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 1f20d1885c4e387965154c0b9c9054c712b0a2a1..264d5af65ec2df4c54d2e0b0da98d02b427d7411 100644 (file)
--- a/src/backend/optimizer/prep/prepjointree.c
+++ b/src/backend/optimizer/prep/prepjointree.c
@@ -2364,8 +2364,13 @@ 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 b11a1cabc34066aca42eec9264586f7f4a5c188a..8eaa964d4627b33c073837cb792370b65153a126 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 bb72975ffbd289dde4e921d3e12eed3ba4eeb599..f8ed53fcc438b5314d99160ba919dd63b602131e 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