1 files changed, 36 insertions, 110 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 47d5ced51f2d..bee53495a829 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -220,22 +220,6 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 	return nr;
 }
 
-unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
-{
-	unsigned long nr;
-
-	nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) +
-	     node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) +
-	     node_page_state_snapshot(pgdat, NR_ISOLATED_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) +
-		      node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) +
-		      node_page_state_snapshot(pgdat, NR_ISOLATED_ANON);
-
-	return nr;
-}
-
 /**
  * lruvec_lru_size -  Returns the number of pages on the given LRU list.
  * @lruvec: lru vector
@@ -310,9 +294,7 @@ EXPORT_SYMBOL(unregister_shrinker);
 #define SHRINK_BATCH 128
 
 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
-				    struct shrinker *shrinker,
-				    unsigned long nr_scanned,
-				    unsigned long nr_eligible)
+				    struct shrinker *shrinker, int priority)
 {
 	unsigned long freed = 0;
 	unsigned long long delta;
@@ -337,9 +319,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
 
 	total_scan = nr;
-	delta = (4 * nr_scanned) / shrinker->seeks;
-	delta *= freeable;
-	do_div(delta, nr_eligible + 1);
+	delta = freeable >> priority;
+	delta *= 4;
+	do_div(delta, shrinker->seeks);
 	total_scan += delta;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
@@ -373,8 +355,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
-				   nr_scanned, nr_eligible,
-				   freeable, delta, total_scan);
+				   freeable, delta, total_scan, priority);
 
 	/*
 	 * Normally, we should not scan less than batch_size objects in one
@@ -434,8 +415,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
  * @gfp_mask: allocation context
  * @nid: node whose slab caches to target
  * @memcg: memory cgroup whose slab caches to target
- * @nr_scanned: pressure numerator
- * @nr_eligible: pressure denominator
+ * @priority: the reclaim priority
  *
  * Call the shrink functions to age shrinkable caches.
  *
@@ -447,20 +427,14 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
  * objects from the memory cgroup specified. Otherwise, only unaware
  * shrinkers are called.
  *
- * @nr_scanned and @nr_eligible form a ratio that indicate how much of
- * the available objects should be scanned.  Page reclaim for example
- * passes the number of pages scanned and the number of pages on the
- * LRU lists that it considered on @nid, plus a bias in @nr_scanned
- * when it encountered mapped pages.  The ratio is further biased by
- * the ->seeks setting of the shrink function, which indicates the
- * cost to recreate an object relative to that of an LRU page.
+ * @priority is sc->priority, we take the number of objects and >> by priority
+ * in order to get the scan target.
  *
  * Returns the number of reclaimed slab objects.
  */
 static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 				 struct mem_cgroup *memcg,
-				 unsigned long nr_scanned,
-				 unsigned long nr_eligible)
+				 int priority)
 {
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
@@ -468,9 +442,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
 		return 0;
 
-	if (nr_scanned == 0)
-		nr_scanned = SWAP_CLUSTER_MAX;
-
 	if (!down_read_trylock(&shrinker_rwsem)) {
 		/*
 		 * If we would return 0, our callers would understand that we
@@ -501,7 +472,16 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
 			sc.nid = 0;
 
-		freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
+		freed += do_shrink_slab(&sc, shrinker, priority);
+		/*
+		 * Bail out if someone want to register a new shrinker to
+		 * prevent the regsitration from being stalled for long periods
+		 * by parallel ongoing shrinking.
+		 */
+		if (rwsem_is_contended(&shrinker_rwsem)) {
+			freed = freed ? : 1;
+			break;
+		}
 	}
 
 	up_read(&shrinker_rwsem);
@@ -519,8 +499,7 @@ void drop_slab_node(int nid)
 
