[PATCH] mm/mglru: fix using folio_mark_accessed to replace folio_set_active

[PATCH] mm/mglru: fix using folio_mark_accessed to replace folio_set_active

[Barry Song (Xiaomi)]

Commit 6cbdd9726fb5 ("mm/mglru: use folio_mark_accessed to
replace folio_set_active") attempted to avoid over-protecting
in-fault read-ahead file folios by placing them in the
second-oldest generation rather than the young generations.

However, it repurposes `PG_referenced` on in-fault read-ahead
file folios for this purpose, potentially coupling their
handling with that of regular file accesses through syscalls,
which also use `PG_referenced`.

This could regress some workloads, as reported by Kairui Song[1]
and Ehab Ababneh[2]. Many thanks to both for reporting these
issues!

The long-term fix is Kairui's MGLRU-FG, but in the meantime,
we also need a quick fix that can be backported to stable.

This patch reverts the original commit's abuse of `PG_referenced`
while preserving its goal of avoiding over-protection of
in-fault read-ahead file folios by adjusting only
`lru_gen_folio_seq()`.

Specifically, in-fault read-ahead file folios with `PG_active`
set but `PG_workingset` clear are placed in the second-oldest
generation (the third-youngest generation). Activated file
folios and refaulted workingset file folios remain in the
youngest generations.

Kernel build tests in a memcg show that this approach not only
preserves the original patch's benefits but also further
improves performance.

w/o fix:

real    1m49.094s
user    25m31.484s
sys     3m40.959s
pswpin: 662112
pswpout: 2504415
pgpgin: 4424336
pgpgout: 10355273
refault_file: 359626
refault_anon: 670724

w/ fix:

real    1m48.913s
user    25m31.639s
sys     3m30.875s
pswpin: 689815
pswpout: 2689894
pgpgin: 4422659
pgpgout: 11043464
refault_file: 326566
refault_anon: 697138

Revert original patch:

real    1m50.044s
user    25m37.137s
sys     4m4.493s
pswpin: 1349087
pswpout: 4317933
pgpgin: 7083597
pgpgout: 17602735
refault_file: 337676
refault_anon: 1368542

[1] https://lore.kernel.org/linux-mm/20261003-mglru-fg-v3-0-cbd4546a5bd9@tencent.com/
[2] https://lore.kernel.org/linux-mm/20260901180704.168106-1-ehab.ababneh@intel.com/
Fixes: 6cbdd9726fb5 ("mm/mglru: use folio_mark_accessed to replace folio_set_active")
Cc: <stable@vger.kernel.org>
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 * An earlier discussion can be found here:
 https://lore.kernel.org/linux-mm/20261016084256.12955-1-baohua@kernel.org/
 Thanks for Kairui's comment on it.

 include/linux/mm_inline.h |  5 +++--
 mm/folio.c                | 16 +++-------------
 mm/vmscan.c               |  9 ++-------
 mm/workingset.c           | 10 ++++------
 4 files changed, 12 insertions(+), 28 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index ab69b9930893..97f157aafd58 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -319,7 +319,8 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
 	 * |<---------------------------- MAX_NR_GENS ---------------------------->|
 	 */
 	if (folio_test_active(folio))
-		gen = MIN_NR_GENS - folio_test_workingset(folio);
+		gen = MIN_NR_GENS - folio_test_workingset(folio) +
+		      (type ? !folio_test_workingset(folio) : 0);
 	else if (reclaiming)
 		gen = MAX_NR_GENS;
 	else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) ||
@@ -327,7 +328,7 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
 		gen = MIN_NR_GENS;
 	else
-		gen = MAX_NR_GENS - (folio_test_workingset(folio) || folio_test_referenced(folio));
+		gen = MAX_NR_GENS - folio_test_workingset(folio);
 
