[dpdk-dev] [PATCH RFC] raw: add dpaa qdma driver

[Gagandeep Singh <g.singh@nxp.com>]

This patch adds support for dpaa qdma based driver.

Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
Signed-off-by: Peng Ma <peng.ma@nxp.com>
---
 doc/guides/rawdevs/dpaa_qdma.rst                   |   98 ++
 doc/guides/rawdevs/index.rst                       |    1 +
 drivers/bus/dpaa/dpaa_bus.c                        |   22 +
 drivers/bus/dpaa/rte_dpaa_bus.h                    |    5 +
 drivers/common/dpaax/dpaa_list.h                   |    6 +-
 drivers/raw/dpaa_qdma/dpaa_qdma.c                  | 1074 ++++++++++++++++++++
 drivers/raw/dpaa_qdma/dpaa_qdma.h                  |  275 +++++
 drivers/raw/dpaa_qdma/dpaa_qdma_logs.h             |   46 +
 drivers/raw/dpaa_qdma/meson.build                  |   15 +
 .../raw/dpaa_qdma/rte_rawdev_dpaa_qdma_version.map |    3 +
 drivers/raw/meson.build                            |    2 +-
 11 files changed, 1543 insertions(+), 4 deletions(-)
 create mode 100644 doc/guides/rawdevs/dpaa_qdma.rst
 create mode 100644 drivers/raw/dpaa_qdma/dpaa_qdma.c
 create mode 100644 drivers/raw/dpaa_qdma/dpaa_qdma.h
 create mode 100644 drivers/raw/dpaa_qdma/dpaa_qdma_logs.h
 create mode 100644 drivers/raw/dpaa_qdma/meson.build
 create mode 100644 drivers/raw/dpaa_qdma/rte_rawdev_dpaa_qdma_version.map

diff --git a/doc/guides/rawdevs/dpaa_qdma.rst b/doc/guides/rawdevs/dpaa_qdma.rst
new file mode 100644
index 0000000..49457f6
--- /dev/null
+++ b/doc/guides/rawdevs/dpaa_qdma.rst
@@ -0,0 +1,98 @@
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright 2018 NXP
+
+NXP DPAA QDMA Driver
+=====================
+
+The DPAA QDMA is an implementation of the rawdev API, that provide means
+to initiate a DMA transaction from CPU. The initiated DMA is performed
+without CPU being involved in the actual DMA transaction. This is achieved
+via using the DPDMAI device exposed by MC.
+
+More information can be found at `NXP Official Website
+<http://www.nxp.com/products/microcontrollers-and-processors/arm-processors/qoriq-arm-processors:QORIQ-ARM>`_.
+
+Features
+--------
+
+The DPAA QDMA implements following features in the rawdev API;
+
+- Supports issuing DMA of data within memory without hogging CPU while
+  performing DMA operation.
+- Supports configuring to optionally get status of the DMA translation on
+  per DMA operation basis.
+
+Supported DPAA SoCs
+--------------------
+
+- LS1043A
+- LS1046A
+
+Prerequisites
+-------------
+
+See :doc:`../platform/dpaa` for setup information
+
+Currently supported by DPDK:
+
+- NXP SDK **19.09+**.
+- Supported architectures:  **arm64 LE**.
+
+- Follow the DPDK :ref:`Getting Started Guide for Linux <linux_gsg>` to setup the basic DPDK environment.
+
+.. note::
+
+   Some part of fslmc bus code (mc flib - object library) routines are
+   dual licensed (BSD & GPLv2).
+
+Pre-Installation Configuration
+------------------------------
+
+Config File Options
+~~~~~~~~~~~~~~~~~~~
+
+The following options can be modified in the ``config`` file.
+
+- ``CONFIG_RTE_LIBRTE_PMD_DPAA_QDMA_RAWDEV`` (default ``y``)
+
+  Toggle compilation of the ``lrte_pmd_dpaa_qdma`` driver.
+
+Enabling logs
+-------------
+
+For enabling logs, use the following EAL parameter:
+
+.. code-block:: console
+
+   ./your_qdma_application <EAL args> --log-level=pmd.raw.dpaa.qdma,<level>
+
+Using ``pmd.raw.dpaa.qdma`` as log matching criteria, all Event PMD logs can be
+enabled which are lower than logging ``level``.
