The ability to have height 0 radix trees (a direct pointer to the data item
rather than going through a full node->slot) quietly disappeared with
old-2.6-bkcvs commit ffee171812d51652f9ba284302d9e5c5cc14bdfd.  On 64-bit
machines this causes nearly 600 bytes to be used for every <= 4K file in
pagecache.

Re-introduce this feature, root tags stored in spare ->gfp_mask bits.

Simplify radix_tree_delete's complex tag clearing arrangement (which would
become even more complex) by just falling back to tag clearing functions
(the pagecache radix-tree never uses this path anyway, so the icache
savings will mean it's actually a speedup).

On my 4GB G5, this saves 8MB RAM per kernel kernel source+object tree in
pagecache.

Pagecache lookup, insertion, and removal speed for small files will also be
improved.

This makes RCU radix tree harder, but it's worth it.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>