openwrt/target/linux/layerscape/patches-4.9/805-dma-support-layerscape.patch

From 854c1f0e9574e9b25a55b439608c71e013b34a56 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Sep 2017 12:12:20 +0800
Subject: [PATCH] dma: support layerscape

This is a integrated patch for layerscape dma support.

Signed-off-by: jiaheng.fan <jiaheng.fan@nxp.com>
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
---
 drivers/dma/Kconfig                     |   31 +
 drivers/dma/Makefile                    |    3 +
 drivers/dma/caam_dma.c                  |  563 +++++++++++++++
 drivers/dma/dpaa2-qdma/Kconfig          |    8 +
 drivers/dma/dpaa2-qdma/Makefile         |    8 +
 drivers/dma/dpaa2-qdma/dpaa2-qdma.c     |  986 +++++++++++++++++++++++++
 drivers/dma/dpaa2-qdma/dpaa2-qdma.h     |  262 +++++++
 drivers/dma/dpaa2-qdma/dpdmai.c         |  454 ++++++++++++
 drivers/dma/dpaa2-qdma/fsl_dpdmai.h     |  521 ++++++++++++++
 drivers/dma/dpaa2-qdma/fsl_dpdmai_cmd.h |  222 ++++++
 drivers/dma/fsl-qdma.c                  | 1201 +++++++++++++++++++++++++++++++
 11 files changed, 4259 insertions(+)
 create mode 100644 drivers/dma/caam_dma.c
 create mode 100644 drivers/dma/dpaa2-qdma/Kconfig
 create mode 100644 drivers/dma/dpaa2-qdma/Makefile
 create mode 100644 drivers/dma/dpaa2-qdma/dpaa2-qdma.c
 create mode 100644 drivers/dma/dpaa2-qdma/dpaa2-qdma.h
 create mode 100644 drivers/dma/dpaa2-qdma/dpdmai.c
 create mode 100644 drivers/dma/dpaa2-qdma/fsl_dpdmai.h
 create mode 100644 drivers/dma/dpaa2-qdma/fsl_dpdmai_cmd.h
 create mode 100644 drivers/dma/fsl-qdma.c

--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -192,6 +192,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config FSL_QDMA
+       tristate "Freescale qDMA engine support"
+       select DMA_ENGINE
+       select DMA_VIRTUAL_CHANNELS
+       select DMA_ENGINE_RAID
+       select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+       help
+         Support the Freescale qDMA engine with command queue and legacy mode.
+         Channel virtualization is supported through enqueuing of DMA jobs to,
+         or dequeuing DMA jobs from, different work queues.
+         This module can be found on Freescale LS SoCs.
+
+source drivers/dma/dpaa2-qdma/Kconfig
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH
@@ -564,6 +578,23 @@ config ZX_DMA
 	help
 	  Support the DMA engine for ZTE ZX296702 platform devices.
 
+config CRYPTO_DEV_FSL_CAAM_DMA
+	tristate "CAAM DMA engine support"
+	depends on CRYPTO_DEV_FSL_CAAM_JR
+	default y
+	select DMA_ENGINE
+	select ASYNC_CORE
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	help
+	  Selecting this will offload the DMA operations for users of
+	  the scatter gather memcopy API to the CAAM via job rings. The
+	  CAAM is a hardware module that provides hardware acceleration to
+	  cryptographic operations. It has a built-in DMA controller that can
+	  be programmed to read/write cryptographic data. This module defines
+	  a DMA driver that uses the DMA capabilities of the CAAM.
+
+	  To compile this as a module, choose M here: the module
+	  will be called caam_dma.
 
 # driver files
 source "drivers/dma/bestcomm/Kconfig"
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -29,6 +29,8 @@ obj-$(CONFIG_DW_DMAC_CORE) += dw/
 obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
+obj-$(CONFIG_FSL_DPAA2_QDMA) += dpaa2-qdma/
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
@@ -67,6 +69,7 @@ obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-
 obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx296702_dma.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_DMA) += caam_dma.o
 
 obj-y += qcom/
 obj-y += xilinx/
--- /dev/null
+++ b/drivers/dma/caam_dma.c
@@ -0,0 +1,563 @@
+/*
+ * caam support for SG DMA
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc
+ * Copyright 2017 NXP
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+
+#include <linux/dmaengine.h>
+#include "dmaengine.h"
+
+#include "../crypto/caam/regs.h"
+#include "../crypto/caam/jr.h"
+#include "../crypto/caam/error.h"
+#include "../crypto/caam/intern.h"
+#include "../crypto/caam/desc_constr.h"
+#include "../crypto/caam/sg_sw_sec4.h"
+
+#define DESC_DMA_MEMCPY_LEN	((CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN) / \
+				 CAAM_CMD_SZ)
+
+/* This is max chunk size of a DMA transfer. If a buffer is larger than this
+ * value it is internally broken into chunks of max CAAM_DMA_CHUNK_SIZE bytes
+ * and for each chunk a DMA transfer request is issued.
+ * This value is the largest number on 16 bits that is a multiple of 256 bytes
+ * (the largest configurable CAAM DMA burst size).
+ */
+#define CAAM_DMA_CHUNK_SIZE	65280
+
+struct caam_dma_sh_desc {
+	u32 desc[DESC_DMA_MEMCPY_LEN] ____cacheline_aligned;
+	dma_addr_t desc_dma;
+};
+
+/* caam dma extended descriptor */
+struct caam_dma_edesc {
+	struct dma_async_tx_descriptor async_tx;
+	struct list_head node;
+	struct caam_dma_ctx *ctx;
+	dma_addr_t src_dma;
+	dma_addr_t dst_dma;
+	unsigned int src_len;
+	unsigned int dst_len;
+	struct sec4_sg_entry *sec4_sg;
+	u32 jd[] ____cacheline_aligned;
+};
+
+/*
+ * caam_dma_ctx - per jr/channel context
+ * @chan: dma channel used by async_tx API
+ * @node: list_head used to attach to the global dma_ctx_list
+ * @jrdev: Job Ring device
+ * @submit_q: queue of pending (submitted, but not enqueued) jobs
+ * @done_not_acked: jobs that have been completed by jr, but maybe not acked
+ * @edesc_lock: protects extended descriptor
+ */
+struct caam_dma_ctx {
+	struct dma_chan chan;
+	struct list_head node;
+	struct device *jrdev;
+	struct list_head submit_q;
+	struct list_head done_not_acked;
+	spinlock_t edesc_lock;
+};
+
+static struct dma_device *dma_dev;
+static struct caam_dma_sh_desc *dma_sh_desc;
+static LIST_HEAD(dma_ctx_list);
+
+static dma_cookie_t caam_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct caam_dma_edesc *edesc = NULL;
+	struct caam_dma_ctx *ctx = NULL;
+	dma_cookie_t cookie;
+
+	edesc = container_of(tx, struct caam_dma_edesc, async_tx);
+	ctx = container_of(tx->chan, struct caam_dma_ctx, chan);
+
+	spin_lock_bh(&ctx->edesc_lock);
+
+	cookie = dma_cookie_assign(tx);
+	list_add_tail(&edesc->node, &ctx->submit_q);
+
+	spin_unlock_bh(&ctx->edesc_lock);
+
+	return cookie;
+}
+
+static unsigned int caam_dma_sg_dma_len(struct scatterlist *sg,
+					unsigned int nents)
+{
+	unsigned int len;
+
+	for (len = 0; sg && nents; sg = sg_next(sg), nents--)
+		len += sg_dma_len(sg);
+
+	return len;
+}
+
+static struct caam_dma_edesc *
+caam_dma_sg_edesc_alloc(struct dma_chan *chan,
+			struct scatterlist *dst_sg, unsigned int dst_nents,
+			struct scatterlist *src_sg, unsigned int src_nents,
+			unsigned long flags)
+{
+	struct caam_dma_ctx *ctx = container_of(chan, struct caam_dma_ctx,
+						chan);
+	struct device *jrdev = ctx->jrdev;
+	struct caam_dma_edesc *edesc;
+	struct sec4_sg_entry *sec4_sg;
+	dma_addr_t sec4_sg_dma_src;
+	unsigned int sec4_sg_bytes;
+
+	if (!dst_sg || !src_sg || !dst_nents || !src_nents)
+		return NULL;
+
+	sec4_sg_bytes = (src_nents + dst_nents) * sizeof(*sec4_sg);
+
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN + sec4_sg_bytes,
+			GFP_DMA | GFP_NOWAIT);
+	if (!edesc)
+		return ERR_PTR(-ENOMEM);
+
+	edesc->src_len = caam_dma_sg_dma_len(src_sg, src_nents);
+	edesc->dst_len = caam_dma_sg_dma_len(dst_sg, dst_nents);
+	if (edesc->src_len != edesc->dst_len) {
+		dev_err(jrdev, "%s: src(%u) and dst(%u) len mismatch.\n",
+			__func__, edesc->src_len, edesc->dst_len);
+		kfree(edesc);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dma_async_tx_descriptor_init(&edesc->async_tx, chan);
+	edesc->async_tx.tx_submit = caam_dma_tx_submit;
+	edesc->async_tx.flags = flags;
+	edesc->async_tx.cookie = -EBUSY;
+
+	/* Prepare SEC SGs */
+	edesc->sec4_sg = (void *)edesc + offsetof(struct caam_dma_edesc, jd) +
+			 DESC_JOB_IO_LEN;
+
+	sec4_sg = edesc->sec4_sg;
+	sg_to_sec4_sg_last(src_sg, src_nents, sec4_sg, 0);
+
+	sec4_sg += src_nents;
+	sg_to_sec4_sg_last(dst_sg, dst_nents, sec4_sg, 0);
+
+	sec4_sg_dma_src = dma_map_single(jrdev, edesc->sec4_sg, sec4_sg_bytes,
+					 DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, sec4_sg_dma_src)) {
+		dev_err(jrdev, "error mapping segments to device\n");
+		kfree(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->src_dma = sec4_sg_dma_src;
+	edesc->dst_dma = sec4_sg_dma_src + src_nents * sizeof(*sec4_sg);
+	edesc->ctx = ctx;
+
+	return edesc;
+}
+
+static void caam_jr_chan_free_edesc(struct caam_dma_edesc *edesc)
+{
+	struct caam_dma_ctx *ctx = edesc->ctx;
+	struct caam_dma_edesc *_edesc = NULL;
+
+	spin_lock_bh(&ctx->edesc_lock);
+
+	list_add_tail(&edesc->node, &ctx->done_not_acked);
+	list_for_each_entry_safe(edesc, _edesc, &ctx->done_not_acked, node) {
+		if (async_tx_test_ack(&edesc->async_tx)) {
+			list_del(&edesc->node);
+			kfree(edesc);
+		}
+	}
+
+	spin_unlock_bh(&ctx->edesc_lock);
+}
+
+static void caam_dma_done(struct device *dev, u32 *hwdesc, u32 err,
+			  void *context)
+{
+	struct caam_dma_edesc *edesc = context;
+	struct caam_dma_ctx *ctx = edesc->ctx;
+	dma_async_tx_callback callback;
+	void *callback_param;
+
+	if (err)
+		caam_jr_strstatus(ctx->jrdev, err);
+
+	dma_run_dependencies(&edesc->async_tx);
+
+	spin_lock_bh(&ctx->edesc_lock);
+	dma_cookie_complete(&edesc->async_tx);
+	spin_unlock_bh(&ctx->edesc_lock);
+
+	callback = edesc->async_tx.callback;
+	callback_param = edesc->async_tx.callback_param;
+
+	dma_descriptor_unmap(&edesc->async_tx);
+
+	caam_jr_chan_free_edesc(edesc);
+
+	if (callback)
+		callback(callback_param);
+}
+
+static void caam_dma_sg_init_job_desc(struct caam_dma_edesc *edesc)
+{
+	u32 *jd = edesc->jd;
+	u32 *sh_desc = dma_sh_desc->desc;
+	dma_addr_t desc_dma = dma_sh_desc->desc_dma;
+
+	/* init the job descriptor */
+	init_job_desc_shared(jd, desc_dma, desc_len(sh_desc), HDR_REVERSE);
+
+	/* set SEQIN PTR */
+	append_seq_in_ptr(jd, edesc->src_dma, edesc->src_len, LDST_SGF);
+
+	/* set SEQOUT PTR */
+	append_seq_out_ptr(jd, edesc->dst_dma, edesc->dst_len, LDST_SGF);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "caam dma desc@" __stringify(__LINE__) ": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, jd, desc_bytes(jd), 1);
+#endif
+}
+
+/* This function can be called from an interrupt context */
+static struct dma_async_tx_descriptor *
+caam_dma_prep_sg(struct dma_chan *chan, struct scatterlist *dst_sg,
+		 unsigned int dst_nents, struct scatterlist *src_sg,
+		 unsigned int src_nents, unsigned long flags)
+{
+	struct caam_dma_edesc *edesc;
+
+	/* allocate extended descriptor */
+	edesc = caam_dma_sg_edesc_alloc(chan, dst_sg, dst_nents, src_sg,
+					src_nents, flags);
+	if (IS_ERR_OR_NULL(edesc))
+		return ERR_CAST(edesc);
+
+	/* Initialize job descriptor */
+	caam_dma_sg_init_job_desc(edesc);
+
+	return &edesc->async_tx;
+}
+
+static void caam_dma_memcpy_init_job_desc(struct caam_dma_edesc *edesc)
+{
+	u32 *jd = edesc->jd;
+	u32 *sh_desc = dma_sh_desc->desc;
+	dma_addr_t desc_dma = dma_sh_desc->desc_dma;
+
+	/* init the job descriptor */
+	init_job_desc_shared(jd, desc_dma, desc_len(sh_desc), HDR_REVERSE);
+
+	/* set SEQIN PTR */
+	append_seq_in_ptr(jd, edesc->src_dma, edesc->src_len, 0);
+
+	/* set SEQOUT PTR */
+	append_seq_out_ptr(jd, edesc->dst_dma, edesc->dst_len, 0);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "caam dma desc@" __stringify(__LINE__) ": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, jd, desc_bytes(jd), 1);
+#endif
+}
+
+static struct dma_async_tx_descriptor *
+caam_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
+		     size_t len, unsigned long flags)
+{
+	struct caam_dma_edesc *edesc;
+	struct caam_dma_ctx *ctx = container_of(chan, struct caam_dma_ctx,
+						chan);
+
+	edesc = kzalloc(sizeof(*edesc) + DESC_JOB_IO_LEN, GFP_DMA | GFP_NOWAIT);
+	if (!edesc)
+		return ERR_PTR(-ENOMEM);
+
+	dma_async_tx_descriptor_init(&edesc->async_tx, chan);
+	edesc->async_tx.tx_submit = caam_dma_tx_submit;
+	edesc->async_tx.flags = flags;
+	edesc->async_tx.cookie = -EBUSY;
+
+	edesc->src_dma = src;
+	edesc->src_len = len;
+	edesc->dst_dma = dst;
+	edesc->dst_len = len;
+	edesc->ctx = ctx;
+
+	caam_dma_memcpy_init_job_desc(edesc);
+
+	return &edesc->async_tx;
+}
+
+/* This function can be called in an interrupt context */
+static void caam_dma_issue_pending(struct dma_chan *chan)
+{
+	struct caam_dma_ctx *ctx = container_of(chan, struct caam_dma_ctx,
+						chan);
+	struct caam_dma_edesc *edesc, *_edesc;
+
+	spin_lock_bh(&ctx->edesc_lock);
+	list_for_each_entry_safe(edesc, _edesc, &ctx->submit_q, node) {
+		if (caam_jr_enqueue(ctx->jrdev, edesc->jd,
+				    caam_dma_done, edesc) < 0)
+			break;
+		list_del(&edesc->node);
+	}
+	spin_unlock_bh(&ctx->edesc_lock);
+}
+
+static void caam_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct caam_dma_ctx *ctx = container_of(chan, struct caam_dma_ctx,
+						chan);
+	struct caam_dma_edesc *edesc, *_edesc;
+
+	spin_lock_bh(&ctx->edesc_lock);
+	list_for_each_entry_safe(edesc, _edesc, &ctx->submit_q, node) {
+		list_del(&edesc->node);
+		kfree(edesc);
+	}
+	list_for_each_entry_safe(edesc, _edesc, &ctx->done_not_acked, node) {
+		list_del(&edesc->node);
+		kfree(edesc);
+	}
+	spin_unlock_bh(&ctx->edesc_lock);
+}
+
+static int caam_dma_jr_chan_bind(void)
+{
+	struct device *jrdev;
+	struct caam_dma_ctx *ctx;
+	int bonds = 0;
+	int i;
+
+	for (i = 0; i < caam_jr_driver_probed(); i++) {
+		jrdev = caam_jridx_alloc(i);
+		if (IS_ERR(jrdev)) {
+			pr_err("job ring device %d allocation failed\n", i);
+			continue;
+		}
+
+		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+		if (!ctx) {
+			caam_jr_free(jrdev);
+			continue;
+		}
+
+		ctx->chan.device = dma_dev;
+		ctx->chan.private = ctx;
+
+		ctx->jrdev = jrdev;
+
+		INIT_LIST_HEAD(&ctx->submit_q);
+		INIT_LIST_HEAD(&ctx->done_not_acked);
+		INIT_LIST_HEAD(&ctx->node);
+		spin_lock_init(&ctx->edesc_lock);
+
+		dma_cookie_init(&ctx->chan);
+
+		/* add the context of this channel to the context list */
+		list_add_tail(&ctx->node, &dma_ctx_list);
+
+		/* add this channel to the device chan list */
+		list_add_tail(&ctx->chan.device_node, &dma_dev->channels);
+
+		bonds++;
+	}
+
+	return bonds;
+}
+
+static inline void caam_jr_dma_free(struct dma_chan *chan)
+{
+	struct caam_dma_ctx *ctx = container_of(chan, struct caam_dma_ctx,
+						chan);
+
+	list_del(&ctx->node);
+	list_del(&chan->device_node);
+	caam_jr_free(ctx->jrdev);
+	kfree(ctx);
+}
+
+static void set_caam_dma_desc(u32 *desc)
+{
+	u32 *jmp_cmd;
+
+	/* dma shared descriptor */
+	init_sh_desc(desc, HDR_SHARE_NEVER | (1 << HDR_START_IDX_SHIFT));
+
+	/* REG1 = CAAM_DMA_CHUNK_SIZE */
+	append_math_add_imm_u32(desc, REG1, ZERO, IMM, CAAM_DMA_CHUNK_SIZE);
+
