Fix incorrect hash equality operator bug in Memoize

david-rowley · david-rowley · commit 39a3105678a2 · 2021-11-08T14:40:33.000+13:00
In v14, because we don't have a field in RestrictInfo to cache both the left and right type's hash equality operator, we just restrict the scope of Memoize to only when the left and right types of a RestrictInfo are the same. In master we add another field to RestrictInfo and cache both hash equality operators. Reported-by: Jaime Casanova Author: David Rowley Discussion: https://postgr.es/m/20210929185544.GB24346%40ahch-to Backpatch-through: 14
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
@@ -2362,7 +2362,8 @@ _copyRestrictInfo(const RestrictInfo *from)
 	COPY_SCALAR_FIELD(right_bucketsize);
 	COPY_SCALAR_FIELD(left_mcvfreq);
 	COPY_SCALAR_FIELD(right_mcvfreq);
-	COPY_SCALAR_FIELD(hasheqoperator);
+	COPY_SCALAR_FIELD(left_hasheqoperator);
+	COPY_SCALAR_FIELD(right_hasheqoperator);
 
 	return newnode;
 }
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
@@ -2565,7 +2565,8 @@ _outRestrictInfo(StringInfo str, const RestrictInfo *node)
 	WRITE_NODE_FIELD(right_em);
 	WRITE_BOOL_FIELD(outer_is_left);
 	WRITE_OID_FIELD(hashjoinoperator);
-	WRITE_OID_FIELD(hasheqoperator);
+	WRITE_OID_FIELD(left_hasheqoperator);
+	WRITE_OID_FIELD(right_hasheqoperator);
 }
 
 static void
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
@@ -394,27 +394,42 @@ paraminfo_get_equal_hashops(PlannerInfo *root, ParamPathInfo *param_info,
 			RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc);
 			OpExpr	   *opexpr;
 			Node	   *expr;
+			Oid			hasheqoperator;
 
-			/* can't use a memoize node without a valid hash equals operator */
-			if (!OidIsValid(rinfo->hasheqoperator) ||
+			opexpr = (OpExpr *) rinfo->clause;
+
+			/*
+			 * Bail if the rinfo is not compatible.  We need a join OpExpr
+			 * with 2 args.
+			 */
+			if (!IsA(opexpr, OpExpr) || list_length(opexpr->args) != 2 ||
 				!clause_sides_match_join(rinfo, outerrel, innerrel))
 			{
 				list_free(*operators);
 				list_free(*param_exprs);
 				return false;
 			}
 
-			/*
-			 * We already checked that this is an OpExpr with 2 args when
-			 * setting hasheqoperator.
-			 */
-			opexpr = (OpExpr *) rinfo->clause;
 			if (rinfo->outer_is_left)
+			{
 				expr = (Node *) linitial(opexpr->args);
+				hasheqoperator = rinfo->left_hasheqoperator;
+			}
 			else
+			{
 				expr = (Node *) lsecond(opexpr->args);
+				hasheqoperator = rinfo->right_hasheqoperator;
+			}
+
+			/* can't do memoize if we can't hash the outer type */
+			if (!OidIsValid(hasheqoperator))
+			{
+				list_free(*operators);
+				list_free(*param_exprs);
+				return false;
+			}
 
-			*operators = lappend_oid(*operators, rinfo->hasheqoperator);
+			*operators = lappend_oid(*operators, hasheqoperator);
 			*param_exprs = lappend(*param_exprs, expr);
 		}
 	}
diff --git a/src/backend/optimizer/plan/initsplan.c b/src/backend/optimizer/plan/initsplan.c
@@ -2711,15 +2711,16 @@ check_hashjoinable(RestrictInfo *restrictinfo)
 /*
  * check_memoizable
  *	  If the restrictinfo's clause is suitable to be used for a Memoize node,
- *	  set the hasheqoperator to the hash equality operator that will be needed
- *	  during caching.
+ *	  set the lefthasheqoperator and righthasheqoperator to the hash equality
+ *	  operator that will be needed during caching.
  */
 static void
 check_memoizable(RestrictInfo *restrictinfo)
 {
 	TypeCacheEntry *typentry;
 	Expr	   *clause = restrictinfo->clause;
-	Node	   *leftarg;
+	Oid			lefttype;
+	Oid			righttype;
 
 	if (restrictinfo->pseudoconstant)
 		return;
@@ -2728,13 +2729,24 @@ check_memoizable(RestrictInfo *restrictinfo)
 	if (list_length(((OpExpr *) clause)->args) != 2)
 		return;
 
