diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7a8d2516c73a8d7c570e2b14494bc5287c22339d..935293a24f7d4f3b1a17a8a0f2fc0ee626afc38c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -335,6 +335,9 @@ static inline void radix_tree_preload_end(void)
preempt_enable();
}
+int radix_tree_join(struct radix_tree_root *, unsigned long index,
+ unsigned new_order, void *);
+
#define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */
#define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */
#define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d1f4ca5b798961cf5e7bdc2b4199092a2c17a34c..962cfb3a76713572d8b16ccda80bbb4f681094bd 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -339,17 +339,14 @@ static void radix_tree_node_rcu_free(struct rcu_head *head)
{
struct radix_tree_node *node =
container_of(head, struct radix_tree_node, rcu_head);
- int i;
/*
- * must only free zeroed nodes into the slab. radix_tree_shrink
- * can leave us with a non-NULL entry in the first slot, so clear
- * that here to make sure.
+ * Must only free zeroed nodes into the slab. We can be left with
+ * non-NULL entries by radix_tree_free_nodes, so clear the entries
+ * and tags here.
*/
- for (i = 0; i < RADIX_TREE_MAX_TAGS; i++)
- tag_clear(node, i, 0);
-
- node->slots[0] = NULL;
+ memset(node->slots, 0, sizeof(node->slots));
+ memset(node->tags, 0, sizeof(node->tags));
INIT_LIST_HEAD(&node->private_list);
kmem_cache_free(radix_tree_node_cachep, node);
@@ -678,14 +675,14 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
shift = radix_tree_load_root(root, &child, &maxindex);
/* Make sure the tree is high enough. */
+ if (order > 0 && max == ((1UL << order) - 1))
+ max++;
if (max > maxindex) {
int error = radix_tree_extend(root, max, shift);
if (error < 0)
return error;
shift = error;
child = root->rnode;
- if (order == shift)
- shift += RADIX_TREE_MAP_SHIFT;
}
while (shift > order) {
@@ -697,6 +694,8 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
return -ENOMEM;
child->shift = shift;
child->offset = offset;
+ child->count = 0;
+ child->exceptional = 0;
child->parent = node;
rcu_assign_pointer(*slot, node_to_entry(child));
if (node)
@@ -710,31 +709,121 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
slot = &node->slots[offset];
}
+ if (nodep)
+ *nodep = node;
+ if (slotp)
+ *slotp = slot;
+ return 0;
+}
+
#ifdef CONFIG_RADIX_TREE_MULTIORDER
- /* Insert pointers to the canonical entry */
- if (order > shift) {
- unsigned i, n = 1 << (order - shift);
+/*
+ * Free any nodes below this node. The tree is presumed to not need
+ * shrinking, and any user data in the tree is presumed to not need a
+ * destructor called on it. If we need to add a destructor, we can
+ * add that functionality later. Note that we may not clear tags or
+ * slots from the tree as an RCU walker may still have a pointer into
+ * this subtree. We could replace the entries with RADIX_TREE_RETRY,
+ * but we'll still have to clear those in rcu_free.
+ */
+static void radix_tree_free_nodes(struct radix_tree_node *node)
+{
+ unsigned offset = 0;
+ struct radix_tree_node *child = entry_to_node(node);
+
+ for (;;) {
+ void *entry = child->slots[offset];
+ if (radix_tree_is_internal_node(entry) &&
+ !is_sibling_entry(child, entry)) {
+ child = entry_to_node(entry);
+ offset = 0;
+ continue;
+ }
+ offset++;
+ while (offset == RADIX_TREE_MAP_SIZE) {
+ struct radix_tree_node *old = child;
+ offset = child->offset + 1;
+ child = child->parent;
+ radix_tree_node_free(old);
+ if (old == entry_to_node(node))
+ return;
+ }
+ }
+}
+
+static inline int insert_entries(struct radix_tree_node *node, void **slot,
+ void *item, unsigned order, bool replace)
+{
+ struct radix_tree_node *child;
+ unsigned i, n, tag, offset, tags = 0;
+
+ if (node) {
+ n = 1 << (order - node->shift);
+ offset = get_slot_offset(node, slot);
+ } else {
+ n = 1;
+ offset = 0;
+ }
+
+ if (n > 1) {
offset = offset & ~(n - 1);
slot = &node->slots[offset];
- child = node_to_entry(slot);
- for (i = 0; i < n; i++) {
- if (slot[i])
+ }
+ child = node_to_entry(slot);
+
+ for (i = 0; i < n; i++) {
+ if (slot[i]) {
+ if (replace) {
+ node->count--;
+ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
+ if (tag_get(node, tag, offset + i))
+ tags |= 1 << tag;
+ } else
return -EEXIST;
}
+ }
- for (i = 1; i < n; i++) {
+ for (i = 0; i < n; i++) {
+ struct radix_tree_node *old = slot[i];
+ if (i) {
rcu_assign_pointer(slot[i], child);
- node->count++;
+ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
+ if (tags & (1 << tag))
