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, 74 insertions, 16 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index a603c4d7d3c9..d6df3bacb0fb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -110,11 +110,17 @@
 static void page_cache_tree_delete(struct address_space *mapping,
                                    struct page *page, void *shadow)
 {
-        if (shadow) {
-                void **slot;
+        struct radix_tree_node *node;
+        unsigned long index;
+        unsigned int offset;
+        unsigned int tag;
+        void **slot;
 
-                slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
-                radix_tree_replace_slot(slot, shadow);
+        VM_BUG_ON(!PageLocked(page));
+
+        __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
+
+        if (shadow) {
                 mapping->nrshadows++;
                 /*
                  * Make sure the nrshadows update is committed before
@@ -123,9 +129,45 @@ static void page_cache_tree_delete(struct address_space *mapping,
                  * same time and miss a shadow entry.
                  */
                 smp_wmb();
-        } else
-                radix_tree_delete(&mapping->page_tree, page->index);
+        }
         mapping->nrpages--;
+
+        if (!node) {
+                /* Clear direct pointer tags in root node */
+                mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
+                radix_tree_replace_slot(slot, shadow);
+                return;
+        }
+
+        /* Clear tree tags for the removed page */
+        index = page->index;
+        offset = index & RADIX_TREE_MAP_MASK;
+        for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
+                if (test_bit(offset, node->tags[tag]))
+                        radix_tree_tag_clear(&mapping->page_tree, index, tag);
+        }
+
+        /* Delete page, swap shadow entry */
+        radix_tree_replace_slot(slot, shadow);
+        workingset_node_pages_dec(node);
+        if (shadow)
+                workingset_node_shadows_inc(node);
+        else
+                if (__radix_tree_delete_node(&mapping->page_tree, node))
+                        return;
+
+        /*
+         * Track node that only contains shadow entries.
+         *
+         * Avoid acquiring the list_lru lock if already tracked.  The
+         * list_empty() test is safe as node->private_list is
+         * protected by mapping->tree_lock.
+         */
+        if (!workingset_node_pages(node) &&
+            list_empty(&node->private_list)) {
+                node->private_data = mapping;
+                list_lru_add(&workingset_shadow_nodes, &node->private_list);
+        }
 }
 
 /*
@@ -471,27 +513,43 @@ EXPORT_SYMBOL_GPL(replace_page_cache_page);
 static int page_cache_tree_insert(struct address_space *mapping,
                                   struct page *page, void **shadowp)
 {
+        struct radix_tree_node *node;
         void **slot;
         int error;
 
-        slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
-        if (slot) {
+        error = __radix_tree_create(&mapping->page_tree, page->index,
+                                    &node, &slot);
+        if (error)
+                return error;
+        if (*slot) {
                 void *p;
 
                 p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
                 if (!radix_tree_exceptional_entry(p))
                         return -EEXIST;
-                radix_tree_replace_slot(slot, page);
-                mapping->nrshadows--;
-                mapping->nrpages++;
                 if (shadowp)
                         *shadowp = p;
-                return 0;
+                mapping->nrshadows--;
+                if (node)
+                        workingset_node_shadows_dec(node);
         }
-        error = radix_tree_insert(&mapping->page_tree, page->index, page);
-        if (!error)
-                mapping->nrpages++;
-        return error;
+        radix_tree_replace_slot(slot, page);
+        mapping->nrpages++;
+        if (node) {
+                workingset_node_pages_inc(node);
+                /*
+                 * Don't track node that contains actual pages.
+                 *
+                 * Avoid acquiring the list_lru lock if already
+                 * untracked.  The list_empty() test is safe as
+                 * node->private_list is protected by
+                 * mapping->tree_lock.
+                 */
+                if (!list_empty(&node->private_list))
+                        list_lru_del(&workingset_shadow_nodes,
+                                     &node->private_list);
+        }
+        return 0;
 }
 
 static int __add_to_page_cache_locked(struct page *page,