tableam: Add tuple_{insert, delete, update, lock} and use.

This adds new, required, table AM callbacks for insert/delete/update
and lock_tuple. To be able to reasonably use those, the EvalPlanQual
mechanism had to be adapted, moving more logic into the AM.

Previously both delete/update/lock call-sites and the EPQ mechanism had
to have awareness of the specific tuple format to be able to fetch the
latest version of a tuple. Obviously that needs to be abstracted
away. To do so, move the logic that find the latest row version into
the AM. lock_tuple has a new flag argument,
TUPLE_LOCK_FLAG_FIND_LAST_VERSION, that forces it to lock the last
version, rather than the current one.  It'd have been possible to do
so via a separate callback as well, but finding the last version
usually also necessitates locking the newest version, making it
sensible to combine the two. This replaces the previous use of
EvalPlanQualFetch().  Additionally HeapTupleUpdated, which previously
signaled either a concurrent update or delete, is now split into two,
to avoid callers needing AM specific knowledge to differentiate.

The move of finding the latest row version into tuple_lock means that
encountering a row concurrently moved into another partition will now
raise an error about "tuple to be locked" rather than "tuple to be
updated/deleted" - which is accurate, as that always happens when
locking rows. While possible slightly less helpful for users, it seems
like an acceptable trade-off.

As part of this commit HTSU_Result has been renamed to TM_Result, and
its members been expanded to differentiated between updating and
deleting. HeapUpdateFailureData has been renamed to TM_FailureData.

The interface to speculative insertion is changed so nodeModifyTable.c
does not have to set the speculative token itself anymore. Instead
there's a version of tuple_insert, tuple_insert_speculative, that
performs the speculative insertion (without requiring a flag to signal
that fact), and the speculative insertion is either made permanent
with table_complete_speculative(succeeded = true) or aborted with
succeeded = false).

Note that multi_insert is not yet routed through tableam, nor is
COPY. Changing multi_insert requires changes to copy.c that are large
enough to better be done separately.

Similarly, although simpler, CREATE TABLE AS and CREATE MATERIALIZED
VIEW are also only going to be adjusted in a later commit.

Author: Andres Freund and Haribabu Kommi
Discussion:
    https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de
    https://postgr.es/m/20190313003903.nwvrxi7rw3ywhdel@alap3.anarazel.de
    https://postgr.es/m/20160812231527.GA690404@alvherre.pgsql

1 files changed, 256 insertions, 179 deletions

diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c
index fa92db130bb..1374b751767 100644
--- a/src/backend/executor/nodeModifyTable.c
+++ b/src/backend/executor/nodeModifyTable.c
@@ -181,7 +181,7 @@ ExecProcessReturning(ResultRelInfo *resultRelInfo,
 }
 
 /*
- * ExecCheckHeapTupleVisible -- verify heap tuple is visible
+ * ExecCheckTupleVisible -- verify tuple is visible
  *
  * It would not be consistent with guarantees of the higher isolation levels to
  * proceed with avoiding insertion (taking speculative insertion's alternative
@@ -189,41 +189,44 @@ ExecProcessReturning(ResultRelInfo *resultRelInfo,
  * Check for the need to raise a serialization failure, and do so as necessary.
  */
 static void
-ExecCheckHeapTupleVisible(EState *estate,
-						  HeapTuple tuple,
-						  Buffer buffer)
+ExecCheckTupleVisible(EState *estate,
+					  Relation rel,
+					  TupleTableSlot *slot)
 {
 	if (!IsolationUsesXactSnapshot())
 		return;
 
-	/*
-	 * We need buffer pin and lock to call HeapTupleSatisfiesVisibility.
-	 * Caller should be holding pin, but not lock.
-	 */
-	LockBuffer(buffer, BUFFER_LOCK_SHARE);
-	if (!HeapTupleSatisfiesVisibility(tuple, estate->es_snapshot, buffer))
+	if (!table_tuple_satisfies_snapshot(rel, slot, estate->es_snapshot))
 	{
+		Datum		xminDatum;
+		TransactionId xmin;
+		bool		isnull;
+
+		xminDatum = slot_getsysattr(slot, MinTransactionIdAttributeNumber, &isnull);
+		Assert(!isnull);
+		xmin = DatumGetTransactionId(xminDatum);
+
 		/*
 		 * We should not raise a serialization failure if the conflict is
 		 * against a tuple inserted by our own transaction, even if it's not
 		 * visible to our snapshot.  (This would happen, for example, if
 		 * conflicting keys are proposed for insertion in a single command.)
 		 */
-		if (!TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple->t_data)))
+		if (!TransactionIdIsCurrentTransactionId(xmin))
 			ereport(ERROR,
 					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
 					 errmsg("could not serialize access due to concurrent update")));
 	}
-	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 }
 
