Doc: split up wait_event table.

The previous design for this table didn't really work in narrow views,
such as PDF output; besides which its reliance on large morerows
values made it a pain to maintain (cf ab3e4fbd5, for example).

I experimented with a couple of ways to fix it, but the best and
simplest is to split it up into a separate table for each event
type category.

I also rearranged the event ordering to be strictly alphabetical,
as nobody would ever be able to find entries otherwise.

There is work afoot to revise the set of event names described
in this table, but this commit just changes the layout, not the
contents.

In passing, add a missing entry to pg_locks.locktype,
and cross-reference that to the related wait event list.

Discussion: https://postgr.es/m/6916.1589146280@sss.pgh.pa.us

doc/src/sgml/catalogs.sgml

@@ -10238,9 +10238,11 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
        <literal>tuple</literal>,
        <literal>transactionid</literal>,
        <literal>virtualxid</literal>,
+       <literal>speculative token</literal>,
        <literal>object</literal>,
        <literal>userlock</literal>, or
-       <literal>advisory</literal>
+       <literal>advisory</literal>.
+       (See also <xref linkend="wait-event-lock-table"/>.)
       </para></entry>
      </row>