1 files changed, 67 insertions, 16 deletions

diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index f42189d2bf6..b593d22c48a 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -571,17 +571,12 @@ typedef struct EState
 	ExprContext *es_per_tuple_exprcontext;
 
 	/*
-	 * These fields are for re-evaluating plan quals when an updated tuple is
-	 * substituted in READ COMMITTED mode.  es_epqTupleSlot[] contains test
-	 * tuples that scan plan nodes should return instead of whatever they'd
-	 * normally return, or an empty slot if there is nothing to return; if
-	 * es_epqTupleSlot[] is not NULL if a particular array entry is valid; and
-	 * es_epqScanDone[] is state to remember if the tuple has been returned
-	 * already.  Arrays are of size es_range_table_size and are indexed by
-	 * scan node scanrelid - 1.
+	 * If not NULL, this is an EPQState's EState. This is a field in EState
+	 * both to allow EvalPlanQual aware executor nodes to detect that they
+	 * need to perform EPQ related work, and to provide necessary information
+	 * to do so.
 	 */
-	TupleTableSlot **es_epqTupleSlot;	/* array of EPQ substitute tuples */
-	bool	   *es_epqScanDone; /* true if EPQ tuple has been fetched */
+	struct EPQState *es_epq_active;
 
 	bool		es_use_parallel_mode;	/* can we use parallel workers? */
 
@@ -1057,17 +1052,73 @@ typedef struct PlanState
 
 /*
  * EPQState is state for executing an EvalPlanQual recheck on a candidate
- * tuple in ModifyTable or LockRows.  The estate and planstate fields are
- * NULL if inactive.
+ * tuples e.g. in ModifyTable or LockRows.
+ *
+ * To execute EPQ a separate EState is created (stored in ->recheckestate),
+ * which shares some resources, like the rangetable, with the main query's
+ * EState (stored in ->parentestate). The (sub-)tree of the plan that needs to
+ * be rechecked (in ->plan), is separately initialized (into
+ * ->recheckplanstate), but shares plan nodes with the corresponding nodes in
+ * the main query. The scan nodes in that separate executor tree are changed
+ * to return only the current tuple of interest for the respective
+ * table. Those tuples are either provided by the caller (using
+ * EvalPlanQualSlot), and/or found using the rowmark mechanism (non-locking
+ * rowmarks by the EPQ machinery itself, locking ones by the caller).
+ *
+ * While the plan to be checked may be changed using EvalPlanQualSetPlan() -
+ * e.g. so all source plans for a ModifyTable node can be processed - all such
+ * plans need to share the same EState.
  */
 typedef struct EPQState
 {
-	EState	   *estate;			/* subsidiary EState */
-	PlanState  *planstate;		/* plan state tree ready to be executed */
-	TupleTableSlot *origslot;	/* original output tuple to be rechecked */
+	/* Initialized at EvalPlanQualInit() time: */
+
+	EState	   *parentestate;	/* main query's EState */
+	int			epqParam;		/* ID of Param to force scan node re-eval */
+
+	/*
+	 * Tuples to be substituted by scan nodes. They need to set up, before
+	 * calling EvalPlanQual()/EvalPlanQualNext(), into the slot returned by
+	 * EvalPlanQualSlot(scanrelid). The array is indexed by scanrelid - 1.
+	 */
+	List	   *tuple_table;	/* tuple table for relsubs_slot */
+	TupleTableSlot **relsubs_slot;
+
+	/*
+	 * Initialized by EvalPlanQualInit(), may be changed later with
+	 * EvalPlanQualSetPlan():
+	 */
+
 	Plan	   *plan;			/* plan tree to be executed */
 	List	   *arowMarks;		/* ExecAuxRowMarks (non-locking only) */
-	int			epqParam;		/* ID of Param to force scan node re-eval */
+
+
+	/*
+	 * The original output tuple to be rechecked.  Set by
+	 * EvalPlanQualSetSlot(), before EvalPlanQualNext() or EvalPlanQual() may
+	 * be called.
+	 */
+	TupleTableSlot *origslot;
+
+
+	/* Initialized or reset by EvalPlanQualBegin(): */
+
+	EState	   *recheckestate;	/* EState for EPQ execution, see above */
+
+	/*
+	 * Rowmarks that can be fetched on-demand using
+	 * EvalPlanQualFetchRowMark(), indexed by scanrelid - 1. Only non-locking
+	 * rowmarks.
+	 */
+	ExecAuxRowMark **relsubs_rowmark;
+
+	/*
+	 * True if a relation's EPQ tuple has been fetched for relation, indexed
+	 * by scanrelid - 1.
+	 */
+	bool	   *relsubs_done;
+
+	PlanState  *recheckplanstate;	/* EPQ specific exec nodes, for ->plan */
 } EPQState;