1 files changed, 174 insertions, 36 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeae2f6bc532..740d03e6dae2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -41,6 +41,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/memcontrol.h>
+#include <linux/migrate.h>
 #include <linux/delayacct.h>
 #include <linux/sysctl.h>
 #include <linux/oom.h>
@@ -121,6 +122,9 @@ struct scan_control {
 	/* The file pages on the current node are dangerously low */
 	unsigned int file_is_tiny:1;
 
+	/* Always discard instead of demoting to lower tier memory */
+	unsigned int no_demotion:1;
+
 	/* Allocation order */
 	s8 order;
 
@@ -518,6 +522,48 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker,
 	return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
 }
 
+static bool can_demote(int nid, struct scan_control *sc)
+{
+	if (!numa_demotion_enabled)
+		return false;
+	if (sc) {
+		if (sc->no_demotion)
+			return false;
+		/* It is pointless to do demotion in memcg reclaim */
+		if (cgroup_reclaim(sc))
+			return false;
+	}
+	if (next_demotion_node(nid) == NUMA_NO_NODE)
+		return false;
+
+	return true;
+}
+
+static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
+					  int nid,
+					  struct scan_control *sc)
+{
+	if (memcg == NULL) {
+		/*
+		 * For non-memcg reclaim, is there
+		 * space in any swap device?
+		 */
+		if (get_nr_swap_pages() > 0)
+			return true;
+	} else {
+		/* Is the memcg below its swap limit? */
+		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
+			return true;
+	}
+
+	/*
+	 * The page can not be swapped.
+	 *
+	 * Can it be reclaimed from this node via demotion?
+	 */
+	return can_demote(nid, sc);
+}
+
 /*
  * This misses isolated pages which are not accounted for to save counters.
  * As the data only determines if reclaim or compaction continues, it is
@@ -529,7 +575,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 
 	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
 		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	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);
 
@@ -893,6 +939,7 @@ out:
 void drop_slab_node(int nid)
 {
 	unsigned long freed;
+	int shift = 0;
 
 	do {
 		struct mem_cgroup *memcg = NULL;
@@ -905,7 +952,7 @@ void drop_slab_node(int nid)
 		do {
 			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
 		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
-	} while (freed > 10);
+	} while ((freed >> shift++) > 1);
 }
 
 void drop_slab(void)
@@ -1052,14 +1099,13 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed, struct mem_cgroup *target_memcg)
 {
-	unsigned long flags;
 	int refcount;
 	void *shadow = NULL;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	xa_lock_irqsave(&mapping->i_pages, flags);
+	xa_lock_irq(&mapping->i_pages);
 	/*
 	 * The non racy check for a busy page.
 	 *
@@ -1100,7 +1146,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && !mapping_exiting(mapping))
 			shadow = workingset_eviction(page, target_memcg);
 		__delete_from_swap_cache(page, swap, shadow);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		xa_unlock_irq(&mapping->i_pages);
 		put_swap_page(page, swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -1126,7 +1172,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(page, target_memcg);
 		__delete_from_page_cache(page, shadow);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		xa_unlock_irq(&mapping->i_pages);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -1135,7 +1181,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	return 1;
 
 cannot_free:
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 	return 0;
 }
 
@@ -1264,6 +1310,54 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
+static struct page *alloc_demote_page(struct page *page, unsigned long node)
+{
+	struct migration_target_control mtc = {
+		/*
+		 * Allocate from 'node', or fail quickly and quietly.
+		 * When this happens, 'page' will likely just be discarded
+		 * instead of migrated.
+		 */
+		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
+			    __GFP_THISNODE  | __GFP_NOWARN |
+			    __GFP_NOMEMALLOC | GFP_NOWAIT,
+		.nid = node
+	};
+
+	return alloc_migration_target(page, (unsigned long)&mtc);
+}
+
+/*
+ * Take pages on @demote_list and attempt to demote them to
+ * another node.  Pages which are not demoted are left on
+ * @demote_pages.
+ */
+static unsigned int demote_page_list(struct list_head *demote_pages,
+				     struct pglist_data *pgdat)
+{
+	int target_nid = next_demotion_node(pgdat->node_id);
+	unsigned int nr_succeeded;
+	int err;
+
+	if (list_empty(demote_pages))
+		return 0;
+
+	if (target_nid == NUMA_NO_NODE)
+		return 0;
+
+	/* Demotion ignores all cpuset and mempolicy settings */
+	err = migrate_pages(demote_pages, alloc_demote_page, NULL,
+			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
+			    &nr_succeeded);
+
+	if (current_is_kswapd())
+		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);
+	else
+		__count_vm_events(PGDEMOTE_DIRECT, nr_succeeded);
+
+	return nr_succeeded;
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -1275,12 +1369,16 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
+	LIST_HEAD(demote_pages);
 	unsigned int nr_reclaimed = 0;
 	unsigned int pgactivate = 0;
+	bool do_demote_pass;
 
 	memset(stat, 0, sizeof(*stat));
 	cond_resched();
+	do_demote_pass = can_demote(pgdat->node_id, sc);
 
+retry:
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
 		struct page *page;
@@ -1430,6 +1528,17 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 		}
 