+ tag_clear(node, tag, offset + i);
+ } else {
+ rcu_assign_pointer(slot[i], item);
+ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
+ if (tags & (1 << tag))
+ tag_set(node, tag, offset);
}
+ if (radix_tree_is_internal_node(old) &&
+ !is_sibling_entry(node, old))
+ radix_tree_free_nodes(old);
+ if (radix_tree_exceptional_entry(old))
+ node->exceptional--;
}
-#endif
-
- if (nodep)
- *nodep = node;
- if (slotp)
- *slotp = slot;
- return 0;
+ if (node) {
+ node->count += n;
+ if (radix_tree_exceptional_entry(item))
+ node->exceptional += n;
+ }
+ return n;
}
+#else
+static inline int insert_entries(struct radix_tree_node *node, void **slot,
+ void *item, unsigned order, bool replace)
+{
+ if (*slot)
+ return -EEXIST;
+ rcu_assign_pointer(*slot, item);
+ if (node) {
+ node->count++;
+ if (radix_tree_exceptional_entry(item))
+ node->exceptional++;
+ }
+ return 1;
+}
+#endif
/**
* __radix_tree_insert - insert into a radix tree
@@ -757,15 +846,13 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
error = __radix_tree_create(root, index, order, &node, &slot);
if (error)
return error;
- if (*slot != NULL)
- return -EEXIST;
- rcu_assign_pointer(*slot, item);
+
+ error = insert_entries(node, slot, item, order, false);
+ if (error < 0)
+ return error;
if (node) {
unsigned offset = get_slot_offset(node, slot);
- node->count++;
- if (radix_tree_exceptional_entry(item))
- node->exceptional++;
BUG_ON(tag_get(node, 0, offset));
BUG_ON(tag_get(node, 1, offset));
BUG_ON(tag_get(node, 2, offset));
@@ -942,6 +1029,40 @@ void radix_tree_replace_slot(struct radix_tree_root *root,
replace_slot(root, NULL, slot, item, true);
}
+#ifdef CONFIG_RADIX_TREE_MULTIORDER
+/**
+ * radix_tree_join - replace multiple entries with one multiorder entry
+ * @root: radix tree root
+ * @index: an index inside the new entry
+ * @order: order of the new entry
+ * @item: new entry
+ *
+ * Call this function to replace several entries with one larger entry.
+ * The existing entries are presumed to not need freeing as a result of
+ * this call.
+ *
+ * The replacement entry will have all the tags set on it that were set
+ * on any of the entries it is replacing.
+ */
+int radix_tree_join(struct radix_tree_root *root, unsigned long index,
+ unsigned order, void *item)
+{
+ struct radix_tree_node *node;
+ void **slot;
+ int error;
+
+ BUG_ON(radix_tree_is_internal_node(item));
+
+ error = __radix_tree_create(root, index, order, &node, &slot);
+ if (!error)
+ error = insert_entries(node, slot, item, order, true);
+ if (error > 0)
+ error = 0;
+
+ return error;
+}
+#endif
+
/**
* radix_tree_tag_set - set a tag on a radix tree node
* @root: radix tree root
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 86daf23b3509620de06a8b0d2daee0ca58c69188..c9f656cf5f5291a43d408ac2fd0cbe3372cb8fac 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -332,6 +332,63 @@ void multiorder_tagged_iteration(void)
item_kill_tree(&tree);
}
+static void __multiorder_join(unsigned long index,
+ unsigned order1, unsigned order2)
+{
+ unsigned long loc;
+ void *item, *item2 = item_create(index + 1, order1);
+ RADIX_TREE(tree, GFP_KERNEL);
+
+ item_insert_order(&tree, index, order2);
+ item = radix_tree_lookup(&tree, index);
+ radix_tree_join(&tree, index + 1, order1, item2);
+ loc = find_item(&tree, item);
+ if (loc == -1)
+ free(item);
+ item = radix_tree_lookup(&tree, index + 1);
+ assert(item == item2);
+ item_kill_tree(&tree);
+}
+
+static void __multiorder_join2(unsigned order1, unsigned order2)
+{
+ RADIX_TREE(tree, GFP_KERNEL);
+ struct radix_tree_node *node;
+ void *item1 = item_create(0, order1);
+ void *item2;
+
+ item_insert_order(&tree, 0, order2);
+ radix_tree_insert(&tree, 1 << order2, (void *)0x12UL);
+ item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
+ assert(item2 == (void *)0x12UL);
+ assert(node->exceptional == 1);
+
+ radix_tree_join(&tree, 0, order1, item1);
+ item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
+ assert(item2 == item1);
+ assert(node->exceptional == 0);
+ item_kill_tree(&tree);
+}
+
+static void multiorder_join(void)
+{
+ int i, j, idx;
+
+ for (idx = 0; idx < 1024; idx = idx * 2 + 3) {
+ for (i = 1; i < 15; i++) {
+ for (j = 0; j < i; j++) {
+ __multiorder_join(idx, i, j);
+ }
+ }
+ }
+
+ for (i = 1; i < 15; i++) {
+ for (j = 0; j < i; j++) {
+ __multiorder_join2(i, j);
+ }
+ }
+}
+
void multiorder_checks(void)
{
int i;
@@ -349,4 +406,5 @@ void multiorder_checks(void)
multiorder_tag_tests();
multiorder_iteration();
multiorder_tagged_iteration();
+ multiorder_join();
}