 /*
- * ExecCheckTIDVisible -- convenience variant of ExecCheckHeapTupleVisible()
+ * ExecCheckTIDVisible -- convenience variant of ExecCheckTupleVisible()
  */
 static void
 ExecCheckTIDVisible(EState *estate,
 					ResultRelInfo *relinfo,
-					ItemPointer tid)
+					ItemPointer tid,
+					TupleTableSlot *tempSlot)
 {
 	Relation	rel = relinfo->ri_RelationDesc;
 	Buffer		buffer;
@@ -234,10 +237,11 @@ ExecCheckTIDVisible(EState *estate,
 		return;
 
 	tuple.t_self = *tid;
-	if (!heap_fetch(rel, SnapshotAny, &tuple, &buffer, false, NULL))
+	if (!heap_fetch(rel, SnapshotAny, &tuple, &buffer, NULL))
 		elog(ERROR, "failed to fetch conflicting tuple for ON CONFLICT");
-	ExecCheckHeapTupleVisible(estate, &tuple, buffer);
-	ReleaseBuffer(buffer);
+	ExecStorePinnedBufferHeapTuple(&tuple, tempSlot, buffer);
+	ExecCheckTupleVisible(estate, rel, tempSlot);
+	ExecClearTuple(tempSlot);
 }
 
 /* ----------------------------------------------------------------
@@ -319,7 +323,6 @@ ExecInsert(ModifyTableState *mtstate,
 	else
 	{
 		WCOKind		wco_kind;
-		HeapTuple	inserttuple;
 
 		/*
 		 * Constraints might reference the tableoid column, so (re-)initialize
@@ -417,16 +420,21 @@ ExecInsert(ModifyTableState *mtstate,
 					 * In case of ON CONFLICT DO NOTHING, do nothing. However,
 					 * verify that the tuple is visible to the executor's MVCC
 					 * snapshot at higher isolation levels.
+					 *
+					 * Using ExecGetReturningSlot() to store the tuple for the
+					 * recheck isn't that pretty, but we can't trivially use
+					 * the input slot, because it might not be of a compatible
+					 * type. As there's no conflicting usage of
+					 * ExecGetReturningSlot() in the DO NOTHING case...
 					 */
 					Assert(onconflict == ONCONFLICT_NOTHING);
-					ExecCheckTIDVisible(estate, resultRelInfo, &conflictTid);
+					ExecCheckTIDVisible(estate, resultRelInfo, &conflictTid,
+										ExecGetReturningSlot(estate, resultRelInfo));
 					InstrCountTuples2(&mtstate->ps, 1);
 					return NULL;
 				}
 			}
 
-			inserttuple = ExecFetchSlotHeapTuple(slot, true, NULL);
-
 			/*
 			 * Before we start insertion proper, acquire our "speculative
 			 * insertion lock".  Others can use that to wait for us to decide
@@ -434,26 +442,22 @@ ExecInsert(ModifyTableState *mtstate,
 			 * waiting for the whole transaction to complete.
 			 */
 			specToken = SpeculativeInsertionLockAcquire(GetCurrentTransactionId());
-			HeapTupleHeaderSetSpeculativeToken(inserttuple->t_data, specToken);
 
 			/* insert the tuple, with the speculative token */
-			heap_insert(resultRelationDesc, inserttuple,
-						estate->es_output_cid,
-						HEAP_INSERT_SPECULATIVE,
-						NULL);
-			slot->tts_tableOid = RelationGetRelid(resultRelationDesc);
-			ItemPointerCopy(&inserttuple->t_self, &slot->tts_tid);
+			table_insert_speculative(resultRelationDesc, slot,
+									 estate->es_output_cid,
+									 0,
+									 NULL,
+									 specToken);
 
 			/* insert index entries for tuple */
-			recheckIndexes = ExecInsertIndexTuples(slot, &(inserttuple->t_self),
-												   estate, true, &specConflict,
+			recheckIndexes = ExecInsertIndexTuples(slot, estate, true,
+												   &specConflict,
 												   arbiterIndexes);
 