+
+Driver Compilation
+~~~~~~~~~~~~~~~~~~
+
+To compile the DPAA QDMA PMD for Linux arm64 gcc target, run the
+following ``make`` command:
+
+.. code-block:: console
+
+   cd <DPDK-source-directory>
+   make config T=arm64-dpaa-linux-gcc install
+
+Initialization
+--------------
+
+The DPAA QDMA is exposed as a vdev device which consists of dpdmai devices.
+On EAL initialization, dpdmai devices will be probed and populated into the
+rawdevices. The rawdev ID of the device can be obtained using
+
+* Invoking ``rte_rawdev_get_dev_id("dpdmai.x")`` from the application
+  where x is the object ID of the DPDMAI object created by MC. Use can
+  use this index for further rawdev function calls.
+
+Platform Requirement
+~~~~~~~~~~~~~~~~~~~~
+
+DPAA drivers for DPDK can only work on NXP SoCs as listed in the
+``Supported DPAA SoCs``.
diff --git a/doc/guides/rawdevs/index.rst b/doc/guides/rawdevs/index.rst
index f64ec44..8450006 100644
--- a/doc/guides/rawdevs/index.rst
+++ b/doc/guides/rawdevs/index.rst
@@ -11,6 +11,7 @@ application through rawdev API.
     :maxdepth: 2
     :numbered:
 
+    dpaa_qdma
     dpaa2_cmdif
     dpaa2_qdma
     ifpga
diff --git a/drivers/bus/dpaa/dpaa_bus.c b/drivers/bus/dpaa/dpaa_bus.c
index 32e872d..8697e9e 100644
--- a/drivers/bus/dpaa/dpaa_bus.c
+++ b/drivers/bus/dpaa/dpaa_bus.c
@@ -229,6 +229,28 @@ dpaa_create_device_list(void)
 
 	rte_dpaa_bus.device_count += i;
 
+	/* Creating QDMA Device */
+	for (i = 0; i < RTE_DPAA_QDMA_DEVICES; i++) {
+		dev = calloc(1, sizeof(struct rte_dpaa_device));
+		if (!dev) {
+			DPAA_BUS_LOG(ERR, "Failed to allocate QDMA device");
+			ret = -1;
+			goto cleanup;
+		}
+
+		dev->device_type = FSL_DPAA_QDMA;
+		dev->id.dev_id = rte_dpaa_bus.device_count + i;
+
+		memset(dev->name, 0, RTE_ETH_NAME_MAX_LEN);
+		sprintf(dev->name, "dpaa_qdma-%d", i+1);
+		DPAA_BUS_LOG(INFO, "%s qdma device added", dev->name);
+		dev->device.name = dev->name;
+		dev->device.devargs = dpaa_devargs_lookup(dev);
+
+		dpaa_add_to_device_list(dev);
+	}
+	rte_dpaa_bus.device_count += i;
+
 	return 0;
 
 cleanup:
diff --git a/drivers/bus/dpaa/rte_dpaa_bus.h b/drivers/bus/dpaa/rte_dpaa_bus.h
index fdaa63a..959cfdb 100644
--- a/drivers/bus/dpaa/rte_dpaa_bus.h
+++ b/drivers/bus/dpaa/rte_dpaa_bus.h
@@ -33,6 +33,9 @@
 /** Device driver supports link state interrupt */
 #define RTE_DPAA_DRV_INTR_LSC  0x0008
 
+/** Number of supported QDMA devices */
+#define RTE_DPAA_QDMA_DEVICES  1
+
 #define RTE_DEV_TO_DPAA_CONST(ptr) \
 	container_of(ptr, const struct rte_dpaa_device, device)
 
@@ -48,6 +51,7 @@ TAILQ_HEAD(rte_dpaa_driver_list, rte_dpaa_driver);
 enum rte_dpaa_type {
 	FSL_DPAA_ETH = 1,
 	FSL_DPAA_CRYPTO,
+	FSL_DPAA_QDMA,
 };
 
 struct rte_dpaa_bus {
@@ -70,6 +74,7 @@ struct rte_dpaa_device {
 	union {
 		struct rte_eth_dev *eth_dev;
 		struct rte_cryptodev *crypto_dev;