 	return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
 }
diff --git a/mm/folio.c b/mm/folio.c
index 35e242b48870..2af724cecb31 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -474,20 +474,10 @@ void folio_add_lru(struct folio *folio)
 			folio_test_unevictable(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-	/*
-	 * For refaulted workingset folios, set PG_active so they
-	 * can be added to active generations.
-	 * For prefaulted file folios, folio_mark_accessed() sets
-	 * PG_referenced so lru_gen_folio_seq() places them into
-	 * the second oldest generation.
-	 */
+	/* see the comment in lru_gen_folio_seq() */
 	if (lru_gen_enabled() && !folio_test_unevictable(folio) &&
-	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) {
-		if (folio_test_workingset(folio))
-			folio_set_active(folio);
-		else if (!folio_test_referenced(folio))
-			folio_mark_accessed(folio);
-	}
+	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
+		folio_set_active(folio);
 
 	folio_batch_add_and_move(folio, lru_add);
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index daa7e37c2236..e82ba737c028 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -952,13 +952,8 @@ static bool lru_gen_set_refs(struct folio *folio, const vma_flags_t *vma_flags)
 		return false;
 	}
 
-	/* Promote on second access */
-	if (folio_lru_refs(folio) > 1) {
-		folio_set_workingset(folio);
-		folio_set_lru_refs(folio, 0);
-	} else {
-		folio_mark_accessed(folio);
-	}
+	folio_set_workingset(folio);
+	folio_set_lru_refs(folio, 0);
 	return true;
 }
 #else
diff --git a/mm/workingset.c b/mm/workingset.c
index 1504f91cdca5..10d4ce202cca 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -319,13 +319,11 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 
 	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
 
+	/* see folio_add_lru() where folio_set_active() will be called */
+	if (lru_gen_in_fault())
+		mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
+
 	if (workingset) {
-		/*
-		 * see folio_add_lru(), where folio_set_active() is
-		 * called for workingset folios
-		 */
-		if (lru_gen_in_fault())
-			mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
 		folio_set_workingset(folio);
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	} else
-- 
2.34.1

Re: [PATCH] mm/mglru: fix using folio_mark_accessed to replace folio_set_active

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] mm/mglru: lru_gen_folio_seq() demotes non-workingset active file folios
- [Medium] mm/mglru: lru_gen_refault() miscounts WORKINGSET_ACTIVATE_FILE
--

commit fa50b3cc1b1d64cb457afbbf37dc545c6d4e06f1
Author: Barry Song (Xiaomi) <baohua@kernel.org>

mm/mglru: fix using folio_mark_accessed to replace folio_set_active

This commit reverts the use of PG_referenced on in-fault readahead file
folios from commit 6cbdd9726fb5 ("mm/mglru: use folio_mark_accessed to
replace folio_set_active"), and instead adjusts lru_gen_folio_seq() to place
file folios with PG_active set and PG_workingset clear into the
third-youngest generation.

> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
> index ab69b9930893f..97f157aafd581 100644
> --- a/include/linux/mm_inline.h
> +++ b/include/linux/mm_inline.h
> @@ -319,7 +319,8 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
>  	 * |<---------------------------- MAX_NR_GENS ---------------------------->|
>  	 */
>  	if (folio_test_active(folio))
> -		gen = MIN_NR_GENS - folio_test_workingset(folio);
> +		gen = MIN_NR_GENS - folio_test_workingset(folio) +
> +		      (type ? !folio_test_workingset(folio) : 0);

[Severity: High]
Does assigning gen = 3 (lrugen->max_seq - 2) for all file folios (type == 1)
that have PG_active set and PG_workingset clear break other MGLRU paths that
set PG_active expecting the folio to land in an active generation?

First, in mm/vmscan.c, evict_folios() promotes folios rejected by
shrink_folio_list() out of min_seq[type] by clearing LRU_REFS_FLAGS and
setting PG_active:

mm/vmscan.c:evict_folios() {
	...
		folio_set_lru_refs(folio, 0);
		if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type])
			folio_set_active(folio);
	}

	move_folios_to_lru(&list, false);
}

When 3 generations exist (lrugen->max_seq - lrugen->min_seq[1] == 2),
max(lrugen->max_seq - 2, lrugen->min_seq[1]) equals min_seq[1]. A rejected
!PG_workingset file folio (for example, a mapped file folio spared via
FOLIOREF_KEEP on its first rmap scan in lru_gen_set_refs(), a DMA-pinned
folio, or a folio failing try_to_unmap()) has its PTE accessed bit and
PG_referenced cleared, and move_folios_to_lru() -> lru_gen_add_folio() puts
it right back into min_seq[1] instead of promoting it. Even when 4
generations exist, evict_folios() clears PG_referenced and puts the folio in
lrugen->max_seq - 2, so the next rmap scan in lru_gen_set_refs() sees
!folio_test_referenced(folio) && !folio_test_workingset(folio) again and can
never promote it to PG_workingset.