 			/* adjust the tuple's state accordingly */
-			if (!specConflict)
-				heap_finish_speculative(resultRelationDesc, inserttuple);
-			else
-				heap_abort_speculative(resultRelationDesc, inserttuple);
+			table_complete_speculative(resultRelationDesc, slot,
+									   specToken, specConflict);
 
 			/*
 			 * Wake up anyone waiting for our decision.  They will re-check
@@ -479,23 +483,14 @@ ExecInsert(ModifyTableState *mtstate,
 		}
 		else
 		{
-			/*
-			 * insert the tuple normally.
-			 *
-			 * Note: heap_insert returns the tid (location) of the new tuple
-			 * in the t_self field.
-			 */
-			inserttuple = ExecFetchSlotHeapTuple(slot, true, NULL);
-			heap_insert(resultRelationDesc, inserttuple,
-						estate->es_output_cid,
-						0, NULL);
-			slot->tts_tableOid = RelationGetRelid(resultRelationDesc);
-			ItemPointerCopy(&inserttuple->t_self, &slot->tts_tid);
+			/* insert the tuple normally */
+			table_insert(resultRelationDesc, slot,
+						 estate->es_output_cid,
+						 0, NULL);
 
 			/* insert index entries for tuple */
 			if (resultRelInfo->ri_NumIndices > 0)
-				recheckIndexes = ExecInsertIndexTuples(slot, &(inserttuple->t_self),
-													   estate, false, NULL,
+				recheckIndexes = ExecInsertIndexTuples(slot, estate, false, NULL,
 													   NIL);
 		}
 	}
@@ -594,8 +589,8 @@ ExecDelete(ModifyTableState *mtstate,
 {
 	ResultRelInfo *resultRelInfo;
 	Relation	resultRelationDesc;
-	HTSU_Result result;
-	HeapUpdateFailureData hufd;
+	TM_Result	result;
+	TM_FailureData tmfd;
 	TupleTableSlot *slot = NULL;
 	TransitionCaptureState *ar_delete_trig_tcs;
 
@@ -671,15 +666,17 @@ ExecDelete(ModifyTableState *mtstate,
 		 * mode transactions.
 		 */
 ldelete:;
-		result = heap_delete(resultRelationDesc, tupleid,
-							 estate->es_output_cid,
-							 estate->es_crosscheck_snapshot,
-							 true /* wait for commit */ ,
-							 &hufd,
-							 changingPart);
+		result = table_delete(resultRelationDesc, tupleid,
+							  estate->es_output_cid,
+							  estate->es_snapshot,
+							  estate->es_crosscheck_snapshot,
+							  true /* wait for commit */ ,
+							  &tmfd,
+							  changingPart);
+
 		switch (result)
 		{
-			case HeapTupleSelfUpdated:
+			case TM_SelfModified:
 
 				/*
 				 * The target tuple was already updated or deleted by the
@@ -705,7 +702,7 @@ ldelete:;
 				 * can re-execute the DELETE and then return NULL to cancel
 				 * the outer delete.
 				 */
-				if (hufd.cmax != estate->es_output_cid)
+				if (tmfd.cmax != estate->es_output_cid)
 					ereport(ERROR,
 							(errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION),
 							 errmsg("tuple to be updated was already modified by an operation triggered by the current command"),
@@ -714,52 +711,98 @@ ldelete:;
 				/* Else, already deleted by self; nothing to do */
 				return NULL;
 
-			case HeapTupleMayBeUpdated:
+			case TM_Ok:
 				break;
 