+		struct rte_rawdev *rawdev;
 	};
 	struct rte_dpaa_driver *driver;
 	struct dpaa_device_id id;
diff --git a/drivers/common/dpaax/dpaa_list.h b/drivers/common/dpaax/dpaa_list.h
index e945759..58c563e 100644
--- a/drivers/common/dpaax/dpaa_list.h
+++ b/drivers/common/dpaax/dpaa_list.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- *
- *   Copyright 2017 NXP
- *
+ * Copyright 2017,2020 NXP
  */
 
 #ifndef __DPAA_LIST_H
@@ -35,6 +33,8 @@ do { \
 	const struct list_head *__p298 = (p); \
 	((__p298->next == __p298) && (__p298->prev == __p298)); \
 })
+#define list_first_entry(ptr, type, member) \
+	list_entry((ptr)->next, type, member)
 #define list_add(p, l) \
 do { \
 	struct list_head *__p298 = (p); \
diff --git a/drivers/raw/dpaa_qdma/dpaa_qdma.c b/drivers/raw/dpaa_qdma/dpaa_qdma.c
new file mode 100644
index 0000000..6897dc4
--- /dev/null
+++ b/drivers/raw/dpaa_qdma/dpaa_qdma.c
@@ -0,0 +1,1074 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 NXP
+ * Driver for NXP Layerscape Queue direct memory access controller (qDMA)
+ */
+
+#include <sys/time.h>
+#include <semaphore.h>
+
+#include <rte_mbuf.h>
+#include <rte_rawdev.h>
+#include <rte_dpaa_bus.h>
+#include <rte_rawdev_pmd.h>
+#include <compat.h>
+#include <rte_hexdump.h>
+
+#include <rte_pmd_dpaa2_qdma.h>
+#include "dpaa_qdma.h"
+#include "dpaa_qdma_logs.h"
+
+/* Dynamic log type identifier */
+int dpaa_qdma_logtype;
+
+static inline u64
+qdma_ccdf_addr_get64(const struct fsl_qdma_format *ccdf)
+{
+	return rte_le_to_cpu_64(ccdf->data) & 0xffffffffffLLU;
+}
+
+static inline void
+qdma_desc_addr_set64(struct fsl_qdma_format *ccdf, u64 addr)
+{
+	ccdf->addr_hi = upper_32_bits(addr);
+	ccdf->addr_lo = rte_cpu_to_le_32(lower_32_bits(addr));
+}
+
+static inline u64
+qdma_ccdf_get_queue(const struct fsl_qdma_format *ccdf)
+{
+	return ccdf->cfg8b_w1 & 0xff;
+}
+
+static inline int
+qdma_ccdf_get_offset(const struct fsl_qdma_format *ccdf)
+{
+	return (rte_le_to_cpu_32(ccdf->cfg) & QDMA_CCDF_MASK) >> QDMA_CCDF_OFFSET;
+}
+
+static inline void
+qdma_ccdf_set_format(struct fsl_qdma_format *ccdf, int offset)
+{
+	ccdf->cfg = rte_cpu_to_le_32(QDMA_CCDF_FOTMAT | offset);
+}
+
+static inline int
+qdma_ccdf_get_status(const struct fsl_qdma_format *ccdf)
+{
+	return (rte_le_to_cpu_32(ccdf->status) & QDMA_CCDF_MASK) >> QDMA_CCDF_STATUS;
+}
+
+static inline void
+qdma_ccdf_set_ser(struct fsl_qdma_format *ccdf, int status)
+{
+	ccdf->status = rte_cpu_to_le_32(QDMA_CCDF_SER | status);
+}
+
+static inline void qdma_csgf_set_len(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = rte_cpu_to_le_32(len & QDMA_SG_LEN_MASK);
+}
+
+static inline void qdma_csgf_set_f(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = rte_cpu_to_le_32(QDMA_SG_FIN | (len & QDMA_SG_LEN_MASK));
+}
+
