* [PATCH v2 1/2] mm: vmscan: convert folio_referenced() to use vma_flags_t
2026-07-16 10:46 [PATCH v2 0/2] promote mapped executable folios after first usage for MGLRU Baolin Wang
@ 2026-07-16 10:46 ` Baolin Wang
2026-07-16 11:00 ` David Hildenbrand (Arm)
2026-07-16 10:46 ` [PATCH v2 2/2] mm: mglru: promote mapped executable folios after first usage Baolin Wang
1 sibling, 1 reply; 6+ messages in thread
From: Baolin Wang @ 2026-07-16 10:46 UTC (permalink / raw)
To: akpm, david, ljs, hannes
Cc: riel, liam, vbabka, harry, jannh, lance.yang, kasong, qi.zheng,
shakeel.butt, baohua, axelrasmussen, yuanchu, weixugc, mhocko,
baolin.wang, linux-mm, linux-kernel
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>
---
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 e854679553b9..4085540b6a25 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 986dde8e7429..de62899c108d 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;
@@ -2065,7 +2065,7 @@ 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);
@@ -2109,7 +2109,7 @@ 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
@@ -2119,7 +2119,7 @@ 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
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v2 2/2] mm: mglru: promote mapped executable folios after first usage
2026-07-16 10:46 [PATCH v2 0/2] promote mapped executable folios after first usage for MGLRU Baolin Wang
2026-07-16 10:46 ` [PATCH v2 1/2] mm: vmscan: convert folio_referenced() to use vma_flags_t Baolin Wang
@ 2026-07-16 10:46 ` Baolin Wang
2026-07-16 11:10 ` David Hildenbrand (Arm)
1 sibling, 1 reply; 6+ messages in thread
From: Baolin Wang @ 2026-07-16 10:46 UTC (permalink / raw)
To: akpm, david, ljs, hannes
Cc: riel, liam, vbabka, harry, jannh, lance.yang, kasong, qi.zheng,
shakeel.butt, baohua, axelrasmussen, yuanchu, weixugc, mhocko,
baolin.wang, linux-mm, linux-kernel
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>
---
include/linux/mm_inline.h | 6 ++++++
mm/vmscan.c | 41 ++++++++++++++++++++++++---------------
2 files changed, 31 insertions(+), 16 deletions(-)
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index b5c4dc0f3fe3..30fdf1056312 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -30,6 +30,12 @@ static inline int folio_is_file_lru(const struct folio *folio)
return !folio_test_swapbacked(folio);
}
+static inline bool folio_is_exec_file(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 __always_inline void __update_lru_size(struct lruvec *lruvec,
enum lru_list lru, enum zone_type zid,
long nr_pages)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index de62899c108d..fa808721b64d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -835,11 +835,15 @@ 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)) {
set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
+ /* Activate file-backed executable folios after first usage. */
+ if (folio_is_exec_file(folio, vma_flags))
+ return true;
+
return false;
}
@@ -851,7 +855,7 @@ 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;
}
@@ -886,7 +890,7 @@ 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);
@@ -914,7 +918,7 @@ 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 (folio_is_exec_file(folio, &vma_flags))
return FOLIOREF_ACTIVATE;
return FOLIOREF_KEEP;
@@ -2119,7 +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 (folio_is_exec_file(folio, &vma_flags)) {
nr_rotated += folio_nr_pages(folio);
list_add(&folio->lru, &l_active);
continue;
@@ -3188,7 +3192,7 @@ 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);
@@ -3196,10 +3200,15 @@ static int folio_update_gen(struct folio *folio, int gen)
/* 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 (folio_is_exec_file(folio, vma_flags))
+ goto promote;
+
set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
return -1;
}
+promote:
do {
/* lru_gen_del_folio() has isolated this page? */
if (!(old_flags & LRU_GEN_MASK))
@@ -3428,8 +3437,8 @@ 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;
@@ -3442,10 +3451,10 @@ 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);
@@ -3518,7 +3527,7 @@ 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;
@@ -3531,7 +3540,7 @@ 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))
@@ -3609,7 +3618,7 @@ 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;
@@ -3623,7 +3632,7 @@ 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);
@@ -4258,7 +4267,7 @@ 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;
@@ -4270,7 +4279,7 @@ 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
^ permalink raw reply related [flat|nested] 6+ messages in thread