Second, in mm/vmscan.c, shrink_folio_list() sets PG_reclaim on dirty or
writeback file folios and jumps to activate_locked, which sets PG_active:

mm/vmscan.c:shrink_folio_list() {
	...
		if (folio_test_dirty(folio)) {
			if (folio_is_file_lru(folio)) {
				node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
						nr_pages);
				if (!folio_test_reclaim(folio))
					folio_set_reclaim(folio);

				goto activate_locked;
			}
	...
activate_locked:
	...
		folio_set_active(folio);
}

Because lru_gen_folio_seq() checks folio_test_active(folio) before the
PG_reclaim && (folio_test_dirty(folio) || folio_test_writeback(folio))
branch (which assigns gen = MIN_NR_GENS = 2), won't setting PG_active on a
!PG_workingset dirty or writeback file folio downgrade it from gen = 2
(active) to gen = 3 (inactive, or min_seq[1] when 3 generations exist)?

Third, when a !PG_workingset file folio is explicitly activated via
folio_activate() -> lru_activate(), or when it is isolated from the active
generation lrugen->max_seq - 1 for migration/compaction via
lru_gen_del_folio() (which sets BIT(PG_active) when !reclaiming &&
lru_gen_is_active(lruvec, gen)), re-adding it via lru_gen_add_folio() now
places it into lrugen->max_seq - 2 (LRU_INACTIVE_FILE). Doesn't this demote
activated and migrated active file folios into an inactive generation?

>  	else if (reclaiming)
>  		gen = MAX_NR_GENS;
>  	else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) ||
> @@ -327,7 +328,7 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
>  		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
>  		gen = MIN_NR_GENS;
>  	else
> -		gen = MAX_NR_GENS - (folio_test_workingset(folio) || folio_test_referenced(folio));
> +		gen = MAX_NR_GENS - folio_test_workingset(folio);
>  
>  	return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
>  }

[ ... ]

> diff --git a/mm/workingset.c b/mm/workingset.c
> index 1504f91cdca5f..10d4ce202cca4 100644
> --- a/mm/workingset.c
> +++ b/mm/workingset.c
> @@ -319,13 +319,11 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
>  
>  	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
>  
> +	/* see folio_add_lru() where folio_set_active() will be called */
> +	if (lru_gen_in_fault())
> +		mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
> +
>  	if (workingset) {
> -		/*
> -		 * see folio_add_lru(), where folio_set_active() is
> -		 * called for workingset folios
> -		 */
> -		if (lru_gen_in_fault())
> -			mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
>  		folio_set_workingset(folio);
>  		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
>  	} else

[Severity: Medium]
When a file folio (type == 1) refaults in a page fault with workingset ==
false, should WORKINGSET_ACTIVATE_FILE still be incremented here?

With workingset == false, PG_workingset is not set. Although folio_add_lru()
calls folio_set_active(folio), lru_gen_add_folio() clears PG_active and
lru_gen_folio_seq() now maps a file folio with PG_active and !PG_workingset
to gen = 3 (lrugen->max_seq - 2).

