Allow subquery pullup to wrap a PlaceHolderVar in another one.

The code for wrapping subquery output expressions in PlaceHolderVars
believed that if the expression already was a PlaceHolderVar, it was
never necessary to wrap that in another one.  That's wrong if the
expression is underneath an outer join and involves a lateral
reference to outside that scope: failing to add an additional PHV
risks evaluating the expression at the wrong place and hence not
forcing it to null when the outer join should do so.  This is an
oversight in commit 9e7e29c75, which added logic to forcibly wrap
lateral-reference Vars in PlaceHolderVars, but didn't see that the
adjacent case for PlaceHolderVars needed the same treatment.

The test case we have for this doesn't fail before 4be058fe9, but now
that I see the problem I wonder if it is possible to demonstrate
related errors before that.  That's moot though, since all such
branches are out of support.

Per bug #18284 from Holger Reise.  Back-patch to all supported
branches.

Discussion: https://postgr.es/m/18284-47505a20c23647f8@postgresql.org

diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c
index 7f4bb7b99a2f6252c9122b7d456b8b69133038a3..ea0576305d0a5f7c9d153bab276fea036080ce39 100644 (file)
--- a/src/backend/optimizer/prep/prepjointree.c
+++ b/src/backend/optimizer/prep/prepjointree.c
@@ -2471,8 +2471,13 @@ pullup_replace_vars_callback(Var *var,
                        else if (newnode && IsA(newnode, PlaceHolderVar) &&
                                         ((PlaceHolderVar *) newnode)->phlevelsup == 0)
                        {
-                               /* No need to wrap a PlaceHolderVar with another one, either */
-                               wrap = false;
+                               /* The same rules apply for a PlaceHolderVar */
+                               if (rcon->target_rte->lateral &&
+                                       !bms_is_subset(((PlaceHolderVar *) newnode)->phrels,
+                                                                  rcon->relids))
+                                       wrap = true;
+                               else
+                                       wrap = false;
                        }
                        else if (rcon->wrap_non_vars)
                        {

diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out
index 0eb6339f6089b78245124188075c240c4b4e73b6..867c6d20ccf8ab9fe513da137a970f478d838ba7 100644 (file)
--- a/src/test/regress/expected/join.out
+++ b/src/test/regress/expected/join.out
@@ -5803,6 +5803,32 @@ select * from
          Output: (COALESCE((COALESCE(b.q2, '42'::bigint)), d.q2))
 (24 rows)
 
+-- another case requiring nested PlaceHolderVars
+explain (verbose, costs off)
+select * from
+  (select 0 as val0) as ss0
+  left join (select 1 as val) as ss1 on true
+  left join lateral (select ss1.val as val_filtered where false) as ss2 on true;
+           QUERY PLAN           
+--------------------------------
+ Nested Loop Left Join
+   Output: 0, (1), ((1))
+   ->  Result
+         Output: 1
+   ->  Result
+         Output: (1)
+         One-Time Filter: false
+(7 rows)
+
+select * from
+  (select 0 as val0) as ss0
+  left join (select 1 as val) as ss1 on true
+  left join lateral (select ss1.val as val_filtered where false) as ss2 on true;
+ val0 | val | val_filtered 
+------+-----+--------------
+    0 |   1 |             
+(1 row)
+
 -- case that breaks the old ph_may_need optimization
 explain (verbose, costs off)
 select c.*,a.*,ss1.q1,ss2.q1,ss3.* from

diff --git a/src/test/regress/sql/join.sql b/src/test/regress/sql/join.sql
index 5fdacce91dfab9437c85253fcaf0a9393f0d4adf..1113e98445a328ee6d39374d40cb9ae0ffd18dd2 100644 (file)
--- a/src/test/regress/sql/join.sql
+++ b/src/test/regress/sql/join.sql
@@ -1978,6 +1978,18 @@ select * from
   ) on c.q2 = ss2.q1,
   lateral (select ss2.y offset 0) ss3;
 
+-- another case requiring nested PlaceHolderVars
+explain (verbose, costs off)
+select * from
+  (select 0 as val0) as ss0
+  left join (select 1 as val) as ss1 on true
+  left join lateral (select ss1.val as val_filtered where false) as ss2 on true;
+
+select * from
+  (select 0 as val0) as ss0
+  left join (select 1 as val) as ss1 on true
+  left join lateral (select ss1.val as val_filtered where false) as ss2 on true;
+
 -- case that breaks the old ph_may_need optimization
 explain (verbose, costs off)
 select c.*,a.*,ss1.q1,ss2.q1,ss3.* from