+static inline void qdma_csgf_set_e(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = rte_cpu_to_le_32(QDMA_SG_EXT | (len & QDMA_SG_LEN_MASK));
+}
+
+static inline int ilog2(int x)
+{
+	int log = 0;
+
+	x >>= 1;
+
+	while (x) {
+		log++;
+		x >>= 1;
+	}
+	return log;
+}
+
+static u32 qdma_readl(struct fsl_qdma_engine *qdma, void *addr)
+{
+	return QDMA_IN(qdma, addr);
+}
+
+static void qdma_writel(struct fsl_qdma_engine *qdma, u32 val,
+			void *addr)
+{
+	QDMA_OUT(qdma, addr, val);
+}
+
+static void *dma_pool_alloc(int size, int aligned, dma_addr_t *phy_addr)
+{
+#ifdef QDMA_MEMZONE
+	void *virt_addr;
+
+	virt_addr = rte_malloc("dma pool alloc", size, aligned);
+	if (!virt_addr)
+		return NULL;
+
+	*phy_addr = rte_mem_virt2iova(virt_addr);
+
+	return virt_addr;
+#else
+	const struct rte_memzone *mz;
+	char mz_name[RTE_MEMZONE_NAMESIZE];
+	uint32_t core_id = rte_lcore_id();
+	unsigned int socket_id;
+	int count = 0;
+
+	bzero(mz_name, sizeof(*mz_name));
+	snprintf(mz_name, sizeof(mz_name) - 1, "%lx-times-%d",
+		 (unsigned long)rte_get_timer_cycles(), count);
+	if (core_id == (unsigned int)LCORE_ID_ANY)
+		core_id = 0;
+	socket_id = rte_lcore_to_socket_id(core_id);
+	mz = rte_memzone_reserve_aligned(mz_name, size, socket_id, 0, aligned);
+	if (!mz) {
+		*phy_addr = 0;
+		return NULL;
+	}
+	*phy_addr = mz->iova;
+
+	qdma_mz_mapping[qdma_mz_count++] = mz;
+
+	return mz->addr;
+
+#endif
+}
+
+#ifdef QDMA_MEMZONE
+static void dma_pool_free(void *addr)
+{
+	rte_free(addr);
+# else
+static void dma_pool_free(dma_addr_t *addr)
+{
+	uint16_t i;
+
+	for (i = 0 ; i < qdma_mz_count; i++) {
+		if (addr == (dma_addr_t *)qdma_mz_mapping[i]->iova) {
+			rte_memzone_free(qdma_mz_mapping[i]);
+			return;
+		}
+	}
+#endif
+}
+
+static void fsl_qdma_free_chan_resources(struct fsl_qdma_chan *fsl_chan)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+	int id;
+
+	if (--fsl_queue->count)
+		goto finally;
+
+	id = (fsl_qdma->block_base - fsl_queue->block_base) /
+	      fsl_qdma->block_offset;
+
+	while (rte_atomic32_read(&wait_task[id]) == 1)
+		rte_delay_us(QDMA_DELAY);
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_used,	list) {
+		list_del(&comp_temp->list);
+#ifdef QDMA_MEMZONE
+		dma_pool_free(comp_temp->virt_addr);
+		dma_pool_free(comp_temp->desc_virt_addr);
+#else
+		dma_pool_free((dma_addr_t *)comp_temp->bus_addr);
+		dma_pool_free((dma_addr_t *)comp_temp->desc_bus_addr);
+#endif
+		rte_free(comp_temp);
+	}
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_free, list) {
+		list_del(&comp_temp->list);
+#ifdef QDMA_MEMZONE
+		dma_pool_free(comp_temp->virt_addr);
+		dma_pool_free(comp_temp->desc_virt_addr);
+#else
+		dma_pool_free((dma_addr_t *)comp_temp->bus_addr);
+		dma_pool_free((dma_addr_t *)comp_temp->desc_bus_addr);
+#endif
+		rte_free(comp_temp);
+	}
+
+finally:
+	fsl_qdma->desc_allocated--;
+}
+