-			case HeapTupleUpdated:
-				if (IsolationUsesXactSnapshot())
-					ereport(ERROR,
-							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
-							 errmsg("could not serialize access due to concurrent update")));
-				if (ItemPointerIndicatesMovedPartitions(&hufd.ctid))
-					ereport(ERROR,
-							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
-							 errmsg("tuple to be deleted was already moved to another partition due to concurrent update")));
-
-				if (!ItemPointerEquals(tupleid, &hufd.ctid))
+			case TM_Updated:
 				{
-					TupleTableSlot *my_epqslot;
-
-					my_epqslot = EvalPlanQual(estate,
-											  epqstate,
-											  resultRelationDesc,
-											  resultRelInfo->ri_RangeTableIndex,
-											  LockTupleExclusive,
-											  &hufd.ctid,
-											  hufd.xmax);
-					if (!TupIsNull(my_epqslot))
+					TupleTableSlot *inputslot;
+					TupleTableSlot *epqslot;
+
+					if (IsolationUsesXactSnapshot())
+						ereport(ERROR,
+								(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+								 errmsg("could not serialize access due to concurrent update")));
+
+					/*
+					 * Already know that we're going to need to do EPQ, so
+					 * fetch tuple directly into the right slot.
+					 */
+					EvalPlanQualBegin(epqstate, estate);
+					inputslot = EvalPlanQualSlot(epqstate, resultRelationDesc,
+												 resultRelInfo->ri_RangeTableIndex);
+
+					result = table_lock_tuple(resultRelationDesc, tupleid,
+											  estate->es_snapshot,
+											  inputslot, estate->es_output_cid,
+											  LockTupleExclusive, LockWaitBlock,
+											  TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
+											  &tmfd);
+
+					switch (result)
 					{
-						*tupleid = hufd.ctid;
+						case TM_Ok:
+							Assert(tmfd.traversed);
+							epqslot = EvalPlanQual(estate,
+												   epqstate,
+												   resultRelationDesc,
+												   resultRelInfo->ri_RangeTableIndex,
+												   inputslot);
+							if (TupIsNull(epqslot))
+								/* Tuple not passing quals anymore, exiting... */
+								return NULL;
+
+							/*
+							 * If requested, skip delete and pass back the
+							 * updated row.
+							 */
+							if (epqreturnslot)
+							{
+								*epqreturnslot = epqslot;
+								return NULL;
+							}
+							else
+								goto ldelete;
+
+						case TM_Deleted:
+							/* tuple already deleted; nothing to do */
+							return NULL;
 
-						/*
-						 * If requested, skip delete and pass back the updated
-						 * row.
-						 */
-						if (epqreturnslot)
-						{
-							*epqreturnslot = my_epqslot;
+						default:
+
+							/*
+							 * TM_Invisible should be impossible because we're
+							 * waiting for updated row versions, and would
+							 * already have errored out if the first version
+							 * is invisible.
+							 *
+							 * TM_SelfModified should be impossible, as we'd
+							 * otherwise should have hit the TM_SelfModified
+							 * case in response to table_delete above.
+							 *
+							 * TM_Updated should be impossible, because we're
+							 * locking the latest version via
+							 * TUPLE_LOCK_FLAG_FIND_LAST_VERSION.
+							 */
+							elog(ERROR, "unexpected table_lock_tuple status: %u",
+								 result);
 							return NULL;
-						}
-						else
-							goto ldelete;
 					}
+
+					Assert(false);
+					break;
 				}
+
+			case TM_Deleted:
+				if (IsolationUsesXactSnapshot())
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("could not serialize access due to concurrent delete")));
 				/* tuple already deleted; nothing to do */
 				return NULL;
 
 			default:
-				elog(ERROR, "unrecognized heap_delete status: %u", result);
+				elog(ERROR, "unrecognized table_delete status: %u", result);
 				return NULL;
 		}
 
@@ -832,8 +875,8 @@ ldelete:;
 			else
 			{
 				BufferHeapTupleTableSlot *bslot;
-				HeapTuple deltuple;
-				Buffer buffer;
+				HeapTuple	deltuple;
+				Buffer		buffer;
 
 				Assert(TTS_IS_BUFFERTUPLE(slot));
 				ExecClearTuple(slot);
@@ -842,7 +885,7 @@ ldelete:;
 
 				deltuple->t_self = *tupleid;
 				if (!heap_fetch(resultRelationDesc, SnapshotAny,
-								deltuple, &buffer, false, NULL))
+								deltuple, &buffer, NULL))
 					elog(ERROR, "failed to fetch deleted tuple for DELETE RETURNING");
 
 				ExecStorePinnedBufferHeapTuple(deltuple, slot, buffer);
@@ -897,11 +940,10 @@ ExecUpdate(ModifyTableState *mtstate,
 		   EState *estate,
 		   bool canSetTag)
 {
-	HeapTuple	updatetuple;
 	ResultRelInfo *resultRelInfo;
 	Relation	resultRelationDesc;
-	HTSU_Result result;
-	HeapUpdateFailureData hufd;
+	TM_Result	result;
+	TM_FailureData tmfd;
 	List	   *recheckIndexes = NIL;
 	TupleConversionMap *saved_tcs_map = NULL;
 
