From: Yu Zhao <yuzhao@google.com>

When the MM_WALK capability is enabled, memory that is mostly accessed
by a VM appears younger than it really is, therefore this memory will be
less likely to be evicted. Therefore, the presence of a running VM can
significantly increase swap-outs for non-VM memory, regressing the
performance for the rest of the system.

Fix this regression by always calling {ptep,pmdp}_clear_young_notify()
whenever we clear the young bits on PMDs/PTEs.

Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
Reported-by: David Stevens <stevensd@google.com>
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
---
 include/linux/mmzone.h |  5 ++-
 mm/rmap.c              |  9 ++---
 mm/vmscan.c            | 91 +++++++++++++++++++++++-------------------
 3 files changed, 55 insertions(+), 50 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 691c635d8d1f..2e8c4307c728 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -557,7 +557,7 @@ struct lru_gen_memcg {
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
 void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -576,8 +576,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 }
 
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
+	return false;
 }
 
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
diff --git a/mm/rmap.c b/mm/rmap.c
index 2c561b1e52cc..4785a693857a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -896,13 +896,10 @@ static bool folio_referenced_one(struct folio *folio,
 			return false;
 		}
 
-		if (pvmw.pte) {
-			if (lru_gen_enabled() &&
-			    pte_young(ptep_get(pvmw.pte))) {
-				lru_gen_look_around(&pvmw);
+		if (lru_gen_enabled() && pvmw.pte) {
+			if (lru_gen_look_around(&pvmw))
 				referenced++;
-			}
-
+		} else if (pvmw.pte) {
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte))
 				referenced++;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 60669f8bba46..29c098790b01 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -56,6 +56,7 @@
 #include <linux/khugepaged.h>
 #include <linux/rculist_nulls.h>
 #include <linux/random.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -3293,7 +3294,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk
 	return false;
 }
 
-static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -3305,13 +3307,20 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
 		return -1;
 
+	if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
-static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pmd_pfn(pmd);
 
@@ -3323,9 +3332,15 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pmd_devmap(pmd)))
 		return -1;
 
+	if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
@@ -3334,10 +3349,6 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
 {
 	struct folio *folio;
 
-	/* try to avoid unnecessary memory loads */
-	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-		return NULL;
-
 	folio = pfn_folio(pfn);
 	if (folio_nid(folio) != pgdat->node_id)
 		return NULL;
@@ -3400,20 +3411,16 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 		total++;
 		walk->mm_stats[MM_LEAF_TOTAL]++;
 
-		pfn = get_pte_pfn(ptent, args->vma, addr);
+		pfn = get_pte_pfn(ptent, args->vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent)) {
-			continue;
-		}
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
+			continue;
 
 		young++;
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3479,21 +3486,22 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		/* don't round down the first address */
 		addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
 
-		pfn = get_pmd_pfn(pmd[i], vma, addr);
-		if (pfn == -1)
-			goto next;
-
-		if (!pmd_trans_huge(pmd[i])) {
-			if (!walk->force_scan && should_clear_pmd_young())
+		if (pmd_present(pmd[i]) && !pmd_trans_huge(pmd[i])) {
+			if (!walk->force_scan && should_clear_pmd_young() &&
+			    !mm_has_notifiers(args->mm))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
 		}
 
+		pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat);
+		if (pfn == -1)
+			goto next;
+
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			goto next;
 
-		if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
+		if (!pmdp_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3551,24 +3559,18 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 		}
 
 		if (pmd_trans_huge(val)) {
-			unsigned long pfn = pmd_pfn(val);
 			struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+			unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat);
 
 			walk->mm_stats[MM_LEAF_TOTAL]++;
 
-			if (!pmd_young(val)) {
-				continue;
-			}
-
-			/* try to avoid unnecessary memory loads */
-			if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-				continue;
-
-			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
+			if (pfn != -1)
+				walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 			continue;
 		}
 
-		if (!walk->force_scan && should_clear_pmd_young()) {
+		if (!walk->force_scan && should_clear_pmd_young() &&
+		    !mm_has_notifiers(args->mm)) {
 			if (!pmd_young(val))
 				continue;
 
@@ -4042,13 +4044,13 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
  * the PTE table to the Bloom filter. This forms a feedback loop between the
  * eviction and the aging.
  */
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 	int i;
 	unsigned long start;
 	unsigned long end;
 	struct lru_gen_mm_walk *walk;
-	int young = 0;
+	int young = 1;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
@@ -4064,12 +4066,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
 
+	if (!ptep_clear_young_notify(vma, addr, pte))
+		return false;
+
 	if (spin_is_contended(pvmw->ptl))
-		return;
+		return true;
 
 	/* exclude special VMAs containing anon pages from COW */
 	if (vma->vm_flags & VM_SPECIAL)
-		return;
+		return true;
 
 	/* avoid taking the LRU lock under the PTL when possible */
 	walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
@@ -4077,6 +4082,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	start = max(addr & PMD_MASK, vma->vm_start);
 	end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
 
+	if (end - start == PAGE_SIZE)
+		return true;
+
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
 			end = start + MIN_LRU_BATCH * PAGE_SIZE;
@@ -4090,7 +4098,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 
 	/* folio_update_gen() requires stable folio_memcg() */
 	if (!mem_cgroup_trylock_pages(memcg))
-		return;
+		return true;
 
 	arch_enter_lazy_mmu_mode();
 
@@ -4100,19 +4108,16 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		unsigned long pfn;
 		pte_t ptent = ptep_get(pte + i);
 
-		pfn = get_pte_pfn(ptent, vma, addr);
+		pfn = get_pte_pfn(ptent, vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent))
-			continue;
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(vma, addr, pte + i))
+			continue;
 
 		young++;
 
@@ -4144,6 +4149,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	/* feedback from rmap walkers to page table walkers */
 	if (mm_state && suitable_to_scan(i, young))
 		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
+
+	return true;
 }
 
 /******************************************************************************
-- 
2.47.0.105.g07ac214952-goog