Support for QCOM BAM DMA command descriptor

index 5336808..45fc833 100644
@@ -186,6 +186,9 @@ struct dma_interleaved_template {
  *  on the result of this operation
  * @DMA_CTRL_REUSE: client can reuse the descriptor and submit again till
  *  cleared or freed
+ * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command
+ *  data and the descriptor should be in different format from normal
+ *  data descriptors.
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),

@@ -195,6 +198,7 @@ enum dma_ctrl_flags {
 	DMA_PREP_CONTINUE = (1 << 4),
 	DMA_PREP_FENCE = (1 << 5),
 	DMA_CTRL_REUSE = (1 << 6),
+	DMA_PREP_CMD = (1 << 7),
 };
 
 /**

new file mode 100644
index 0000000..077d43a
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c) 2016-2017, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _QCOM_BAM_DMA_H
+#define _QCOM_BAM_DMA_H
+
+#include <asm/byteorder.h>
+
+/*
+ * This data type corresponds to the native Command Element
+ * supported by BAM DMA Engine.
+ *
+ * @cmd_and_addr - upper 8 bits command and lower 24 bits register address.
+ * @data - for write command: content to be written into peripheral register.
+ *	   for read command: dest addr to write peripheral register value.
+ * @mask - register mask.
+ * @reserved - for future usage.
+ *
+ */
+struct bam_cmd_element {
+	__le32 cmd_and_addr;
+	__le32 data;
+	__le32 mask;
+	__le32 reserved;
+};
+
+/*
+ * This enum indicates the command type in a command element
+ */
+enum bam_command_type {
+	BAM_WRITE_COMMAND = 0,
+	BAM_READ_COMMAND,
+};
+
+/*
+ * prep_bam_ce_le32 - Wrapper function to prepare a single BAM command
+ * element with the data already in le32 format.
+ *
+ * @bam_ce: bam command element
+ * @addr: target address
+ * @cmd: BAM command
+ * @data: actual data for write and dest addr for read in le32
+ */
+static inline void
+bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr,
+		 enum bam_command_type cmd, __le32 data)
+{
+	bam_ce->cmd_and_addr =
+		cpu_to_le32((addr & 0xffffff) | ((cmd & 0xff) << 24));
+	bam_ce->data = data;
+	bam_ce->mask = cpu_to_le32(0xffffffff);
+}
+
+/*
+ * bam_prep_ce - Wrapper function to prepare a single BAM command element
+ * with the data.
+ *
+ * @bam_ce: BAM command element
+ * @addr: target address
+ * @cmd: BAM command
+ * @data: actual data for write and dest addr for read
+ */
+static inline void
+bam_prep_ce(struct bam_cmd_element *bam_ce, u32 addr,
+	    enum bam_command_type cmd, u32 data)
+{
+	bam_prep_ce_le32(bam_ce, addr, cmd, cpu_to_le32(data));
+}
+#endif

index 03c4eb3..6d89fb6 100644
@@ -65,6 +65,7 @@ struct bam_desc_hw {
 #define DESC_FLAG_EOT BIT(14)
 #define DESC_FLAG_EOB BIT(13)
 #define DESC_FLAG_NWD BIT(12)
+#define DESC_FLAG_CMD BIT(11)
 
 struct bam_async_desc {
 	struct virt_dma_desc vd;

@@ -645,6 +646,9 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 		unsigned int curr_offset = 0;
 
 		do {
+			if (flags & DMA_PREP_CMD)
+				desc->flags |= cpu_to_le16(DESC_FLAG_CMD);
+
 			desc->addr = cpu_to_le32(sg_dma_address(sg) +
 						 curr_offset);
 

@@ -960,7 +964,7 @@ static void bam_start_dma(struct bam_chan *bchan)
 
 	/* set any special flags on the last descriptor */
 	if (async_desc->num_desc == async_desc->xfer_len)
-		desc[async_desc->xfer_len - 1].flags =
+		desc[async_desc->xfer_len - 1].flags |=
 					cpu_to_le16(async_desc->flags);
 	else
 		desc[async_desc->xfer_len - 1].flags |=