[PATCH v4 0/3] promote mapped executable folios after first usage for MGLRU

[PATCH v4 0/3] promote mapped executable folios after first usage for MGLRU

[Baolin Wang]

Now MGLRU's protection of mapped executable file folios is less reliable.
Follow the classical LRU's logic, promoting mapped executable file folios
after their first usage to give executable code a better chance to stay in
memory and improve workload performance (See patch 2 for more details).

Changes from v3:
https://lore.kernel.org/all/cover.1784268206.git.baolin.wang@linux.alibaba.com/
 - Collect tags from Johannes, Axel, Barry and Kairui. Thanks.
 - Split the helper addition out into a separate patch (per Johannes).
 - Set PG_workingset before promoting in lru_gen_set_refs() (per Kairui).
 - Some code cleanups (per Kairui).

Changes from v2:
https://lore.kernel.org/all/cover.1784197559.git.baolin.wang@linux.alibaba.com/
 - Add acked tag from David. Thanks.
 - Rename the exec-file-folio helper and move it into vmscan.c (per David).

Changes from v1:
https://lore.kernel.org/all/4b921ed528c483e13c9e22d1ae44ba58b4a15b0b.1784096432.git.baolin.wang@linux.alibaba.com/
 - Add a new patch to clean up vma flags as preparation.
 - Add a new helper to check exec file folios (per Kaisui).
 - Promote exec file folios in lru_gen_set_refs (Per Sashiko).

Baolin Wang (3):
  mm: vmscan: convert folio_referenced() to use vma_flags_t
  mm: vmscan: add a helper to identify file-backed executable folios
  mm: mglru: promote mapped executable folios after first usage

 include/linux/rmap.h |  7 +++--
 mm/rmap.c            | 19 +++++++------
 mm/vmscan.c          | 63 ++++++++++++++++++++++++++++----------------
 3 files changed, 54 insertions(+), 35 deletions(-)

-- 
2.47.3

[PATCH v4 1/3] mm: vmscan: convert folio_referenced() to use vma_flags_t

[Baolin Wang]

Replace use of the legacy vm_flags_t flags with vma_flags_t values for
folio_referenced() and related logic. This is also a preparation for the
following changes.

No functional changes.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
---
 include/linux/rmap.h |  7 +++----
 mm/rmap.c            | 19 +++++++++++--------
 mm/vmscan.c          | 14 +++++++-------
 3 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 8dc0871e5f00..e090aa09825d 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -843,7 +843,7 @@ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
  * Called from mm/vmscan.c to handle paging out
  */
 int folio_referenced(struct folio *, int is_locked,
-			struct mem_cgroup *memcg, vm_flags_t *vm_flags);
+		struct mem_cgroup *memcg, vma_flags_t *vma_flags);
 
 void try_to_migrate(struct folio *folio, enum ttu_flags flags);
 void try_to_unmap(struct folio *, enum ttu_flags flags);
@@ -975,10 +975,9 @@ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
 #define anon_vma_prepare(vma)	(0)
 
 static inline int folio_referenced(struct folio *folio, int is_locked,
-				  struct mem_cgroup *memcg,
-				  vm_flags_t *vm_flags)
+		struct mem_cgroup *memcg, vma_flags_t *vma_flags)
 {
-	*vm_flags = 0;
+	vma_flags_clear_all(vma_flags);
 	return 0;
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index ad820fe86f7d..73c2fe2d1946 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -907,7 +907,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 struct folio_referenced_arg {
 	int mapcount;
 	int referenced;
-	vm_flags_t vm_flags;
+	vma_flags_t vma_flags;
 	struct mem_cgroup *memcg;
 };
 
@@ -926,7 +926,7 @@ static bool folio_referenced_one(struct folio *folio,
 		address = pvmw.address;
 		nr = 1;
 
-		if (vma->vm_flags & VM_LOCKED) {
+		if (vma_test(vma, VMA_LOCKED_BIT)) {
 			ptes++;
 			pra->mapcount--;
 
@@ -947,7 +947,7 @@ static bool folio_referenced_one(struct folio *folio,
 			/* Restore the mlock which got missed */
 			mlock_vma_folio(folio, vma);
 			page_vma_mapped_walk_done(&pvmw);
-			pra->vm_flags |= VM_LOCKED;
+			vma_flags_set(&pra->vma_flags, VMA_LOCKED_BIT);
 			return false; /* To break the loop */
 		}
 