@@ -960,6 +1002,7 @@ ExecUpdate(ModifyTableState *mtstate,
 	{
 		LockTupleMode lockmode;
 		bool		partition_constraint_failed;
+		bool		update_indexes;
 
 		/*
 		 * Constraints might reference the tableoid column, so (re-)initialize
@@ -973,11 +1016,14 @@ ExecUpdate(ModifyTableState *mtstate,
 		 * If we generate a new candidate tuple after EvalPlanQual testing, we
 		 * must loop back here and recheck any RLS policies and constraints.
 		 * (We don't need to redo triggers, however.  If there are any BEFORE
-		 * triggers then trigger.c will have done heap_lock_tuple to lock the
+		 * triggers then trigger.c will have done table_lock_tuple to lock the
 		 * correct tuple, so there's no need to do them again.)
 		 */
 lreplace:;
 
+		/* ensure slot is independent, consider e.g. EPQ */
+		ExecMaterializeSlot(slot);
+
 		/*
 		 * If partition constraint fails, this row might get moved to another
 		 * partition, in which case we should check the RLS CHECK policy just
@@ -1145,18 +1191,16 @@ lreplace:;
 		 * needed for referential integrity updates in transaction-snapshot
 		 * mode transactions.
 		 */
-		updatetuple = ExecFetchSlotHeapTuple(slot, true, NULL);
-		result = heap_update(resultRelationDesc, tupleid,
-							 updatetuple,
-							 estate->es_output_cid,
-							 estate->es_crosscheck_snapshot,
-							 true /* wait for commit */ ,
-							 &hufd, &lockmode);
-		ItemPointerCopy(&updatetuple->t_self, &slot->tts_tid);
+		result = table_update(resultRelationDesc, tupleid, slot,
+							  estate->es_output_cid,
+							  estate->es_snapshot,
+							  estate->es_crosscheck_snapshot,
+							  true /* wait for commit */ ,
+							  &tmfd, &lockmode, &update_indexes);
 
 		switch (result)
 		{
-			case HeapTupleSelfUpdated:
+			case TM_SelfModified:
 
 				/*
 				 * The target tuple was already updated or deleted by the
@@ -1181,7 +1225,7 @@ lreplace:;
 				 * can re-execute the UPDATE (assuming it can figure out how)
 				 * and then return NULL to cancel the outer update.
 				 */
-				if (hufd.cmax != estate->es_output_cid)
+				if (tmfd.cmax != estate->es_output_cid)
 					ereport(ERROR,
 							(errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION),
 							 errmsg("tuple to be updated was already modified by an operation triggered by the current command"),
@@ -1190,64 +1234,81 @@ lreplace:;
 				/* Else, already updated by self; nothing to do */
 				return NULL;
 
-			case HeapTupleMayBeUpdated:
+			case TM_Ok:
 				break;
 
-			case HeapTupleUpdated:
-				if (IsolationUsesXactSnapshot())
-					ereport(ERROR,
-							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
-							 errmsg("could not serialize access due to concurrent update")));
-				if (ItemPointerIndicatesMovedPartitions(&hufd.ctid))
-					ereport(ERROR,
-							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
-							 errmsg("tuple to be updated was already moved to another partition due to concurrent update")));
-
-				if (!ItemPointerEquals(tupleid, &hufd.ctid))
+			case TM_Updated:
 				{
+					TupleTableSlot *inputslot;
 					TupleTableSlot *epqslot;
 
