Add a generic associative array implementation.

Add a generic associative array implementation that can be used as the
container for keyrings, thereby massively increasing the capacity available
whilst also speeding up searching in keyrings that contain a lot of keys.

This may also be useful in FS-Cache for tracking cookies.

Documentation is added into Documentation/associative_array.txt

Some of the properties of the implementation are:

 (1) Objects are opaque pointers.  The implementation does not care where they
     point (if anywhere) or what they point to (if anything).

     [!] NOTE: Pointers to objects _must_ be zero in the two least significant
     	       bits.

 (2) Objects do not need to contain linkage blocks for use by the array.  This
     permits an object to be located in multiple arrays simultaneously.
     Rather, the array is made up of metadata blocks that point to objects.

 (3) Objects are labelled as being one of two types (the type is a bool value).
     This information is stored in the array, but has no consequence to the
     array itself or its algorithms.

 (4) Objects require index keys to locate them within the array.

 (5) Index keys must be unique.  Inserting an object with the same key as one
     already in the array will replace the old object.

 (6) Index keys can be of any length and can be of different lengths.

 (7) Index keys should encode the length early on, before any variation due to
     length is seen.

 (8) Index keys can include a hash to scatter objects throughout the array.

 (9) The array can iterated over.  The objects will not necessarily come out in
     key order.

(10) The array can be iterated whilst it is being modified, provided the RCU
     readlock is being held by the iterator.  Note, however, under these
     circumstances, some objects may be seen more than once.  If this is a
     problem, the iterator should lock against modification.  Objects will not
     be missed, however, unless deleted.

(11) Objects in the array can be looked up by means of their index key.

(12) Objects can be looked up whilst the array is being modified, provided the
     RCU readlock is being held by the thread doing the look up.

The implementation uses a tree of 16-pointer nodes internally that are indexed
on each level by nibbles from the index key.  To improve memory efficiency,
shortcuts can be emplaced to skip over what would otherwise be a series of
single-occupancy nodes.  Further, nodes pack leaf object pointers into spare
space in the node rather than making an extra branch until as such time an
object needs to be added to a full node.

