mm: vmscan: refactor move_folios_to_lru()

In a subsequent patch, we'll reparent the LRU folios.  The folios that are
moved to the appropriate LRU list can undergo reparenting during the
move_folios_to_lru() process.  Hence, it's incorrect for the caller to
hold a lruvec lock.  Instead, we should utilize the more general interface
of folio_lruvec_relock_irq() to obtain the correct lruvec lock.

This patch involves only code refactoring and doesn't introduce any
functional changes.

Link: https://lore.kernel.org/6f1dac88b61e2e3cb7a3e90bacdf06b654acfc15.1772711148.git.zhengqi.arch@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Allen Pais <apais@linux.microsoft.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Chen Ridong <chenridong@huawei.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Imran Khan <imran.f.khan@oracle.com>
Cc: Kamalesh Babulal <kamalesh.babulal@oracle.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yosry Ahmed <yosry@kernel.org>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 21 insertions, 25 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d88d00f0c2cd..031fbd35ae10 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1885,24 +1885,27 @@ static bool too_many_isolated(struct pglist_data *pgdat, int file,
 /*
  * move_folios_to_lru() moves folios from private @list to appropriate LRU list.
  *
- * Returns the number of pages moved to the given lruvec.
+ * Returns the number of pages moved to the appropriate lruvec.
+ *
+ * Note: The caller must not hold any lruvec lock.
  */
-static unsigned int move_folios_to_lru(struct lruvec *lruvec,
-		struct list_head *list)
+static unsigned int move_folios_to_lru(struct list_head *list)
 {
 	int nr_pages, nr_moved = 0;
+	struct lruvec *lruvec = NULL;
 	struct folio_batch free_folios;
 
 	folio_batch_init(&free_folios);
 	while (!list_empty(list)) {
 		struct folio *folio = lru_to_folio(list);
 
+		lruvec = folio_lruvec_relock_irq(folio, lruvec);
 		VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 		list_del(&folio->lru);
 		if (unlikely(!folio_evictable(folio))) {
-			spin_unlock_irq(&lruvec->lru_lock);
+			lruvec_unlock_irq(lruvec);
 			folio_putback_lru(folio);
-			spin_lock_irq(&lruvec->lru_lock);
+			lruvec = NULL;
 			continue;
 		}
 
@@ -1924,19 +1927,15 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
 
 			folio_unqueue_deferred_split(folio);
 			if (folio_batch_add(&free_folios, folio) == 0) {
-				spin_unlock_irq(&lruvec->lru_lock);
+				lruvec_unlock_irq(lruvec);
 				mem_cgroup_uncharge_folios(&free_folios);
 				free_unref_folios(&free_folios);
-				spin_lock_irq(&lruvec->lru_lock);
+				lruvec = NULL;
 			}
 
 			continue;
 		}
 
-		/*
-		 * All pages were isolated from the same lruvec (and isolation
-		 * inhibits memcg migration).
-		 */
 		VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
 		lruvec_add_folio(lruvec, folio);
 		nr_pages = folio_nr_pages(folio);
@@ -1945,11 +1944,12 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
 			workingset_age_nonresident(lruvec, nr_pages);
 	}
 
+	if (lruvec)
+		lruvec_unlock_irq(lruvec);
+
 	if (free_folios.nr) {
-		spin_unlock_irq(&lruvec->lru_lock);
 		mem_cgroup_uncharge_folios(&free_folios);
 		free_unref_folios(&free_folios);
-		spin_lock_irq(&lruvec->lru_lock);
 	}
 
 	return nr_moved;
@@ -2016,8 +2016,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false,
 					 lruvec_memcg(lruvec));
 
-	spin_lock_irq(&lruvec->lru_lock);
-	move_folios_to_lru(lruvec, &folio_list);
+	move_folios_to_lru(&folio_list);
 
 	mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc),
 					stat.nr_demoted);
@@ -2026,6 +2025,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	mod_lruvec_state(lruvec, item, nr_reclaimed);
 	mod_lruvec_state(lruvec, PGSTEAL_ANON + file, nr_reclaimed);
 
+	spin_lock_irq(&lruvec->lru_lock);
 	lru_note_cost_unlock_irq(lruvec, file, stat.nr_pageout,
 					nr_scanned - nr_reclaimed);
 
@@ -2162,16 +2162,14 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move folios back to the lru list.
 	 */
-	spin_lock_irq(&lruvec->lru_lock);
-
-	nr_activate = move_folios_to_lru(lruvec, &l_active);
-	nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);
+	nr_activate = move_folios_to_lru(&l_active);
+	nr_deactivate = move_folios_to_lru(&l_inactive);
 
 	count_vm_events(PGDEACTIVATE, nr_deactivate);
 	count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
-
 	mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 
+	spin_lock_irq(&lruvec->lru_lock);
 	lru_note_cost_unlock_irq(lruvec, file, 0, nr_rotated);
 	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
 			nr_deactivate, nr_rotated, sc->priority, file);
@@ -4749,14 +4747,14 @@ retry:
 			set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_active));
 	}
 
-	spin_lock_irq(&lruvec->lru_lock);
-
-	move_folios_to_lru(lruvec, &list);
+	move_folios_to_lru(&list);
 
 	walk = current->reclaim_state->mm_walk;
 	if (walk && walk->batched) {
 		walk->lruvec = lruvec;
+		spin_lock_irq(&lruvec->lru_lock);
 		reset_batch_size(walk);
+		spin_unlock_irq(&lruvec->lru_lock);
 	}
 
 	mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc),
@@ -4766,8 +4764,6 @@ retry:
 	mod_lruvec_state(lruvec, item, reclaimed);
 	mod_lruvec_state(lruvec, PGSTEAL_ANON + type, reclaimed);
 
-	spin_unlock_irq(&lruvec->lru_lock);
-
 	list_splice_init(&clean, &list);
 
 	if (!list_empty(&list)) {