+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_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
+	struct fsl_qdma_sdf *sdf;
+	struct fsl_qdma_ddf *ddf;
+
+	ccdf = (struct fsl_qdma_format *)fsl_comp->virt_addr;
+	csgf_desc = (struct fsl_qdma_format *)fsl_comp->virt_addr + 1;
+	csgf_src = (struct fsl_qdma_format *)fsl_comp->virt_addr + 2;
+	csgf_dest = (struct fsl_qdma_format *)fsl_comp->virt_addr + 3;
+	sdf = (struct fsl_qdma_sdf *)fsl_comp->desc_virt_addr;
+	ddf = (struct fsl_qdma_ddf *)fsl_comp->desc_virt_addr + 1;
+
+	memset(fsl_comp->virt_addr, 0, FSL_QDMA_COMMAND_BUFFER_SIZE);
+	memset(fsl_comp->desc_virt_addr, 0, FSL_QDMA_DESCRIPTOR_BUFFER_SIZE);
+	/* Head Command Descriptor(Frame Descriptor) */
+	qdma_desc_addr_set64(ccdf, fsl_comp->bus_addr + 16);
+	qdma_ccdf_set_format(ccdf, qdma_ccdf_get_offset(ccdf));
+	qdma_ccdf_set_ser(ccdf, qdma_ccdf_get_status(ccdf));
+	/* Status notification is enqueued to status queue. */
+	/* Compound Command Descriptor(Frame List Table) */
+	qdma_desc_addr_set64(csgf_desc, fsl_comp->desc_bus_addr);
+	/* It must be 32 as Compound S/G Descriptor */
+	qdma_csgf_set_len(csgf_desc, 32);
+	qdma_desc_addr_set64(csgf_src, src);
+	qdma_csgf_set_len(csgf_src, len);
+	qdma_desc_addr_set64(csgf_dest, dst);
+	qdma_csgf_set_len(csgf_dest, len);
+	/* This entry is the last entry. */
+	qdma_csgf_set_f(csgf_dest, len);
+	/* Descriptor Buffer */
+	sdf->cmd = rte_cpu_to_le_32(FSL_QDMA_CMD_RWTTYPE <<
+			       FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->cmd = rte_cpu_to_le_32(FSL_QDMA_CMD_RWTTYPE <<
+			       FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->cmd |= rte_cpu_to_le_32(FSL_QDMA_CMD_LWC <<
+				FSL_QDMA_CMD_LWC_OFFSET);
+}
+
+/*
+ * Pre-request command descriptor and compound S/G for enqueue.
+ */
+static int fsl_qdma_pre_request_enqueue_comp_desc(struct fsl_qdma_queue *queue,
+						  int size, int aligned)
+{
+	struct fsl_qdma_comp *comp_temp;
+	int i;
+
+	for (i = 0; i < (int)(queue->n_cq + COMMAND_QUEUE_OVERFLLOW); i++) {
+		comp_temp = rte_zmalloc("qdma: comp temp",
+					sizeof(*comp_temp), 0);
+		if (!comp_temp)
+			return -ENOMEM;
+
+		comp_temp->virt_addr =
+		dma_pool_alloc(size, aligned, &comp_temp->bus_addr);
+		if (!comp_temp->virt_addr) {
+			rte_free(comp_temp);
+			return -ENOMEM;
+		}
+
+		list_add_tail(&comp_temp->list, &queue->comp_free);
+	}
+
+	return 0;
+}
+
+/*
+ * Pre-request source and destination descriptor for enqueue.
+ */
+static int fsl_qdma_pre_request_enqueue_sd_desc(struct fsl_qdma_queue *queue,
+						int size, int aligned)
+{
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &queue->comp_free, list) {
+		comp_temp->desc_virt_addr =
+		dma_pool_alloc(size, aligned, &comp_temp->desc_bus_addr);
+		if (!comp_temp->desc_virt_addr)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/*
+ * Request a command descriptor for enqueue.
