[PATCH] 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() 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.

Follow the classical LRU's logic, promoting mapped executable file folios
after their first usage in folio_update_gen(), 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@xxxxxxxxxxxxxxxxx>
---
 mm/vmscan.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 986dde8e7429..429857852bdb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3188,7 +3188,7 @@ 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 vm_area_struct *vma, struct folio *folio, int gen)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f);
 
@@ -3196,10 +3196,15 @@ 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 (vma_test(vma, VMA_EXEC_BIT) && folio_is_file_lru(folio))
+			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 +3433,8 @@ 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;
 
@@ -3442,7 +3447,7 @@ 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(vma, folio, new_gen);
 		if (old_gen >= 0 && old_gen != new_gen)
 			update_batch_size(walk, folio, old_gen, new_gen);
 	} else if (lru_gen_set_refs(folio)) {
@@ -3518,7 +3523,7 @@ 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 +3536,7 @@ 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 +3614,7 @@ 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 +3628,7 @@ 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 +4263,7 @@ 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 +4275,7 @@ 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