@@ -1015,8 +1015,11 @@ static bool folio_referenced_one(struct folio *folio,
 		referenced++;
 
 	if (referenced) {
+		vma_flags_t vma_flags = vma->flags;
+
 		pra->referenced++;
-		pra->vm_flags |= vma->vm_flags & ~VM_LOCKED;
+		vma_flags_clear(&vma_flags, VMA_LOCKED_BIT);
+		vma_flags_set_mask(&pra->vma_flags, vma_flags);
 	}
 
 	if (!pra->mapcount)
@@ -1054,7 +1057,7 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
  * @folio: The folio to test.
  * @is_locked: Caller holds lock on the folio.
  * @memcg: target memory cgroup
- * @vm_flags: A combination of all the vma->vm_flags which referenced the folio.
+ * @vma_flags: A combination of all the vma->flags which referenced the folio.
  *
  * Quick test_and_clear_referenced for all mappings of a folio,
  *
@@ -1062,7 +1065,7 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
  * the function bailed out due to rmap lock contention.
  */
 int folio_referenced(struct folio *folio, int is_locked,
-		     struct mem_cgroup *memcg, vm_flags_t *vm_flags)
+		struct mem_cgroup *memcg, vma_flags_t *vma_flags)
 {
 	bool we_locked = false;
 	struct folio_referenced_arg pra = {
@@ -1078,7 +1081,7 @@ int folio_referenced(struct folio *folio, int is_locked,
 	};
 
 	VM_WARN_ON_ONCE_FOLIO(folio_is_zone_device(folio), folio);
-	*vm_flags = 0;
+	vma_flags_clear_all(vma_flags);
 	if (!pra.mapcount)
 		return 0;
 
@@ -1092,7 +1095,7 @@ int folio_referenced(struct folio *folio, int is_locked,
 	}
 
 	rmap_walk(folio, &rwc);
-	*vm_flags = pra.vm_flags;
+	vma_flags_set_mask(vma_flags, pra.vma_flags);
 
 	if (we_locked)
 		folio_unlock(folio);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7ef032e78a0..11357b86ba2c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -861,16 +861,16 @@ static enum folio_references folio_check_references(struct folio *folio,
 						  struct scan_control *sc)
 {
 	int referenced_ptes, referenced_folio;
-	vm_flags_t vm_flags;
+	vma_flags_t vma_flags;
 
 	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
-					   &vm_flags);
+					   &vma_flags);
 
 	/*
 	 * The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
 	 * Let the folio, now marked Mlocked, be moved to the unevictable list.
 	 */
-	if (vm_flags & VM_LOCKED)
+	if (vma_flags_test(&vma_flags, VMA_LOCKED_BIT))
 		return FOLIOREF_ACTIVATE;
 
 	/*
@@ -914,7 +914,7 @@ static enum folio_references folio_check_references(struct folio *folio,
 		/*
 		 * Activate file-backed executable folios after first usage.
 		 */
-		if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio))
+		if (vma_flags_test(&vma_flags, VMA_EXEC_BIT) && folio_is_file_lru(folio))
 			return FOLIOREF_ACTIVATE;
 
 		return FOLIOREF_KEEP;
@@ -2063,7 +2063,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 {
 	unsigned long nr_taken;
 	unsigned long nr_scanned;
-	vm_flags_t vm_flags;
+	vma_flags_t vma_flags;
 	LIST_HEAD(l_hold);	/* The folios which were snipped off */
 	LIST_HEAD(l_active);
 	LIST_HEAD(l_inactive);
@@ -2107,7 +2107,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 		/* Referenced or rmap lock contention: rotate */
 		if (folio_referenced(folio, 0, sc->target_mem_cgroup,
-				     &vm_flags) != 0) {
+				     &vma_flags) != 0) {
 			/*
 			 * Identify referenced, file-backed active folios and
 			 * give them one more trip around the active list. So
@@ -2117,7 +2117,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			 * IO, plus JVM can create lots of anon VM_EXEC folios,
 			 * so we ignore them here.
 			 */
-			if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
+			if (vma_flags_test(&vma_flags, VMA_EXEC_BIT) && folio_is_file_lru(folio)) {
 				nr_rotated += folio_nr_pages(folio);
 				list_add(&folio->lru, &l_active);
 				continue;
-- 
2.47.3

[PATCH v4 2/3] mm: vmscan: add a helper to identify file-backed executable folios

[Baolin Wang]

Add a helper to identify file-backed executable folios to avoid
duplicate code.