In include/linux/mm_inline.h, lru_gen_update_size() only accounts
lrugen->max_seq and lrugen->max_seq - 1 as active:

include/linux/mm_inline.h:lru_gen_update_size() {
	...
	/* addition */
	if (old_gen < 0) {
		if (lru_gen_is_active(lruvec, new_gen))
			lru += LRU_ACTIVE;
		__update_lru_size(lruvec, lru, zone, delta);
		return;
	}
	...
}

When 3 or more generations exist, the folio is added to LRU_INACTIVE_FILE,
so moving the mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type,
delta) call outside if (workingset) counts an activation for a file folio
that is placed in an inactive generation.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261016213115.70515-1-baohua@kernel.org?part=1

Re: [PATCH] mm/mglru: fix using folio_mark_accessed to replace folio_set_active

[Barry Song (Xiaomi)]

On Sun, Oct 18, 2026 at 5:31 AM <sashiko-bot@kernel.org> wrote:
>
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] mm/mglru: lru_gen_folio_seq() demotes non-workingset active file folios
> - [Medium] mm/mglru: lru_gen_refault() miscounts WORKINGSET_ACTIVATE_FILE
> --
>
> commit fa50b3cc1b1d64cb457afbbf37dc545c6d4e06f1
> Author: Barry Song (Xiaomi) <baohua@kernel.org>
>
> mm/mglru: fix using folio_mark_accessed to replace folio_set_active
>
> This commit reverts the use of PG_referenced on in-fault readahead file
> folios from commit 6cbdd9726fb5 ("mm/mglru: use folio_mark_accessed to
> replace folio_set_active"), and instead adjusts lru_gen_folio_seq() to place
> file folios with PG_active set and PG_workingset clear into the
> third-youngest generation.
>
> > diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
> > index ab69b9930893f..97f157aafd581 100644
> > --- a/include/linux/mm_inline.h
> > +++ b/include/linux/mm_inline.h
> > @@ -319,7 +319,8 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
> >        * |<---------------------------- MAX_NR_GENS ---------------------------->|
> >        */
> >       if (folio_test_active(folio))
> > -             gen = MIN_NR_GENS - folio_test_workingset(folio);
> > +             gen = MIN_NR_GENS - folio_test_workingset(folio) +
> > +                   (type ? !folio_test_workingset(folio) : 0);
>
> [Severity: High]
> Does assigning gen = 3 (lrugen->max_seq - 2) for all file folios (type == 1)
> that have PG_active set and PG_workingset clear break other MGLRU paths that
> set PG_active expecting the folio to land in an active generation?
>
> First, in mm/vmscan.c, evict_folios() promotes folios rejected by
> shrink_folio_list() out of min_seq[type] by clearing LRU_REFS_FLAGS and
> setting PG_active:
>
> mm/vmscan.c:evict_folios() {
>         ...
>                 folio_set_lru_refs(folio, 0);
>                 if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type])
>                         folio_set_active(folio);
>         }
>
>         move_folios_to_lru(&list, false);
> }
>
> When 3 generations exist (lrugen->max_seq - lrugen->min_seq[1] == 2),
> max(lrugen->max_seq - 2, lrugen->min_seq[1]) equals min_seq[1]. A rejected
> !PG_workingset file folio (for example, a mapped file folio spared via
> FOLIOREF_KEEP on its first rmap scan in lru_gen_set_refs(), a DMA-pinned
> folio, or a folio failing try_to_unmap()) has its PTE accessed bit and
> PG_referenced cleared, and move_folios_to_lru() -> lru_gen_add_folio() puts
> it right back into min_seq[1] instead of promoting it. Even when 4
> generations exist, evict_folios() clears PG_referenced and puts the folio in
> lrugen->max_seq - 2, so the next rmap scan in lru_gen_set_refs() sees
> !folio_test_referenced(folio) && !folio_test_workingset(folio) again and can
> never promote it to PG_workingset.
>
> Second, in mm/vmscan.c, shrink_folio_list() sets PG_reclaim on dirty or
> writeback file folios and jumps to activate_locked, which sets PG_active:
>
> mm/vmscan.c:shrink_folio_list() {
>         ...
>                 if (folio_test_dirty(folio)) {
>                         if (folio_is_file_lru(folio)) {
>                                 node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
>                                                 nr_pages);
>                                 if (!folio_test_reclaim(folio))
>                                         folio_set_reclaim(folio);
>
>                                 goto activate_locked;
>                         }
>         ...
> activate_locked:
>         ...
>                 folio_set_active(folio);
> }
>
> Because lru_gen_folio_seq() checks folio_test_active(folio) before the
> PG_reclaim && (folio_test_dirty(folio) || folio_test_writeback(folio))
> branch (which assigns gen = MIN_NR_GENS = 2), won't setting PG_active on a
> !PG_workingset dirty or writeback file folio downgrade it from gen = 2
> (active) to gen = 3 (inactive, or min_seq[1] when 3 generations exist)?
>
> Third, when a !PG_workingset file folio is explicitly activated via
> folio_activate() -> lru_activate(), or when it is isolated from the active
> generation lrugen->max_seq - 1 for migration/compaction via
> lru_gen_del_folio() (which sets BIT(PG_active) when !reclaiming &&
> lru_gen_is_active(lruvec, gen)), re-adding it via lru_gen_add_folio() now
> places it into lrugen->max_seq - 2 (LRU_INACTIVE_FILE). Doesn't this demote
> activated and migrated active file folios into an inactive generation?

