Fix mishandling of resjunk columns in ON CONFLICT ... UPDATE tlists.

tglsfdc · tglsfdc · commit 0fcb8e2e0154 · 2021-05-10T11:02:30.000-04:00
It's unusual to have any resjunk columns in an ON CONFLICT ... UPDATE list, but it can happen when MULTIEXPR_SUBLINK SubPlans are present. If it happens, the ON CONFLICT UPDATE code path would end up storing tuples that include the values of the extra resjunk columns. That's fairly harmless in the short run, but if new columns are added to the table then the values would become accessible, possibly leading to malfunctions if they don't match the datatypes of the new columns. This had escaped notice through a confluence of missing sanity checks, including * There's no cross-check that a tuple presented to heap_insert or heap_update matches the table rowtype. While it's difficult to check that fully at reasonable cost, we can easily add assertions that there aren't too many columns. * The output-column-assignment cases in execExprInterp.c lacked any sanity checks on the output column numbers, which seems like an oversight considering there are plenty of assertion checks on input column numbers. Add assertions there too. * We failed to apply nodeModifyTable's ExecCheckPlanOutput() to the ON CONFLICT UPDATE tlist. That wouldn't have caught this specific error, since that function is chartered to ignore resjunk columns; but it sure seems like a bad omission now that we've seen this bug. In HEAD, the right way to fix this is to make the processing of ON CONFLICT UPDATE tlists work the same as regular UPDATE tlists now do, that is don't add "SET x = x" entries, and use ExecBuildUpdateProjection to evaluate the tlist and combine it with old values of the not-set columns. This adds a little complication to ExecBuildUpdateProjection, but allows removal of a comparable amount of now-dead code from the planner. In the back branches, the most expedient solution seems to be to (a) use an output slot for the ON CONFLICT UPDATE projection that actually matches the target table, and then (b) invent a variant of ExecBuildProjectionInfo that can be told to not store values resulting from resjunk columns, so it doesn't try to store into nonexistent columns of the output slot. (We can't simply ignore the resjunk columns altogether; they have to be evaluated for MULTIEXPR_SUBLINK to work.) This works back to v10. In 9.6, projections work much differently and we can't cheaply give them such an option. The 9.6 version of this patch works by inserting a JunkFilter when it's necessary to get rid of resjunk columns. In addition, v11 and up have the reverse problem when trying to perform ON CONFLICT UPDATE on a partitioned table. Through a further oversight, adjust_partition_tlist() discarded resjunk columns when re-ordering the ON CONFLICT UPDATE tlist to match a partition. This accidentally prevented the storing-bogus-tuples problem, but at the cost that MULTIEXPR_SUBLINK cases didn't work, typically crashing if more than one row has to be updated. Fix by preserving resjunk columns in that routine. (I failed to resist the temptation to add more assertions there too, and to do some minor code beautification.) Per report from Andres Freund. Back-patch to all supported branches. Security: CVE-2021-32028
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
@@ -2389,6 +2389,10 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	Buffer		vmbuffer = InvalidBuffer;
 	bool		all_visible_cleared = false;
 
+	/* Cheap, simplistic check that the tuple matches the rel's rowtype. */
+	Assert(HeapTupleHeaderGetNatts(tup->t_data) <=
+		   RelationGetNumberOfAttributes(relation));
+
 	/*
 	 * Fill in tuple header fields, assign an OID, and toast the tuple if
 	 * necessary.
@@ -3490,6 +3494,10 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
 
 	Assert(ItemPointerIsValid(otid));
 
+	/* Cheap, simplistic check that the tuple matches the rel's rowtype. */
+	Assert(HeapTupleHeaderGetNatts(newtup->t_data) <=
+		   RelationGetNumberOfAttributes(relation));
+
 	/*
 	 * Forbid this during a parallel operation, lest it allocate a combocid.
 	 * Other workers might need that combocid for visibility checks, and we
diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c
@@ -1233,6 +1233,10 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 	/* Project the new tuple version */
 	ExecProject(resultRelInfo->ri_onConflictSetProj, NULL);
 