-	leftarg = linitial(((OpExpr *) clause)->args);
+	lefttype = exprType(linitial(((OpExpr *) clause)->args));
 
-	typentry = lookup_type_cache(exprType(leftarg), TYPECACHE_HASH_PROC |
+	typentry = lookup_type_cache(lefttype, TYPECACHE_HASH_PROC |
 								 TYPECACHE_EQ_OPR);
 
-	if (!OidIsValid(typentry->hash_proc) || !OidIsValid(typentry->eq_opr))
-		return;
+	if (OidIsValid(typentry->hash_proc) && OidIsValid(typentry->eq_opr))
+		restrictinfo->left_hasheqoperator = typentry->eq_opr;
+
+	righttype = exprType(lsecond(((OpExpr *) clause)->args));
+
+	/*
+	 * Lookup the right type, unless it's the same as the left type, in which
+	 * case typentry is already pointing to the required TypeCacheEntry.
+	 */
+	if (lefttype != righttype)
+		typentry = lookup_type_cache(righttype, TYPECACHE_HASH_PROC |
+									 TYPECACHE_EQ_OPR);
 
-	restrictinfo->hasheqoperator = typentry->eq_opr;
+	if (OidIsValid(typentry->hash_proc) && OidIsValid(typentry->eq_opr))
+		restrictinfo->right_hasheqoperator = typentry->eq_opr;
 }
diff --git a/src/backend/optimizer/util/restrictinfo.c b/src/backend/optimizer/util/restrictinfo.c
@@ -217,7 +217,8 @@ make_restrictinfo_internal(PlannerInfo *root,
 	restrictinfo->left_mcvfreq = -1;
 	restrictinfo->right_mcvfreq = -1;
 
-	restrictinfo->hasheqoperator = InvalidOid;
+	restrictinfo->left_hasheqoperator = InvalidOid;
+	restrictinfo->right_hasheqoperator = InvalidOid;
 
 	return restrictinfo;
 }
@@ -368,7 +369,8 @@ commute_restrictinfo(RestrictInfo *rinfo, Oid comm_op)
 	result->right_bucketsize = rinfo->left_bucketsize;
 	result->left_mcvfreq = rinfo->right_mcvfreq;
 	result->right_mcvfreq = rinfo->left_mcvfreq;
-	result->hasheqoperator = InvalidOid;
+	result->left_hasheqoperator = InvalidOid;
+	result->right_hasheqoperator = InvalidOid;
 
 	return result;
 }
diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h
@@ -2122,8 +2122,9 @@ typedef struct RestrictInfo
 	Selectivity left_mcvfreq;	/* left side's most common val's freq */
 	Selectivity right_mcvfreq;	/* right side's most common val's freq */
 
-	/* hash equality operator used for memoize nodes, else InvalidOid */
-	Oid			hasheqoperator;
+	/* hash equality operators used for memoize nodes, else InvalidOid */
+	Oid			left_hasheqoperator;
+	Oid			right_hasheqoperator;
 } RestrictInfo;
 
 /*

Original file line number	Diff line number	Diff line change
`@@ -2362,7 +2362,8 @@ _copyRestrictInfo(const RestrictInfo *from)`
`2362`	`2362`	`COPY_SCALAR_FIELD(right_bucketsize);`
`2363`	`2363`	`COPY_SCALAR_FIELD(left_mcvfreq);`
`2364`	`2364`	`COPY_SCALAR_FIELD(right_mcvfreq);`
`2365`		`- COPY_SCALAR_FIELD(hasheqoperator);`
	`2365`	`+ COPY_SCALAR_FIELD(left_hasheqoperator);`
	`2366`	`+ COPY_SCALAR_FIELD(right_hasheqoperator);`
`2366`	`2367`
`2367`	`2368`	`return newnode;`
`2368`	`2369`	`}`
Original file line number	Diff line number	Diff line change
`@@ -2565,7 +2565,8 @@ _outRestrictInfo(StringInfo str, const RestrictInfo *node)`
`2565`	`2565`	`WRITE_NODE_FIELD(right_em);`
`2566`	`2566`	`WRITE_BOOL_FIELD(outer_is_left);`
`2567`	`2567`	`WRITE_OID_FIELD(hashjoinoperator);`
`2568`		`- WRITE_OID_FIELD(hasheqoperator);`
	`2568`	`+ WRITE_OID_FIELD(left_hasheqoperator);`
	`2569`	`+ WRITE_OID_FIELD(right_hasheqoperator);`
`2569`	`2570`	`}`
`2570`	`2571`
`2571`	`2572`	`static void`