-					epqslot = EvalPlanQual(estate,
-										   epqstate,
-										   resultRelationDesc,
-										   resultRelInfo->ri_RangeTableIndex,
-										   lockmode,
-										   &hufd.ctid,
-										   hufd.xmax);
-					if (!TupIsNull(epqslot))
+					if (IsolationUsesXactSnapshot())
+						ereport(ERROR,
+								(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+								 errmsg("could not serialize access due to concurrent update")));
+
+					/*
+					 * Already know that we're going to need to do EPQ, so
+					 * fetch tuple directly into the right slot.
+					 */
+					EvalPlanQualBegin(epqstate, estate);
+					inputslot = EvalPlanQualSlot(epqstate, resultRelationDesc,
+												 resultRelInfo->ri_RangeTableIndex);
+
+					result = table_lock_tuple(resultRelationDesc, tupleid,
+											  estate->es_snapshot,
+											  inputslot, estate->es_output_cid,
+											  lockmode, LockWaitBlock,
+											  TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
+											  &tmfd);
+
+					switch (result)
 					{
-						*tupleid = hufd.ctid;
-						slot = ExecFilterJunk(resultRelInfo->ri_junkFilter, epqslot);
-						goto lreplace;
+						case TM_Ok:
+							Assert(tmfd.traversed);
+
+							epqslot = EvalPlanQual(estate,
+												   epqstate,
+												   resultRelationDesc,
+												   resultRelInfo->ri_RangeTableIndex,
+												   inputslot);
+							if (TupIsNull(epqslot))
+								/* Tuple not passing quals anymore, exiting... */
+								return NULL;
+
+							slot = ExecFilterJunk(resultRelInfo->ri_junkFilter, epqslot);
+							goto lreplace;
+
+						case TM_Deleted:
+							/* tuple already deleted; nothing to do */
+							return NULL;
+
+						default:
+							/* see table_lock_tuple call in ExecDelete() */
+							elog(ERROR, "unexpected table_lock_tuple status: %u",
+								 result);
+							return NULL;
 					}
 				}
+
+				break;
+
+			case TM_Deleted:
+				if (IsolationUsesXactSnapshot())
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("could not serialize access due to concurrent delete")));
 				/* tuple already deleted; nothing to do */
 				return NULL;
 
 			default:
-				elog(ERROR, "unrecognized heap_update status: %u", result);
+				elog(ERROR, "unrecognized table_update status: %u", result);
 				return NULL;
 		}
 
-		/*
-		 * Note: instead of having to update the old index tuples associated
-		 * with the heap tuple, all we do is form and insert new index tuples.
-		 * This is because UPDATEs are actually DELETEs and INSERTs, and index
-		 * tuple deletion is done later by VACUUM (see notes in ExecDelete).
-		 * All we do here is insert new index tuples.  -cim 9/27/89
-		 */
-
-		/*
-		 * insert index entries for tuple
-		 *
-		 * Note: heap_update returns the tid (location) of the new tuple in
-		 * the t_self field.
-		 *
-		 * If it's a HOT update, we mustn't insert new index entries.
-		 */
-		if (resultRelInfo->ri_NumIndices > 0 && !HeapTupleIsHeapOnly(updatetuple))
-			recheckIndexes = ExecInsertIndexTuples(slot, &(updatetuple->t_self),
-												   estate, false, NULL, NIL);
+		/* insert index entries for tuple if necessary */
+		if (resultRelInfo->ri_NumIndices > 0 && update_indexes)
+			recheckIndexes = ExecInsertIndexTuples(slot, estate, false, NULL, NIL);
 	}
 
 	if (canSetTag)
@@ -1306,11 +1367,12 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 	Relation	relation = resultRelInfo->ri_RelationDesc;
 	ExprState  *onConflictSetWhere = resultRelInfo->ri_onConflict->oc_WhereClause;
 	TupleTableSlot *existing = resultRelInfo->ri_onConflict->oc_Existing;
-	HeapTupleData tuple;
-	HeapUpdateFailureData hufd;
+	TM_FailureData tmfd;
 	LockTupleMode lockmode;
-	HTSU_Result test;
-	Buffer		buffer;
+	TM_Result	test;
+	Datum		xminDatum;
+	TransactionId xmin;
+	bool		isnull;
 
 	/* Determine lock mode to use */
 	lockmode = ExecUpdateLockMode(estate, resultRelInfo);
@@ -1321,35 +1383,42 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 	 * previous conclusion that the tuple is conclusively committed is not
 	 * true anymore.
 	 */
-	tuple.t_self = *conflictTid;
-	test = heap_lock_tuple(relation, &tuple, estate->es_output_cid,
-						   lockmode, LockWaitBlock, false, &buffer,
-						   &hufd);
+	test = table_lock_tuple(relation, conflictTid,
+							estate->es_snapshot,
+							existing, estate->es_output_cid,
+							lockmode, LockWaitBlock, 0,
+							&tmfd);
 	switch (test)
 	{
-		case HeapTupleMayBeUpdated:
+		case TM_Ok:
 			/* success! */
 			break;
 
-		case HeapTupleInvisible:
+		case TM_Invisible:
 