 		freed = 0;
 		do {
-			freed += shrink_slab(GFP_KERNEL, nid, memcg,
-					     1000, 1000);
+			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
 		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
 	} while (freed > 10);
 }
@@ -790,64 +769,7 @@ int remove_mapping(struct address_space *mapping, struct page *page)
  */
 void putback_lru_page(struct page *page)
 {
-	bool is_unevictable;
-	int was_unevictable = PageUnevictable(page);
-
-	VM_BUG_ON_PAGE(PageLRU(page), page);
-
-redo:
-	ClearPageUnevictable(page);
-
-	if (page_evictable(page)) {
-		/*
-		 * For evictable pages, we can use the cache.
-		 * In event of a race, worst case is we end up with an
-		 * unevictable page on [in]active list.
-		 * We know how to handle that.
-		 */
-		is_unevictable = false;
-		lru_cache_add(page);
-	} else {
-		/*
-		 * Put unevictable pages directly on zone's unevictable
-		 * list.
-		 */
-		is_unevictable = true;
-		add_page_to_unevictable_list(page);
-		/*
-		 * When racing with an mlock or AS_UNEVICTABLE clearing
-		 * (page is unlocked) make sure that if the other thread
-		 * does not observe our setting of PG_lru and fails
-		 * isolation/check_move_unevictable_pages,
-		 * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
-		 * the page back to the evictable list.
-		 *
-		 * The other side is TestClearPageMlocked() or shmem_lock().
-		 */
-		smp_mb();
-	}
-
-	/*
-	 * page's status can change while we move it among lru. If an evictable
-	 * page is on unevictable list, it never be freed. To avoid that,
-	 * check after we added it to the list, again.
-	 */
-	if (is_unevictable && page_evictable(page)) {
-		if (!isolate_lru_page(page)) {
-			put_page(page);
-			goto redo;
-		}
-		/* This means someone else dropped this page from LRU
-		 * So, it will be freed or putback to LRU again. There is
-		 * nothing to do here.
-		 */
-	}
-
-	if (was_unevictable && !is_unevictable)
-		count_vm_event(UNEVICTABLE_PGRESCUED);
-	else if (!was_unevictable && is_unevictable)
-		count_vm_event(UNEVICTABLE_PGCULLED);
-
+	lru_cache_add(page);
 	put_page(page);		/* drop ref from isolate */
 }
 
@@ -1436,14 +1358,24 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 
 		if (PageDirty(page)) {
 			struct address_space *mapping;
+			bool migrate_dirty;
 
 			/*
 			 * Only pages without mappings or that have a
 			 * ->migratepage callback are possible to migrate
-			 * without blocking
+			 * without blocking. However, we can be racing with
+			 * truncation so it's necessary to lock the page
+			 * to stabilise the mapping as truncation holds
+			 * the page lock until after the page is removed
+			 * from the page cache.
 			 */
+			if (!trylock_page(page))
+				return ret;
+
 			mapping = page_mapping(page);
-			if (mapping && !mapping->a_ops->migratepage)
+			migrate_dirty = mapping && mapping->a_ops->migratepage;
+			unlock_page(page);
+			if (!migrate_dirty)
 				return ret;
 		}
 	}
@@ -1606,6 +1538,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
  * found will be decremented.
  *
  * Restrictions:
+ *
  * (1) Must be called with an elevated refcount on the page. This is a
  *     fundamentnal difference from isolate_lru_pages (which is called
  *     without a stable reference).
@@ -2615,14 +2548,12 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 
 			reclaimed = sc->nr_reclaimed;
 			scanned = sc->nr_scanned;
-
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
 			if (memcg)
 				shrink_slab(sc->gfp_mask, pgdat->node_id,
-					    memcg, sc->nr_scanned - scanned,
-					    lru_pages);
+					    memcg, sc->priority);
 
 			/* Record the group's reclaim efficiency */
 			vmpressure(sc->gfp_mask, memcg, false,
@@ -2646,14 +2577,9 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			}
 		} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
 
-		/*
-		 * Shrink the slab caches in the same proportion that
-		 * the eligible LRU pages were scanned.
-		 */
 		if (global_reclaim(sc))
 			shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
-				    sc->nr_scanned - nr_scanned,
-				    node_lru_pages);
+				    sc->priority);
 
 		if (reclaim_state) {
 			sc->nr_reclaimed += reclaim_state->reclaimed_slab;