Fix const-simplification for constraints and stats

Constraint expressions and statistics expressions loaded from the
system catalogs need to be run through const-simplification, because
the planner will be comparing them to similarly-processed qual
clauses.  Without this step, the planner may fail to detect valid
matches.

Currently, NullTest clauses in these expressions may not be reduced
correctly during const-simplification.  This happens because their Var
nodes do not yet have the correct varno when eval_const_expressions is
applied.  Since eval_const_expressions relies on varno to reduce
NullTest quals, incorrect varno can cause problems.

Additionally, for statistics expressions, eval_const_expressions is
called with root set to NULL, which also inhibits NullTest reduction.

This patch fixes the issue by ensuring that Vars are updated to have
the correct varno before const-simplification, and that a valid root
is passed to eval_const_expressions when needed.

Author: Richard Guo <guofenglinux@gmail.com>
Discussion: https://postgr.es/m/19007-4cc6e252ed8aa54a@postgresql.org

src/backend/optimizer/util/plancat.c

@@ -77,7 +77,8 @@ static List *get_relation_constraints(PlannerInfo *root,
 									  bool include_partition);
 static List *build_index_tlist(PlannerInfo *root, IndexOptInfo *index,
 							   Relation heapRelation);
-static List *get_relation_statistics(RelOptInfo *rel, Relation relation);
+static List *get_relation_statistics(PlannerInfo *root, RelOptInfo *rel,
+									 Relation relation);
 static void set_relation_partition_info(PlannerInfo *root, RelOptInfo *rel,
 										Relation relation);
 static PartitionScheme find_partition_scheme(PlannerInfo *root,
@@ -508,7 +509,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 
 	rel->indexlist = indexinfos;
 
-	rel->statlist = get_relation_statistics(rel, relation);
+	rel->statlist = get_relation_statistics(root, rel, relation);
 
 	/* Grab foreign-table info using the relcache, while we have it */
 	if (relation->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
@@ -1406,6 +1407,14 @@ get_relation_constraints(PlannerInfo *root,
 
 			cexpr = stringToNode(constr->check[i].ccbin);
 
+			/*
+			 * Fix Vars to have the desired varno.  This must be done before
+			 * const-simplification because eval_const_expressions reduces
+			 * NullTest for Vars based on varno.
+			 */
+			if (varno != 1)
+				ChangeVarNodes(cexpr, 1, varno, 0);
+
 			/*
 			 * Run each expression through const-simplification and
 			 * canonicalization.  This is not just an optimization, but is
@@ -1420,10 +1429,6 @@ get_relation_constraints(PlannerInfo *root,
 
 			cexpr = (Node *) canonicalize_qual((Expr *) cexpr, true);
 
-			/* Fix Vars to have the desired varno */
-			if (varno != 1)
-				ChangeVarNodes(cexpr, 1, varno, 0);
-
 			/*
 			 * Finally, convert to implicit-AND format (that is, a List) and
 			 * append the resulting item(s) to our output list.
@@ -1572,7 +1577,8 @@ get_relation_statistics_worker(List **stainfos, RelOptInfo *rel,
  * just the identifying metadata.  Only stats actually built are considered.
  */
 static List *
-get_relation_statistics(RelOptInfo *rel, Relation relation)
+get_relation_statistics(PlannerInfo *root, RelOptInfo *rel,
+						Relation relation)
 {
 	Index		varno = rel->relid;
 	List	   *statoidlist;
@@ -1604,8 +1610,8 @@ get_relation_statistics(RelOptInfo *rel, Relation relation)
 			keys = bms_add_member(keys, staForm->stxkeys.values[i]);
 
 		/*
-		 * Preprocess expressions (if any). We read the expressions, run them
+		 * Preprocess expressions (if any). We read the expressions, fix the
-		 * through eval_const_expressions, and fix the varnos.
+		 * varnos, and run them through eval_const_expressions.
 		 *
 		 * XXX We don't know yet if there are any data for this stats object,
 		 * with either stxdinherit value. But it's reasonable to assume there
@@ -1628,6 +1634,18 @@ get_relation_statistics(RelOptInfo *rel, Relation relation)
 				exprs = (List *) stringToNode(exprsString);
 				pfree(exprsString);
 
