Separate arena_avail trees

Separate run trees by index, replacing the previous quantize logic.
Quantization by index is now performed only on insertion / removal from
the tree, and not on node comparison, saving some cpu.  This also means
we don't have to dereference the miscelm* pointers, saving half of the
memory loads from miscelms/mapbits that have fallen out of cache.  A
linear scan of the indicies appears to be fast enough.

The only cost of this is an extra tree array in each arena.

include/jemalloc/internal/arena.h

@@ -351,12 +351,6 @@ struct arena_s {
 	 */
 	size_t			ndirty;
 
-	/*
-	 * Size/address-ordered tree of this arena's available runs.  The tree
-	 * is used for first-best-fit run allocation.
-	 */
-	arena_avail_tree_t	runs_avail;
-
 	/*
 	 * Unused dirty memory this arena manages.  Dirty memory is conceptually
 	 * tracked as an arbitrarily interleaved LRU of dirty runs and cached
@@ -462,6 +456,12 @@ struct arena_s {
 
 	/* bins is used to store trees of free regions. */
 	arena_bin_t		bins[NBINS];
+
+	/*
+	 * Quantized address-ordered trees of this arena's available runs.  The
+	 * trees are used for first-best-fit run allocation.
+	 */
+	arena_avail_tree_t	runs_avail[1]; /* Dynamically sized. */
 };
 
 /* Used in conjunction with tsd for fast arena-related context lookup. */