 			/*
 			 * This can occur when a just inserted tuple is updated again in
 			 * the same command. E.g. because multiple rows with the same
 			 * conflicting key values are inserted.
 			 *
-			 * This is somewhat similar to the ExecUpdate()
-			 * HeapTupleSelfUpdated case.  We do not want to proceed because
-			 * it would lead to the same row being updated a second time in
-			 * some unspecified order, and in contrast to plain UPDATEs
-			 * there's no historical behavior to break.
+			 * This is somewhat similar to the ExecUpdate() TM_SelfModified
+			 * case.  We do not want to proceed because it would lead to the
+			 * same row being updated a second time in some unspecified order,
+			 * and in contrast to plain UPDATEs there's no historical behavior
+			 * to break.
 			 *
 			 * It is the user's responsibility to prevent this situation from
 			 * occurring.  These problems are why SQL-2003 similarly specifies
 			 * that for SQL MERGE, an exception must be raised in the event of
 			 * an attempt to update the same row twice.
 			 */
-			if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple.t_data)))
+			xminDatum = slot_getsysattr(existing,
+										MinTransactionIdAttributeNumber,
+										&isnull);
+			Assert(!isnull);
+			xmin = DatumGetTransactionId(xminDatum);
+
+			if (TransactionIdIsCurrentTransactionId(xmin))
 				ereport(ERROR,
 						(errcode(ERRCODE_CARDINALITY_VIOLATION),
 						 errmsg("ON CONFLICT DO UPDATE command cannot affect row a second time"),
@@ -1359,7 +1428,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 			elog(ERROR, "attempted to lock invisible tuple");
 			break;
 
-		case HeapTupleSelfUpdated:
+		case TM_SelfModified:
 
 			/*
 			 * This state should never be reached. As a dirty snapshot is used
@@ -1369,7 +1438,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 			elog(ERROR, "unexpected self-updated tuple");
 			break;
 
-		case HeapTupleUpdated:
+		case TM_Updated:
 			if (IsolationUsesXactSnapshot())
 				ereport(ERROR,
 						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
@@ -1381,7 +1450,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 			 * be lock is moved to another partition due to concurrent update
 			 * of the partition key.
 			 */
-			Assert(!ItemPointerIndicatesMovedPartitions(&hufd.ctid));
+			Assert(!ItemPointerIndicatesMovedPartitions(&tmfd.ctid));
 
 			/*
 			 * Tell caller to try again from the very start.
@@ -1390,11 +1459,22 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 			 * loop here, as the new version of the row might not conflict
 			 * anymore, or the conflicting tuple has actually been deleted.
 			 */
-			ReleaseBuffer(buffer);
+			ExecClearTuple(existing);
+			return false;
+
+		case TM_Deleted:
+			if (IsolationUsesXactSnapshot())
+				ereport(ERROR,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("could not serialize access due to concurrent delete")));
+
+			/* see TM_Updated case */
+			Assert(!ItemPointerIndicatesMovedPartitions(&tmfd.ctid));
+			ExecClearTuple(existing);
 			return false;
 
 		default:
-			elog(ERROR, "unrecognized heap_lock_tuple status: %u", test);
+			elog(ERROR, "unrecognized table_lock_tuple status: %u", test);
 	}
 
 	/* Success, the tuple is locked. */
@@ -1412,10 +1492,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 	 * snapshot.  This is in line with the way UPDATE deals with newer tuple
 	 * versions.
 	 */
-	ExecCheckHeapTupleVisible(estate, &tuple, buffer);
-
-	/* Store target's existing tuple in the state's dedicated slot */
-	ExecStorePinnedBufferHeapTuple(&tuple, existing, buffer);
+	ExecCheckTupleVisible(estate, relation, existing);
 
 	/*
 	 * Make tuple and any needed join variables available to ExecQual and
@@ -1462,7 +1539,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 
 	/*
 	 * 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
+	 * this session, after the above table_lock_tuple. We choose to not error
 	 * out in that case, in line with ExecUpdate's treatment of similar cases.
 	 * This can happen if an UPDATE is triggered from within ExecQual(),
 	 * ExecWithCheckOptions() or ExecProject() above, e.g. by selecting from a
@@ -1470,7 +1547,7 @@ ExecOnConflictUpdate(ModifyTableState *mtstate,
 	 */
 
 	/* Execute UPDATE with projection */
-	*returning = ExecUpdate(mtstate, &tuple.t_self, NULL,
+	*returning = ExecUpdate(mtstate, conflictTid, NULL,
 							resultRelInfo->ri_onConflict->oc_ProjSlot,
 							planSlot,
 							&mtstate->mt_epqstate, mtstate->ps.state,