Signed-off-by: David Howells <dhowells@redhat.com>

2 files changed, 274 insertions, 0 deletions

diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h
new file mode 100644
index 00000000000..9a193b84238
--- /dev/null
+++ b/include/linux/assoc_array.h
@@ -0,0 +1,92 @@
+/* Generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_H
+#define _LINUX_ASSOC_ARRAY_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/types.h>
+
+#define ASSOC_ARRAY_KEY_CHUNK_SIZE BITS_PER_LONG /* Key data retrieved in chunks of this size */
+
+/*
+ * Generic associative array.
+ */
+struct assoc_array {
+	struct assoc_array_ptr	*root;		/* The node at the root of the tree */
+	unsigned long		nr_leaves_on_tree;
+};
+
+/*
+ * Operations on objects and index keys for use by array manipulation routines.
+ */
+struct assoc_array_ops {
+	/* Method to get a chunk of an index key from caller-supplied data */
+	unsigned long (*get_key_chunk)(const void *index_key, int level);
+
+	/* Method to get a piece of an object's index key */
+	unsigned long (*get_object_key_chunk)(const void *object, int level);
+
+	/* Is this the object we're looking for? */
+	bool (*compare_object)(const void *object, const void *index_key);
+
+	/* How different are two objects, to a bit position in their keys? (or
+	 * -1 if they're the same)
+	 */
+	int (*diff_objects)(const void *a, const void *b);
+
+	/* Method to free an object. */
+	void (*free_object)(void *object);
+};
+
+/*
+ * Access and manipulation functions.
+ */
+struct assoc_array_edit;
+
+static inline void assoc_array_init(struct assoc_array *array)
+{
+	array->root = NULL;
+	array->nr_leaves_on_tree = 0;
+}
+
+extern int assoc_array_iterate(const struct assoc_array *array,
+			       int (*iterator)(const void *object,
+					       void *iterator_data),
+			       void *iterator_data);
+extern void *assoc_array_find(const struct assoc_array *array,
+			      const struct assoc_array_ops *ops,
+			      const void *index_key);
+extern void assoc_array_destroy(struct assoc_array *array,
+				const struct assoc_array_ops *ops);
+extern struct assoc_array_edit *assoc_array_insert(struct assoc_array *array,
+						   const struct assoc_array_ops *ops,
+						   const void *index_key,
+						   void *object);
+extern void assoc_array_insert_set_object(struct assoc_array_edit *edit,
+					  void *object);
+extern struct assoc_array_edit *assoc_array_delete(struct assoc_array *array,
+						   const struct assoc_array_ops *ops,
+						   const void *index_key);
+extern struct assoc_array_edit *assoc_array_clear(struct assoc_array *array,
+						  const struct assoc_array_ops *ops);
+extern void assoc_array_apply_edit(struct assoc_array_edit *edit);
+extern void assoc_array_cancel_edit(struct assoc_array_edit *edit);
+extern int assoc_array_gc(struct assoc_array *array,
+			  const struct assoc_array_ops *ops,
+			  bool (*iterator)(void *object, void *iterator_data),
+			  void *iterator_data);
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_H */
diff --git a/include/linux/assoc_array_priv.h b/include/linux/assoc_array_priv.h
new file mode 100644
index 00000000000..711275e6681
--- /dev/null
+++ b/include/linux/assoc_array_priv.h
@@ -0,0 +1,182 @@
+/* Private definitions for the generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_PRIV_H
+#define _LINUX_ASSOC_ARRAY_PRIV_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/assoc_array.h>
+
+#define ASSOC_ARRAY_FAN_OUT		16	/* Number of slots per node */
+#define ASSOC_ARRAY_FAN_MASK		(ASSOC_ARRAY_FAN_OUT - 1)
+#define ASSOC_ARRAY_LEVEL_STEP		(ilog2(ASSOC_ARRAY_FAN_OUT))
+#define ASSOC_ARRAY_LEVEL_STEP_MASK	(ASSOC_ARRAY_LEVEL_STEP - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_MASK	(ASSOC_ARRAY_KEY_CHUNK_SIZE - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_SHIFT	(ilog2(BITS_PER_LONG))
+
+/*
+ * Undefined type representing a pointer with type information in the bottom
+ * two bits.
+ */
+struct assoc_array_ptr;
+
+/*
+ * An N-way node in the tree.
+ *
+ * Each slot contains one of four things:
+ *
+ *	(1) Nothing (NULL).
+ *
+ *	(2) A leaf object (pointer types 0).
+ *
+ *	(3) A next-level node (pointer type 1, subtype 0).
+ *
+ *	(4) A shortcut (pointer type 1, subtype 1).
+ *
+ * The tree is optimised for search-by-ID, but permits reasonable iteration