No functional changes.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
---
 mm/vmscan.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 11357b86ba2c..8f0c31a4848e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -268,6 +268,12 @@ static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
 }
 #endif
 
+static inline bool is_exec_file_folio(const struct folio *folio,
+		const vma_flags_t *vma_flags)
+{
+	return vma_flags_test(vma_flags, VMA_EXEC_BIT) && folio_is_file_lru(folio);
+}
+
 static void set_task_reclaim_state(struct task_struct *task,
 				   struct reclaim_state *rs)
 {
@@ -914,7 +920,7 @@ static enum folio_references folio_check_references(struct folio *folio,
 		/*
 		 * Activate file-backed executable folios after first usage.
 		 */
-		if (vma_flags_test(&vma_flags, VMA_EXEC_BIT) && folio_is_file_lru(folio))
+		if (is_exec_file_folio(folio, &vma_flags))
 			return FOLIOREF_ACTIVATE;
 
 		return FOLIOREF_KEEP;
@@ -2117,7 +2123,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			 * IO, plus JVM can create lots of anon VM_EXEC folios,
 			 * so we ignore them here.
 			 */
-			if (vma_flags_test(&vma_flags, VMA_EXEC_BIT) && folio_is_file_lru(folio)) {
+			if (is_exec_file_folio(folio, &vma_flags)) {
 				nr_rotated += folio_nr_pages(folio);
 				list_add(&folio->lru, &l_active);
 				continue;
-- 
2.47.3

[PATCH v4 3/3] mm: mglru: promote mapped executable folios after first usage

[Baolin Wang]

Classical LRU protects mapped executable file folios through commit
8cab4754d24a0 ("vmscan: make mapped executable pages the first class
citizen") and commit c909e99364c8 ("vmscan: activate executable pages
after first usage"), giving executable code a better chance to stay in
memory, avoiding IO thrashing and improving workload performance.

However, MGLRU's protection of mapped executable file folios is less
reliable. Although shrink_folio_list() checks references, the access flag
of mapped executable file folios may have already been checked and
cleared by lru_gen_look_around() or walk_mm(). Additionally,
folio_update_gen() or lru_gen_set_refs() only sets the 'PG_referenced'
flag for mapped executable file folios, which causes shrink_folio_list()
to ignore the first usage of these mapped executable file folios and
reclaim them easily.

Follow the classical LRU's logic, promoting mapped executable file folios
after their first usage in folio_update_gen() and lru_gen_set_refs(),
giving executable code a better chance to stay in memory.

On my 32-core Arm machine, with the memcg limit set to 2G, running
'make -j32' to build kernel showed some improvement in sys time.

base			patched
9248.543s		7861.579s

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
---
 mm/vmscan.c | 43 +++++++++++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 16 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8f0c31a4848e..b1ec65fb8947 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -841,10 +841,16 @@ enum folio_references {
  * with PG_active set. In contrast, the aging (page table walk) path uses
  * folio_update_gen().
  */
-static bool lru_gen_set_refs(struct folio *folio)
+static bool lru_gen_set_refs(struct folio *folio, const vma_flags_t *vma_flags)
 {
 	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+		/* Activate file-backed executable folios after first usage. */
+		if (is_exec_file_folio(folio, vma_flags)) {
+			set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_workingset));
+			return true;
+		}
+
 		set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
 		return false;
 	}
@@ -857,7 +863,7 @@ static bool lru_gen_set_refs(struct folio *folio)
 	return true;
 }
 #else
-static bool lru_gen_set_refs(struct folio *folio)
+static bool lru_gen_set_refs(struct folio *folio, const vma_flags_t *vma_flags)
 {
 	return false;
 }
@@ -892,7 +898,7 @@ static enum folio_references folio_check_references(struct folio *folio,
 		if (!referenced_ptes)
 			return FOLIOREF_RECLAIM;
 
-		return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP;
+		return lru_gen_set_refs(folio, &vma_flags) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP;
 	}
 
 	referenced_folio = folio_test_clear_referenced(folio);
@@ -3192,14 +3198,19 @@ 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 gen)
+static int folio_update_gen(struct folio *folio, int gen, const vma_flags_t *vma_flags)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f);
 