+	if (mtstate->mt_confljunk)
+		(void) ExecFilterJunk(mtstate->mt_confljunk,
+							  resultRelInfo->ri_onConflictSetProj->pi_slot);
+
 	/*
 	 * Note that it is possible that the target tuple has been modified in
 	 * this session, after the above heap_lock_tuple. We choose to not error
@@ -1744,7 +1748,6 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags)
 	{
 		ExprContext *econtext;
 		ExprState  *setexpr;
-		TupleDesc	tupDesc;
 
 		/* insert may only have one plan, inheritance is not expanded */
 		Assert(nplans == 1);
@@ -1764,17 +1767,54 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags)
 		mtstate->mt_excludedtlist = node->exclRelTlist;
 
 		/* create target slot for UPDATE SET projection */
-		tupDesc = ExecTypeFromTL((List *) node->onConflictSet,
-						 resultRelInfo->ri_RelationDesc->rd_rel->relhasoids);
 		mtstate->mt_conflproj = ExecInitExtraTupleSlot(mtstate->ps.state);
-		ExecSetSlotDescriptor(mtstate->mt_conflproj, tupDesc);
+		ExecSetSlotDescriptor(mtstate->mt_conflproj,
+							  resultRelInfo->ri_RelationDesc->rd_att);
 
-		/* build UPDATE SET expression and projection state */
+		/* initialize UPDATE SET tlist expressions */
 		setexpr = ExecInitExpr((Expr *) node->onConflictSet, &mtstate->ps);
-		resultRelInfo->ri_onConflictSetProj =
-			ExecBuildProjectionInfo((List *) setexpr, econtext,
-									mtstate->mt_conflproj,
-									resultRelInfo->ri_RelationDesc->rd_att);
+
+		/*
+		 * The onConflictSet tlist should already have been adjusted to emit
+		 * the table's exact column list.
+		 */
+		ExecCheckPlanOutput(resultRelInfo->ri_RelationDesc,
+							node->onConflictSet);
+
+		/*
+		 * However, it might also contain resjunk columns, in which case we'll
+		 * need a junkfilter to get rid of those.
+		 */
+		if (ExecCleanTargetListLength(node->onConflictSet) ==
+			list_length(node->onConflictSet))
+		{
+			/* No junk columns, so we'll just project into mt_conflproj. */
+			resultRelInfo->ri_onConflictSetProj =
+				ExecBuildProjectionInfo((List *) setexpr, econtext,
+										mtstate->mt_conflproj,
+										resultRelInfo->ri_RelationDesc->rd_att);
+			mtstate->mt_confljunk = NULL;
+		}
+		else
+		{
+			/*
+			 * Project into a slot matching the tlist's output rowtype, then
+			 * apply a junkfilter.
+			 */
+			TupleDesc	tupDesc = ExecTypeFromTL(node->onConflictSet, false);
+			TupleTableSlot *ocsSlot;
+
+			ocsSlot = ExecInitExtraTupleSlot(mtstate->ps.state);
+			ExecSetSlotDescriptor(ocsSlot, tupDesc);
+			resultRelInfo->ri_onConflictSetProj =
+				ExecBuildProjectionInfo((List *) setexpr, econtext,
+										ocsSlot,
+										resultRelInfo->ri_RelationDesc->rd_att);
+			mtstate->mt_confljunk =
+				ExecInitJunkFilter(node->onConflictSet,
+								   resultRelInfo->ri_RelationDesc->rd_att->tdhasoid,
+								   mtstate->mt_conflproj);
+		}
 
 		/* build DO UPDATE WHERE clause expression */
 		if (node->onConflictWhere)
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
@@ -1141,6 +1141,7 @@ typedef struct ModifyTableState
 										 * tlist  */
 	TupleTableSlot *mt_conflproj;		/* CONFLICT ... SET ... projection
 										 * target */
+	JunkFilter *mt_confljunk;	/* CONFLICT ... SET might need a junkfilter */
 } ModifyTableState;
 
