- * - A RCU "order table" indexed by log2(hash index) is copied and
- * expanded by the resize operation. This order table allows finding
- * the "bucket node" tables.
- * - There is one bucket node table per hash index order. The size of
- * each bucket node table is half the number of hashes contained in
- * this order (except for order 0).
- * - synchronzie_rcu is used to garbage-collect the old bucket node table.
- * - The per-order bucket node tables contain a compact version of the
- * hash table nodes. These tables are invariant after they are
- * populated into the hash table.
+ * - There are three memory backends for the hash table buckets: the
+ * "order table", the "chunks", and the "mmap".
+ * - These bucket containers contain a compact version of the hash table
+ * nodes.
+ * - The RCU "order table":
+ * - has a first level table indexed by log2(hash index) which is
+ * copied and expanded by the resize operation. This order table
+ * allows finding the "bucket node" tables.
+ * - There is one bucket node table per hash index order. The size of
+ * each bucket node table is half the number of hashes contained in
+ * this order (except for order 0).
+ * - The RCU "chunks" is best suited for close interaction with a page
+ * allocator. It uses a linear array as index to "chunks" containing
+ * each the same number of buckets.
+ * - The RCU "mmap" memory backend uses a single memory map to hold
+ * all buckets.
+ * - synchronize_rcu is used to garbage-collect the old bucket node table.