Thanks. I guess the real problem is that we have no reliable way to
identify whether a folio comes from in-fault readahead. I've tried
various combinations of PG_ flags, but none of them works. So the
only solution seems to be separate LRU-add callbacks for readahead
file folios and other folios.

I've drafted a version below, but it's pretty ugly and feels like
using a sledgehammer to crack a nut for a quick fix — simply not
worth it. Maybe the best approach is to revert 6cbdd9726fb5 and
leave the proper fix to Kairui's MGLRU-FG.

Unless there are objections, I'll send a v2 that simply reverts
6cbdd9726fb5.

Subject: [Don'tMerge] mm/mglru: fix using folio_mark_accessed to replace
 folio_set_active

Commit 6cbdd9726fb5 ("mm/mglru: use folio_mark_accessed to
replace folio_set_active") attempted to avoid over-protecting
in-fault read-ahead file folios by placing them in the
second-oldest generation rather than the young generations.

However, it repurposes `PG_referenced` on in-fault read-ahead
file folios for this purpose, potentially coupling their
handling with that of regular file accesses through syscalls,
which also use `PG_referenced`.

This could regress some workloads, as reported by Kairui Song[1]
and Ehab Ababneh[2]. Many thanks to both for reporting these
issues!

The long-term fix is Kairui's MGLRU-FG, but in the meantime,
we also need a quick fix that can be backported to stable.

This patch reverts the original commit's abuse of `PG_referenced`
while preserving its goal of avoiding over-protection of
in-fault read-ahead file folios.

This also restores the `folio_set_workingset()` behavior to
what it was before commit 6cbdd9726fb5. We don't need
`folio_lru_refs(folio) > 1` to call `folio_set_workingset()`,
since `folio_add_lru()` no longer sets `PG_referenced`.

We can't reliably identify fault-readahead files using a
`PG_` flag. v1 tried `PG_active && !PG_workingset`, but
this doesn't work either, as some non-fault-readahead folios
can have the same flags.

An alternative approach used by this patch is to give
fault-readahead folios a separate code path (callback) for
adding them to the LRU.

Specifically, in-fault read-ahead file folios are placed in
the second-oldest generation (the third-youngest generation)
through dedicated functions.

Activated file folios and refaulted file folios remain in the
younger generations. Unlike the code before commit
6cbdd9726fb5, `folio_set_active()` is no longer always called
in `folio_add_lru()` for the `lru_gen_in_fault()` case.
Instead, it is called explicitly in the activation and refault
paths.

[1] https://lore.kernel.org/linux-mm/20261003-mglru-fg-v3-0-cbd4546a5bd9@tencent.com/
[2] https://lore.kernel.org/linux-mm/20260901180704.168106-1-ehab.ababneh@intel.com/
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 include/linux/mm_inline.h | 24 ++++++++++++-------
 mm/folio.c                | 50 ++++++++++++++++++++++++++++-----------
 mm/vmscan.c               | 14 ++++-------
 mm/workingset.c           | 11 ++++-----
 4 files changed, 61 insertions(+), 38 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index ab69b9930893..73acba1c0bc9 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -298,13 +298,17 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli
 	VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
 }
 