+ */
+static struct fsl_qdma_comp *
+fsl_qdma_request_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	struct fsl_qdma_queue *queue = fsl_chan->queue;
+	struct fsl_qdma_comp *comp_temp;
+	int timeout = COMP_TIMEOUT;
+
+	while (timeout) {
+		if (!list_empty(&queue->comp_free)) {
+			comp_temp = list_first_entry(&queue->comp_free,
+						     struct fsl_qdma_comp,
+						     list);
+			list_del(&comp_temp->list);
+			return comp_temp;
+		}
+		timeout--;
+	}
+
+	return NULL;
+}
+
+static struct fsl_qdma_queue
+*fsl_qdma_alloc_queue_resources(struct fsl_qdma_engine *fsl_qdma)
+{
+	struct fsl_qdma_queue *queue_head, *queue_temp;
+	int len, i, j;
+	int queue_num;
+	int blocks;
+	unsigned int queue_size[FSL_QDMA_QUEUE_MAX];
+
+	queue_num = fsl_qdma->n_queues;
+	blocks = fsl_qdma->num_blocks;
+
+	len = sizeof(*queue_head) * queue_num * blocks;
+	queue_head = rte_zmalloc("qdma: queue head", len, 0);
+	if (!queue_head)
+		return NULL;
+
+	for (i = 0; i < FSL_QDMA_QUEUE_MAX; i++)
+		queue_size[i] = QDMA_QUEUE_SIZE;
+
+	for (j = 0; j < blocks; j++) {
+		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) {
+				DPAA_QDMA_ERR("Get wrong queue-sizes.\n");
+				return NULL;
+			}
+			queue_temp = queue_head + i + (j * queue_num);
+
+			queue_temp->cq =
+			dma_pool_alloc(sizeof(struct fsl_qdma_format) *
+				       queue_size[i],
+				       sizeof(struct fsl_qdma_format) *
+				       queue_size[i], &queue_temp->bus_addr);
+
+			memset(queue_temp->cq, 0x0, queue_size[i] *
+			       sizeof(struct fsl_qdma_format));
+
+			if (!queue_temp->cq)
+				return NULL;
+
+			queue_temp->block_base = fsl_qdma->block_base +
+				FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+			queue_temp->n_cq = queue_size[i];
+			queue_temp->id = i;
+			queue_temp->count = 0;
+			queue_temp->virt_head = queue_temp->cq;
+
+		}
+	}
+	return queue_head;
+}
+
+static struct fsl_qdma_queue *fsl_qdma_prep_status_queue(void)
+{
+	struct fsl_qdma_queue *status_head;
+	unsigned int status_size;
+
+	status_size = QDMA_STATUS_SIZE;
+	if (status_size > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX ||
+	    status_size < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+		DPAA_QDMA_ERR("Get wrong status_size.\n");
+		return NULL;
+	}
+
+	status_head = rte_zmalloc("qdma: status head", sizeof(*status_head), 0);
+	if (!status_head)
+		return NULL;
+
+	/*
+	 * Buffer for queue command
+	 */
+	status_head->cq = dma_pool_alloc(sizeof(struct fsl_qdma_format) *
+					 status_size,
+					 sizeof(struct fsl_qdma_format) *
+					 status_size,
+					 &status_head->bus_addr);
+
+	memset(status_head->cq, 0x0, status_size *
+	       sizeof(struct fsl_qdma_format));
+	if (!status_head->cq)
+		return NULL;
+
+	status_head->n_cq = status_size;
+	status_head->virt_head = status_head->cq;
+
+	return status_head;
+}
+
+static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
+{
+	void *ctrl = fsl_qdma->ctrl_base;
+	void *block;
+	int i, count = RETRIES;
+	unsigned int j;
+	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 (j = 0; j < fsl_qdma->num_blocks; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < FSL_QDMA_QUEUE_NUM_MAX; i++)
+			qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQMR(i));
+	}
+	while (true) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DSR);
+		if (!(reg & FSL_QDMA_DSR_DB))
+			break;
+		if (count-- < 0)
+			return -EBUSY;
+		rte_delay_us(100);
+	}
+
+	for (j = 0; j < fsl_qdma->num_blocks; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+
+		/* 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,
+				 void *block, int id,
+				 struct rte_qdma_enqdeq *e_context)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+	struct fsl_qdma_queue *fsl_status = fsl_qdma->status[id];
+	struct fsl_qdma_queue *temp_queue;
+	struct fsl_qdma_format *status_addr;