+ * also.
+ *
+ * The tree is navigated by constructing an index key consisting of an array of
+ * segments, where each segment is ilog2(ASSOC_ARRAY_FAN_OUT) bits in size.
+ *
+ * The segments correspond to levels of the tree (the first segment is used at
+ * level 0, the second at level 1, etc.).
+ */
+struct assoc_array_node {
+	struct assoc_array_ptr	*back_pointer;
+	u8			parent_slot;
+	struct assoc_array_ptr	*slots[ASSOC_ARRAY_FAN_OUT];
+	unsigned long		nr_leaves_on_branch;
+};
+
+/*
+ * A shortcut through the index space out to where a collection of nodes/leaves
+ * with the same IDs live.
+ */
+struct assoc_array_shortcut {
+	struct assoc_array_ptr	*back_pointer;
+	int			parent_slot;
+	int			skip_to_level;
+	struct assoc_array_ptr	*next_node;
+	unsigned long		index_key[];
+};
+
+/*
+ * Preallocation cache.
+ */
+struct assoc_array_edit {
+	struct rcu_head			rcu;
+	struct assoc_array		*array;
+	const struct assoc_array_ops	*ops;
+	const struct assoc_array_ops	*ops_for_excised_subtree;
+	struct assoc_array_ptr		*leaf;
+	struct assoc_array_ptr		**leaf_p;
+	struct assoc_array_ptr		*dead_leaf;
+	struct assoc_array_ptr		*new_meta[3];
+	struct assoc_array_ptr		*excised_meta[1];
+	struct assoc_array_ptr		*excised_subtree;
+	struct assoc_array_ptr		**set_backpointers[ASSOC_ARRAY_FAN_OUT];
+	struct assoc_array_ptr		*set_backpointers_to;
+	struct assoc_array_node		*adjust_count_on;
+	long				adjust_count_by;
+	struct {
+		struct assoc_array_ptr	**ptr;
+		struct assoc_array_ptr	*to;
+	} set[2];
+	struct {
+		u8			*p;
+		u8			to;
+	} set_parent_slot[1];
+	u8				segment_cache[ASSOC_ARRAY_FAN_OUT + 1];
+};
+
+/*
+ * Internal tree member pointers are marked in the bottom one or two bits to
+ * indicate what type they are so that we don't have to look behind every
+ * pointer to see what it points to.
+ *
+ * We provide functions to test type annotations and to create and translate
+ * the annotated pointers.
+ */
+#define ASSOC_ARRAY_PTR_TYPE_MASK 0x1UL
+#define ASSOC_ARRAY_PTR_LEAF_TYPE 0x0UL	/* Points to leaf (or nowhere) */
+#define ASSOC_ARRAY_PTR_META_TYPE 0x1UL	/* Points to node or shortcut */
+#define ASSOC_ARRAY_PTR_SUBTYPE_MASK	0x2UL
+#define ASSOC_ARRAY_PTR_NODE_SUBTYPE	0x0UL
+#define ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE 0x2UL
+
+static inline bool assoc_array_ptr_is_meta(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & ASSOC_ARRAY_PTR_TYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_leaf(const struct assoc_array_ptr *x)
+{
+	return !assoc_array_ptr_is_meta(x);
+}
+static inline bool assoc_array_ptr_is_shortcut(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & ASSOC_ARRAY_PTR_SUBTYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_node(const struct assoc_array_ptr *x)
+{
+	return !assoc_array_ptr_is_shortcut(x);
+}
+
+static inline void *assoc_array_ptr_to_leaf(const struct assoc_array_ptr *x)
+{
+	return (void *)((unsigned long)x & ~ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+
+static inline
+unsigned long __assoc_array_ptr_to_meta(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x &
+		~(ASSOC_ARRAY_PTR_SUBTYPE_MASK | ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+static inline
+struct assoc_array_node *assoc_array_ptr_to_node(const struct assoc_array_ptr *x)
+{
+	return (struct assoc_array_node *)__assoc_array_ptr_to_meta(x);
+}
+static inline
+struct assoc_array_shortcut *assoc_array_ptr_to_shortcut(const struct assoc_array_ptr *x)
+{
+	return (struct assoc_array_shortcut *)__assoc_array_ptr_to_meta(x);
+}
+
+static inline
+struct assoc_array_ptr *__assoc_array_x_to_ptr(const void *p, unsigned long t)
+{
+	return (struct assoc_array_ptr *)((unsigned long)p | t);
+}
+static inline
+struct assoc_array_ptr *assoc_array_leaf_to_ptr(const void *p)
+{
+	return __assoc_array_x_to_ptr(p, ASSOC_ARRAY_PTR_LEAF_TYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_node_to_ptr(const struct assoc_array_node *p)
+{
+	return __assoc_array_x_to_ptr(
+		p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_NODE_SUBTYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_shortcut_to_ptr(const struct assoc_array_shortcut *p)
+{
+	return __assoc_array_x_to_ptr(
+		p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE);
+}
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_PRIV_H */