+	/* REG0 = SEQINLEN - CAAM_DMA_CHUNK_SIZE */
+	append_math_sub_imm_u32(desc, REG0, SEQINLEN, IMM, CAAM_DMA_CHUNK_SIZE);
+
+	/* if (REG0 > 0)
+	 *	jmp to LABEL1
+	 */
+	jmp_cmd = append_jump(desc, JUMP_TEST_INVALL | JUMP_COND_MATH_N |
+			      JUMP_COND_MATH_Z);
+
+	/* REG1 = SEQINLEN */
+	append_math_sub(desc, REG1, SEQINLEN, ZERO, CAAM_CMD_SZ);
+
+	/* LABEL1 */
+	set_jump_tgt_here(desc, jmp_cmd);
+
+	/* VARSEQINLEN = REG1 */
+	append_math_add(desc, VARSEQINLEN, REG1, ZERO, CAAM_CMD_SZ);
+
+	/* VARSEQOUTLEN = REG1 */
+	append_math_add(desc, VARSEQOUTLEN, REG1, ZERO, CAAM_CMD_SZ);
+
+	/* do FIFO STORE */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_METADATA | LDST_VLF);
+
+	/* do FIFO LOAD */
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 |
+			     FIFOLD_TYPE_IFIFO | LDST_VLF);
+
+	/* if (REG0 > 0)
+	 *	jmp 0xF8 (after shared desc header)
+	 */
+	append_jump(desc, JUMP_TEST_INVALL | JUMP_COND_MATH_N |
+		    JUMP_COND_MATH_Z | 0xF8);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "caam dma shdesc@" __stringify(__LINE__) ": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+}
+
+static int __init caam_dma_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device *ctrldev = dev->parent;
+	struct dma_chan *chan, *_chan;
+	u32 *sh_desc;
+	int err = -ENOMEM;
+	int bonds;
+
+	if (!caam_jr_driver_probed()) {
+		dev_info(dev, "Defer probing after JR driver probing\n");
+		return -EPROBE_DEFER;
+	}
+
+	dma_dev = kzalloc(sizeof(*dma_dev), GFP_KERNEL);
+	if (!dma_dev)
+		return -ENOMEM;
+
+	dma_sh_desc = kzalloc(sizeof(*dma_sh_desc), GFP_KERNEL | GFP_DMA);
+	if (!dma_sh_desc)
+		goto desc_err;
+
+	sh_desc = dma_sh_desc->desc;
+	set_caam_dma_desc(sh_desc);
+	dma_sh_desc->desc_dma = dma_map_single(ctrldev, sh_desc,
+					       desc_bytes(sh_desc),
+					       DMA_TO_DEVICE);
+	if (dma_mapping_error(ctrldev, dma_sh_desc->desc_dma)) {
+		dev_err(dev, "unable to map dma descriptor\n");
+		goto map_err;
+	}
+
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	bonds = caam_dma_jr_chan_bind();
+	if (!bonds) {
+		err = -ENODEV;
+		goto jr_bind_err;
+	}
+
+	dma_dev->dev = dev;
+	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dma_cap_set(DMA_SG, dma_dev->cap_mask);
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+	dma_dev->device_tx_status = dma_cookie_status;
+	dma_dev->device_issue_pending = caam_dma_issue_pending;
+	dma_dev->device_prep_dma_sg = caam_dma_prep_sg;
+	dma_dev->device_prep_dma_memcpy = caam_dma_prep_memcpy;
+	dma_dev->device_free_chan_resources = caam_dma_free_chan_resources;
+
+	err = dma_async_device_register(dma_dev);
+	if (err) {
+		dev_err(dev, "Failed to register CAAM DMA engine\n");
+		goto jr_bind_err;
+	}
+
+	dev_info(dev, "caam dma support with %d job rings\n", bonds);
+
+	return err;
+
+jr_bind_err:
+	list_for_each_entry_safe(chan, _chan, &dma_dev->channels, device_node)
+		caam_jr_dma_free(chan);
+
+	dma_unmap_single(ctrldev, dma_sh_desc->desc_dma, desc_bytes(sh_desc),
+			 DMA_TO_DEVICE);
+map_err:
+	kfree(dma_sh_desc);
+desc_err:
+	kfree(dma_dev);
+	return err;
+}
+
+static int caam_dma_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device *ctrldev = dev->parent;
+	struct caam_dma_ctx *ctx, *_ctx;
+
+	dma_async_device_unregister(dma_dev);
+
+	list_for_each_entry_safe(ctx, _ctx, &dma_ctx_list, node) {
+		list_del(&ctx->node);
+		caam_jr_free(ctx->jrdev);
+		kfree(ctx);
+	}
+
+	dma_unmap_single(ctrldev, dma_sh_desc->desc_dma,
+			 desc_bytes(dma_sh_desc->desc), DMA_TO_DEVICE);
+
+	kfree(dma_sh_desc);
+	kfree(dma_dev);
+
+	dev_info(dev, "caam dma support disabled\n");
+	return 0;
+}
+
+static const struct of_device_id caam_dma_match[] = {
+	{ .compatible = "fsl,sec-v5.4-dma", },
+	{ .compatible = "fsl,sec-v5.0-dma", },
+	{ .compatible = "fsl,sec-v4.0-dma", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, caam_dma_match);
+
+static struct platform_driver caam_dma_driver = {
+	.driver = {
+		.name = "caam-dma",
+		.of_match_table = caam_dma_match,
+	},
+	.probe  = caam_dma_probe,
+	.remove = caam_dma_remove,
+};
+module_platform_driver(caam_dma_driver);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("NXP CAAM support for SG DMA");
+MODULE_AUTHOR("NXP Semiconductors");
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/Kconfig
@@ -0,0 +1,8 @@
+menuconfig FSL_DPAA2_QDMA
+	tristate "NXP DPAA2 QDMA"
+	depends on FSL_MC_BUS && FSL_MC_DPIO
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	---help---
+	  NXP Data Path Acceleration Architecture 2 QDMA driver,
+	  using the NXP MC bus driver.
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for the NXP DPAA2 CAAM controllers
+#
+ccflags-y += -DVERSION=\"\"
+
+obj-$(CONFIG_FSL_DPAA2_QDMA) += fsl-dpaa2-qdma.o
+
+fsl-dpaa2-qdma-objs    := dpaa2-qdma.o dpdmai.o
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/dpaa2-qdma.c
@@ -0,0 +1,986 @@
+/*
+ * drivers/dma/dpaa2-qdma/dpaa2-qdma.c
+ *
+ * Copyright 2015-2017 NXP Semiconductor, Inc.
+ * Author: Changming Huang <jerry.huang@nxp.com>
+ *
+ * Driver for the NXP QDMA engine with QMan mode.
+ * Channel virtualization is supported through enqueuing of DMA jobs to,
+ * or dequeuing DMA jobs from different work queues with QMan portal.
+ * This module can be found on NXP LS2 SoCs.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_dma.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/iommu.h>
+
+#include "../virt-dma.h"
+
+#include "../../../drivers/staging/fsl-mc/include/mc.h"
+#include "../../../drivers/staging/fsl-mc/include/dpaa2-io.h"
+#include "../../../drivers/staging/fsl-mc/include/dpaa2-fd.h"
+#include "fsl_dpdmai_cmd.h"
+#include "fsl_dpdmai.h"
+#include "dpaa2-qdma.h"
+
+static bool smmu_disable = true;
+
+static struct dpaa2_qdma_chan *to_dpaa2_qdma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct dpaa2_qdma_chan, vchan.chan);
+}
+
+static struct dpaa2_qdma_comp *to_fsl_qdma_comp(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct dpaa2_qdma_comp, vdesc);
+}
+
+static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	return 0;
+}
+
+static void dpaa2_qdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct dpaa2_qdma_chan *dpaa2_chan = to_dpaa2_qdma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&dpaa2_chan->vchan.lock, flags);
+	vchan_get_all_descriptors(&dpaa2_chan->vchan, &head);
+	spin_unlock_irqrestore(&dpaa2_chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&dpaa2_chan->vchan, &head);
+}
+
+/*
+ * Request a command descriptor for enqueue.
+ */
+static struct dpaa2_qdma_comp *
+dpaa2_qdma_request_desc(struct dpaa2_qdma_chan *dpaa2_chan)
+{
+	struct dpaa2_qdma_comp *comp_temp = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dpaa2_chan->queue_lock, flags);
+	if (list_empty(&dpaa2_chan->comp_free)) {
+		spin_unlock_irqrestore(&dpaa2_chan->queue_lock, flags);
+		comp_temp = kzalloc(sizeof(*comp_temp), GFP_KERNEL);
+		if (!comp_temp)
+			goto err;
+		comp_temp->fd_virt_addr = dma_pool_alloc(dpaa2_chan->fd_pool,
+				GFP_NOWAIT, &comp_temp->fd_bus_addr);
+		if (!comp_temp->fd_virt_addr)
+			goto err;
+
+		comp_temp->fl_virt_addr =
+			(void *)((struct dpaa2_fd *)
+				comp_temp->fd_virt_addr + 1);
+		comp_temp->fl_bus_addr = comp_temp->fd_bus_addr +
+					sizeof(struct dpaa2_fd);
+		comp_temp->desc_virt_addr =
+			(void *)((struct dpaa2_frame_list *)
+				comp_temp->fl_virt_addr + 3);
+		comp_temp->desc_bus_addr = comp_temp->fl_bus_addr +
+				sizeof(struct dpaa2_frame_list) * 3;
+
+		comp_temp->qchan = dpaa2_chan;
+		comp_temp->sg_blk_num = 0;
+		INIT_LIST_HEAD(&comp_temp->sg_src_head);
+		INIT_LIST_HEAD(&comp_temp->sg_dst_head);
+		return comp_temp;
+	}
+	comp_temp = list_first_entry(&dpaa2_chan->comp_free,
+			struct dpaa2_qdma_comp, list);
+	list_del(&comp_temp->list);
+	spin_unlock_irqrestore(&dpaa2_chan->queue_lock, flags);
+
+	comp_temp->qchan = dpaa2_chan;
+err:
+	return comp_temp;
+}
+
+static void dpaa2_qdma_populate_fd(uint32_t format,
+		struct dpaa2_qdma_comp *dpaa2_comp)
+{
+	struct dpaa2_fd *fd;
+
+	fd = (struct dpaa2_fd *)dpaa2_comp->fd_virt_addr;
+	memset(fd, 0, sizeof(struct dpaa2_fd));
+
+	/* fd populated */
+	fd->simple.addr = dpaa2_comp->fl_bus_addr;
+	/* Bypass memory translation, Frame list format, short length disable */
+	/* we need to disable BMT if fsl-mc use iova addr */
+	if (smmu_disable)
+		fd->simple.bpid = QMAN_FD_BMT_ENABLE;
+	fd->simple.format_offset = QMAN_FD_FMT_ENABLE | QMAN_FD_SL_DISABLE;
+
+	fd->simple.frc = format | QDMA_SER_CTX;
+}
+
+/* first frame list for descriptor buffer */
+static void dpaa2_qdma_populate_first_framel(
+		struct dpaa2_frame_list *f_list,
+		struct dpaa2_qdma_comp *dpaa2_comp)
+{
+	struct dpaa2_qdma_sd_d *sdd;
+
+	sdd = (struct dpaa2_qdma_sd_d *)dpaa2_comp->desc_virt_addr;
+	memset(sdd, 0, 2 * (sizeof(*sdd)));
+	/* source and destination descriptor */
+	sdd->cmd = QDMA_SD_CMD_RDTTYPE_COHERENT; /* source descriptor CMD */
+	sdd++;
+	sdd->cmd = QDMA_DD_CMD_WRTTYPE_COHERENT; /* dest descriptor CMD */
+
+	memset(f_list, 0, sizeof(struct dpaa2_frame_list));
+	/* first frame list to source descriptor */
+	f_list->addr_lo = dpaa2_comp->desc_bus_addr;
+	f_list->addr_hi = (dpaa2_comp->desc_bus_addr >> 32);
+	f_list->data_len.data_len_sl0 = 0x20; /* source/destination desc len */
+	f_list->fmt = QDMA_FL_FMT_SBF; /* single buffer frame */
+	if (smmu_disable)
+		f_list->bmt = QDMA_FL_BMT_ENABLE; /* bypass memory translation */
+	f_list->sl = QDMA_FL_SL_LONG; /* long length */
+	f_list->f = 0; /* not the last frame list */
+}
+
+/* source and destination frame list */
+static void dpaa2_qdma_populate_frames(struct dpaa2_frame_list *f_list,
+		dma_addr_t dst, dma_addr_t src, size_t len, uint8_t fmt)
+{
+	/* source frame list to source buffer */
+	memset(f_list, 0, sizeof(struct dpaa2_frame_list));
+	f_list->addr_lo = src;
+	f_list->addr_hi = (src >> 32);
+	f_list->data_len.data_len_sl0 = len;
+	f_list->fmt = fmt; /* single buffer frame or scatter gather frame */
+	if (smmu_disable)
+		f_list->bmt = QDMA_FL_BMT_ENABLE; /* bypass memory translation */
+	f_list->sl = QDMA_FL_SL_LONG; /* long length */
+	f_list->f = 0; /* not the last frame list */
+
+	f_list++;
+	/* destination frame list to destination buffer */
+	memset(f_list, 0, sizeof(struct dpaa2_frame_list));
+	f_list->addr_lo = dst;
+	f_list->addr_hi = (dst >> 32);
+	f_list->data_len.data_len_sl0 = len;
+	f_list->fmt = fmt; /* single buffer frame or scatter gather frame */
+	if (smmu_disable)
+		f_list->bmt = QDMA_FL_BMT_ENABLE; /* bypass memory translation */
+	f_list->sl = QDMA_FL_SL_LONG; /* long length */
+	f_list->f = QDMA_FL_F; /* Final bit: 1, for last frame list */
+}
+
+static struct dma_async_tx_descriptor *dpaa2_qdma_prep_memcpy(
+		struct dma_chan *chan, dma_addr_t dst,
+		dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct dpaa2_qdma_chan *dpaa2_chan = to_dpaa2_qdma_chan(chan);
+	struct dpaa2_qdma_comp *dpaa2_comp;
+	struct dpaa2_frame_list *f_list;
+	uint32_t format;
+
+	dpaa2_comp = dpaa2_qdma_request_desc(dpaa2_chan);
+
+#ifdef LONG_FORMAT
+	format = QDMA_FD_LONG_FORMAT;
+#else
+	format = QDMA_FD_SHORT_FORMAT;
+#endif
+	/* populate Frame descriptor */
+	dpaa2_qdma_populate_fd(format, dpaa2_comp);
+
+	f_list = (struct dpaa2_frame_list *)dpaa2_comp->fl_virt_addr;
+
+#ifdef LONG_FORMAT
+	/* first frame list for descriptor buffer (logn format) */
+	dpaa2_qdma_populate_first_framel(f_list, dpaa2_comp);
+
+	f_list++;
+#endif
+
+	dpaa2_qdma_populate_frames(f_list, dst, src, len, QDMA_FL_FMT_SBF);
+
+	return vchan_tx_prep(&dpaa2_chan->vchan, &dpaa2_comp->vdesc, flags);
+}
+
+static struct qdma_sg_blk *dpaa2_qdma_get_sg_blk(
+	struct dpaa2_qdma_comp *dpaa2_comp,
+	struct dpaa2_qdma_chan *dpaa2_chan)
+{
+	struct qdma_sg_blk *sg_blk = NULL;
+	dma_addr_t phy_sgb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dpaa2_chan->queue_lock, flags);
+	if (list_empty(&dpaa2_chan->sgb_free)) {
+		sg_blk = (struct qdma_sg_blk *)dma_pool_alloc(
+				dpaa2_chan->sg_blk_pool,
+				GFP_NOWAIT, &phy_sgb);
+		if (!sg_blk) {
+			spin_unlock_irqrestore(&dpaa2_chan->queue_lock, flags);
+			return sg_blk;
+		}
+		sg_blk->blk_virt_addr = (void *)(sg_blk + 1);
+		sg_blk->blk_bus_addr = phy_sgb + sizeof(*sg_blk);
+	} else {
+		sg_blk = list_first_entry(&dpaa2_chan->sgb_free,
+			struct qdma_sg_blk, list);
+		list_del(&sg_blk->list);
+	}
+	spin_unlock_irqrestore(&dpaa2_chan->queue_lock, flags);
+
+	return sg_blk;
+}
+
+static uint32_t dpaa2_qdma_populate_sg(struct device *dev,
+		struct dpaa2_qdma_chan *dpaa2_chan,
+		struct dpaa2_qdma_comp *dpaa2_comp,
+		struct scatterlist *dst_sg, u32 dst_nents,
+		struct scatterlist *src_sg, u32 src_nents)
+{
+	struct dpaa2_qdma_sg *src_sge;
+	struct dpaa2_qdma_sg *dst_sge;
+	struct qdma_sg_blk *sg_blk;
+	struct qdma_sg_blk *sg_blk_dst;
+	dma_addr_t src;
+	dma_addr_t dst;
+	uint32_t num;
+	uint32_t blocks;
+	uint32_t len = 0;
+	uint32_t total_len = 0;
+	int i, j = 0;
+
+	num = min(dst_nents, src_nents);
+	blocks = num / (NUM_SG_PER_BLK - 1);
+	if (num % (NUM_SG_PER_BLK - 1))
+		blocks += 1;
+	if (dpaa2_comp->sg_blk_num < blocks) {
+		len = blocks - dpaa2_comp->sg_blk_num;
+		for (i = 0; i < len; i++) {
+			/* source sg blocks */
+			sg_blk = dpaa2_qdma_get_sg_blk(dpaa2_comp, dpaa2_chan);
+			if (!sg_blk)
+				return 0;
+			list_add_tail(&sg_blk->list, &dpaa2_comp->sg_src_head);
+			/* destination sg blocks */
+			sg_blk = dpaa2_qdma_get_sg_blk(dpaa2_comp, dpaa2_chan);
+			if (!sg_blk)
+				return 0;
+			list_add_tail(&sg_blk->list, &dpaa2_comp->sg_dst_head);
+		}
+	} else {
+		len = dpaa2_comp->sg_blk_num - blocks;
+		for (i = 0; i < len; i++) {
+			spin_lock(&dpaa2_chan->queue_lock);
+			/* handle source sg blocks */
+			sg_blk = list_first_entry(&dpaa2_comp->sg_src_head,
+					struct qdma_sg_blk, list);
+			list_del(&sg_blk->list);
+			list_add_tail(&sg_blk->list, &dpaa2_chan->sgb_free);
+			/* handle destination sg blocks */
+			sg_blk = list_first_entry(&dpaa2_comp->sg_dst_head,
+					struct qdma_sg_blk, list);
+			list_del(&sg_blk->list);
+			list_add_tail(&sg_blk->list, &dpaa2_chan->sgb_free);
+			spin_unlock(&dpaa2_chan->queue_lock);
+		}
+	}
+	dpaa2_comp->sg_blk_num = blocks;
+
+	/* get the first source sg phy address */
+	sg_blk = list_first_entry(&dpaa2_comp->sg_src_head,
+				struct qdma_sg_blk, list);
+	dpaa2_comp->sge_src_bus_addr = sg_blk->blk_bus_addr;
+	/* get the first destinaiton sg phy address */
+	sg_blk_dst = list_first_entry(&dpaa2_comp->sg_dst_head,
+				struct qdma_sg_blk, list);
+	dpaa2_comp->sge_dst_bus_addr = sg_blk_dst->blk_bus_addr;
+
+	for (i = 0; i < blocks; i++) {
+		src_sge = (struct dpaa2_qdma_sg *)sg_blk->blk_virt_addr;
+		dst_sge = (struct dpaa2_qdma_sg *)sg_blk_dst->blk_virt_addr;
+
+		for (j = 0; j < (NUM_SG_PER_BLK - 1); j++) {
+			len = min(sg_dma_len(dst_sg), sg_dma_len(src_sg));
