diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 237578030a2a..fc2014997dde 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -213,6 +213,8 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
 #define QPIC_PER_CW_CMD_SGL		32
 #define QPIC_PER_CW_DATA_SGL		8
 
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
 /*
  * Flags used in DMA descriptor preparation helper functions
  * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma)
@@ -245,6 +247,11 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
  * @tx_sgl_start - start index in data sgl for tx.
  * @rx_sgl_pos - current index in data sgl for rx.
  * @rx_sgl_start - start index in data sgl for rx.
+ * @wait_second_completion - wait for second DMA desc completion before making
+ *			     the NAND transfer completion.
+ * @txn_done - completion for NAND transfer.
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
  */
 struct bam_transaction {
 	struct bam_cmd_element *bam_ce;
@@ -258,6 +265,10 @@ struct bam_transaction {
 	u32 tx_sgl_start;
 	u32 rx_sgl_pos;
 	u32 rx_sgl_start;
+	bool wait_second_completion;
+	struct completion txn_done;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
 };
 
 /*
@@ -504,6 +515,8 @@ alloc_bam_transaction(struct qcom_nand_controller *nandc)
 
 	bam_txn->data_sgl = bam_txn_buf;
 
+	init_completion(&bam_txn->txn_done);
+
 	return bam_txn;
 }
 
@@ -523,11 +536,33 @@ static void clear_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn->tx_sgl_start = 0;
 	bam_txn->rx_sgl_pos = 0;
 	bam_txn->rx_sgl_start = 0;
+	bam_txn->last_data_desc = NULL;
+	bam_txn->wait_second_completion = false;
 
 	sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_CMD_SGL);
 	sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_DATA_SGL);
+
+	reinit_completion(&bam_txn->txn_done);
+}
+
+/* Callback for DMA descriptor completion */
+static void qpic_bam_dma_done(void *data)
+{
+	struct bam_transaction *bam_txn = data;
+
+	/*
+	 * In case of data transfer with NAND, 2 callbacks will be generated.
+	 * One for command channel and another one for data channel.
+	 * If current transaction has data descriptors
+	 * (i.e. wait_second_completion is true), then set this to false
+	 * and wait for second DMA descriptor completion.
+	 */
+	if (bam_txn->wait_second_completion)
+		bam_txn->wait_second_completion = false;
+	else
+		complete(&bam_txn->txn_done);
 }
 
 static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip)
@@ -756,6 +791,12 @@ static int prepare_bam_async_desc(struct qcom_nand_controller *nandc,
 
 	desc->dma_desc = dma_desc;
 
+	/* update last data/command descriptor */
+	if (chan == nandc->cmd_chan)
+		bam_txn->last_cmd_desc = dma_desc;
+	else
+		bam_txn->last_data_desc = dma_desc;
+
 	list_add_tail(&desc->node, &nandc->desc_list);
 
 	return 0;
@@ -1273,10 +1314,20 @@ static int submit_descs(struct qcom_nand_controller *nandc)
 		cookie = dmaengine_submit(desc->dma_desc);
 
 	if (nandc->props->is_bam) {
+		bam_txn->last_cmd_desc->callback = qpic_bam_dma_done;
+		bam_txn->last_cmd_desc->callback_param = bam_txn;
+		if (bam_txn->last_data_desc) {
+			bam_txn->last_data_desc->callback = qpic_bam_dma_done;
+			bam_txn->last_data_desc->callback_param = bam_txn;
+			bam_txn->wait_second_completion = true;
+		}
+
 		dma_async_issue_pending(nandc->tx_chan);
 		dma_async_issue_pending(nandc->rx_chan);
+		dma_async_issue_pending(nandc->cmd_chan);
 
-		if (dma_sync_wait(nandc->cmd_chan, cookie) != DMA_COMPLETE)
+		if (!wait_for_completion_timeout(&bam_txn->txn_done,
+						 QPIC_NAND_COMPLETION_TIMEOUT))
 			return -ETIMEDOUT;
 	} else {
 		if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE)