mm: keep page cache radix tree nodes in check

Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers.  But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed.  This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting.  The shadow entries will just
sit there and waste memory.  In the worst case, the shadow entries will
accumulate until the machine runs out of memory.

To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list.  Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads.  A simple shrinker will then
reclaim these nodes on memory pressure.

A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:

1. There is no index available that would describe the reverse path
   from the node up to the tree root, which is needed to perform a
   deletion.  To solve this, encode in each node its offset inside the
   parent.  This can be stored in the unused upper bits of the same
   member that stores the node's height at no extra space cost.

2. The number of shadow entries needs to be counted in addition to the
   regular entries, to quickly detect when the node is ready to go to
   the shadow node LRU list.  The current entry count is an unsigned
   int but the maximum number of entries is 64, so a shadow counter
   can easily be stored in the unused upper bits.

3. Tree modification needs tree lock and tree root, which are located
   in the address space, so store an address_space backpointer in the
   node.  The parent pointer of the node is in a union with the 2-word
   rcu_head, so the backpointer comes at no extra cost as well.

4. The node needs to be linked to an LRU list, which requires a list
   head inside the node.  This does increase the size of the node, but
   it does not change the number of objects that fit into a slab page.

[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 63 insertions, 9 deletions

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 3ce541753c88..f3434533fbf8 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -13,6 +13,8 @@
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
 	LRU_REMOVED,		/* item removed from list */
+	LRU_REMOVED_RETRY,	/* item removed, but lock has been
+				   dropped and reacquired */
 	LRU_ROTATE,		/* item referenced, give another pass */
 	LRU_SKIP,		/* item cannot be locked, skip */
 	LRU_RETRY,		/* item not freeable. May drop the lock
@@ -32,7 +34,11 @@ struct list_lru {
 };
 
 void list_lru_destroy(struct list_lru *lru);
-int list_lru_init(struct list_lru *lru);
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
+static inline int list_lru_init(struct list_lru *lru)
+{
+	return list_lru_init_key(lru, NULL);
+}
 
 /**
  * list_lru_add: add an element to the lru list's tail
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f25db1d74a21..fac5509c18f0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -144,6 +144,7 @@ enum zone_stat_item {
 #endif
 	WORKINGSET_REFAULT,
 	WORKINGSET_ACTIVATE,
+	WORKINGSET_NODERECLAIM,
 	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 13636c40bc42..33170dbd9db4 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -72,21 +72,37 @@ static inline int radix_tree_is_indirect_ptr(void *ptr)
 #define RADIX_TREE_TAG_LONGS	\
 	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
 
+#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
+#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
+					  RADIX_TREE_MAP_SHIFT))
+
+/* Height component in node->path */
+#define RADIX_TREE_HEIGHT_SHIFT	(RADIX_TREE_MAX_PATH + 1)
+#define RADIX_TREE_HEIGHT_MASK	((1UL << RADIX_TREE_HEIGHT_SHIFT) - 1)
+
+/* Internally used bits of node->count */
+#define RADIX_TREE_COUNT_SHIFT	(RADIX_TREE_MAP_SHIFT + 1)
+#define RADIX_TREE_COUNT_MASK	((1UL << RADIX_TREE_COUNT_SHIFT) - 1)
+
 struct radix_tree_node {
-	unsigned int	height;		/* Height from the bottom */
+	unsigned int	path;	/* Offset in parent & height from the bottom */
 	unsigned int	count;
 	union {
-		struct radix_tree_node *parent;	/* Used when ascending tree */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
+		struct {
+			/* Used when ascending tree */
+			struct radix_tree_node *parent;
+			/* For tree user */
+			void *private_data;
+		};
+		/* Used when freeing node */
+		struct rcu_head	rcu_head;
 	};
+	/* For tree user */
+	struct list_head private_list;
 	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
-#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
-					  RADIX_TREE_MAP_SHIFT))
-
 /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */
 struct radix_tree_root {
 	unsigned int		height;
@@ -251,7 +267,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
-bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
+bool __radix_tree_delete_node(struct radix_tree_root *root,
 			      struct radix_tree_node *node);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b83cf61403ed..350711560753 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -264,6 +264,37 @@ struct swap_list_t {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
+extern struct list_lru workingset_shadow_nodes;
+
+static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
+{
+	return node->count & RADIX_TREE_COUNT_MASK;
+}
+
+static inline void workingset_node_pages_inc(struct radix_tree_node *node)
+{
+	node->count++;
+}
+
+static inline void workingset_node_pages_dec(struct radix_tree_node *node)
+{
+	node->count--;
+}
+
+static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)
+{
+	return node->count >> RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
+{
+	node->count += 1U << RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
+{
+	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+}
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;