+			if (0 == len)
+				goto fetch;
+			total_len += len;
+			src = sg_dma_address(src_sg);
+			dst = sg_dma_address(dst_sg);
+
+			/* source SG */
+			src_sge->addr_lo = src;
+			src_sge->addr_hi = (src >> 32);
+			src_sge->data_len.data_len_sl0 = len;
+			src_sge->ctrl.sl = QDMA_SG_SL_LONG;
+			src_sge->ctrl.fmt = QDMA_SG_FMT_SDB;
+			/* destination SG */
+			dst_sge->addr_lo = dst;
+			dst_sge->addr_hi = (dst >> 32);
+			dst_sge->data_len.data_len_sl0 = len;
+			dst_sge->ctrl.sl = QDMA_SG_SL_LONG;
+			dst_sge->ctrl.fmt = QDMA_SG_FMT_SDB;
+fetch:
+			num--;
+			if (0 == num) {
+				src_sge->ctrl.f = QDMA_SG_F;
+				dst_sge->ctrl.f = QDMA_SG_F;
+				goto end;
+			}
+			dst_sg = sg_next(dst_sg);
+			src_sg = sg_next(src_sg);
+			src_sge++;
+			dst_sge++;
+			if (j == (NUM_SG_PER_BLK - 2)) {
+				/* for next blocks, extension */
+				sg_blk = list_next_entry(sg_blk, list);
+				sg_blk_dst = list_next_entry(sg_blk_dst, list);
+				src_sge->addr_lo = sg_blk->blk_bus_addr;
+				src_sge->addr_hi = sg_blk->blk_bus_addr >> 32;
+				src_sge->ctrl.sl = QDMA_SG_SL_LONG;
+				src_sge->ctrl.fmt = QDMA_SG_FMT_SGTE;
+				dst_sge->addr_lo = sg_blk_dst->blk_bus_addr;
+				dst_sge->addr_hi =
+					sg_blk_dst->blk_bus_addr >> 32;
+				dst_sge->ctrl.sl = QDMA_SG_SL_LONG;
+				dst_sge->ctrl.fmt = QDMA_SG_FMT_SGTE;
+			}
+		}
+	}
+
+end:
+	return total_len;
+}
+
+static struct dma_async_tx_descriptor *dpaa2_qdma_prep_sg(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, u32 dst_nents,
+		struct scatterlist *src_sg, u32 src_nents,
+		unsigned long flags)
+{
+	struct dpaa2_qdma_chan *dpaa2_chan = to_dpaa2_qdma_chan(chan);
+	struct dpaa2_qdma_comp *dpaa2_comp;
+	struct dpaa2_frame_list *f_list;
+	struct device *dev = dpaa2_chan->qdma->priv->dev;
+	uint32_t total_len = 0;
+
+	/* basic sanity checks */
+	if (dst_nents == 0 || src_nents == 0)
+		return NULL;
+
+	if (dst_sg == NULL || src_sg == NULL)
+		return NULL;
+
+	/* get the descriptors required */
+	dpaa2_comp = dpaa2_qdma_request_desc(dpaa2_chan);
+
+	/* populate Frame descriptor */
+	dpaa2_qdma_populate_fd(QDMA_FD_LONG_FORMAT, dpaa2_comp);
+
+	/* prepare Scatter gather entry for source and destination */
+	total_len = dpaa2_qdma_populate_sg(dev, dpaa2_chan,
+			dpaa2_comp, dst_sg, dst_nents, src_sg, src_nents);
+
+	f_list = (struct dpaa2_frame_list *)dpaa2_comp->fl_virt_addr;
+	/* first frame list for descriptor buffer */
+	dpaa2_qdma_populate_first_framel(f_list, dpaa2_comp);
+	f_list++;
+	/* prepare Scatter gather entry for source and destination */
+	/* populate source and destination frame list table */
+	dpaa2_qdma_populate_frames(f_list, dpaa2_comp->sge_dst_bus_addr,
+			dpaa2_comp->sge_src_bus_addr,
+			total_len, QDMA_FL_FMT_SGE);
+
+	return vchan_tx_prep(&dpaa2_chan->vchan, &dpaa2_comp->vdesc, flags);
+}
+
+static enum dma_status dpaa2_qdma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(chan, cookie, txstate);
+}
+
+static void dpaa2_qdma_free_desc(struct virt_dma_desc *vdesc)
+{
+}
+
+static void dpaa2_qdma_issue_pending(struct dma_chan *chan)
+{
+	struct dpaa2_qdma_comp *dpaa2_comp;
+	struct dpaa2_qdma_chan *dpaa2_chan = to_dpaa2_qdma_chan(chan);
+	struct dpaa2_qdma_engine *dpaa2_qdma = dpaa2_chan->qdma;
+	struct dpaa2_qdma_priv *priv = dpaa2_qdma->priv;
+	struct virt_dma_desc *vdesc;
+	struct dpaa2_fd *fd;
+	int err;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dpaa2_chan->queue_lock, flags);
+	spin_lock(&dpaa2_chan->vchan.lock);
+	if (vchan_issue_pending(&dpaa2_chan->vchan)) {
+		vdesc = vchan_next_desc(&dpaa2_chan->vchan);
+		if (!vdesc)
+			goto err_enqueue;
+		dpaa2_comp = to_fsl_qdma_comp(vdesc);
+
+		fd = (struct dpaa2_fd *)dpaa2_comp->fd_virt_addr;
+
+		list_del(&vdesc->node);
+		list_add_tail(&dpaa2_comp->list, &dpaa2_chan->comp_used);
+
+		/* TOBO: priority hard-coded to zero */
+		err = dpaa2_io_service_enqueue_fq(NULL,
+				priv->tx_queue_attr[0].fqid, fd);
+		if (err) {
+			list_del(&dpaa2_comp->list);
+			list_add_tail(&dpaa2_comp->list,
+				&dpaa2_chan->comp_free);
+		}
+
+	}
+err_enqueue:
+	spin_unlock(&dpaa2_chan->vchan.lock);
+	spin_unlock_irqrestore(&dpaa2_chan->queue_lock, flags);
+}
+
+static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev)
+{
+	struct device *dev = &ls_dev->dev;
+	struct dpaa2_qdma_priv *priv;
+	struct dpaa2_qdma_priv_per_prio *ppriv;
+	uint8_t prio_def = DPDMAI_PRIO_NUM;
+	int err;
+	int i;
+
+	priv = dev_get_drvdata(dev);
+
+	priv->dev = dev;
+	priv->dpqdma_id = ls_dev->obj_desc.id;
+
+	/*Get the handle for the DPDMAI this interface is associate with */
+	err = dpdmai_open(priv->mc_io, 0, priv->dpqdma_id, &ls_dev->mc_handle);
+	if (err) {
+		dev_err(dev, "dpdmai_open() failed\n");
+		return err;
+	}
+	dev_info(dev, "Opened dpdmai object successfully\n");
+
+	err = dpdmai_get_attributes(priv->mc_io, 0, ls_dev->mc_handle,
+				&priv->dpdmai_attr);
+	if (err) {
+		dev_err(dev, "dpdmai_get_attributes() failed\n");
+		return err;
+	}
+
+	if (priv->dpdmai_attr.version.major > DPDMAI_VER_MAJOR) {
+		dev_err(dev, "DPDMAI major version mismatch\n"
+			     "Found %u.%u, supported version is %u.%u\n",
+				priv->dpdmai_attr.version.major,
+				priv->dpdmai_attr.version.minor,
+				DPDMAI_VER_MAJOR, DPDMAI_VER_MINOR);
+	}
+
+	if (priv->dpdmai_attr.version.minor > DPDMAI_VER_MINOR) {
+		dev_err(dev, "DPDMAI minor version mismatch\n"
+			     "Found %u.%u, supported version is %u.%u\n",
+				priv->dpdmai_attr.version.major,
+				priv->dpdmai_attr.version.minor,
+				DPDMAI_VER_MAJOR, DPDMAI_VER_MINOR);
+	}
+
+	priv->num_pairs = min(priv->dpdmai_attr.num_of_priorities, prio_def);
+	ppriv = kcalloc(priv->num_pairs, sizeof(*ppriv), GFP_KERNEL);
+	if (!ppriv) {
+		dev_err(dev, "kzalloc for ppriv failed\n");
+		return -1;
+	}
+	priv->ppriv = ppriv;
+
+	for (i = 0; i < priv->num_pairs; i++) {
+		err = dpdmai_get_rx_queue(priv->mc_io, 0, ls_dev->mc_handle,
+				i, &priv->rx_queue_attr[i]);
+		if (err) {
+			dev_err(dev, "dpdmai_get_rx_queue() failed\n");
+			return err;
+		}
+		ppriv->rsp_fqid = priv->rx_queue_attr[i].fqid;
+
+		err = dpdmai_get_tx_queue(priv->mc_io, 0, ls_dev->mc_handle,
+				i, &priv->tx_queue_attr[i]);
+		if (err) {
+			dev_err(dev, "dpdmai_get_tx_queue() failed\n");
+			return err;
+		}
+		ppriv->req_fqid = priv->tx_queue_attr[i].fqid;
+		ppriv->prio = i;
+		ppriv->priv = priv;
+		ppriv++;
+	}
+
+	return 0;
+}
+
+static void dpaa2_qdma_fqdan_cb(struct dpaa2_io_notification_ctx *ctx)
+{
+	struct dpaa2_qdma_priv_per_prio *ppriv = container_of(ctx,
+			struct dpaa2_qdma_priv_per_prio, nctx);
+	struct dpaa2_qdma_priv *priv = ppriv->priv;
+	struct dpaa2_qdma_comp *dpaa2_comp, *_comp_tmp;
+	struct dpaa2_qdma_chan *qchan;
+	const struct dpaa2_fd *fd;
+	const struct dpaa2_fd *fd_eq;
+	struct dpaa2_dq *dq;
+	int err;
+	int is_last = 0;
+	uint8_t status;
+	int i;
+	int found;
+	uint32_t n_chans = priv->dpaa2_qdma->n_chans;
+
+	do {
+		err = dpaa2_io_service_pull_fq(NULL, ppriv->rsp_fqid,
+						ppriv->store);
+	} while (err);
+
+	while (!is_last) {
+		do {
+			dq = dpaa2_io_store_next(ppriv->store, &is_last);
+		} while (!is_last && !dq);
+		if (!dq) {
+			dev_err(priv->dev, "FQID returned no valid frames!\n");
+			continue;
+		}
+
+		/* obtain FD and process the error */
+		fd = dpaa2_dq_fd(dq);
+		status = fd->simple.ctrl & 0xff;
+		if (status)
+			dev_err(priv->dev, "FD error occurred\n");
+		found = 0;
+		for (i = 0; i < n_chans; i++) {
+			qchan = &priv->dpaa2_qdma->chans[i];
+			spin_lock(&qchan->queue_lock);
+			if (list_empty(&qchan->comp_used)) {
+				spin_unlock(&qchan->queue_lock);
+				continue;
+			}
+			list_for_each_entry_safe(dpaa2_comp, _comp_tmp,
+				&qchan->comp_used, list) {
+				fd_eq = (struct dpaa2_fd *)
+					dpaa2_comp->fd_virt_addr;
+
+				if (fd_eq->simple.addr ==
+					fd->simple.addr) {
+
+					list_del(&dpaa2_comp->list);
+					list_add_tail(&dpaa2_comp->list,
+							&qchan->comp_free);
+
+					spin_lock(&qchan->vchan.lock);
+					vchan_cookie_complete(
+						&dpaa2_comp->vdesc);
+					spin_unlock(&qchan->vchan.lock);
+					found = 1;
+					break;
+				}
+			}
+			spin_unlock(&qchan->queue_lock);
+			if (found)
+				break;
+		}
+	}
+
+	dpaa2_io_service_rearm(NULL, ctx);
+}
+
+static int __cold dpaa2_qdma_dpio_setup(struct dpaa2_qdma_priv *priv)
+{
+	int err, i, num;
+	struct device *dev = priv->dev;
+	struct dpaa2_qdma_priv_per_prio *ppriv;
+
+	num = priv->num_pairs;
+	ppriv = priv->ppriv;
+	for (i = 0; i < num; i++) {
+		ppriv->nctx.is_cdan = 0;
+		ppriv->nctx.desired_cpu = 1;
+		ppriv->nctx.id = ppriv->rsp_fqid;
+		ppriv->nctx.cb = dpaa2_qdma_fqdan_cb;
+		err = dpaa2_io_service_register(NULL, &ppriv->nctx);
+		if (err) {
+			dev_err(dev, "Notification register failed\n");
+			goto err_service;
+		}
+
+		ppriv->store = dpaa2_io_store_create(DPAA2_QDMA_STORE_SIZE,
+						dev);
+		if (!ppriv->store) {
+			dev_err(dev, "dpaa2_io_store_create() failed\n");
+			goto err_store;
+		}
+
+		ppriv++;
+	}
+	return 0;
+
+err_store:
+	dpaa2_io_service_deregister(NULL, &ppriv->nctx);
+err_service:
+	ppriv--;
+	while (ppriv >= priv->ppriv) {
+		dpaa2_io_service_deregister(NULL, &ppriv->nctx);
+		dpaa2_io_store_destroy(ppriv->store);
+		ppriv--;
+	}
+	return -1;
+}
+
+static void __cold dpaa2_dpmai_store_free(struct dpaa2_qdma_priv *priv)
+{
+	struct dpaa2_qdma_priv_per_prio *ppriv = priv->ppriv;
+	int i;
+
+	for (i = 0; i < priv->num_pairs; i++) {
+		dpaa2_io_store_destroy(ppriv->store);
+		ppriv++;
+	}
+}
+
+static void __cold dpaa2_dpdmai_dpio_free(struct dpaa2_qdma_priv *priv)
+{
+	struct dpaa2_qdma_priv_per_prio *ppriv = priv->ppriv;
+	int i;
+
+	for (i = 0; i < priv->num_pairs; i++) {
+		dpaa2_io_service_deregister(NULL, &ppriv->nctx);
+		ppriv++;
+	}
+}
+
+static int __cold dpaa2_dpdmai_bind(struct dpaa2_qdma_priv *priv)
+{
+	int err;
+	struct dpdmai_rx_queue_cfg rx_queue_cfg;
+	struct device *dev = priv->dev;
+	struct dpaa2_qdma_priv_per_prio *ppriv;
+	struct fsl_mc_device *ls_dev = to_fsl_mc_device(dev);
+	int i, num;
+
+	num = priv->num_pairs;
+	ppriv = priv->ppriv;
+	for (i = 0; i < num; i++) {
+		rx_queue_cfg.options = DPDMAI_QUEUE_OPT_USER_CTX |
+					DPDMAI_QUEUE_OPT_DEST;
+		rx_queue_cfg.user_ctx = ppriv->nctx.qman64;
+		rx_queue_cfg.dest_cfg.dest_type = DPDMAI_DEST_DPIO;
+		rx_queue_cfg.dest_cfg.dest_id = ppriv->nctx.dpio_id;
+		rx_queue_cfg.dest_cfg.priority = ppriv->prio;
+		err = dpdmai_set_rx_queue(priv->mc_io, 0, ls_dev->mc_handle,
+				rx_queue_cfg.dest_cfg.priority, &rx_queue_cfg);
+		if (err) {
+			dev_err(dev, "dpdmai_set_rx_queue() failed\n");
+			return err;
+		}
+
+		ppriv++;
+	}
+
+	return 0;
+}
+
+static int __cold dpaa2_dpdmai_dpio_unbind(struct dpaa2_qdma_priv *priv)
+{
+	int err = 0;
+	struct device *dev = priv->dev;
+	struct fsl_mc_device *ls_dev = to_fsl_mc_device(dev);
+	struct dpaa2_qdma_priv_per_prio *ppriv = priv->ppriv;
+	int i;
+
+	for (i = 0; i < priv->num_pairs; i++) {
+		ppriv->nctx.qman64 = 0;
+		ppriv->nctx.dpio_id = 0;
+		ppriv++;
+	}
+
+	err = dpdmai_reset(priv->mc_io, 0, ls_dev->mc_handle);
+	if (err)
+		dev_err(dev, "dpdmai_reset() failed\n");
+
+	return err;
+}
+
+static void __cold dpaa2_dpdmai_free_pool(struct dpaa2_qdma_chan *qchan,
+							struct list_head *head)
+{
+	struct qdma_sg_blk *sgb_tmp, *_sgb_tmp;
+	/* free the QDMA SG pool block */
+	list_for_each_entry_safe(sgb_tmp, _sgb_tmp, head, list) {
+		sgb_tmp->blk_virt_addr = (void *)((struct qdma_sg_blk *)
+						sgb_tmp->blk_virt_addr - 1);
+		sgb_tmp->blk_bus_addr = sgb_tmp->blk_bus_addr
+							- sizeof(*sgb_tmp);
+		dma_pool_free(qchan->sg_blk_pool, sgb_tmp->blk_virt_addr,
+						sgb_tmp->blk_bus_addr);
+	}
+
+}
+
+static void __cold dpaa2_dpdmai_free_comp(struct dpaa2_qdma_chan *qchan,
+						struct list_head *head)
+{
+	struct dpaa2_qdma_comp *comp_tmp, *_comp_tmp;
+	/* free the QDMA comp resource */
+	list_for_each_entry_safe(comp_tmp, _comp_tmp,
+			head, list) {
+		dma_pool_free(qchan->fd_pool,
+			comp_tmp->fd_virt_addr,
+			comp_tmp->fd_bus_addr);
+		/* free the SG source block on comp */
+		dpaa2_dpdmai_free_pool(qchan, &comp_tmp->sg_src_head);
+		/* free the SG destination block on comp */
+		dpaa2_dpdmai_free_pool(qchan, &comp_tmp->sg_dst_head);
+		list_del(&comp_tmp->list);
+		kfree(comp_tmp);
+	}
+
+}
+
+static void __cold dpaa2_dpdmai_free_channels(
+		struct dpaa2_qdma_engine *dpaa2_qdma)
+{
+	struct dpaa2_qdma_chan *qchan;
+	int num, i;
+
+	num = dpaa2_qdma->n_chans;
+	for (i = 0; i < num; i++) {
+		qchan = &dpaa2_qdma->chans[i];
+		dpaa2_dpdmai_free_comp(qchan, &qchan->comp_used);
+		dpaa2_dpdmai_free_comp(qchan, &qchan->comp_free);
+		dpaa2_dpdmai_free_pool(qchan, &qchan->sgb_free);
+		dma_pool_destroy(qchan->fd_pool);
+		dma_pool_destroy(qchan->sg_blk_pool);
+	}
+}
+
+static int dpaa2_dpdmai_alloc_channels(struct dpaa2_qdma_engine *dpaa2_qdma)
+{
+	struct dpaa2_qdma_chan *dpaa2_chan;
+	struct device *dev = &dpaa2_qdma->priv->dpdmai_dev->dev;
+	int i;
+
+	INIT_LIST_HEAD(&dpaa2_qdma->dma_dev.channels);
+	for (i = 0; i < dpaa2_qdma->n_chans; i++) {
+		dpaa2_chan = &dpaa2_qdma->chans[i];
+		dpaa2_chan->qdma = dpaa2_qdma;
+		dpaa2_chan->vchan.desc_free = dpaa2_qdma_free_desc;
+		vchan_init(&dpaa2_chan->vchan, &dpaa2_qdma->dma_dev);
+
+		dpaa2_chan->fd_pool = dma_pool_create("fd_pool",
+					dev, FD_POOL_SIZE, 32, 0);
+		if (!dpaa2_chan->fd_pool)
+			return -1;
+		dpaa2_chan->sg_blk_pool = dma_pool_create("sg_blk_pool",
+					dev, SG_POOL_SIZE, 32, 0);
+		if (!dpaa2_chan->sg_blk_pool)
+			return -1;
+
+		spin_lock_init(&dpaa2_chan->queue_lock);
+		INIT_LIST_HEAD(&dpaa2_chan->comp_used);
+		INIT_LIST_HEAD(&dpaa2_chan->comp_free);
+		INIT_LIST_HEAD(&dpaa2_chan->sgb_free);
+	}
+	return 0;
+}
+
+static int dpaa2_qdma_probe(struct fsl_mc_device *dpdmai_dev)
+{
+	struct dpaa2_qdma_priv *priv;
+	struct device *dev = &dpdmai_dev->dev;
+	struct dpaa2_qdma_engine *dpaa2_qdma;
+	int err;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	dev_set_drvdata(dev, priv);
+	priv->dpdmai_dev = dpdmai_dev;
+
+	priv->iommu_domain = iommu_get_domain_for_dev(dev);
+	if (priv->iommu_domain)
+		smmu_disable = false;
+
+	/* obtain a MC portal */
+	err = fsl_mc_portal_allocate(dpdmai_dev, 0, &priv->mc_io);
+	if (err) {
+		dev_err(dev, "MC portal allocation failed\n");
+		goto err_mcportal;
+	}
+
+	/* DPDMAI initialization */
+	err = dpaa2_qdma_setup(dpdmai_dev);
+	if (err) {
+		dev_err(dev, "dpaa2_dpdmai_setup() failed\n");
+		goto err_dpdmai_setup;
+	}
+
+	/* DPIO */
+	err = dpaa2_qdma_dpio_setup(priv);
+	if (err) {
+		dev_err(dev, "dpaa2_dpdmai_dpio_setup() failed\n");
+		goto err_dpio_setup;
+	}
+
+	/* DPDMAI binding to DPIO */
+	err = dpaa2_dpdmai_bind(priv);
+	if (err) {
+		dev_err(dev, "dpaa2_dpdmai_bind() failed\n");
+		goto err_bind;
+	}
+
+	/* DPDMAI enable */
+	err = dpdmai_enable(priv->mc_io, 0, dpdmai_dev->mc_handle);
+	if (err) {
+		dev_err(dev, "dpdmai_enable() faile\n");
+		goto err_enable;
+	}
+
+	dpaa2_qdma = kzalloc(sizeof(*dpaa2_qdma), GFP_KERNEL);
+	if (!dpaa2_qdma) {
+		err = -ENOMEM;
+		goto err_eng;
+	}
+
+	priv->dpaa2_qdma = dpaa2_qdma;
+	dpaa2_qdma->priv = priv;
+
+	dpaa2_qdma->n_chans = NUM_CH;
+
+	err = dpaa2_dpdmai_alloc_channels(dpaa2_qdma);
+	if (err) {
+		dev_err(dev, "QDMA alloc channels faile\n");
+		goto err_reg;
+	}
+
+	dma_cap_set(DMA_PRIVATE, dpaa2_qdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_SLAVE, dpaa2_qdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_MEMCPY, dpaa2_qdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_SG, dpaa2_qdma->dma_dev.cap_mask);
+
+	dpaa2_qdma->dma_dev.dev = dev;
+	dpaa2_qdma->dma_dev.device_alloc_chan_resources
+		= dpaa2_qdma_alloc_chan_resources;
+	dpaa2_qdma->dma_dev.device_free_chan_resources
+		= dpaa2_qdma_free_chan_resources;
+	dpaa2_qdma->dma_dev.device_tx_status = dpaa2_qdma_tx_status;
+	dpaa2_qdma->dma_dev.device_prep_dma_memcpy = dpaa2_qdma_prep_memcpy;
+	dpaa2_qdma->dma_dev.device_prep_dma_sg = dpaa2_qdma_prep_sg;
+	dpaa2_qdma->dma_dev.device_issue_pending = dpaa2_qdma_issue_pending;
+
+	err = dma_async_device_register(&dpaa2_qdma->dma_dev);
+	if (err) {
+		dev_err(dev, "Can't register NXP QDMA engine.\n");
+		goto err_reg;
+	}
+
+	return 0;
+
+err_reg:
+	dpaa2_dpdmai_free_channels(dpaa2_qdma);
+	kfree(dpaa2_qdma);
+err_eng:
+	dpdmai_disable(priv->mc_io, 0, dpdmai_dev->mc_handle);
+err_enable:
+	dpaa2_dpdmai_dpio_unbind(priv);
+err_bind:
+	dpaa2_dpmai_store_free(priv);
+	dpaa2_dpdmai_dpio_free(priv);
+err_dpio_setup:
+	dpdmai_close(priv->mc_io, 0, dpdmai_dev->mc_handle);
+err_dpdmai_setup:
+	fsl_mc_portal_free(priv->mc_io);
+err_mcportal:
+	kfree(priv->ppriv);
+	kfree(priv);
+	dev_set_drvdata(dev, NULL);
+	return err;
+}
+
+static int dpaa2_qdma_remove(struct fsl_mc_device *ls_dev)
+{
+	struct device *dev;
+	struct dpaa2_qdma_priv *priv;
+	struct dpaa2_qdma_engine *dpaa2_qdma;
+
+	dev = &ls_dev->dev;
+	priv = dev_get_drvdata(dev);
+	dpaa2_qdma = priv->dpaa2_qdma;
+
+	dpdmai_disable(priv->mc_io, 0, ls_dev->mc_handle);
+	dpaa2_dpdmai_dpio_unbind(priv);
+	dpaa2_dpmai_store_free(priv);
+	dpaa2_dpdmai_dpio_free(priv);
+	dpdmai_close(priv->mc_io, 0, ls_dev->mc_handle);
+	fsl_mc_portal_free(priv->mc_io);
+	dev_set_drvdata(dev, NULL);
+	dpaa2_dpdmai_free_channels(dpaa2_qdma);
+
+	dma_async_device_unregister(&dpaa2_qdma->dma_dev);
+	kfree(priv);
+	kfree(dpaa2_qdma);
+
+	return 0;
+}
+
+static const struct fsl_mc_device_id dpaa2_qdma_id_table[] = {
+	{
+		.vendor = FSL_MC_VENDOR_FREESCALE,
+		.obj_type = "dpdmai",
+	},
+	{ .vendor = 0x0 }
+};
+
+static struct fsl_mc_driver dpaa2_qdma_driver = {
+	.driver		= {
+		.name	= "dpaa2-qdma",
+		.owner  = THIS_MODULE,
+	},
+	.probe          = dpaa2_qdma_probe,
+	.remove		= dpaa2_qdma_remove,
+	.match_id_table	= dpaa2_qdma_id_table
+};
+
+static int __init dpaa2_qdma_driver_init(void)
+{
+	return fsl_mc_driver_register(&(dpaa2_qdma_driver));
+}
+late_initcall(dpaa2_qdma_driver_init);
+
+static void __exit fsl_qdma_exit(void)
+{
+	fsl_mc_driver_unregister(&(dpaa2_qdma_driver));
+}
+module_exit(fsl_qdma_exit);
+
+MODULE_DESCRIPTION("NXP DPAA2 qDMA driver");
+MODULE_LICENSE("Dual BSD/GPL");
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/dpaa2-qdma.h
@@ -0,0 +1,262 @@
+/* Copyright 2015 NXP Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of NXP Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NXP Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL NXP Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __DPAA2_QDMA_H
+#define __DPAA2_QDMA_H
+
+#define LONG_FORMAT 1
+
+#define DPAA2_QDMA_STORE_SIZE 16
+#define NUM_CH 8
+#define NUM_SG_PER_BLK	16
+
+#define QDMA_DMR_OFFSET	0x0
+#define QDMA_DQ_EN (0 << 30)
+#define QDMA_DQ_DIS (1 << 30)
+
+#define QDMA_DSR_M_OFFSET 0x10004
+
+struct dpaa2_qdma_sd_d {
+	uint32_t rsv:32;
+	union {
+		struct {
+			uint32_t ssd:12; /* souce stride distance */
+			uint32_t sss:12; /* souce stride size */
+			uint32_t rsv1:8;
+		} sdf;
+		struct {
+			uint32_t dsd:12; /* Destination stride distance */
+			uint32_t dss:12; /* Destination stride size */
+			uint32_t rsv2:8;
+		} ddf;
+	} df;
+	uint32_t rbpcmd;	/* Route-by-port command */
+	uint32_t cmd;
+} __attribute__((__packed__));
+/* Source descriptor command read transaction type for RBP=0:
+ coherent copy of cacheable memory */
+#define QDMA_SD_CMD_RDTTYPE_COHERENT (0xb << 28)
+/* Destination descriptor command write transaction type for RBP=0:
+ coherent copy of cacheable memory */
+#define QDMA_DD_CMD_WRTTYPE_COHERENT (0x6 << 28)
+
+#define QDMA_SG_FMT_SDB		0x0 /* single data buffer */
+#define QDMA_SG_FMT_FDS		0x1 /* frame data section */
+#define QDMA_SG_FMT_SGTE	0x2 /* SGT extension */
+#define QDMA_SG_SL_SHORT	0x1 /* short length */
+#define QDMA_SG_SL_LONG		0x0 /* short length */
+#define QDMA_SG_F		0x1 /* last sg entry */
+struct dpaa2_qdma_sg {
+	uint32_t addr_lo;		/* address 0:31 */
+	uint32_t addr_hi:17;	/* address 32:48 */
+	uint32_t rsv:15;
+	union {
+		uint32_t data_len_sl0; /* SL=0, the long format */
+		struct {
+			uint32_t len:17; /* SL=1, the short format */
+			uint32_t reserve:3;
+			uint32_t sf:1;
+			uint32_t sr:1;
+			uint32_t size:10; /* buff size */
+		} data_len_sl1;
+	} data_len;	/* AVAIL_LENGTH */
+	struct {
+		uint32_t bpid:14;
+		uint32_t ivp:1;
+		uint32_t mbt:1;
+		uint32_t offset:12;
+		uint32_t fmt:2;
+		uint32_t sl:1;
+		uint32_t f:1;
+	} ctrl;
+} __attribute__((__packed__));
+
+#define QMAN_FD_FMT_ENABLE (1 << 12) /* frame list table enable */
+#define QMAN_FD_BMT_ENABLE (1 << 15) /* bypass memory translation */
+#define QMAN_FD_BMT_DISABLE (0 << 15) /* bypass memory translation */
+#define QMAN_FD_SL_DISABLE (0 << 14) /* short lengthe disabled */
+#define QMAN_FD_SL_ENABLE (1 << 14) /* short lengthe enabled */
+
+#define QDMA_SB_FRAME (0 << 28) /* single frame */
+#define QDMA_SG_FRAME (2 << 28) /* scatter gather frames */
+#define QDMA_FINAL_BIT_DISABLE (0 << 31) /* final bit disable */
+#define QDMA_FINAL_BIT_ENABLE (1 << 31) /* final bit enable */
+
+#define QDMA_FD_SHORT_FORMAT (1 << 11) /* short format */
+#define QDMA_FD_LONG_FORMAT (0 << 11) /* long format */
+#define QDMA_SER_DISABLE (0 << 8) /* no notification */
+#define QDMA_SER_CTX (1 << 8) /* notification by FQD_CTX[fqid] */
+#define QDMA_SER_DEST (2 << 8) /* notification by destination desc */
+#define QDMA_SER_BOTH (3 << 8) /* soruce and dest notification */
+#define QDMA_FD_SPF_ENALBE (1 << 30) /* source prefetch enable */
+
+#define QMAN_FD_VA_ENABLE (1 << 14)  /* Address used is virtual address */
+#define QMAN_FD_VA_DISABLE (0 << 14)/* Address used is a real address */
+#define QMAN_FD_CBMT_ENABLE (1 << 15) /* Flow Context: 49bit physical address */
+#define QMAN_FD_CBMT_DISABLE (0 << 15) /* Flow Context: 64bit virtual address */
+#define QMAN_FD_SC_DISABLE (0 << 27) /* stashing control */
+
+#define QDMA_FL_FMT_SBF 0x0	/* Single buffer frame */
+#define QDMA_FL_FMT_SGE 0x2 /* Scatter gather frame */
+#define QDMA_FL_BMT_ENABLE 0x1 /* enable bypass memory translation */
+#define QDMA_FL_BMT_DISABLE 0x0 /* enable bypass memory translation */
+#define QDMA_FL_SL_LONG 0x0 /* long length */
+#define QDMA_FL_SL_SHORT 0x1 /* short length */
+#define QDMA_FL_F 0x1 /* last frame list bit */
+/*Description of Frame list table structure*/
+struct dpaa2_frame_list  {
+	uint32_t addr_lo;	/* lower 32 bits of address */
+	uint32_t addr_hi:17; /* upper 17 bits of address */
+	uint32_t resrvd:15;
+	union {
+		uint32_t data_len_sl0; /* If SL=0, then data length is 32 */
+		struct {
+			uint32_t data_len:18; /* IF SL=1; length is 18bit */
+			uint32_t resrvd:2;
+			uint32_t mem:12; /* Valid only when SL=1 */
+		} data_len_sl1;
+	} data_len;
+	/* word 4 */
+	uint32_t bpid:14; /* Frame buffer pool ID */
+	uint32_t ivp:1; /* Invalid Pool ID. */
+	uint32_t bmt:1; /* Bypass Memory Translation */
+	uint32_t offset:12; /* Frame offset */
+	uint32_t fmt:2; /* Frame Format */
+	uint32_t sl:1; /* Short Length */
+	uint32_t f:1; /* Final bit */
+
+	uint32_t frc; /* Frame Context */
+	/* word 6 */
+	uint32_t err:8; /* Frame errors */
+	uint32_t resrvd0:8;
+	uint32_t asal:4; /* accelerator-specific annotation length */
+	uint32_t resrvd1:1;
+	uint32_t ptv2:1;
+	uint32_t ptv1:1;
+	uint32_t pta:1; /* pass-through annotation */
+	uint32_t resrvd2:8;
+
+	uint32_t flc_lo; /* lower 32 bits fo flow context */
+	uint32_t flc_hi; /* higher 32 bits fo flow context */
+} __attribute__((__packed__));
+
+struct dpaa2_qdma_chan {
+	struct virt_dma_chan		vchan;
+	struct virt_dma_desc		vdesc;
+	enum dma_status			status;
+	struct dpaa2_qdma_engine	*qdma;
+
+	struct mutex            dpaa2_queue_mutex;
+	spinlock_t		queue_lock;
+	struct dma_pool		*fd_pool;
+	struct dma_pool		*sg_blk_pool;
+
+	struct list_head	comp_used;
+	struct list_head	comp_free;
+
+	struct list_head	sgb_free;
+};
+
+struct qdma_sg_blk {
+	dma_addr_t	blk_bus_addr;
+	void		*blk_virt_addr;
+	struct list_head	list;
+};
+
+struct dpaa2_qdma_comp {
+	dma_addr_t		fd_bus_addr;
+	dma_addr_t		fl_bus_addr;
+	dma_addr_t		desc_bus_addr;
+	dma_addr_t		sge_src_bus_addr;
+	dma_addr_t		sge_dst_bus_addr;
+	void			*fd_virt_addr;
+	void			*fl_virt_addr;
+	void			*desc_virt_addr;
+	void			*sg_src_virt_addr;
+	void			*sg_dst_virt_addr;
+	struct qdma_sg_blk	*sg_blk;
+	uint32_t		sg_blk_num;
+	struct list_head	sg_src_head;
+	struct list_head	sg_dst_head;
+	struct dpaa2_qdma_chan	*qchan;
+	struct virt_dma_desc	vdesc;
+	struct list_head	list;
+};
+
+struct dpaa2_qdma_engine {
+	struct dma_device	dma_dev;
+	u32			n_chans;
+	struct dpaa2_qdma_chan	chans[NUM_CH];
+
+	struct dpaa2_qdma_priv *priv;
+};
+
+/*
+ * dpaa2_qdma_priv - driver private data
+ */
+struct dpaa2_qdma_priv {
+	int dpqdma_id;
+
+	struct iommu_domain *iommu_domain;
+	struct dpdmai_attr dpdmai_attr;
+	struct device *dev;
+	struct fsl_mc_io *mc_io;
+	struct fsl_mc_device *dpdmai_dev;
+
+	struct dpdmai_rx_queue_attr rx_queue_attr[DPDMAI_PRIO_NUM];
+	struct dpdmai_tx_queue_attr tx_queue_attr[DPDMAI_PRIO_NUM];
+
+	uint8_t num_pairs;
+
+	struct dpaa2_qdma_engine *dpaa2_qdma;
+	struct dpaa2_qdma_priv_per_prio *ppriv;
+};
+
+struct dpaa2_qdma_priv_per_prio {
+	int req_fqid;
+	int rsp_fqid;
+	int prio;
+
+	struct dpaa2_io_store *store;
+	struct dpaa2_io_notification_ctx nctx;
+
+	struct dpaa2_qdma_priv *priv;
+};
+
+/* FD pool size: one FD + 3 Frame list + 2 source/destination descriptor */
+#define FD_POOL_SIZE (sizeof(struct dpaa2_fd) + \
+		sizeof(struct dpaa2_frame_list) * 3 + \
+		sizeof(struct dpaa2_qdma_sd_d) * 2)
+
+/* qdma_sg_blk + 16 SGs */
+#define SG_POOL_SIZE (sizeof(struct qdma_sg_blk) +\
+		sizeof(struct dpaa2_qdma_sg) * NUM_SG_PER_BLK)
+#endif /* __DPAA2_QDMA_H */
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/dpdmai.c
@@ -0,0 +1,454 @@
+/* Copyright 2013-2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/types.h>
+#include <linux/io.h>
+#include "fsl_dpdmai.h"
+#include "fsl_dpdmai_cmd.h"
+#include "../../../drivers/staging/fsl-mc/include/mc-sys.h"
+#include "../../../drivers/staging/fsl-mc/include/mc-cmd.h"
+
+int dpdmai_open(struct fsl_mc_io *mc_io,
+		uint32_t cmd_flags,
+		int dpdmai_id,
+		uint16_t *token)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_OPEN,
+					  cmd_flags,
+					  0);
+	DPDMAI_CMD_OPEN(cmd, dpdmai_id);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	*token = MC_CMD_HDR_READ_TOKEN(cmd.header);
+
+	return 0;
+}
+
+int dpdmai_close(struct fsl_mc_io *mc_io,
+		 uint32_t cmd_flags,
+		 uint16_t token)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_CLOSE,
+					  cmd_flags, token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_create(struct fsl_mc_io *mc_io,
+		  uint32_t cmd_flags,
+		  const struct dpdmai_cfg *cfg,
+		  uint16_t *token)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_CREATE,
+					  cmd_flags,
+					  0);
+	DPDMAI_CMD_CREATE(cmd, cfg);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	*token = MC_CMD_HDR_READ_TOKEN(cmd.header);
+
+	return 0;
+}
+
+int dpdmai_destroy(struct fsl_mc_io *mc_io,
+		   uint32_t cmd_flags,
+		   uint16_t token)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_DESTROY,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_enable(struct fsl_mc_io *mc_io,
+		  uint32_t cmd_flags,
+		  uint16_t token)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_ENABLE,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_disable(struct fsl_mc_io *mc_io,
+		   uint32_t cmd_flags,
+		   uint16_t token)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_DISABLE,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_is_enabled(struct fsl_mc_io *mc_io,
+		      uint32_t cmd_flags,
+		      uint16_t token,
+		      int *en)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_IS_ENABLED,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_IS_ENABLED(cmd, *en);
+
+	return 0;
+}
+
+int dpdmai_reset(struct fsl_mc_io *mc_io,
+		 uint32_t cmd_flags,
+		 uint16_t token)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_RESET,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_irq(struct fsl_mc_io *mc_io,
+		   uint32_t cmd_flags,
+		   uint16_t token,
+		   uint8_t irq_index,
+		   int *type,
+		   struct dpdmai_irq_cfg	*irq_cfg)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_IRQ,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_IRQ(cmd, irq_index);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_IRQ(cmd, *type, irq_cfg);
+
+	return 0;
+}
+
+int dpdmai_set_irq(struct fsl_mc_io *mc_io,
+		   uint32_t cmd_flags,
+		   uint16_t token,
+		   uint8_t irq_index,
+		   struct dpdmai_irq_cfg *irq_cfg)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_SET_IRQ,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_SET_IRQ(cmd, irq_index, irq_cfg);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_irq_enable(struct fsl_mc_io *mc_io,
+			  uint32_t cmd_flags,
+			  uint16_t token,
+			  uint8_t irq_index,
+			  uint8_t *en)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_IRQ_ENABLE,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_IRQ_ENABLE(cmd, irq_index);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_IRQ_ENABLE(cmd, *en);
+
+	return 0;
+}
+
+int dpdmai_set_irq_enable(struct fsl_mc_io *mc_io,
+			  uint32_t cmd_flags,
+			  uint16_t token,
+			  uint8_t irq_index,
+			  uint8_t en)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_SET_IRQ_ENABLE,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_SET_IRQ_ENABLE(cmd, irq_index, en);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_irq_mask(struct fsl_mc_io *mc_io,
+			uint32_t cmd_flags,
+			uint16_t token,
+			uint8_t irq_index,
