mm: workingset: move shadow entry tracking to radix tree exceptional tracking

Currently, we track the shadow entries in the page cache in the upper
bits of the radix_tree_node->count, behind the back of the radix tree
implementation.  Because the radix tree code has no awareness of them,
we rely on random subtleties throughout the implementation (such as the
node->count != 1 check in the shrinking code, which is meant to exclude
multi-entry nodes but also happens to skip nodes with only one shadow
entry, as that's accounted in the upper bits).  This is error prone and
has, in fact, caused the bug fixed in d3798ae8c6f3 ("mm: filemap: don't
plant shadow entries without radix tree node").

To remove these subtleties, this patch moves shadow entry tracking from
the upper bits of node->count to the existing counter for exceptional
entries.  node->count goes back to being a simple counter of valid
entries in the tree node and can be shrunk to a single byte.

This vastly simplifies the page cache code.  All accounting happens
natively inside the radix tree implementation, and maintaining the LRU
linkage of shadow nodes is consolidated into a single function in the
workingset code that is called for leaf nodes affected by a change in
the page cache tree.

This also removes the last user of the __radix_delete_node() return
value.  Eliminate it.

Link: http://lkml.kernel.org/r/20161117193211.GE23430@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <mawilcox@linuxonhyperv.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 43 insertions, 13 deletions

diff --git a/mm/workingset.c b/mm/workingset.c
index 98f830897b1ba..ef556bf1323d4 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -10,6 +10,7 @@
 #include <linux/atomic.h>
 #include <linux/module.h>
 #include <linux/swap.h>
+#include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -334,18 +335,45 @@ out:
  * point where they would still be useful.
  */
 
-struct list_lru workingset_shadow_nodes;
+static struct list_lru shadow_nodes;
+
+void workingset_update_node(struct radix_tree_node *node, void *private)
+{
+	struct address_space *mapping = private;
+
+	/* Only regular page cache has shadow entries */
+	if (dax_mapping(mapping) || shmem_mapping(mapping))
+		return;
+
+	/*
+	 * Track non-empty nodes that contain only shadow entries;
+	 * unlink those that contain pages or are being freed.
+	 *
+	 * Avoid acquiring the list_lru lock when the nodes are
+	 * already where they should be. The list_empty() test is safe
+	 * as node->private_list is protected by &mapping->tree_lock.
+	 */
+	if (node->count && node->count == node->exceptional) {
+		if (list_empty(&node->private_list)) {
+			node->private_data = mapping;
+			list_lru_add(&shadow_nodes, &node->private_list);
+		}
+	} else {
+		if (!list_empty(&node->private_list))
+			list_lru_del(&shadow_nodes, &node->private_list);
+	}
+}
 
 static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 					struct shrink_control *sc)
 {
-	unsigned long shadow_nodes;
 	unsigned long max_nodes;
+	unsigned long nodes;
 	unsigned long pages;
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
+	nodes = list_lru_shrink_count(&shadow_nodes, sc);
 	local_irq_enable();
 
 	if (sc->memcg) {
@@ -372,10 +400,10 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	 */
 	max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3);
 
-	if (shadow_nodes <= max_nodes)
+	if (nodes <= max_nodes)
 		return 0;
 
-	return shadow_nodes - max_nodes;
+	return nodes - max_nodes;
 }
 
 static enum lru_status shadow_lru_isolate(struct list_head *item,
@@ -418,22 +446,25 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * no pages, so we expect to be able to remove them all and
 	 * delete and free the empty node afterwards.
 	 */
-	if (WARN_ON_ONCE(!workingset_node_shadows(node)))
+	if (WARN_ON_ONCE(!node->exceptional))
 		goto out_invalid;
-	if (WARN_ON_ONCE(workingset_node_pages(node)))
+	if (WARN_ON_ONCE(node->count != node->exceptional))
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
 			if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
 				goto out_invalid;
+			if (WARN_ON_ONCE(!node->exceptional))
+				goto out_invalid;
 			if (WARN_ON_ONCE(!mapping->nrexceptional))
 				goto out_invalid;
 			node->slots[i] = NULL;
-			workingset_node_shadows_dec(node);
+			node->exceptional--;
+			node->count--;
 			mapping->nrexceptional--;
 		}
 	}
-	if (WARN_ON_ONCE(workingset_node_shadows(node)))
+	if (WARN_ON_ONCE(node->exceptional))
 		goto out_invalid;
 	inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
 	__radix_tree_delete_node(&mapping->page_tree, node);
@@ -456,8 +487,7 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	ret =  list_lru_shrink_walk(&workingset_shadow_nodes, sc,
-				    shadow_lru_isolate, NULL);
+	ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL);
 	local_irq_enable();
 	return ret;
 }
@@ -496,7 +526,7 @@ static int __init workingset_init(void)
 	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
 	       timestamp_bits, max_order, bucket_order);
 
-	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
+	ret = list_lru_init_key(&shadow_nodes, &shadow_nodes_key);
 	if (ret)
 		goto err;
 	ret = register_shrinker(&workingset_shadow_shrinker);
@@ -504,7 +534,7 @@ static int __init workingset_init(void)
 		goto err_list_lru;
 	return 0;
 err_list_lru:
-	list_lru_destroy(&workingset_shadow_nodes);
+	list_lru_destroy(&shadow_nodes);
 err:
 	return ret;
 }