diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index 692de47b16701dc7b9f75aefa657618a352149d5..783ae763f445229dfe2f4122dc90870f6680f6a2 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -192,6 +192,7 @@ u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir)
 static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 {
 	struct dw_edma_burst *child;
+	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma_v0_lli __iomem *lli;
 	struct dw_edma_v0_llp __iomem *llp;
 	u32 control = 0, i = 0;
@@ -205,9 +206,11 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	j = chunk->bursts_alloc;
 	list_for_each_entry(child, &chunk->burst->list, list) {
 		j--;
-		if (!j)
-			control |= (DW_EDMA_V0_LIE | DW_EDMA_V0_RIE);
-
+		if (!j) {
+			control |= DW_EDMA_V0_LIE;
+			if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+				control |= DW_EDMA_V0_RIE;
+		}
 		/* Channel control */
 		SET_LL(&lli[i].control, control);
 		/* Transfer size */
@@ -233,6 +236,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	SET_LL(&llp->llp_high, upper_32_bits(chunk->ll_region.paddr));
 }
 
+static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote eDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -262,6 +279,9 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH(dw, chan->dir, chan->id, llp_high,
 		       upper_32_bits(chunk->ll_region.paddr));
 	}
+
+	dw_edma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_RW(dw, chan->dir, doorbell,
 	       FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index cab6e18773dadd2149f6310e0c87316137419d24..0cda04f9f610f994946cfdcb86368f254c02cecf 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -14,17 +14,27 @@
 
 struct dw_edma;
 
+/**
+ * enum dw_edma_chip_flags - Flags specific to an eDMA chip
+ * @DW_EDMA_CHIP_LOCAL:		eDMA is used locally by an endpoint
+ */
+enum dw_edma_chip_flags {
+	DW_EDMA_CHIP_LOCAL	= BIT(0),
+};
+
 /**
  * struct dw_edma_chip - representation of DesignWare eDMA controller hardware
  * @dev:		 struct device of the eDMA controller
  * @id:			 instance ID
  * @irq:		 irq line
  * @dw:			 struct dw_edma that is filed by dw_edma_probe()
+ * @flags		 dw_edma_chip_flags
  */
 struct dw_edma_chip {
 	struct device		*dev;
 	int			id;
 	int			irq;
+	u32			flags;
 	struct dw_edma		*dw;
 };