+			uint32_t *mask)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_IRQ_MASK,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_IRQ_MASK(cmd, irq_index);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_IRQ_MASK(cmd, *mask);
+
+	return 0;
+}
+
+int dpdmai_set_irq_mask(struct fsl_mc_io *mc_io,
+			uint32_t cmd_flags,
+			uint16_t token,
+			uint8_t irq_index,
+			uint32_t mask)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_SET_IRQ_MASK,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_SET_IRQ_MASK(cmd, irq_index, mask);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_irq_status(struct fsl_mc_io *mc_io,
+			  uint32_t cmd_flags,
+			  uint16_t token,
+			  uint8_t irq_index,
+			  uint32_t *status)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_IRQ_STATUS,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_IRQ_STATUS(cmd, irq_index, *status);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_IRQ_STATUS(cmd, *status);
+
+	return 0;
+}
+
+int dpdmai_clear_irq_status(struct fsl_mc_io *mc_io,
+			    uint32_t cmd_flags,
+			    uint16_t token,
+			    uint8_t irq_index,
+			    uint32_t status)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_CLEAR_IRQ_STATUS,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_CLEAR_IRQ_STATUS(cmd, irq_index, status);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_attributes(struct fsl_mc_io *mc_io,
+			  uint32_t cmd_flags,
+			  uint16_t token,
+			  struct dpdmai_attr *attr)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_ATTR,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_ATTR(cmd, attr);
+
+	return 0;
+}
+
+int dpdmai_set_rx_queue(struct fsl_mc_io *mc_io,
+			uint32_t cmd_flags,
+			uint16_t token,
+			uint8_t priority,
+			const struct dpdmai_rx_queue_cfg *cfg)
+{
+	struct mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_SET_RX_QUEUE,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_SET_RX_QUEUE(cmd, priority, cfg);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+int dpdmai_get_rx_queue(struct fsl_mc_io *mc_io,
+			uint32_t cmd_flags,
+			uint16_t token,
+			uint8_t priority, struct dpdmai_rx_queue_attr *attr)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_RX_QUEUE,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_RX_QUEUE(cmd, priority);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_RX_QUEUE(cmd, attr);
+
+	return 0;
+}
+
+int dpdmai_get_tx_queue(struct fsl_mc_io *mc_io,
+			uint32_t cmd_flags,
+			uint16_t token,
+			uint8_t priority,
+			struct dpdmai_tx_queue_attr *attr)
+{
+	struct mc_command cmd = { 0 };
+	int err;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPDMAI_CMDID_GET_TX_QUEUE,
+					  cmd_flags,
+					  token);
+	DPDMAI_CMD_GET_TX_QUEUE(cmd, priority);
+
+	/* send command to mc*/
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	/* retrieve response parameters */
+	DPDMAI_RSP_GET_TX_QUEUE(cmd, attr);
+
+	return 0;
+}
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/fsl_dpdmai.h
@@ -0,0 +1,521 @@
+/* Copyright 2013-2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __FSL_DPDMAI_H
+#define __FSL_DPDMAI_H
+
+struct fsl_mc_io;
+
+/* Data Path DMA Interface API
+ * Contains initialization APIs and runtime control APIs for DPDMAI
+ */
+
+/* General DPDMAI macros */
+
+/**
+ * Maximum number of Tx/Rx priorities per DPDMAI object
+ */
+#define DPDMAI_PRIO_NUM		2
+
+/**
+ * All queues considered; see dpdmai_set_rx_queue()
+ */
+#define DPDMAI_ALL_QUEUES	(uint8_t)(-1)
+
+/**
+ * dpdmai_open() - Open a control session for the specified object
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @dpdmai_id:	DPDMAI unique ID
+ * @token:	Returned token; use in subsequent API calls
+ *
+ * This function can be used to open a control session for an
+ * already created object; an object may have been declared in
+ * the DPL or by calling the dpdmai_create() function.
+ * This function returns a unique authentication token,
+ * associated with the specific object ID and the specific MC
+ * portal; this token must be used in all subsequent commands for
+ * this specific object.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_open(struct fsl_mc_io	*mc_io,
+		uint32_t		cmd_flags,
+		int			dpdmai_id,
+		uint16_t		*token);
+
+/**
+ * dpdmai_close() - Close the control session of the object
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ *
+ * After this function is called, no further operations are
+ * allowed on the object without opening a new control session.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_close(struct fsl_mc_io	*mc_io,
+		 uint32_t		cmd_flags,
+		 uint16_t		token);
+
+/**
+ * struct dpdmai_cfg - Structure representing DPDMAI configuration
+ * @priorities: Priorities for the DMA hardware processing; valid priorities are
+ *	configured with values 1-8; the entry following last valid entry
+ *	should be configured with 0
+ */
+struct dpdmai_cfg {
+	uint8_t priorities[DPDMAI_PRIO_NUM];
+};
+
+/**
+ * dpdmai_create() - Create the DPDMAI object
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @cfg:	Configuration structure
+ * @token:	Returned token; use in subsequent API calls
+ *
+ * Create the DPDMAI object, allocate required resources and
+ * perform required initialization.
+ *
+ * The object can be created either by declaring it in the
+ * DPL file, or by calling this function.
+ *
+ * This function returns a unique authentication token,
+ * associated with the specific object ID and the specific MC
+ * portal; this token must be used in all subsequent calls to
+ * this specific object. For objects that are created using the
+ * DPL file, call dpdmai_open() function to get an authentication
+ * token first.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_create(struct fsl_mc_io		*mc_io,
+		  uint32_t			cmd_flags,
+		  const struct dpdmai_cfg	*cfg,
+		  uint16_t			*token);
+
+/**
+ * dpdmai_destroy() - Destroy the DPDMAI object and release all its resources.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ *
+ * Return:	'0' on Success; error code otherwise.
+ */
+int dpdmai_destroy(struct fsl_mc_io	*mc_io,
+		   uint32_t		cmd_flags,
+		   uint16_t		token);
+
+/**
+ * dpdmai_enable() - Enable the DPDMAI, allow sending and receiving frames.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_enable(struct fsl_mc_io	*mc_io,
+		  uint32_t		cmd_flags,
+		  uint16_t		token);
+
+/**
+ * dpdmai_disable() - Disable the DPDMAI, stop sending and receiving frames.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_disable(struct fsl_mc_io	*mc_io,
+		   uint32_t		cmd_flags,
+		   uint16_t		token);
+
+/**
+ * dpdmai_is_enabled() - Check if the DPDMAI is enabled.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @en:		Returns '1' if object is enabled; '0' otherwise
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_is_enabled(struct fsl_mc_io	*mc_io,
+		      uint32_t		cmd_flags,
+		      uint16_t		token,
+		      int		*en);
+
+/**
+ * dpdmai_reset() - Reset the DPDMAI, returns the object to initial state.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_reset(struct fsl_mc_io	*mc_io,
+		 uint32_t		cmd_flags,
+		 uint16_t		token);
+
+/**
+ * struct dpdmai_irq_cfg - IRQ configuration
+ * @addr:	Address that must be written to signal a message-based interrupt
+ * @val:	Value to write into irq_addr address
+ * @irq_num: A user defined number associated with this IRQ
+ */
+struct dpdmai_irq_cfg {
+	     uint64_t		addr;
+	     uint32_t		val;
+	     int		irq_num;
+};
+
+/**
+ * dpdmai_set_irq() - Set IRQ information for the DPDMAI to trigger an interrupt.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @irq_index:	Identifies the interrupt index to configure
+ * @irq_cfg:	IRQ configuration
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_set_irq(struct fsl_mc_io		*mc_io,
+		   uint32_t			cmd_flags,
+		   uint16_t			token,
+		   uint8_t			irq_index,
+		   struct dpdmai_irq_cfg	*irq_cfg);
+
+/**
+ * dpdmai_get_irq() - Get IRQ information from the DPDMAI
+ *
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @type:	Interrupt type: 0 represents message interrupt
+ *		type (both irq_addr and irq_val are valid)
+ * @irq_cfg:	IRQ attributes
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_irq(struct fsl_mc_io		*mc_io,
+		   uint32_t			cmd_flags,
+		   uint16_t			token,
+		   uint8_t			irq_index,
+		   int				*type,
+		   struct dpdmai_irq_cfg	*irq_cfg);
+
+/**
+ * dpdmai_set_irq_enable() - Set overall interrupt state.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:		Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @en:			Interrupt state - enable = 1, disable = 0
+ *
+ * Allows GPP software to control when interrupts are generated.
+ * Each interrupt can have up to 32 causes.  The enable/disable control's the
+ * overall interrupt state. if the interrupt is disabled no causes will cause
+ * an interrupt
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_set_irq_enable(struct fsl_mc_io	*mc_io,
+			  uint32_t		cmd_flags,
+			  uint16_t		token,
+			  uint8_t		irq_index,
+			  uint8_t		en);
+
+/**
+ * dpdmai_get_irq_enable() - Get overall interrupt state
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:		Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @en:			Returned Interrupt state - enable = 1, disable = 0
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_irq_enable(struct fsl_mc_io	*mc_io,
+			  uint32_t		cmd_flags,
+			  uint16_t		token,
+			  uint8_t		irq_index,
+			  uint8_t		*en);
+
+/**
+ * dpdmai_set_irq_mask() - Set interrupt mask.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:		Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @mask:		event mask to trigger interrupt;
+ *				each bit:
+ *					0 = ignore event
+ *					1 = consider event for asserting IRQ
+ *
+ * Every interrupt can have up to 32 causes and the interrupt model supports
+ * masking/unmasking each cause independently
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_set_irq_mask(struct fsl_mc_io	*mc_io,
+			uint32_t		cmd_flags,
+			uint16_t		token,
+			uint8_t		irq_index,
+			uint32_t		mask);
+
+/**
+ * dpdmai_get_irq_mask() - Get interrupt mask.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:		Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @mask:		Returned event mask to trigger interrupt
+ *
+ * Every interrupt can have up to 32 causes and the interrupt model supports
+ * masking/unmasking each cause independently
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_irq_mask(struct fsl_mc_io	*mc_io,
+			uint32_t		cmd_flags,
+			uint16_t		token,
+			uint8_t		irq_index,
+			uint32_t		*mask);
+
+/**
+ * dpdmai_get_irq_status() - Get the current status of any pending interrupts
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:		Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @status:		Returned interrupts status - one bit per cause:
+ *					0 = no interrupt pending
+ *					1 = interrupt pending
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_irq_status(struct fsl_mc_io	*mc_io,
+			  uint32_t		cmd_flags,
+			  uint16_t		token,
+			  uint8_t		irq_index,
+			  uint32_t		*status);
+
+/**
+ * dpdmai_clear_irq_status() - Clear a pending interrupt's status
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @irq_index:	The interrupt index to configure
+ * @status:	bits to clear (W1C) - one bit per cause:
+ *			0 = don't change
+ *			1 = clear status bit
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_clear_irq_status(struct fsl_mc_io	*mc_io,
+			    uint32_t		cmd_flags,
+			    uint16_t		token,
+			    uint8_t		irq_index,
+			    uint32_t		status);
+
+/**
+ * struct dpdmai_attr - Structure representing DPDMAI attributes
+ * @id: DPDMAI object ID
+ * @version: DPDMAI version
+ * @num_of_priorities: number of priorities
+ */
+struct dpdmai_attr {
+	int	id;
+	/**
+	 * struct version - DPDMAI version
+	 * @major: DPDMAI major version
+	 * @minor: DPDMAI minor version
+	 */
+	struct {
+		uint16_t major;
+		uint16_t minor;
+	} version;
+	uint8_t num_of_priorities;
+};
+
+/**
+ * dpdmai_get_attributes() - Retrieve DPDMAI attributes.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @attr:	Returned object's attributes
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_attributes(struct fsl_mc_io	*mc_io,
+			  uint32_t		cmd_flags,
+			  uint16_t		token,
+			  struct dpdmai_attr	*attr);
+
+/**
+ * enum dpdmai_dest - DPDMAI destination types
+ * @DPDMAI_DEST_NONE: Unassigned destination; The queue is set in parked mode
+ *	and does not generate FQDAN notifications; user is expected to dequeue
+ *	from the queue based on polling or other user-defined method
+ * @DPDMAI_DEST_DPIO: The queue is set in schedule mode and generates FQDAN
+ *	notifications to the specified DPIO; user is expected to dequeue
+ *	from the queue only after notification is received
+ * @DPDMAI_DEST_DPCON: The queue is set in schedule mode and does not generate
+ *	FQDAN notifications, but is connected to the specified DPCON object;
+ *	user is expected to dequeue from the DPCON channel
+ */
+enum dpdmai_dest {
+	DPDMAI_DEST_NONE = 0,
+	DPDMAI_DEST_DPIO = 1,
+	DPDMAI_DEST_DPCON = 2
+};
+
+/**
+ * struct dpdmai_dest_cfg - Structure representing DPDMAI destination parameters
+ * @dest_type: Destination type
+ * @dest_id: Either DPIO ID or DPCON ID, depending on the destination type
+ * @priority: Priority selection within the DPIO or DPCON channel; valid values
+ *	are 0-1 or 0-7, depending on the number of priorities in that
+ *	channel; not relevant for 'DPDMAI_DEST_NONE' option
+ */
+struct dpdmai_dest_cfg {
+	enum dpdmai_dest	dest_type;
+	int			dest_id;
+	uint8_t		priority;
+};
+
+/* DPDMAI queue modification options */
+
+/**
+ * Select to modify the user's context associated with the queue
+ */
+#define DPDMAI_QUEUE_OPT_USER_CTX	0x00000001
+
+/**
+ * Select to modify the queue's destination
+ */
+#define DPDMAI_QUEUE_OPT_DEST		0x00000002
+
+/**
+ * struct dpdmai_rx_queue_cfg - DPDMAI RX queue configuration
+ * @options: Flags representing the suggested modifications to the queue;
+ *	Use any combination of 'DPDMAI_QUEUE_OPT_<X>' flags
+ * @user_ctx: User context value provided in the frame descriptor of each
+ *	dequeued frame;
+ *	valid only if 'DPDMAI_QUEUE_OPT_USER_CTX' is contained in 'options'
+ * @dest_cfg: Queue destination parameters;
+ *	valid only if 'DPDMAI_QUEUE_OPT_DEST' is contained in 'options'
+ */
+struct dpdmai_rx_queue_cfg {
+	uint32_t		options;
+	uint64_t		user_ctx;
+	struct dpdmai_dest_cfg	dest_cfg;
+
+};
+
+/**
+ * dpdmai_set_rx_queue() - Set Rx queue configuration
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @priority:	Select the queue relative to number of
+ *			priorities configured at DPDMAI creation; use
+ *			DPDMAI_ALL_QUEUES to configure all Rx queues
+ *			identically.
