1 files changed, 37 insertions, 34 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7de11524a936..b2fc8b626d3d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -398,14 +398,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
 		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
 			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
-	/*
-	 * If there are no reclaimable file-backed or anonymous pages,
-	 * ensure zones with sufficient free pages are not skipped.
-	 * This prevents zones like DMA32 from being ignored in reclaim
-	 * scenarios where they can still help alleviate memory pressure.
-	 */
-	if (nr == 0)
-		nr = zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
 	return nr;
 }
 
@@ -525,7 +518,7 @@ static bool skip_throttle_noprogress(pg_data_t *pgdat)
 	 * If kswapd is disabled, reschedule if necessary but do not
 	 * throttle as the system is likely near OOM.
 	 */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	/*
@@ -737,13 +730,18 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 {
 	int refcount;
 	void *shadow = NULL;
+	struct swap_cluster_info *ci;
 
 	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(mapping != folio_mapping(folio));
 
-	if (!folio_test_swapcache(folio))
+	if (folio_test_swapcache(folio)) {
+		ci = swap_cluster_get_and_lock_irq(folio);
+	} else {
 		spin_lock(&mapping->host->i_lock);
-	xa_lock_irq(&mapping->i_pages);
+		xa_lock_irq(&mapping->i_pages);
+	}
+
 	/*
 	 * The non racy check for a busy folio.
 	 *
@@ -783,9 +781,9 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 
 		if (reclaimed && !mapping_exiting(mapping))
 			shadow = workingset_eviction(folio, target_memcg);
-		__delete_from_swap_cache(folio, swap, shadow);
+		__swap_cache_del_folio(ci, folio, swap, shadow);
 		memcg1_swapout(folio, swap);
-		xa_unlock_irq(&mapping->i_pages);
+		swap_cluster_unlock_irq(ci);
 		put_swap_folio(folio, swap);
 	} else {
 		void (*free_folio)(struct folio *);
@@ -823,9 +821,12 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 	return 1;
 
 cannot_free:
-	xa_unlock_irq(&mapping->i_pages);
-	if (!folio_test_swapcache(folio))
+	if (folio_test_swapcache(folio)) {
+		swap_cluster_unlock_irq(ci);
+	} else {
+		xa_unlock_irq(&mapping->i_pages);
 		spin_unlock(&mapping->host->i_lock);
+	}
 	return 0;
 }
 
@@ -888,11 +889,11 @@ static bool lru_gen_set_refs(struct folio *folio)
 {
 	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
-		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
 		return false;
 	}
 
-	set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset));
+	set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_workingset));
 	return true;
 }
 #else
@@ -3257,13 +3258,13 @@ 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)
 {
-	unsigned long new_flags, old_flags = READ_ONCE(folio->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)) {
-		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced));
 		return -1;
 	}
 
@@ -3274,7 +3275,7 @@ static int folio_update_gen(struct folio *folio, int gen)
 
 		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
 		new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset);
-	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
+	} while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags));
 
 	return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
 }
@@ -3285,7 +3286,7 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai
 	int type = folio_is_file_lru(folio);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
-	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
+	unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f);
 
 	VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio);
 
@@ -3302,7 +3303,7 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai
 		/* for folio_end_writeback() */
 		if (reclaiming)
 			new_flags |= BIT(PG_reclaim);
-	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
+	} while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags));
 
 	lru_gen_update_size(lruvec, folio, old_gen, new_gen);
 
@@ -4507,7 +4508,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* ineligible */
-	if (!folio_test_lru(folio) || zone > sc->reclaim_idx) {
+	if (zone > sc->reclaim_idx) {
 		gen = folio_inc_gen(lruvec, folio, false);
 		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;
@@ -4553,7 +4554,7 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 
 	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio))
-		set_mask_bits(&folio->flags, LRU_REFS_MASK, 0);
+		set_mask_bits(&folio->flags.f, LRU_REFS_MASK, 0);
 
 	/* for shrink_folio_list() */
 	folio_clear_reclaim(folio);
@@ -4766,7 +4767,7 @@ retry:
 
 		/* don't add rejected folios to the oldest generation */
 		if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type])
-			set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active));
+			set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_active));
 	}
 
 	spin_lock_irq(&lruvec->lru_lock);
@@ -5100,7 +5101,7 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *
 	blk_finish_plug(&plug);
 done:
 	if (sc->nr_reclaimed > reclaimed)
-		pgdat->kswapd_failures = 0;
+		atomic_set(&pgdat->kswapd_failures, 0);
 }
 
 /******************************************************************************
@@ -5561,6 +5562,7 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
 	if (memcg_id != mem_cgroup_id(memcg))
 		goto done;
 
+	sc->target_mem_cgroup = memcg;
 	lruvec = get_lruvec(memcg, nid);
 
 	if (swappiness < MIN_SWAPPINESS)
@@ -5597,6 +5599,7 @@ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
 		.may_swap = true,
 		.reclaim_idx = MAX_NR_ZONES - 1,
 		.gfp_mask = GFP_KERNEL,
+		.proactive = true,
 	};
 
 	buf = kvmalloc(len + 1, GFP_KERNEL);
@@ -5772,9 +5775,9 @@ static int __init init_lru_gen(void)
 	if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
 		pr_err("lru_gen: failed to create sysfs group\n");
 
-	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, 1,
+	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false,
 				    &lru_gen_rw_fops);
-	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, 0,
+	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true,
 				    &lru_gen_ro_fops);
 
 	return 0;
@@ -6177,7 +6180,7 @@ again:
 	 * successful direct reclaim run will revive a dormant kswapd.
 	 */
 	if (reclaimable)
-		pgdat->kswapd_failures = 0;
+		atomic_set(&pgdat->kswapd_failures, 0);
 	else if (sc->cache_trim_mode)
 		sc->cache_trim_mode_failed = 1;
 }
@@ -6489,11 +6492,11 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 	int i;
 	bool wmark_ok;
 
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	for_each_managed_zone_pgdat(zone, pgdat, i, ZONE_NORMAL) {
-		if (!zone_reclaimable_pages(zone))
+		if (!zone_reclaimable_pages(zone) && zone_page_state_snapshot(zone, NR_FREE_PAGES))
 			continue;
 
 		pfmemalloc_reserve += min_wmark_pages(zone);
@@ -6899,7 +6902,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order,
 		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	/* Hopeless node, leave it to direct reclaim */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
@@ -7167,7 +7170,7 @@ restart:
 	}
 
 	if (!sc.nr_reclaimed)
-		pgdat->kswapd_failures++;
+		atomic_inc(&pgdat->kswapd_failures);
 
 out:
 	clear_reclaim_active(pgdat, highest_zoneidx);
@@ -7426,7 +7429,7 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 		return;
 
 	/* Hopeless node, leave it to direct reclaim if possible */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES ||
 	    (pgdat_balanced(pgdat, order, highest_zoneidx) &&
 	     !pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
 		/*