+#define LRU_GEN_ADD_RECLAIM	BIT(0)
+#define LRU_GEN_ADD_RA_FILE	BIT(1)
 static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
 					      const struct folio *folio,
-					      bool reclaiming)
+					      int types)
 {
 	int gen;
 	int type = folio_is_file_lru(folio);
 	const struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	bool reclaiming = !!(types & LRU_GEN_ADD_RECLAIM);
+	bool ra_file = !!(types & LRU_GEN_ADD_RA_FILE);
 
 	/*
 	 * +-----------------------------------+-----------------------------------+
@@ -318,7 +322,9 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
 	 * |<---------- MIN_NR_GENS ---------->|                                   |
 	 * |<---------------------------- MAX_NR_GENS ---------------------------->|
 	 */
-	if (folio_test_active(folio))
+	if (ra_file)
+		gen = MIN_NR_GENS + 1;
+	else if (folio_test_active(folio))
 		gen = MIN_NR_GENS - folio_test_workingset(folio);
 	else if (reclaiming)
 		gen = MAX_NR_GENS;
@@ -327,12 +333,12 @@ static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
 		gen = MIN_NR_GENS;
 	else
-		gen = MAX_NR_GENS - (folio_test_workingset(folio) || folio_test_referenced(folio));
+		gen = MAX_NR_GENS - folio_test_workingset(folio);
 
 	return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
 }
 
-static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
+static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, int types)
 {
 	unsigned long seq;
 	unsigned long flags;
@@ -346,7 +352,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
 
-	seq = lru_gen_folio_seq(lruvec, folio, reclaiming);
+	seq = lru_gen_folio_seq(lruvec, folio, types);
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
 	/* see the comment on MIN_NR_GENS about PG_active */
@@ -354,7 +360,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 
 	lru_gen_update_size(lruvec, folio, -1, gen);
 	/* for folio_rotate_reclaimable() */
-	if (reclaiming)
+	if (types & LRU_GEN_ADD_RECLAIM)
 		list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
 	else
 		list_add(&folio->lru, &lrugen->folios[gen][type][zone]);
@@ -415,7 +421,7 @@ static inline bool lru_gen_in_fault(void)
 	return false;
 }
 
-static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
+static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, int types)
 {
 	return false;
 }
@@ -439,7 +445,7 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
 
-	if (lru_gen_add_folio(lruvec, folio, false))
+	if (lru_gen_add_folio(lruvec, folio, 0))
 		return;
 
 	update_lru_size(lruvec, lru, folio_zonenum(folio),
@@ -455,7 +461,7 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
 
-	if (lru_gen_add_folio(lruvec, folio, true))
+	if (lru_gen_add_folio(lruvec, folio, LRU_GEN_ADD_RECLAIM))
 		return;
 
 	update_lru_size(lruvec, lru, folio_zonenum(folio),
diff --git a/mm/folio.c b/mm/folio.c
index 35e242b48870..1c2f067891e6 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -48,6 +48,7 @@ struct cpu_fbatches {
 	 */
 	local_lock_t lock;
 	struct folio_batch lru_add;
+	struct folio_batch lru_add_ra_file;
 	struct folio_batch lru_deactivate_file;
 	struct folio_batch lru_deactivate;
 	struct folio_batch lru_lazyfree;
@@ -109,7 +110,14 @@ EXPORT_SYMBOL(__folio_put);
 
 typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio);
 
-static void lru_add(struct lruvec *lruvec, struct folio *folio)
+static bool lruvec_add_ra_file_folio(struct lruvec *lruvec, struct folio *folio)
+{
+	VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
+
+	return lru_gen_add_folio(lruvec, folio, LRU_GEN_ADD_RA_FILE);
+}
+
+static void __lru_add(struct lruvec *lruvec, struct folio *folio, bool ra_file)
 {
 	int was_unevictable = folio_test_clear_unevictable(folio);
 	long nr_pages = folio_nr_pages(folio);
@@ -145,17 +153,31 @@ static void lru_add(struct lruvec *lruvec, struct folio *folio)
 			__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
 	}
 
+	if (ra_file && lruvec_add_ra_file_folio(lruvec, folio))
+		goto done;
+
 	lruvec_add_folio(lruvec, folio);
+done:
 	trace_mm_lru_insertion(folio);
 }
 