+ * @cfg:	Rx queue configuration
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_set_rx_queue(struct fsl_mc_io			*mc_io,
+			uint32_t				cmd_flags,
+			uint16_t				token,
+			uint8_t					priority,
+			const struct dpdmai_rx_queue_cfg	*cfg);
+
+/**
+ * struct dpdmai_rx_queue_attr - Structure representing attributes of Rx queues
+ * @user_ctx:  User context value provided in the frame descriptor of each
+ *	 dequeued frame
+ * @dest_cfg: Queue destination configuration
+ * @fqid: Virtual FQID value to be used for dequeue operations
+ */
+struct dpdmai_rx_queue_attr {
+	uint64_t		user_ctx;
+	struct dpdmai_dest_cfg	dest_cfg;
+	uint32_t		fqid;
+};
+
+/**
+ * dpdmai_get_rx_queue() - Retrieve Rx queue attributes.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @priority:	Select the queue relative to number of
+ *				priorities configured at DPDMAI creation
+ * @attr:	Returned Rx queue attributes
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_rx_queue(struct fsl_mc_io		*mc_io,
+			uint32_t			cmd_flags,
+			uint16_t			token,
+			uint8_t				priority,
+			struct dpdmai_rx_queue_attr	*attr);
+
+/**
+ * struct dpdmai_tx_queue_attr - Structure representing attributes of Tx queues
+ * @fqid: Virtual FQID to be used for sending frames to DMA hardware
+ */
+
+struct dpdmai_tx_queue_attr {
+	uint32_t fqid;
+};
+
+/**
+ * dpdmai_get_tx_queue() - Retrieve Tx queue attributes.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPDMAI object
+ * @priority:	Select the queue relative to number of
+ *			priorities configured at DPDMAI creation
+ * @attr:	Returned Tx queue attributes
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpdmai_get_tx_queue(struct fsl_mc_io		*mc_io,
+			uint32_t			cmd_flags,
+			uint16_t			token,
+			uint8_t				priority,
+			struct dpdmai_tx_queue_attr	*attr);
+
+#endif /* __FSL_DPDMAI_H */
--- /dev/null
+++ b/drivers/dma/dpaa2-qdma/fsl_dpdmai_cmd.h
@@ -0,0 +1,222 @@
+/* Copyright 2013-2016 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _FSL_DPDMAI_CMD_H
+#define _FSL_DPDMAI_CMD_H
+
+/* DPDMAI Version */
+#define DPDMAI_VER_MAJOR				2
+#define DPDMAI_VER_MINOR				2
+
+#define DPDMAI_CMD_BASE_VERSION			0
+#define DPDMAI_CMD_ID_OFFSET				4
+
+/* Command IDs */
+#define DPDMAI_CMDID_CLOSE                           ((0x800 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_OPEN                            ((0x80E << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_CREATE                          ((0x90E << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_DESTROY                         ((0x900 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+
+#define DPDMAI_CMDID_ENABLE                          ((0x002 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_DISABLE                         ((0x003 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_ATTR                        ((0x004 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_RESET                           ((0x005 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_IS_ENABLED                      ((0x006 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+
+#define DPDMAI_CMDID_SET_IRQ                         ((0x010 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_IRQ                         ((0x011 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_SET_IRQ_ENABLE                  ((0x012 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_IRQ_ENABLE                  ((0x013 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_SET_IRQ_MASK                    ((0x014 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_IRQ_MASK                    ((0x015 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_IRQ_STATUS                  ((0x016 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_CLEAR_IRQ_STATUS                ((0x017 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+
+#define DPDMAI_CMDID_SET_RX_QUEUE                    ((0x1A0 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_RX_QUEUE                    ((0x1A1 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+#define DPDMAI_CMDID_GET_TX_QUEUE                    ((0x1A2 << DPDMAI_CMD_ID_OFFSET) | DPDMAI_CMD_BASE_VERSION)
+
+
+#define MC_CMD_HDR_TOKEN_O 32  /* Token field offset */
+#define MC_CMD_HDR_TOKEN_S 16  /* Token field size */
+
+
+#define MAKE_UMASK64(_width) \
+	((uint64_t)((_width) < 64 ? ((uint64_t)1 << (_width)) - 1 : \
+	(uint64_t)-1))
+
+static inline uint64_t mc_enc(int lsoffset, int width, uint64_t val)
+{
+	return (uint64_t)(((uint64_t)val & MAKE_UMASK64(width)) << lsoffset);
+}
+
+static inline uint64_t mc_dec(uint64_t val, int lsoffset, int width)
+{
+	return (uint64_t)((val >> lsoffset) & MAKE_UMASK64(width));
+}
+
+#define MC_CMD_OP(_cmd, _param, _offset, _width, _type, _arg) \
+	((_cmd).params[_param] |= mc_enc((_offset), (_width), _arg))
+
+#define MC_RSP_OP(_cmd, _param, _offset, _width, _type, _arg) \
+	(_arg = (_type)mc_dec(_cmd.params[_param], (_offset), (_width)))
+
+#define MC_CMD_HDR_READ_TOKEN(_hdr) \
+	((uint16_t)mc_dec((_hdr), MC_CMD_HDR_TOKEN_O, MC_CMD_HDR_TOKEN_S))
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_OPEN(cmd, dpdmai_id) \
+	MC_CMD_OP(cmd, 0, 0,  32, int,      dpdmai_id)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_CREATE(cmd, cfg) \
+do { \
+	MC_CMD_OP(cmd, 0, 8,  8,  uint8_t,  cfg->priorities[0]);\
+	MC_CMD_OP(cmd, 0, 16, 8,  uint8_t,  cfg->priorities[1]);\
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_IS_ENABLED(cmd, en) \
+	MC_RSP_OP(cmd, 0, 0,  1,  int,	    en)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_SET_IRQ(cmd, irq_index, irq_cfg) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  8,  uint8_t,  irq_index);\
+	MC_CMD_OP(cmd, 0, 32, 32, uint32_t, irq_cfg->val);\
+	MC_CMD_OP(cmd, 1, 0,  64, uint64_t, irq_cfg->addr);\
+	MC_CMD_OP(cmd, 2, 0,  32, int,	    irq_cfg->irq_num); \
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_IRQ(cmd, irq_index) \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_IRQ(cmd, type, irq_cfg) \
+do { \
+	MC_RSP_OP(cmd, 0, 0,  32, uint32_t, irq_cfg->val); \
+	MC_RSP_OP(cmd, 1, 0,  64, uint64_t, irq_cfg->addr);\
+	MC_RSP_OP(cmd, 2, 0,  32, int,	    irq_cfg->irq_num); \
+	MC_RSP_OP(cmd, 2, 32, 32, int,	    type); \
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_SET_IRQ_ENABLE(cmd, irq_index, enable_state) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  8,  uint8_t,  enable_state); \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index); \
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_IRQ_ENABLE(cmd, irq_index) \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_IRQ_ENABLE(cmd, enable_state) \
+	MC_RSP_OP(cmd, 0, 0,  8,  uint8_t,  enable_state)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_SET_IRQ_MASK(cmd, irq_index, mask) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  32, uint32_t, mask); \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index); \
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_IRQ_MASK(cmd, irq_index) \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_IRQ_MASK(cmd, mask) \
+	MC_RSP_OP(cmd, 0, 0,  32, uint32_t, mask)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_IRQ_STATUS(cmd, irq_index, status) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  32, uint32_t, status);\
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index);\
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_IRQ_STATUS(cmd, status) \
+	MC_RSP_OP(cmd, 0, 0,  32, uint32_t,  status)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_CLEAR_IRQ_STATUS(cmd, irq_index, status) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  32, uint32_t, status); \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  irq_index); \
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_ATTR(cmd, attr) \
+do { \
+	MC_RSP_OP(cmd, 0, 0,  32, int,	    attr->id); \
+	MC_RSP_OP(cmd, 0, 32,  8,  uint8_t,  attr->num_of_priorities); \
+	MC_RSP_OP(cmd, 1, 0,  16, uint16_t, attr->version.major);\
+	MC_RSP_OP(cmd, 1, 16, 16, uint16_t, attr->version.minor);\
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_SET_RX_QUEUE(cmd, priority, cfg) \
+do { \
+	MC_CMD_OP(cmd, 0, 0,  32, int,      cfg->dest_cfg.dest_id); \
+	MC_CMD_OP(cmd, 0, 32, 8,  uint8_t,  cfg->dest_cfg.priority); \
+	MC_CMD_OP(cmd, 0, 40, 8,  uint8_t,  priority); \
+	MC_CMD_OP(cmd, 0, 48, 4,  enum dpdmai_dest, cfg->dest_cfg.dest_type); \
+	MC_CMD_OP(cmd, 1, 0,  64, uint64_t, cfg->user_ctx); \
+	MC_CMD_OP(cmd, 2, 0,  32, uint32_t, cfg->options);\
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_RX_QUEUE(cmd, priority) \
+	MC_CMD_OP(cmd, 0, 40, 8,  uint8_t,  priority)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_RX_QUEUE(cmd, attr) \
+do { \
+	MC_RSP_OP(cmd, 0, 0,  32, int,      attr->dest_cfg.dest_id);\
+	MC_RSP_OP(cmd, 0, 32, 8,  uint8_t,  attr->dest_cfg.priority);\
+	MC_RSP_OP(cmd, 0, 48, 4,  enum dpdmai_dest, attr->dest_cfg.dest_type);\
+	MC_RSP_OP(cmd, 1, 0,  64, uint64_t,  attr->user_ctx);\
+	MC_RSP_OP(cmd, 2, 0,  32, uint32_t,  attr->fqid);\
+} while (0)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_CMD_GET_TX_QUEUE(cmd, priority) \
+	MC_CMD_OP(cmd, 0, 40, 8,  uint8_t,  priority)
+
+/*                cmd, param, offset, width, type, arg_name */
+#define DPDMAI_RSP_GET_TX_QUEUE(cmd, attr) \
+	MC_RSP_OP(cmd, 1, 0,  32, uint32_t,  attr->fqid)
+
+#endif /* _FSL_DPDMAI_CMD_H */
--- /dev/null
+++ b/drivers/dma/fsl-qdma.c
@@ -0,0 +1,1201 @@
+/*
+ * drivers/dma/fsl-qdma.c
+ *
+ * Copyright 2014-2015 Freescale Semiconductor, Inc.
+ *
+ * Driver for the Freescale qDMA engine with software command queue mode.
+ * Channel virtualization is supported through enqueuing of DMA jobs to,
+ * or dequeuing DMA jobs from, different work queues.
+ * This module can be found on Freescale LS SoCs.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <asm/cacheflush.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "virt-dma.h"
+
+#define FSL_QDMA_DMR			0x0
+#define FSL_QDMA_DSR			0x4
+#define FSL_QDMA_DEIER			0xe00
+#define FSL_QDMA_DEDR			0xe04
+#define FSL_QDMA_DECFDW0R		0xe10
+#define FSL_QDMA_DECFDW1R		0xe14
+#define FSL_QDMA_DECFDW2R		0xe18
+#define FSL_QDMA_DECFDW3R		0xe1c
+#define FSL_QDMA_DECFQIDR		0xe30
+#define FSL_QDMA_DECBR			0xe34
+
+#define FSL_QDMA_BCQMR(x)		(0xc0 + 0x100 * (x))
+#define FSL_QDMA_BCQSR(x)		(0xc4 + 0x100 * (x))
+#define FSL_QDMA_BCQEDPA_SADDR(x)	(0xc8 + 0x100 * (x))
+#define FSL_QDMA_BCQDPA_SADDR(x)	(0xcc + 0x100 * (x))
+#define FSL_QDMA_BCQEEPA_SADDR(x)	(0xd0 + 0x100 * (x))
+#define FSL_QDMA_BCQEPA_SADDR(x)	(0xd4 + 0x100 * (x))
+#define FSL_QDMA_BCQIER(x)		(0xe0 + 0x100 * (x))
+#define FSL_QDMA_BCQIDR(x)		(0xe4 + 0x100 * (x))
+
+#define FSL_QDMA_SQDPAR			0x80c
+#define FSL_QDMA_SQEPAR			0x814
+#define FSL_QDMA_BSQMR			0x800
+#define FSL_QDMA_BSQSR			0x804
+#define FSL_QDMA_BSQICR			0x828
+#define FSL_QDMA_CQMR			0xa00
+#define FSL_QDMA_CQDSCR1		0xa08
+#define FSL_QDMA_CQDSCR2                0xa0c
+#define FSL_QDMA_CQIER			0xa10
+#define FSL_QDMA_CQEDR			0xa14
+#define FSL_QDMA_SQCCMR			0xa20
+
+#define FSL_QDMA_SQICR_ICEN
+
+#define FSL_QDMA_CQIDR_CQT		0xff000000
+#define FSL_QDMA_CQIDR_SQPE		0x800000
+#define FSL_QDMA_CQIDR_SQT		0x8000
+
+#define FSL_QDMA_BCQIER_CQTIE		0x8000
+#define FSL_QDMA_BCQIER_CQPEIE		0x800000
+#define FSL_QDMA_BSQICR_ICEN		0x80000000
+#define FSL_QDMA_BSQICR_ICST(x)		((x) << 16)
+#define FSL_QDMA_CQIER_MEIE		0x80000000
+#define FSL_QDMA_CQIER_TEIE		0x1
+#define FSL_QDMA_SQCCMR_ENTER_WM	0x200000
+
+#define FSL_QDMA_QUEUE_MAX		8
+
+#define FSL_QDMA_BCQMR_EN		0x80000000
+#define FSL_QDMA_BCQMR_EI		0x40000000
+#define FSL_QDMA_BCQMR_CD_THLD(x)	((x) << 20)
+#define FSL_QDMA_BCQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BCQSR_QF		0x10000
+#define FSL_QDMA_BCQSR_XOFF		0x1
+
+#define FSL_QDMA_BSQMR_EN		0x80000000
+#define FSL_QDMA_BSQMR_DI		0x40000000
+#define FSL_QDMA_BSQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BSQSR_QE		0x20000
+
+#define FSL_QDMA_DMR_DQD		0x40000000
+#define FSL_QDMA_DSR_DB			0x80000000
+
+#define FSL_QDMA_BASE_BUFFER_SIZE	96
+#define FSL_QDMA_EXPECT_SG_ENTRY_NUM	16
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MIN	64
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MAX	16384
+#define FSL_QDMA_QUEUE_NUM_MAX		8
+
+#define FSL_QDMA_CMD_RWTTYPE		0x4
+#define FSL_QDMA_CMD_LWC                0x2
+
+#define FSL_QDMA_CMD_RWTTYPE_OFFSET	28
+#define FSL_QDMA_CMD_NS_OFFSET		27
+#define FSL_QDMA_CMD_DQOS_OFFSET	24
+#define FSL_QDMA_CMD_WTHROTL_OFFSET	20
+#define FSL_QDMA_CMD_DSEN_OFFSET	19
+#define FSL_QDMA_CMD_LWC_OFFSET		16
+
+#define FSL_QDMA_E_SG_TABLE		1
+#define FSL_QDMA_E_DATA_BUFFER		0
+#define FSL_QDMA_F_LAST_ENTRY		1
+
+u64 pre_addr, pre_queue;
+
+struct fsl_qdma_ccdf {
+	u8 status;
+	u32 rev1:22;
+	u32 ser:1;
+	u32 rev2:1;
+	u32 rev3:20;
+	u32 offset:9;
+	u32 format:3;
+	union {
+		struct {
+			u32 addr_lo;	/* low 32-bits of 40-bit address */
+			u32 addr_hi:8;	/* high 8-bits of 40-bit address */
+			u32 rev4:16;
+			u32 queue:3;
+			u32 rev5:3;
+			u32 dd:2;	/* dynamic debug */
+		};
+		struct {
+			u64 addr:40;
+			/* More efficient address accessor */
+			u64 __notaddress:24;
+		};
+	};
+} __packed;
+
+struct fsl_qdma_csgf {
+	u32 offset:13;
+	u32 rev1:19;
+	u32 length:30;
+	u32 f:1;
+	u32 e:1;
+	union {
+		struct {
+			u32 addr_lo;	/* low 32-bits of 40-bit address */
+			u32 addr_hi:8;	/* high 8-bits of 40-bit address */
+			u32 rev2:24;
+		};
+		struct {
+			u64 addr:40;
+			/* More efficient address accessor */
+			u64 __notaddress:24;
+		};
+	};
+} __packed;
+
+struct fsl_qdma_sdf {
+	u32 rev3:32;
+	u32 ssd:12;	/* souce stride distance */
+	u32 sss:12;	/* souce stride size */
+	u32 rev4:8;
+	u32 rev5:32;
+	u32 cmd;
+} __packed;
+
+struct fsl_qdma_ddf {
+	u32 rev1:32;
+	u32 dsd:12;	/* Destination stride distance */
+	u32 dss:12;	/* Destination stride size */
+	u32 rev2:8;
+	u32 rev3:32;
+	u32 cmd;
+} __packed;
+
+struct fsl_qdma_chan {
+	struct virt_dma_chan		vchan;
+	struct virt_dma_desc		vdesc;
+	enum dma_status			status;
+	u32				slave_id;
+	struct fsl_qdma_engine		*qdma;
+	struct fsl_qdma_queue		*queue;
+	struct list_head		qcomp;
+};
+
+struct fsl_qdma_queue {
+	struct fsl_qdma_ccdf	*virt_head;
+	struct fsl_qdma_ccdf	*virt_tail;
+	struct list_head	comp_used;
+	struct list_head	comp_free;
+	struct dma_pool		*comp_pool;
+	struct dma_pool		*sg_pool;
+	spinlock_t		queue_lock;
+	dma_addr_t		bus_addr;
+	u32                     n_cq;
+	u32			id;
+	struct fsl_qdma_ccdf	*cq;
+};
+
+struct fsl_qdma_sg {
+	dma_addr_t		bus_addr;
+	void			*virt_addr;
+};
+
+struct fsl_qdma_comp {
+	dma_addr_t              bus_addr;
+	void			*virt_addr;
+	struct fsl_qdma_chan	*qchan;
+	struct fsl_qdma_sg	*sg_block;
+	struct virt_dma_desc    vdesc;
+	struct list_head	list;
+	u32			sg_block_src;
+	u32			sg_block_dst;
+};
+
+struct fsl_qdma_engine {
+	struct dma_device	dma_dev;
+	void __iomem		*ctrl_base;
+	void __iomem            *status_base;
+	void __iomem		*block_base;
+	u32			n_chans;
+	u32			n_queues;
+	struct mutex            fsl_qdma_mutex;
+	int			error_irq;
+	int			queue_irq;
+	bool			big_endian;
+	struct fsl_qdma_queue	*queue;
+	struct fsl_qdma_queue	*status;
+	struct fsl_qdma_chan	chans[];
+
+};
+
+static u32 qdma_readl(struct fsl_qdma_engine *qdma, void __iomem *addr)
+{
+	if (qdma->big_endian)
+		return ioread32be(addr);
+	else
+		return ioread32(addr);
+}
+
+static void qdma_writel(struct fsl_qdma_engine *qdma, u32 val,
+						void __iomem *addr)
+{
+	if (qdma->big_endian)
+		iowrite32be(val, addr);
+	else
+		iowrite32(val, addr);
+}
+
+static struct fsl_qdma_chan *to_fsl_qdma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct fsl_qdma_chan, vchan.chan);
+}
+
+static struct fsl_qdma_comp *to_fsl_qdma_comp(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct fsl_qdma_comp, vdesc);
+}
+
+static int fsl_qdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	/*
+	 * In QDMA mode, We don't need to do anything.