 /* ----------------
diff --git a/src/test/regress/expected/update.out b/src/test/regress/expected/update.out
@@ -201,7 +201,7 @@ SELECT a, b, char_length(c) FROM update_test;
 (4 rows)
 
 -- Test ON CONFLICT DO UPDATE
-INSERT INTO upsert_test VALUES(1, 'Boo');
+INSERT INTO upsert_test VALUES(1, 'Boo'), (3, 'Zoo');
 -- uncorrelated  sub-select:
 WITH aaa AS (SELECT 1 AS a, 'Foo' AS b) INSERT INTO upsert_test
   VALUES (1, 'Bar') ON CONFLICT(a)
@@ -212,22 +212,24 @@ WITH aaa AS (SELECT 1 AS a, 'Foo' AS b) INSERT INTO upsert_test
 (1 row)
 
 -- correlated sub-select:
-INSERT INTO upsert_test VALUES (1, 'Baz') ON CONFLICT(a)
+INSERT INTO upsert_test VALUES (1, 'Baz'), (3, 'Zaz') ON CONFLICT(a)
   DO UPDATE SET (b, a) = (SELECT b || ', Correlated', a from upsert_test i WHERE i.a = upsert_test.a)
   RETURNING *;
  a |        b        
 ---+-----------------
  1 | Foo, Correlated
-(1 row)
+ 3 | Zoo, Correlated
+(2 rows)
 
 -- correlated sub-select (EXCLUDED.* alias):
-INSERT INTO upsert_test VALUES (1, 'Bat') ON CONFLICT(a)
+INSERT INTO upsert_test VALUES (1, 'Bat'), (3, 'Zot') ON CONFLICT(a)
   DO UPDATE SET (b, a) = (SELECT b || ', Excluded', a from upsert_test i WHERE i.a = excluded.a)
   RETURNING *;
  a |             b             
 ---+---------------------------
  1 | Foo, Correlated, Excluded
-(1 row)
+ 3 | Zoo, Correlated, Excluded
+(2 rows)
 
 DROP TABLE update_test;
 DROP TABLE upsert_test;
diff --git a/src/test/regress/sql/update.sql b/src/test/regress/sql/update.sql
@@ -99,17 +99,17 @@ UPDATE update_test t
 SELECT a, b, char_length(c) FROM update_test;
 
 -- Test ON CONFLICT DO UPDATE
-INSERT INTO upsert_test VALUES(1, 'Boo');
+INSERT INTO upsert_test VALUES(1, 'Boo'), (3, 'Zoo');
 -- uncorrelated  sub-select:
 WITH aaa AS (SELECT 1 AS a, 'Foo' AS b) INSERT INTO upsert_test
   VALUES (1, 'Bar') ON CONFLICT(a)
   DO UPDATE SET (b, a) = (SELECT b, a FROM aaa) RETURNING *;
 -- correlated sub-select:
-INSERT INTO upsert_test VALUES (1, 'Baz') ON CONFLICT(a)
+INSERT INTO upsert_test VALUES (1, 'Baz'), (3, 'Zaz') ON CONFLICT(a)
   DO UPDATE SET (b, a) = (SELECT b || ', Correlated', a from upsert_test i WHERE i.a = upsert_test.a)
   RETURNING *;
 -- correlated sub-select (EXCLUDED.* alias):
-INSERT INTO upsert_test VALUES (1, 'Bat') ON CONFLICT(a)
+INSERT INTO upsert_test VALUES (1, 'Bat'), (3, 'Zot') ON CONFLICT(a)
   DO UPDATE SET (b, a) = (SELECT b || ', Excluded', a from upsert_test i WHERE i.a = excluded.a)
   RETURNING *;
 
