diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c
index f9c8598..7d88489 100644
--- a/src/backend/executor/execParallel.c
+++ b/src/backend/executor/execParallel.c
@@ -34,6 +34,7 @@
 #include "optimizer/planner.h"
 #include "storage/spin.h"
 #include "tcop/tcopprot.h"
+#include "utils/dsa.h"
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 
@@ -47,6 +48,7 @@
 #define PARALLEL_KEY_BUFFER_USAGE		UINT64CONST(0xE000000000000003)
 #define PARALLEL_KEY_TUPLE_QUEUE		UINT64CONST(0xE000000000000004)
 #define PARALLEL_KEY_INSTRUMENTATION	UINT64CONST(0xE000000000000005)
+#define PARALLEL_KEY_AREA				UINT64CONST(0xE000000000000006)
 
 #define PARALLEL_TUPLE_QUEUE_SIZE		65536
 
@@ -345,6 +347,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate, int nworkers)
 	int			param_len;
 	int			instrumentation_len = 0;
 	int			instrument_offset = 0;
+	char	   *area_space;
 
 	/* Allocate object for return value. */
 	pei = palloc0(sizeof(ParallelExecutorInfo));
@@ -413,6 +416,10 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate, int nworkers)
 		shm_toc_estimate_keys(&pcxt->estimator, 1);
 	}
 
+	/* Estimate space for DSA area. */
+	shm_toc_estimate_chunk(&pcxt->estimator, dsa_minimum_size());
+	shm_toc_estimate_keys(&pcxt->estimator, 1);
+
 	/* Everyone's had a chance to ask for space, so now create the DSM. */
 	InitializeParallelDSM(pcxt);
 
@@ -466,6 +473,20 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate, int nworkers)
 		pei->instrumentation = instrumentation;
 	}
 
+	/* Create a DSA area that can be used by the leader and all workers. */
+	area_space = shm_toc_allocate(pcxt->toc, dsa_minimum_size());
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_AREA, area_space);
+	pei->area = dsa_create_in_place(area_space, dsa_minimum_size(),
+									LWTRANCHE_PARALLEL_EXEC_AREA,
+									"parallel query memory area",
+									pcxt->seg);
+
+	/*
+	 * Make the area available to executor nodes running in the leader.  See
+	 * also ParallelQueryMain which makes it available to workers.
+	 */
+	estate->es_query_area = pei->area;
+
 	/*
 	 * Give parallel-aware nodes a chance to initialize their shared data.
 	 * This also initializes the elements of instrumentation->ps_instrument,
@@ -571,6 +592,11 @@ ExecParallelFinish(ParallelExecutorInfo *pei)
 void
 ExecParallelCleanup(ParallelExecutorInfo *pei)
 {
+	if (pei->area != NULL)
+	{
+		dsa_detach(pei->area);
+		pei->area = NULL;
+	}
 	if (pei->pcxt != NULL)
 	{
 		DestroyParallelContext(pei->pcxt);
@@ -728,6 +754,8 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 	QueryDesc  *queryDesc;
 	SharedExecutorInstrumentation *instrumentation;
 	int			instrument_options = 0;
+	void *area_space;
+	dsa_area *area;
 
 	/* Set up DestReceiver, SharedExecutorInstrumentation, and QueryDesc. */
 	receiver = ExecParallelGetReceiver(seg, toc);
@@ -739,8 +767,13 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 	/* Prepare to track buffer usage during query execution. */
 	InstrStartParallelQuery();
 
+	/* Attach to the dynamic shared memory area. */
+	area_space = shm_toc_lookup(toc, PARALLEL_KEY_AREA);
+	area = dsa_attach_in_place(area_space, seg);
+
 	/* Start up the executor, have it run the plan, and then shut it down. */
 	ExecutorStart(queryDesc, 0);
+	queryDesc->planstate->state->es_query_area = area;
 	ExecParallelInitializeWorker(queryDesc->planstate, toc);
 	ExecutorRun(queryDesc, ForwardScanDirection, 0L);
 	ExecutorFinish(queryDesc);
@@ -758,6 +791,7 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 	ExecutorEnd(queryDesc);
 
 	/* Cleanup. */
+	dsa_detach(area);
 	FreeQueryDesc(queryDesc);
 	(*receiver->rDestroy) (receiver);
 }
diff --git a/src/include/executor/execParallel.h b/src/include/executor/execParallel.h
index f4c6d37..4b57474 100644
--- a/src/include/executor/execParallel.h
+++ b/src/include/executor/execParallel.h
@@ -17,6 +17,7 @@
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "nodes/plannodes.h"
+#include "utils/dsa.h"
 
 typedef struct SharedExecutorInstrumentation SharedExecutorInstrumentation;
 
@@ -27,6 +28,7 @@ typedef struct ParallelExecutorInfo
 	BufferUsage *buffer_usage;
 	SharedExecutorInstrumentation *instrumentation;
 	shm_mq_handle **tqueue;
+	dsa_area *area;
 	bool		finished;
 } ParallelExecutorInfo;
 
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 8004d85..0837c42 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -20,6 +20,7 @@
 #include "lib/pairingheap.h"
 #include "nodes/params.h"
 #include "nodes/plannodes.h"
+#include "utils/dsa.h"
 #include "utils/hsearch.h"
 #include "utils/reltrigger.h"
 #include "utils/sortsupport.h"
@@ -422,6 +423,9 @@ typedef struct EState
 	HeapTuple  *es_epqTuple;	/* array of EPQ substitute tuples */
 	bool	   *es_epqTupleSet; /* true if EPQ tuple is provided */
 	bool	   *es_epqScanDone; /* true if EPQ tuple has been fetched */
+
+	/* The per-query shared memory area to use for parallel execution. */
+	dsa_area *es_query_area;
 } EState;
 
 
diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h
index 9a2d869..951e421 100644
--- a/src/include/storage/lwlock.h
+++ b/src/include/storage/lwlock.h
@@ -235,6 +235,7 @@ typedef enum BuiltinTrancheIds
 	LWTRANCHE_BUFFER_MAPPING,
 	LWTRANCHE_LOCK_MANAGER,
 	LWTRANCHE_PREDICATE_LOCK_MANAGER,
+	LWTRANCHE_PARALLEL_EXEC_AREA,
 	LWTRANCHE_FIRST_USER_DEFINED
 }	BuiltinTrancheIds;