+	 */
+	return 0;
+}
+
+static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+}
+
+static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
+					dma_addr_t dst, dma_addr_t src, u32 len)
+{
+	struct fsl_qdma_ccdf *ccdf;
+	struct fsl_qdma_csgf *csgf_desc, *csgf_src, *csgf_dest;
+	struct fsl_qdma_sdf *sdf;
+	struct fsl_qdma_ddf *ddf;
+
+	ccdf = (struct fsl_qdma_ccdf *)fsl_comp->virt_addr;
+	csgf_desc = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 1;
+	csgf_src = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 2;
+	csgf_dest = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 3;
+	sdf = (struct fsl_qdma_sdf *)fsl_comp->virt_addr + 4;
+	ddf = (struct fsl_qdma_ddf *)fsl_comp->virt_addr + 5;
+
+	memset(fsl_comp->virt_addr, 0, FSL_QDMA_BASE_BUFFER_SIZE);
+	/* Head Command Descriptor(Frame Descriptor) */
+	ccdf->addr = fsl_comp->bus_addr + 16;
+	ccdf->format = 1; /* Compound S/G format */
+	/* Status notification is enqueued to status queue. */
+	ccdf->ser = 1;
+	/* Compound Command Descriptor(Frame List Table) */
+	csgf_desc->addr = fsl_comp->bus_addr + 64;
+	/* It must be 32 as Compound S/G Descriptor */
+	csgf_desc->length = 32;
+	csgf_src->addr = src;
+	csgf_src->length = len;
+	csgf_dest->addr = dst;
+	csgf_dest->length = len;
+	/* This entry is the last entry. */
+	csgf_dest->f = FSL_QDMA_F_LAST_ENTRY;
+	/* Descriptor Buffer */
+	sdf->cmd = FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET;
+	ddf->cmd = FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET;
+	ddf->cmd |= FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET;
+}
+
+static void fsl_qdma_comp_fill_sg(
+		struct fsl_qdma_comp *fsl_comp,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents)
+{
+	struct fsl_qdma_ccdf *ccdf;
+	struct fsl_qdma_csgf *csgf_desc, *csgf_src, *csgf_dest, *csgf_sg;
+	struct fsl_qdma_sdf *sdf;
+	struct fsl_qdma_ddf *ddf;
+	struct fsl_qdma_sg *sg_block, *temp;
+	struct scatterlist *sg;
+	u64 total_src_len = 0;
+	u64 total_dst_len = 0;
+	u32 i;
+
+	ccdf = (struct fsl_qdma_ccdf *)fsl_comp->virt_addr;
+	csgf_desc = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 1;
+	csgf_src = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 2;
+	csgf_dest = (struct fsl_qdma_csgf *)fsl_comp->virt_addr + 3;
+	sdf = (struct fsl_qdma_sdf *)fsl_comp->virt_addr + 4;
+	ddf = (struct fsl_qdma_ddf *)fsl_comp->virt_addr + 5;
+
+	memset(fsl_comp->virt_addr, 0, FSL_QDMA_BASE_BUFFER_SIZE);
+	/* Head Command Descriptor(Frame Descriptor) */
+	ccdf->addr = fsl_comp->bus_addr + 16;
+	ccdf->format = 1; /* Compound S/G format */
+	/* Status notification is enqueued to status queue. */
+	ccdf->ser = 1;
+
+	/* Compound Command Descriptor(Frame List Table) */
+	csgf_desc->addr = fsl_comp->bus_addr + 64;
+	/* It must be 32 as Compound S/G Descriptor */
+	csgf_desc->length = 32;
+
+	sg_block = fsl_comp->sg_block;
+	csgf_src->addr = sg_block->bus_addr;
+	/* This entry link to the s/g entry. */
+	csgf_src->e = FSL_QDMA_E_SG_TABLE;
+
+	temp = sg_block + fsl_comp->sg_block_src;
+	csgf_dest->addr = temp->bus_addr;
+	/* This entry is the last entry. */
+	csgf_dest->f = FSL_QDMA_F_LAST_ENTRY;
+	/* This entry link to the s/g entry. */
+	csgf_dest->e = FSL_QDMA_E_SG_TABLE;
+
+	for_each_sg(src_sg, sg, src_nents, i) {
+		temp = sg_block + i / (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1);
+		csgf_sg = (struct fsl_qdma_csgf *)temp->virt_addr +
+			  i % (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1);
+		csgf_sg->addr = sg_dma_address(sg);
+		csgf_sg->length = sg_dma_len(sg);
+		total_src_len += sg_dma_len(sg);
+
+		if (i == src_nents - 1)
+			csgf_sg->f = FSL_QDMA_F_LAST_ENTRY;
+		if (i % (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) ==
+		    FSL_QDMA_EXPECT_SG_ENTRY_NUM - 2) {
+			csgf_sg = (struct fsl_qdma_csgf *)temp->virt_addr +
+				  FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1;
+			temp = sg_block +
+				i / (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) + 1;
+			csgf_sg->addr = temp->bus_addr;
+			csgf_sg->e = FSL_QDMA_E_SG_TABLE;
+		}
+	}
+
+	sg_block += fsl_comp->sg_block_src;
+	for_each_sg(dst_sg, sg, dst_nents, i) {
+		temp = sg_block + i / (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1);
+		csgf_sg = (struct fsl_qdma_csgf *)temp->virt_addr +
+			  i % (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1);
+		csgf_sg->addr = sg_dma_address(sg);
+		csgf_sg->length = sg_dma_len(sg);
+		total_dst_len += sg_dma_len(sg);
+
+		if (i == dst_nents - 1)
+			csgf_sg->f = FSL_QDMA_F_LAST_ENTRY;
+		if (i % (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) ==
+		    FSL_QDMA_EXPECT_SG_ENTRY_NUM - 2) {
+			csgf_sg = (struct fsl_qdma_csgf *)temp->virt_addr +
+				  FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1;
+			temp = sg_block +
+				i / (FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) + 1;
+			csgf_sg->addr = temp->bus_addr;
+			csgf_sg->e = FSL_QDMA_E_SG_TABLE;
+		}
+	}
+
+	if (total_src_len != total_dst_len)
+		dev_err(&fsl_comp->qchan->vchan.chan.dev->device,
+			"The data length for src and dst isn't match.\n");
+
+	csgf_src->length = total_src_len;
+	csgf_dest->length = total_dst_len;
+
+	/* Descriptor Buffer */
+	sdf->cmd = FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET;
+	ddf->cmd = FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET;
+}
+
+/*
+ * Prei-request full command descriptor for enqueue.
+ */
+static int fsl_qdma_pre_request_enqueue_desc(struct fsl_qdma_queue *queue)
+{
+	struct fsl_qdma_comp *comp_temp;
+	int i;
+
+	for (i = 0; i < queue->n_cq; i++) {
+		comp_temp = kzalloc(sizeof(*comp_temp), GFP_KERNEL);
+		if (!comp_temp)
+			return -1;
+		comp_temp->virt_addr = dma_pool_alloc(queue->comp_pool,
+						      GFP_NOWAIT,
+						      &comp_temp->bus_addr);
+		if (!comp_temp->virt_addr)
+			return -1;
+		list_add_tail(&comp_temp->list, &queue->comp_free);
+	}
+	return 0;
+}
+
+/*
+ * Request a command descriptor for enqueue.
+ */
+static struct fsl_qdma_comp *fsl_qdma_request_enqueue_desc(
+					struct fsl_qdma_chan *fsl_chan,
+					unsigned int dst_nents,
+					unsigned int src_nents)
+{
+	struct fsl_qdma_comp *comp_temp;
+	struct fsl_qdma_sg *sg_block;
+	struct fsl_qdma_queue *queue = fsl_chan->queue;
+	unsigned long flags;
+	unsigned int dst_sg_entry_block, src_sg_entry_block, sg_entry_total, i;
+
+	spin_lock_irqsave(&queue->queue_lock, flags);
+	if (list_empty(&queue->comp_free)) {
+		spin_unlock_irqrestore(&queue->queue_lock, flags);
+		comp_temp = kzalloc(sizeof(*comp_temp), GFP_KERNEL);
+		if (!comp_temp)
+			return NULL;
+		comp_temp->virt_addr = dma_pool_alloc(queue->comp_pool,
+						      GFP_NOWAIT,
+						      &comp_temp->bus_addr);
+		if (!comp_temp->virt_addr)
+			return NULL;
+	} else {
+		comp_temp = list_first_entry(&queue->comp_free,
+					     struct fsl_qdma_comp,
+					     list);
+		list_del(&comp_temp->list);
+		spin_unlock_irqrestore(&queue->queue_lock, flags);
+	}
+
+	if (dst_nents != 0)
+		dst_sg_entry_block = dst_nents /
+					(FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) + 1;
+	else
+		dst_sg_entry_block = 0;
+
+	if (src_nents != 0)
+		src_sg_entry_block = src_nents /
+					(FSL_QDMA_EXPECT_SG_ENTRY_NUM - 1) + 1;
+	else
+		src_sg_entry_block = 0;
+
+	sg_entry_total = dst_sg_entry_block + src_sg_entry_block;
+	if (sg_entry_total) {
+		sg_block = kzalloc(sizeof(*sg_block) *
+					      sg_entry_total,
+					      GFP_KERNEL);
+		if (!sg_block)
+			return NULL;
+		comp_temp->sg_block = sg_block;
+		for (i = 0; i < sg_entry_total; i++) {
+			sg_block->virt_addr = dma_pool_alloc(queue->sg_pool,
+							GFP_NOWAIT,
+							&sg_block->bus_addr);
+			memset(sg_block->virt_addr, 0,
+					FSL_QDMA_EXPECT_SG_ENTRY_NUM * 16);
+			sg_block++;
+		}
+	}
+
+	comp_temp->sg_block_src = src_sg_entry_block;
+	comp_temp->sg_block_dst = dst_sg_entry_block;
+	comp_temp->qchan = fsl_chan;
+
+	return comp_temp;
+}
+
+static struct fsl_qdma_queue *fsl_qdma_alloc_queue_resources(
+					struct platform_device *pdev,
+					unsigned int queue_num)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_queue *queue_head, *queue_temp;
+	int ret, len, i;
+	unsigned int queue_size[FSL_QDMA_QUEUE_MAX];
+
+	if (queue_num > FSL_QDMA_QUEUE_MAX)
+		queue_num = FSL_QDMA_QUEUE_MAX;
+	len = sizeof(*queue_head) * queue_num;
+	queue_head = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!queue_head)
+		return NULL;
+
+	ret = of_property_read_u32_array(np, "queue-sizes", queue_size,
+								queue_num);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queue-sizes.\n");
+		return NULL;
+	}
+
+	for (i = 0; i < queue_num; i++) {
+		if (queue_size[i] > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX
+			|| queue_size[i] < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+			dev_err(&pdev->dev, "Get wrong queue-sizes.\n");
+			return NULL;
+		}
+		queue_temp = queue_head + i;
+		queue_temp->cq = dma_alloc_coherent(&pdev->dev,
+						sizeof(struct fsl_qdma_ccdf) *
+						queue_size[i],
+						&queue_temp->bus_addr,
+						GFP_KERNEL);
+		if (!queue_temp->cq)
+			return NULL;
+		queue_temp->n_cq = queue_size[i];
+		queue_temp->id = i;
+		queue_temp->virt_head = queue_temp->cq;
+		queue_temp->virt_tail = queue_temp->cq;
+		/*
+		 * The dma pool for queue command buffer
+		 */
+		queue_temp->comp_pool = dma_pool_create("comp_pool",
+						&pdev->dev,
+						FSL_QDMA_BASE_BUFFER_SIZE,
+						16, 0);
+		if (!queue_temp->comp_pool) {
+			dma_free_coherent(&pdev->dev,
+						sizeof(struct fsl_qdma_ccdf) *
+						queue_size[i],
+						queue_temp->cq,
+						queue_temp->bus_addr);
+			return NULL;
+		}
+		/*
+		 * The dma pool for queue command buffer
+		 */
+		queue_temp->sg_pool = dma_pool_create("sg_pool",
+					&pdev->dev,
+					FSL_QDMA_EXPECT_SG_ENTRY_NUM * 16,
+					64, 0);
+		if (!queue_temp->sg_pool) {
+			dma_free_coherent(&pdev->dev,
+						sizeof(struct fsl_qdma_ccdf) *
+						queue_size[i],
+						queue_temp->cq,
+						queue_temp->bus_addr);
+			dma_pool_destroy(queue_temp->comp_pool);
+			return NULL;
+		}
+		/*
+		 * List for queue command buffer
+		 */
+		INIT_LIST_HEAD(&queue_temp->comp_used);
+		INIT_LIST_HEAD(&queue_temp->comp_free);
+		spin_lock_init(&queue_temp->queue_lock);
+	}
+
+	return queue_head;
+}
+
+static struct fsl_qdma_queue *fsl_qdma_prep_status_queue(
+						struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_queue *status_head;
+	unsigned int status_size;
+	int ret;
+
+	ret = of_property_read_u32(np, "status-sizes", &status_size);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get status-sizes.\n");
+		return NULL;
+	}
+	if (status_size > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX
+			|| status_size < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+		dev_err(&pdev->dev, "Get wrong status_size.\n");
+		return NULL;
+	}
+	status_head = devm_kzalloc(&pdev->dev, sizeof(*status_head),
+								GFP_KERNEL);
+	if (!status_head)
+		return NULL;
+
+	/*
+	 * Buffer for queue command
+	 */
+	status_head->cq = dma_alloc_coherent(&pdev->dev,
+						sizeof(struct fsl_qdma_ccdf) *
+						status_size,
+						&status_head->bus_addr,
+						GFP_KERNEL);
+	if (!status_head->cq)
+		return NULL;
+	status_head->n_cq = status_size;
+	status_head->virt_head = status_head->cq;
+	status_head->virt_tail = status_head->cq;
+	status_head->comp_pool = NULL;
+
+	return status_head;
+}
+
+static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
+{
+	void __iomem *ctrl = fsl_qdma->ctrl_base;
+	void __iomem *block = fsl_qdma->block_base;
+	int i, count = 5;
+	u32 reg;
+
+	/* Disable the command queue and wait for idle state. */
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg |= FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+	for (i = 0; i < FSL_QDMA_QUEUE_NUM_MAX; i++)
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQMR(i));
+
+	while (1) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DSR);
+		if (!(reg & FSL_QDMA_DSR_DB))
+			break;
+		if (count-- < 0)
+			return -EBUSY;
+		udelay(100);
+	}
+
+	/* Disable status queue. */
+	qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BSQMR);
+
+	/*
+	 * Clear the command queue interrupt detect register for all queues.