 	VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
 
-	/* see the comment on LRU_REFS_FLAGS */
-	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+	/*
+	 * See the comment on LRU_REFS_FLAGS, and activate file-backed
+	 * executable folios after first usage to avoid typical IO
+	 * thrashing from reclaiming.
+	 */
+	if (!folio_test_referenced(folio) && !folio_test_workingset(folio) &&
+	    !is_exec_file_folio(folio, vma_flags)) {
 		set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
 		return -1;
 	}
@@ -3432,8 +3443,8 @@ static bool suitable_to_scan(int total, int young)
 	return young * n >= total;
 }
 
-static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio,
-			      int new_gen, bool dirty)
+static void walk_update_folio(struct lru_gen_mm_walk *walk, struct vm_area_struct *vma,
+		struct folio *folio, int new_gen, bool dirty)
 {
 	int old_gen;
 
@@ -3446,10 +3457,10 @@ static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio,
 		folio_mark_dirty(folio);
 
 	if (walk) {
-		old_gen = folio_update_gen(folio, new_gen);
+		old_gen = folio_update_gen(folio, new_gen, &vma->flags);
 		if (old_gen >= 0 && old_gen != new_gen)
 			update_batch_size(walk, folio, old_gen, new_gen);
-	} else if (lru_gen_set_refs(folio)) {
+	} else if (lru_gen_set_refs(folio, &vma->flags)) {
 		old_gen = folio_lru_gen(folio);
 		if (old_gen >= 0 && old_gen != new_gen)
 			folio_activate(folio);
@@ -3522,7 +3533,7 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 			continue;
 
 		if (last != folio) {
-			walk_update_folio(walk, last, gen, dirty);
+			walk_update_folio(walk, args->vma, last, gen, dirty);
 
 			last = folio;
 			dirty = false;
@@ -3535,7 +3546,7 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 		walk->mm_stats[MM_LEAF_YOUNG] += nr;
 	}
 
-	walk_update_folio(walk, last, gen, dirty);
+	walk_update_folio(walk, args->vma, last, gen, dirty);
 	last = NULL;
 
 	if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end))
@@ -3613,7 +3624,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 			goto next;
 
 		if (last != folio) {
-			walk_update_folio(walk, last, gen, dirty);
+			walk_update_folio(walk, vma, last, gen, dirty);
 
 			last = folio;
 			dirty = false;
@@ -3627,7 +3638,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1;
 	} while (i <= MIN_LRU_BATCH);
 
-	walk_update_folio(walk, last, gen, dirty);
+	walk_update_folio(walk, vma, last, gen, dirty);
 
 	lazy_mmu_mode_disable();
 	spin_unlock(ptl);
@@ -4262,7 +4273,7 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr)
 			continue;
 
 		if (last != folio) {
-			walk_update_folio(walk, last, gen, dirty);
+			walk_update_folio(walk, vma, last, gen, dirty);
 
 			last = folio;
 			dirty = false;
@@ -4274,7 +4285,7 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr)
 		young += nr;
 	}
 
-	walk_update_folio(walk, last, gen, dirty);
+	walk_update_folio(walk, vma, last, gen, dirty);
 
 	lazy_mmu_mode_disable();
 
-- 
2.47.3

Re: [PATCH v4 2/3] mm: vmscan: add a helper to identify file-backed executable folios

[David Hildenbrand (Arm)]

On 7/20/26 12:12, Baolin Wang wrote:
> Add a helper to identify file-backed executable folios to avoid
> duplicate code.
> 
> No functional changes.
> 
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
> ---

Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>

-- 
Cheers,

David

Re: [PATCH v4 2/3] mm: vmscan: add a helper to identify file-backed executable folios

[Kairui Song]

On Mon, Jul 20, 2026 at 7:13 PM Baolin Wang
<baolin.wang@linux.alibaba.com> wrote:
>
> Add a helper to identify file-backed executable folios to avoid
> duplicate code.
>
> No functional changes.
>
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
> ---
>  mm/vmscan.c | 10 ++++++++--
>  1 file changed, 8 insertions(+), 2 deletions(-)
>

Reviewed-by: Kairui Song <kasong@tencent.com>