 		/*
+		 * Before reclaiming the page, try to relocate
+		 * its contents to another node.
+		 */
+		if (do_demote_pass &&
+		    (thp_migration_supported() || !PageTransHuge(page))) {
+			list_add(&page->lru, &demote_pages);
+			unlock_page(page);
+			continue;
+		}
+
+		/*
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 * Lazyfree page could be freed directly
@@ -1624,11 +1733,14 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			/* follow __remove_mapping for reference */
 			if (!page_ref_freeze(page, 1))
 				goto keep_locked;
-			if (PageDirty(page)) {
-				page_ref_unfreeze(page, 1);
-				goto keep_locked;
-			}
-
+			/*
+			 * The page has only one reference left, which is
+			 * from the isolation. After the caller puts the
+			 * page back on lru and drops the reference, the
+			 * page will be freed anyway. It doesn't matter
+			 * which lru it goes. So we don't bother checking
+			 * PageDirty here.
+			 */
 			count_vm_event(PGLAZYFREED);
 			count_memcg_page_event(page, PGLAZYFREED);
 		} else if (!mapping || !__remove_mapping(mapping, page, true,
@@ -1680,6 +1792,17 @@ keep:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
+	/* 'page_list' is always empty here */
+
+	/* Migrate pages selected for demotion */
+	nr_reclaimed += demote_page_list(&demote_pages, pgdat);
+	/* Pages that could not be demoted are still in @demote_pages */
+	if (!list_empty(&demote_pages)) {
+		/* Pages which failed to demoted go back on @page_list for retry: */
+		list_splice_init(&demote_pages, page_list);
+		do_demote_pass = false;
+		goto retry;
+	}
 
 	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
 
@@ -1698,7 +1821,6 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 {
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 	};
 	struct reclaim_stat stat;
@@ -2323,10 +2445,10 @@ unsigned long reclaim_pages(struct list_head *page_list)
 	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.priority = DEF_PRIORITY,
 		.may_writepage = 1,
 		.may_unmap = 1,
 		.may_swap = 1,
+		.no_demotion = 1,
 	};
 
 	noreclaim_flag = memalloc_noreclaim_save();
@@ -2452,6 +2574,7 @@ enum scan_balance {
 static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			   unsigned long *nr)
 {
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	unsigned long anon_cost, file_cost, total_cost;
 	int swappiness = mem_cgroup_swappiness(memcg);
@@ -2462,7 +2585,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	enum lru_list lru;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
+	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2645,6 +2768,21 @@ out:
 	}
 }
 
+/*
+ * Anonymous LRU management is a waste if there is
+ * ultimately no way to reclaim the memory.
+ */
+static bool can_age_anon_pages(struct pglist_data *pgdat,
+			       struct scan_control *sc)
+{
+	/* Aging the anon LRU is valuable if swap is present: */
+	if (total_swap_pages > 0)
+		return true;
+
+	/* Also valuable if anon pages can be demoted: */
+	return can_demote(pgdat->node_id, sc);
+}
+
 static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
@@ -2754,7 +2892,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON))
+	if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) &&
+	    inactive_is_low(lruvec, LRU_INACTIVE_ANON))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2824,7 +2963,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	 */
 	pages_for_compaction = compact_gap(sc->order);
 	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
 		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 
 	return inactive_lru_pages > pages_for_compaction;
@@ -2898,6 +3037,12 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
 
 again:
+	/*
+	 * Flush the memory cgroup stats, so that we read accurate per-memcg
+	 * lruvec stats for heuristics.
+	 */
+	mem_cgroup_flush_stats();
+
 	memset(&sc->nr, 0, sizeof(sc->nr));
 
 	nr_reclaimed = sc->nr_reclaimed;
@@ -3434,18 +3579,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	 * blocked waiting on the same lock. Instead, throttle for up to a
 	 * second before continuing.
 	 */
-	if (!(gfp_mask & __GFP_FS)) {
+	if (!(gfp_mask & __GFP_FS))
 		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
 			allow_direct_reclaim(pgdat), HZ);
+	else
+		/* Throttle until kswapd wakes the process */
+		wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+			allow_direct_reclaim(pgdat));
 
-		goto check_pending;
-	}
-
-	/* Throttle until kswapd wakes the process */
-	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
-		allow_direct_reclaim(pgdat));
-
-check_pending:
 	if (fatal_signal_pending(current))
 		return true;
 
@@ -3583,7 +3724,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
-	if (!total_swap_pages)
+	if (!can_age_anon_pages(pgdat, sc))
 		return;
 
 	lruvec = mem_cgroup_lruvec(NULL, pgdat);
@@ -3812,7 +3953,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
 	psi_memstall_enter(&pflags);
-	__fs_reclaim_acquire();
+	__fs_reclaim_acquire(_THIS_IP_);
 
 	count_vm_event(PAGEOUTRUN);
 
@@ -3938,9 +4079,9 @@ restart:
 			wake_up_all(&pgdat->pfmemalloc_wait);
 
 		/* Check if kswapd should be suspending */
-		__fs_reclaim_release();
+		__fs_reclaim_release(_THIS_IP_);
 		ret = try_to_freeze();
-		__fs_reclaim_acquire();
+		__fs_reclaim_acquire(_THIS_IP_);
 		if (ret || kthread_should_stop())
 			break;
 
@@ -3992,7 +4133,7 @@ out:
 	}
 
 	snapshot_refaults(NULL, pgdat);
-	__fs_reclaim_release();
+	__fs_reclaim_release(_THIS_IP_);
 	psi_memstall_leave(&pflags);
 	set_task_reclaim_state(current, NULL);
 
@@ -4290,23 +4431,20 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
  * 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.
  */
-int kswapd_run(int nid)
+void kswapd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	int ret = 0;
 
 	if (pgdat->kswapd)
-		return 0;
+		return;
 
 	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
 	if (IS_ERR(pgdat->kswapd)) {
 		/* failure at boot is fatal */
 		BUG_ON(system_state < SYSTEM_RUNNING);
 		pr_err("Failed to start kswapd on node %d\n", nid);
-		ret = PTR_ERR(pgdat->kswapd);
 		pgdat->kswapd = NULL;
 	}
-	return ret;
 }
 
 /*