+	 */
+	qdma_writel(fsl_qdma, 0xffffffff, block + FSL_QDMA_BCQIDR(0));
+
+	return 0;
+}
+
+static int fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+	struct fsl_qdma_queue *fsl_status = fsl_qdma->status;
+	struct fsl_qdma_queue *temp_queue;
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_ccdf *status_addr;
+	struct fsl_qdma_csgf *csgf_src;
+	void __iomem *block = fsl_qdma->block_base;
+	u32 reg, i;
+	bool duplicate, duplicate_handle;
+
+	while (1) {
+		duplicate = 0;
+		duplicate_handle = 0;
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQSR);
+		if (reg & FSL_QDMA_BSQSR_QE)
+			return 0;
+		status_addr = fsl_status->virt_head;
+		if (status_addr->queue == pre_queue &&
+			status_addr->addr == pre_addr)
+			duplicate = 1;
+
+		i = status_addr->queue;
+		pre_queue = status_addr->queue;
+		pre_addr = status_addr->addr;
+		temp_queue = fsl_queue + i;
+		spin_lock(&temp_queue->queue_lock);
+		if (list_empty(&temp_queue->comp_used)) {
+			if (duplicate)
+				duplicate_handle = 1;
+			else {
+				spin_unlock(&temp_queue->queue_lock);
+				return -1;
+			}
+		} else {
+			fsl_comp = list_first_entry(&temp_queue->comp_used,
+							struct fsl_qdma_comp,
+							list);
+			csgf_src = (struct fsl_qdma_csgf *)fsl_comp->virt_addr
+							   + 2;
+			if (fsl_comp->bus_addr + 16 !=
+					(dma_addr_t)status_addr->addr) {
+				if (duplicate)
+					duplicate_handle = 1;
+				else {
+					spin_unlock(&temp_queue->queue_lock);
+					return -1;
+				}
+			}
+		}
+
+			if (duplicate_handle) {
+			reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+			reg |= FSL_QDMA_BSQMR_DI;
+			status_addr->addr = 0x0;
+			fsl_status->virt_head++;
+			if (fsl_status->virt_head == fsl_status->cq
+						   + fsl_status->n_cq)
+				fsl_status->virt_head = fsl_status->cq;
+			qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+			spin_unlock(&temp_queue->queue_lock);
+			continue;
+		}
+		list_del(&fsl_comp->list);
+
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+		reg |= FSL_QDMA_BSQMR_DI;
+		status_addr->addr = 0x0;
+		fsl_status->virt_head++;
+		if (fsl_status->virt_head == fsl_status->cq + fsl_status->n_cq)
+			fsl_status->virt_head = fsl_status->cq;
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+		spin_unlock(&temp_queue->queue_lock);
+
+		spin_lock(&fsl_comp->qchan->vchan.lock);
+		vchan_cookie_complete(&fsl_comp->vdesc);
+		fsl_comp->qchan->status = DMA_COMPLETE;
+		spin_unlock(&fsl_comp->qchan->vchan.lock);
+	}
+	return 0;
+}
+
+static irqreturn_t fsl_qdma_error_handler(int irq, void *dev_id)
+{
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	unsigned int intr;
+	void __iomem *status = fsl_qdma->status_base;
+
+	intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
+
+	if (intr)
+		dev_err(fsl_qdma->dma_dev.dev, "DMA transaction error!\n");
+
+	qdma_writel(fsl_qdma, 0xffffffff, status + FSL_QDMA_DEDR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_qdma_queue_handler(int irq, void *dev_id)
+{
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	unsigned int intr, reg;
+	void __iomem *block = fsl_qdma->block_base;
+	void __iomem *ctrl = fsl_qdma->ctrl_base;
+
+	intr = qdma_readl(fsl_qdma, block + FSL_QDMA_BCQIDR(0));
+
+	if ((intr & FSL_QDMA_CQIDR_SQT) != 0)
+		intr = fsl_qdma_queue_transfer_complete(fsl_qdma);
+
+	if (intr != 0) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+		reg |= FSL_QDMA_DMR_DQD;
+		qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQIER(0));
+		dev_err(fsl_qdma->dma_dev.dev, "QDMA: status err!\n");
+	}
+
+	qdma_writel(fsl_qdma, 0xffffffff, block + FSL_QDMA_BCQIDR(0));
+
+	return IRQ_HANDLED;
+}
+
+static int
+fsl_qdma_irq_init(struct platform_device *pdev,
+		  struct fsl_qdma_engine *fsl_qdma)
+{
+	int ret;
+
+	fsl_qdma->error_irq = platform_get_irq_byname(pdev,
+							"qdma-error");
+	if (fsl_qdma->error_irq < 0) {
+		dev_err(&pdev->dev, "Can't get qdma controller irq.\n");
+		return fsl_qdma->error_irq;
+	}
+
+	fsl_qdma->queue_irq = platform_get_irq_byname(pdev, "qdma-queue");
+	if (fsl_qdma->queue_irq < 0) {
+		dev_err(&pdev->dev, "Can't get qdma queue irq.\n");
+		return fsl_qdma->queue_irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, fsl_qdma->error_irq,
+			fsl_qdma_error_handler, 0, "qDMA error", fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register qDMA controller IRQ.\n");
+		return  ret;
+	}
+	ret = devm_request_irq(&pdev->dev, fsl_qdma->queue_irq,
+			fsl_qdma_queue_handler, 0, "qDMA queue", fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register qDMA queue IRQ.\n");
+		return  ret;
+	}
+
+	return 0;
+}
+
+static int fsl_qdma_reg_init(struct fsl_qdma_engine *fsl_qdma)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+	struct fsl_qdma_queue *temp;
+	void __iomem *ctrl = fsl_qdma->ctrl_base;
+	void __iomem *status = fsl_qdma->status_base;
+	void __iomem *block = fsl_qdma->block_base;
+	int i, ret;
+	u32 reg;
+
+	/* Try to halt the qDMA engine first. */
+	ret = fsl_qdma_halt(fsl_qdma);
+	if (ret) {
+		dev_err(fsl_qdma->dma_dev.dev, "DMA halt failed!");
+		return ret;
+	}
+
+	/*
+	 * Clear the command queue interrupt detect register for all queues.
+	 */
+	qdma_writel(fsl_qdma, 0xffffffff, block + FSL_QDMA_BCQIDR(0));
+
+	for (i = 0; i < fsl_qdma->n_queues; i++) {
+		temp = fsl_queue + i;
+		/*
+		 * Initialize Command Queue registers to point to the first
+		 * command descriptor in memory.
+		 * Dequeue Pointer Address Registers
+		 * Enqueue Pointer Address Registers
+		 */
+		qdma_writel(fsl_qdma, temp->bus_addr,
+				block + FSL_QDMA_BCQDPA_SADDR(i));
+		qdma_writel(fsl_qdma, temp->bus_addr,
+				block + FSL_QDMA_BCQEPA_SADDR(i));
+
+		/* Initialize the queue mode. */
+		reg = FSL_QDMA_BCQMR_EN;
+		reg |= FSL_QDMA_BCQMR_CD_THLD(ilog2(temp->n_cq)-4);
+		reg |= FSL_QDMA_BCQMR_CQ_SIZE(ilog2(temp->n_cq)-6);
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BCQMR(i));
+	}
+
+	/*
+	 * Workaround for erratum: ERR010812.
+	 * We must enable XOFF to avoid the enqueue rejection occurs.
+	 * Setting SQCCMR ENTER_WM to 0x20.
+	 */
+	qdma_writel(fsl_qdma, FSL_QDMA_SQCCMR_ENTER_WM,
+			      block + FSL_QDMA_SQCCMR);
+	/*
+	 * Initialize status queue registers to point to the first
+	 * command descriptor in memory.
+	 * Dequeue Pointer Address Registers
+	 * Enqueue Pointer Address Registers
+	 */
+	qdma_writel(fsl_qdma, fsl_qdma->status->bus_addr,
+					block + FSL_QDMA_SQEPAR);
+	qdma_writel(fsl_qdma, fsl_qdma->status->bus_addr,
+					block + FSL_QDMA_SQDPAR);
+	/* Initialize status queue interrupt. */
+	qdma_writel(fsl_qdma, FSL_QDMA_BCQIER_CQTIE,
+			      block + FSL_QDMA_BCQIER(0));
+	qdma_writel(fsl_qdma, FSL_QDMA_BSQICR_ICEN | FSL_QDMA_BSQICR_ICST(5)
+						   | 0x8000,
+			      block + FSL_QDMA_BSQICR);
+	qdma_writel(fsl_qdma, FSL_QDMA_CQIER_MEIE | FSL_QDMA_CQIER_TEIE,
+			      block + FSL_QDMA_CQIER);
+	/* Initialize controller interrupt register. */
+	qdma_writel(fsl_qdma, 0xffffffff, status + FSL_QDMA_DEDR);
+	qdma_writel(fsl_qdma, 0xffffffff, status + FSL_QDMA_DEIER);
+
+	/* Initialize the status queue mode. */
+	reg = FSL_QDMA_BSQMR_EN;
+	reg |= FSL_QDMA_BSQMR_CQ_SIZE(ilog2(fsl_qdma->status->n_cq)-6);
+	qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg &= ~FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *fsl_qdma_prep_dma_sg(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_comp *fsl_comp;
+
+	fsl_comp = fsl_qdma_request_enqueue_desc(fsl_chan,
+						 dst_nents,
+						 src_nents);
+	fsl_qdma_comp_fill_sg(fsl_comp, dst_sg, dst_nents, src_sg, src_nents);
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_comp->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *
+fsl_qdma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst,
+		dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_comp *fsl_comp;
+
+	fsl_comp = fsl_qdma_request_enqueue_desc(fsl_chan, 0, 0);
+	fsl_qdma_comp_fill_memcpy(fsl_comp, dst, src, len);
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_comp->vdesc, flags);
+}
+
+static void fsl_qdma_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	void __iomem *block = fsl_chan->qdma->block_base;
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	struct fsl_qdma_comp *fsl_comp;
+	struct virt_dma_desc *vdesc;
+	u32 reg;
+
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQSR(fsl_queue->id));
+	if (reg & (FSL_QDMA_BCQSR_QF | FSL_QDMA_BCQSR_XOFF))
+		return;
+	vdesc = vchan_next_desc(&fsl_chan->vchan);
+	if (!vdesc)
+		return;
+	list_del(&vdesc->node);
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+
+	memcpy(fsl_queue->virt_head++, fsl_comp->virt_addr, 16);
+	if (fsl_queue->virt_head == fsl_queue->cq + fsl_queue->n_cq)
+		fsl_queue->virt_head = fsl_queue->cq;
+
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_used);
+	barrier();
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	reg |= FSL_QDMA_BCQMR_EI;
+	qdma_writel(fsl_chan->qdma, reg, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	fsl_chan->status = DMA_IN_PROGRESS;
+}
+
+static enum dma_status fsl_qdma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(chan, cookie, txstate);
+}
+
+static void fsl_qdma_free_desc(struct virt_dma_desc *vdesc)
+{
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_queue *fsl_queue;
+	struct fsl_qdma_sg *sg_block;
+	unsigned long flags;
+	unsigned int i;
+
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+	fsl_queue = fsl_comp->qchan->queue;
+
+	if (fsl_comp->sg_block) {
+		for (i = 0; i < fsl_comp->sg_block_src +
+				fsl_comp->sg_block_dst; i++) {
+			sg_block = fsl_comp->sg_block + i;
+			dma_pool_free(fsl_queue->sg_pool,
+				      sg_block->virt_addr,
+				      sg_block->bus_addr);
+		}
+		kfree(fsl_comp->sg_block);
+	}
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_free);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static void fsl_qdma_issue_pending(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	spin_lock(&fsl_chan->vchan.lock);
+	if (vchan_issue_pending(&fsl_chan->vchan))
+		fsl_qdma_enqueue_desc(fsl_chan);
+	spin_unlock(&fsl_chan->vchan.lock);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static int fsl_qdma_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_engine *fsl_qdma;
+	struct fsl_qdma_chan *fsl_chan;
+	struct resource *res;
+	unsigned int len, chans, queues;
+	int ret, i;
+
+	ret = of_property_read_u32(np, "channels", &chans);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get channels.\n");
+		return ret;
+	}
+
+	len = sizeof(*fsl_qdma) + sizeof(*fsl_chan) * chans;
+	fsl_qdma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(np, "queues", &queues);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queues.\n");
+		return ret;
+	}
+
+	fsl_qdma->queue = fsl_qdma_alloc_queue_resources(pdev, queues);
+	if (!fsl_qdma->queue)
+		return -ENOMEM;
+
+	fsl_qdma->status = fsl_qdma_prep_status_queue(pdev);
+	if (!fsl_qdma->status)
+		return -ENOMEM;
+
+	fsl_qdma->n_chans = chans;
+	fsl_qdma->n_queues = queues;
+	mutex_init(&fsl_qdma->fsl_qdma_mutex);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	fsl_qdma->ctrl_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->ctrl_base))
+		return PTR_ERR(fsl_qdma->ctrl_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	fsl_qdma->status_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->status_base))
+		return PTR_ERR(fsl_qdma->status_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	fsl_qdma->block_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->block_base))
+		return PTR_ERR(fsl_qdma->block_base);
+
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	fsl_qdma->big_endian = of_property_read_bool(np, "big-endian");
+	INIT_LIST_HEAD(&fsl_qdma->dma_dev.channels);
+	for (i = 0; i < fsl_qdma->n_chans; i++) {
+		struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[i];
+
+		fsl_chan->qdma = fsl_qdma;
+		fsl_chan->queue = fsl_qdma->queue + i % fsl_qdma->n_queues;
+		fsl_chan->vchan.desc_free = fsl_qdma_free_desc;
+		INIT_LIST_HEAD(&fsl_chan->qcomp);
+		vchan_init(&fsl_chan->vchan, &fsl_qdma->dma_dev);
+	}
+	for (i = 0; i < fsl_qdma->n_queues; i++)
+		fsl_qdma_pre_request_enqueue_desc(fsl_qdma->queue + i);
+
+	dma_cap_set(DMA_MEMCPY, fsl_qdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_SG, fsl_qdma->dma_dev.cap_mask);
+
+	fsl_qdma->dma_dev.dev = &pdev->dev;
+	fsl_qdma->dma_dev.device_alloc_chan_resources
+		= fsl_qdma_alloc_chan_resources;
+	fsl_qdma->dma_dev.device_free_chan_resources
+		= fsl_qdma_free_chan_resources;
+	fsl_qdma->dma_dev.device_tx_status = fsl_qdma_tx_status;
+	fsl_qdma->dma_dev.device_prep_dma_memcpy = fsl_qdma_prep_memcpy;
+	fsl_qdma->dma_dev.device_prep_dma_sg = fsl_qdma_prep_dma_sg;
+	fsl_qdma->dma_dev.device_issue_pending = fsl_qdma_issue_pending;
+
+	dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+
+	platform_set_drvdata(pdev, fsl_qdma);
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register Freescale qDMA engine.\n");
+		return ret;
+	}
+
+	ret = fsl_qdma_reg_init(fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		return ret;
+	}
+
+
+	return 0;
+}
+
+static int fsl_qdma_remove(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
+	struct fsl_qdma_queue *queue_temp;
+	struct fsl_qdma_queue *status = fsl_qdma->status;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+	int i;
+
+	of_dma_controller_free(np);
+	dma_async_device_unregister(&fsl_qdma->dma_dev);
+
+	/* Free descriptor areas */
+	for (i = 0; i < fsl_qdma->n_queues; i++) {
+		queue_temp = fsl_qdma->queue + i;
+		list_for_each_entry_safe(comp_temp, _comp_temp,
+					&queue_temp->comp_used,	list) {
+			dma_pool_free(queue_temp->comp_pool,
+					comp_temp->virt_addr,
+					comp_temp->bus_addr);
+			list_del(&comp_temp->list);
+			kfree(comp_temp);
+		}
+		list_for_each_entry_safe(comp_temp, _comp_temp,
+					&queue_temp->comp_free, list) {
+			dma_pool_free(queue_temp->comp_pool,
+					comp_temp->virt_addr,
+					comp_temp->bus_addr);
+			list_del(&comp_temp->list);
+			kfree(comp_temp);
+		}
+		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_ccdf) *
+					queue_temp->n_cq, queue_temp->cq,
+					queue_temp->bus_addr);
+		dma_pool_destroy(queue_temp->comp_pool);
+	}
+
+	dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_ccdf) *
+				status->n_cq, status->cq, status->bus_addr);
+	return 0;
+}
+
+static const struct of_device_id fsl_qdma_dt_ids[] = {
+	{ .compatible = "fsl,ls1021a-qdma", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_qdma_dt_ids);
+
+static struct platform_driver fsl_qdma_driver = {
+	.driver		= {
+		.name	= "fsl-qdma",
+		.owner  = THIS_MODULE,
+		.of_match_table = fsl_qdma_dt_ids,
+	},
+	.probe          = fsl_qdma_probe,
+	.remove		= fsl_qdma_remove,
+};
+
+static int __init fsl_qdma_init(void)
+{
+	return platform_driver_register(&fsl_qdma_driver);
+}
+subsys_initcall(fsl_qdma_init);
+
+static void __exit fsl_qdma_exit(void)
+{
+	platform_driver_unregister(&fsl_qdma_driver);
+}
+module_exit(fsl_qdma_exit);
+
+MODULE_ALIAS("platform:fsl-qdma");
+MODULE_DESCRIPTION("Freescale qDMA engine driver");
+MODULE_LICENSE("GPL v2");