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>

1 files changed, 22 insertions, 14 deletions

diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d60be40c111b..9599aa72d7a0 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -342,7 +342,8 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 
 		/* Increase the height.  */
 		newheight = root->height+1;
-		node->height = newheight;
+		BUG_ON(newheight & ~RADIX_TREE_HEIGHT_MASK);
+		node->path = newheight;
 		node->count = 1;
 		node->parent = NULL;
 		slot = root->rnode;
@@ -400,11 +401,12 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 			/* Have to add a child node.  */
 			if (!(slot = radix_tree_node_alloc(root)))
 				return -ENOMEM;
-			slot->height = height;
+			slot->path = height;
 			slot->parent = node;
 			if (node) {
 				rcu_assign_pointer(node->slots[offset], slot);
 				node->count++;
+				slot->path |= offset << RADIX_TREE_HEIGHT_SHIFT;
 			} else
 				rcu_assign_pointer(root->rnode, ptr_to_indirect(slot));
 		}
@@ -498,7 +500,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 	}
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return NULL;
 
@@ -704,7 +706,7 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 		return (index == 0);
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return 0;
 
@@ -741,7 +743,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 {
 	unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK;
 	struct radix_tree_node *rnode, *node;
-	unsigned long index, offset;
+	unsigned long index, offset, height;
 
 	if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
 		return NULL;
@@ -772,7 +774,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 		return NULL;
 
 restart:
-	shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT;
+	height = rnode->path & RADIX_TREE_HEIGHT_MASK;
+	shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
 	offset = index >> shift;
 
 	/* Index outside of the tree */
@@ -1142,7 +1145,7 @@ static unsigned long __locate(struct radix_tree_node *slot, void *item,
 	unsigned int shift, height;
 	unsigned long i;
 
-	height = slot->height;
+	height = slot->path & RADIX_TREE_HEIGHT_MASK;
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 
 	for ( ; height > 1; height--) {
@@ -1205,7 +1208,8 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
 		}
 
 		node = indirect_to_ptr(node);
-		max_index = radix_tree_maxindex(node->height);
+		max_index = radix_tree_maxindex(node->path &
+						RADIX_TREE_HEIGHT_MASK);
 		if (cur_index > max_index) {
 			rcu_read_unlock();
 			break;
@@ -1301,7 +1305,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
  *
  *	Returns %true if @node was freed, %false otherwise.
  */
-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)
 {
 	bool deleted = false;
@@ -1320,9 +1324,10 @@ bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
 
 		parent = node->parent;
 		if (parent) {
-			index >>= RADIX_TREE_MAP_SHIFT;
+			unsigned int offset;
 
-			parent->slots[index & RADIX_TREE_MAP_MASK] = NULL;
+			offset = node->path >> RADIX_TREE_HEIGHT_SHIFT;
+			parent->slots[offset] = NULL;
 			parent->count--;
 		} else {
 			root_tag_clear_all(root);
@@ -1386,7 +1391,7 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
 	node->slots[offset] = NULL;
 	node->count--;
 
-	__radix_tree_delete_node(root, index, node);
+	__radix_tree_delete_node(root, node);
 
 	return entry;
 }
@@ -1419,9 +1424,12 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag)
 EXPORT_SYMBOL(radix_tree_tagged);
 
 static void
-radix_tree_node_ctor(void *node)
+radix_tree_node_ctor(void *arg)
 {
-	memset(node, 0, sizeof(struct radix_tree_node));
+	struct radix_tree_node *node = arg;
+
+	memset(node, 0, sizeof(*node));
+	INIT_LIST_HEAD(&node->private_list);
 }
 
 static __init unsigned long __maxindex(unsigned int height)