1 files changed, 39 insertions, 81 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c05eb9efec07..2e8e690d2813 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1084,9 +1084,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
 		struct page *page;
-		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM;
-		bool dirty, writeback;
+		bool dirty, writeback, may_enter_fs;
 		unsigned int nr_pages;
 
 		cond_resched();
@@ -1267,7 +1266,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 						goto activate_locked_split;
 				}
 
-				may_enter_fs = 1;
+				may_enter_fs = true;
 
 				/* Adding to swap updated mapping */
 				mapping = page_mapping(page);
@@ -2096,7 +2095,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 unsigned long reclaim_pages(struct list_head *page_list)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 	unsigned long nr_reclaimed = 0;
 	LIST_HEAD(node_page_list);
 	struct reclaim_stat dummy_stat;
@@ -2111,7 +2110,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 
 	while (!list_empty(page_list)) {
 		page = lru_to_page(page_list);
-		if (nid == -1) {
+		if (nid == NUMA_NO_NODE) {
 			nid = page_to_nid(page);
 			INIT_LIST_HEAD(&node_page_list);
 		}
@@ -2132,7 +2131,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 			putback_lru_page(page);
 		}
 
-		nid = -1;
+		nid = NUMA_NO_NODE;
 	}
 
 	if (!list_empty(&node_page_list)) {
@@ -2415,19 +2414,20 @@ out:
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:
 		case SCAN_ANON:
 			/* Scan one type exclusively */
-			if ((scan_balance == SCAN_FILE) != file) {
-				lruvec_size = 0;
+			if ((scan_balance == SCAN_FILE) != file)
 				scan = 0;
-			}
 			break;
 		default:
 			/* Look ma, no brain */
@@ -3093,7 +3093,6 @@ retry:
 	if (sc->memcg_low_skipped) {
 		sc->priority = initial_priority;
 		sc->force_deactivate = 0;
-		sc->skipped_deactivate = 0;
 		sc->memcg_low_reclaim = 1;
 		sc->memcg_low_skipped = 0;
 		goto retry;
@@ -3133,8 +3132,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
-						(enum zone_type)ZONE_NORMAL);
+		if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+			WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
 
@@ -3766,9 +3766,9 @@ out:
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
 					   enum zone_type prev_classzone_idx)
 {
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return prev_classzone_idx;
-	return pgdat->kswapd_classzone_idx;
+	enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3812,8 +3812,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
 		 * the previous request that slept prematurely.
 		 */
 		if (remaining) {
-			pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+			WRITE_ONCE(pgdat->kswapd_classzone_idx,
+				   kswapd_classzone_idx(pgdat, classzone_idx));
+
+			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
+				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
 		}
 
 		finish_wait(&pgdat->kswapd_wait, &wait);
@@ -3890,12 +3893,12 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	pgdat->kswapd_order = 0;
-	pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+	WRITE_ONCE(pgdat->kswapd_order, 0);
+	WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 	for ( ; ; ) {
 		bool ret;
 
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 
 kswapd_try_sleep:
@@ -3903,10 +3906,10 @@ kswapd_try_sleep:
 					classzone_idx);
 
 		/* Read the new order and classzone_idx */
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-		pgdat->kswapd_order = 0;
-		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+		WRITE_ONCE(pgdat->kswapd_order, 0);
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3950,20 +3953,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	enum zone_type curr_idx;
 
 	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
+
 	pgdat = zone->zone_pgdat;
+	curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+	if (READ_ONCE(pgdat->kswapd_order) < order)
+		WRITE_ONCE(pgdat->kswapd_order, order);
 
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		pgdat->kswapd_classzone_idx = classzone_idx;
-	else
-		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
-						  classzone_idx);
-	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
@@ -4027,27 +4033,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 }
 #endif /* CONFIG_HIBERNATION */
 
-/* It's optimal to keep kswapds on the same CPUs as their memory, but
-   not required for correctness.  So if the last cpu in a node goes
-   away, we get changed to run anywhere: as the first one comes back,
-   restore their cpu bindings. */
-static int kswapd_cpu_online(unsigned int cpu)
-{
-	int nid;
-
-	for_each_node_state(nid, N_MEMORY) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-		const struct cpumask *mask;
-
-		mask = cpumask_of_node(pgdat->node_id);
-
-		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-			/* One of our CPUs online: restore mask */
-			set_cpus_allowed_ptr(pgdat->kswapd, mask);
-	}
-	return 0;
-}
-
 /*
  * This kswapd start function will be called by init and node-hot-add.
  * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
@@ -4087,15 +4072,11 @@ void kswapd_stop(int nid)
 
 static int __init kswapd_init(void)
 {
-	int nid, ret;
+	int nid;
 
 	swap_setup();
 	for_each_node_state(nid, N_MEMORY)
  		kswapd_run(nid);
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					"mm/vmscan:online", kswapd_cpu_online,
-					NULL);
-	WARN_ON(ret < 0);
 	return 0;
 }
 
@@ -4274,29 +4255,6 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 }
 #endif
 
-/*
- * page_evictable - test whether a page is evictable
- * @page: the page to test
- *
- * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
- *
- * Reasons page might not be evictable:
- * (1) page's mapping marked unevictable
- * (2) page is part of an mlocked VMA
- *
- */
-int page_evictable(struct page *page)
-{
-	int ret;
-
-	/* Prevent address_space of inode and swap cache from being freed */
-	rcu_read_lock();
-	ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
-	rcu_read_unlock();
-	return ret;
-}
-
 /**
  * check_move_unevictable_pages - check pages for evictability and move to
  * appropriate zone lru list