+				/*
+				 * Modify the copies we obtain from the relcache to have the
+				 * correct varno for the parent relation, so that they match
+				 * up correctly against qual clauses.
+				 *
+				 * This must be done before const-simplification because
+				 * eval_const_expressions reduces NullTest for Vars based on
+				 * varno.
+				 */
+				if (varno != 1)
+					ChangeVarNodes((Node *) exprs, 1, varno, 0);
+
 				/*
 				 * Run the expressions through eval_const_expressions. This is
 				 * not just an optimization, but is necessary, because the
@@ -1636,18 +1654,10 @@ get_relation_statistics(RelOptInfo *rel, Relation relation)
 				 * We must not use canonicalize_qual, however, since these
 				 * aren't qual expressions.
 				 */
-				exprs = (List *) eval_const_expressions(NULL, (Node *) exprs);
+				exprs = (List *) eval_const_expressions(root, (Node *) exprs);
 
 				/* May as well fix opfuncids too */
 				fix_opfuncids((Node *) exprs);
-
-				/*
-				 * Modify the copies we obtain from the relcache to have the
-				 * correct varno for the parent relation, so that they match
-				 * up correctly against qual clauses.
-				 */
-				if (varno != 1)
-					ChangeVarNodes((Node *) exprs, 1, varno, 0);
 			}
 		}
 

src/test/regress/expected/predicate.out

@@ -409,3 +409,30 @@ SELECT * FROM pred_tab t1
 
 DROP TABLE pred_tab;
 DROP TABLE pred_tab_notnull;
+-- Validate that NullTest quals in constraint expressions are reduced correctly
+CREATE TABLE pred_tab1 (a int NOT NULL, b int,
+	CONSTRAINT check_tab1 CHECK (a IS NULL OR b > 2));
+CREATE TABLE pred_tab2 (a int, b int,
+	CONSTRAINT check_a CHECK (a IS NOT NULL));
+SET constraint_exclusion TO ON;
+-- Ensure that we get a dummy plan
+EXPLAIN (COSTS OFF)
+SELECT * FROM pred_tab1, pred_tab2 WHERE pred_tab2.a IS NULL;
+        QUERY PLAN        
+--------------------------
+ Result
+   One-Time Filter: false
+(2 rows)
+
+-- Ensure that we get a dummy plan
+EXPLAIN (COSTS OFF)
+SELECT * FROM pred_tab2, pred_tab1 WHERE pred_tab1.a IS NULL OR pred_tab1.b < 2;
+        QUERY PLAN        
+--------------------------
+ Result
+   One-Time Filter: false
+(2 rows)
+
+RESET constraint_exclusion;
+DROP TABLE pred_tab1;
+DROP TABLE pred_tab2;

src/test/regress/sql/predicate.sql

@@ -201,3 +201,23 @@ SELECT * FROM pred_tab t1
 
 DROP TABLE pred_tab;
 DROP TABLE pred_tab_notnull;
+
+-- Validate that NullTest quals in constraint expressions are reduced correctly
+CREATE TABLE pred_tab1 (a int NOT NULL, b int,
+	CONSTRAINT check_tab1 CHECK (a IS NULL OR b > 2));
+CREATE TABLE pred_tab2 (a int, b int,
+	CONSTRAINT check_a CHECK (a IS NOT NULL));
+
+SET constraint_exclusion TO ON;
+
+-- Ensure that we get a dummy plan
+EXPLAIN (COSTS OFF)
+SELECT * FROM pred_tab1, pred_tab2 WHERE pred_tab2.a IS NULL;
+
+-- Ensure that we get a dummy plan
+EXPLAIN (COSTS OFF)
+SELECT * FROM pred_tab2, pred_tab1 WHERE pred_tab1.a IS NULL OR pred_tab1.b < 2;
+
+RESET constraint_exclusion;
+DROP TABLE pred_tab1;
+DROP TABLE pred_tab2;