+static void lru_add(struct lruvec *lruvec, struct folio *folio)
+{
+	__lru_add(lruvec, folio, false);
+}
+
+static void lru_add_ra_file(struct lruvec *lruvec, struct folio *folio)
+{
+	__lru_add(lruvec, folio, true);
+}
+
 static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 {
 	int i;
 	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 	struct folio_batch free_fbatch;
-	bool is_lru_add = (move_fn == lru_add);
+	bool is_lru_add = (move_fn == lru_add || move_fn == lru_add_ra_file);
 
 	/*
 	 * If we're adding to the LRU, preemptively filter dead folios. Use
@@ -474,19 +496,12 @@ void folio_add_lru(struct folio *folio)
 			folio_test_unevictable(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-	/*
-	 * For refaulted workingset folios, set PG_active so they
-	 * can be added to active generations.
-	 * For prefaulted file folios, folio_mark_accessed() sets
-	 * PG_referenced so lru_gen_folio_seq() places them into
-	 * the second oldest generation.
-	 */
+	/* see the comment in lru_gen_folio_seq() */
 	if (lru_gen_enabled() && !folio_test_unevictable(folio) &&
-	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) {
-		if (folio_test_workingset(folio))
-			folio_set_active(folio);
-		else if (!folio_test_referenced(folio))
-			folio_mark_accessed(folio);
+	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC) &&
+	    folio_is_file_lru(folio) && !folio_test_active(folio)) {
+		folio_batch_add_and_move(folio, lru_add_ra_file);
+		return;
 	}
 
 	folio_batch_add_and_move(folio, lru_add);
@@ -631,6 +646,13 @@ void lru_add_drain_cpu(int cpu)
 		trace_mm_lru_add_drain_tp(cpu, nr_folios);
 	}
 
+	fbatch = &fbatches->lru_add_ra_file;
+	nr_folios = folio_batch_count(fbatch);
+	if (nr_folios) {
+		folio_batch_move_lru(fbatch, lru_add_ra_file);
+		trace_mm_lru_add_drain_tp(cpu, nr_folios);
+	}
+
 	fbatch = &fbatches->lru_move_tail;
 	/* Disabling interrupts below acts as a compiler barrier. */
 	if (data_race(folio_batch_count(fbatch))) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index daa7e37c2236..22d589275d95 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -952,13 +952,8 @@ static bool lru_gen_set_refs(struct folio *folio, const vma_flags_t *vma_flags)
 		return false;
 	}
 
-	/* Promote on second access */
-	if (folio_lru_refs(folio) > 1) {
-		folio_set_workingset(folio);
-		folio_set_lru_refs(folio, 0);
-	} else {
-		folio_mark_accessed(folio);
-	}
+	folio_set_workingset(folio);
+	folio_set_lru_refs(folio, 0);
 	return true;
 }
 #else
@@ -5527,10 +5522,11 @@ static bool fill_evictable(struct lruvec *lruvec)
 
 			lruvec_del_folio(lruvec, folio);
 			/*
-			 * Borrow reclaiming=true to place inactive folios in
+			 * Borrow LRU_GEN_ADD_RECLAIM to place inactive folios in
 			 * the older gens.
 			 */
-			success = lru_gen_add_folio(lruvec, folio, !active);
+			success = lru_gen_add_folio(lruvec, folio,
+						    active ? 0 : LRU_GEN_ADD_RECLAIM);
 			VM_WARN_ON_ONCE(!success);
 
 			if (!--remaining)
diff --git a/mm/workingset.c b/mm/workingset.c
index 1504f91cdca5..c9e42322d24c 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -319,13 +319,12 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 
 	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
 
+	if (lru_gen_in_fault()) {
+		folio_set_active(folio);
+		mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
+	}
+
 	if (workingset) {
-		/*
-		 * see folio_add_lru(), where folio_set_active() is
-		 * called for workingset folios
-		 */
-		if (lru_gen_in_fault())
-			mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
 		folio_set_workingset(folio);
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	} else
-- 
2.39.3 (Apple Git-146)