if (old_gen != new_gen)
+		else if (old_gen != new_gen) {
+			folio_clear_lru_refs(folio);
 			folio_activate(folio);
+		}
 	}
 
 	arch_leave_lazy_mmu_mode();
@@ -4376,7 +4376,7 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 
 	/* see the comment on MAX_NR_TIERS */
 	if (!folio_test_referenced(folio))
-		set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
+		folio_clear_lru_refs(folio);
 
 	/* for shrink_folio_list() */
 	folio_clear_reclaim(folio);