+	struct fsl_qdma_comp *fsl_comp = NULL;
+	u32 reg, i;
+	int count = 0;
+	bool duplicate, duplicate_handle;
+
+	while (true) {
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQSR);
+		if (reg & FSL_QDMA_BSQSR_QE)
+			return count;
+
+		duplicate = 0;
+		duplicate_handle = 0;
+		status_addr = fsl_status->virt_head;
+
+		if (qdma_ccdf_get_queue(status_addr) ==
+			pre_queue[id] &&
+			qdma_ccdf_addr_get64(status_addr) ==
+			pre_addr[id]) {
+			duplicate = 1;
+		}
+		i = qdma_ccdf_get_queue(status_addr) +
+			id * fsl_qdma->n_queues;
+		pre_addr[id] = qdma_ccdf_addr_get64(status_addr);
+		pre_queue[id] = qdma_ccdf_get_queue(status_addr);
+		temp_queue = fsl_queue + i;
+
+		if (list_empty(&temp_queue->comp_used)) {
+			if (duplicate)
+				duplicate_handle = 1;
+			else
+				continue;
+		} else {
+			fsl_comp = list_first_entry(&temp_queue->comp_used,
+						    struct fsl_qdma_comp,
+						    list);
+			if (fsl_comp->bus_addr + 16 !=
+				pre_addr[id]) {
+				if (duplicate)
+					duplicate_handle = 1;
+				else
+					return -1;
+			}
+		}
+
+		if (duplicate_handle) {
+			reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+			reg |= FSL_QDMA_BSQMR_DI;
+			qdma_desc_addr_set64(status_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);
+			continue;
+		}
+		list_del(&fsl_comp->list);
+
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+		reg |= FSL_QDMA_BSQMR_DI;
+		qdma_desc_addr_set64(status_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);
+		list_add_tail(&fsl_comp->list, &temp_queue->comp_free);
+		e_context->job[count] = (struct rte_qdma_job *)fsl_comp->params;
+		count++;
+
+		fsl_comp->qchan->status = DMA_COMPLETE;
+	}
+	return count;
+}
+
+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 *ctrl = fsl_qdma->ctrl_base;
+	void *status = fsl_qdma->status_base;
+	void *block;
+	u32 i, j;
+	u32 reg;
+	int ret, val;
+
+	/* Try to halt the qDMA engine first. */
+	ret = fsl_qdma_halt(fsl_qdma);
+	if (ret) {
+		DPAA_QDMA_ERR("DMA halt failed!");
+		return ret;
+	}
+
+	for (j = 0; j < fsl_qdma->num_blocks; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < fsl_qdma->n_queues; i++) {
+			temp = fsl_queue + i + (j * fsl_qdma->n_queues);
+			/*
+			 * 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, lower_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQDPA_SADDR(i));
+			qdma_writel(fsl_qdma, upper_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQEDPA_SADDR(i));
+			qdma_writel(fsl_qdma, lower_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQEPA_SADDR(i));
+			qdma_writel(fsl_qdma, upper_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQEEPA_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,
+			    upper_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEEPAR);
+		qdma_writel(fsl_qdma,
+			    lower_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEPAR);
+		qdma_writel(fsl_qdma,
+			    upper_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEDPAR);
+		qdma_writel(fsl_qdma,
+			    lower_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQDPAR);
+		/* Desiable status queue interrupt. */
+
+		qdma_writel(fsl_qdma, 0x0, block + FSL_QDMA_BCQIER(0));
+		qdma_writel(fsl_qdma, 0x0, block + FSL_QDMA_BSQICR);
+		qdma_writel(fsl_qdma, 0x0, block + FSL_QDMA_CQIER);
+
+		/* Initialize the status queue mode. */
+		reg = FSL_QDMA_BSQMR_EN;
+		val = ilog2(fsl_qdma->status[j]->n_cq) - 6;
+		reg |= FSL_QDMA_BSQMR_CQ_SIZE(val);
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+	}
+
+	/* Initialize controller interrupt register. */
+	qdma_writel(fsl_qdma, 0xffffffff, status + FSL_QDMA_DEDR);
+	qdma_writel(fsl_qdma, 0xffffffff, status + FSL_QDMA_DEIER);
+
+	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 void *
+fsl_qdma_prep_memcpy(void *fsl_chan, dma_addr_t dst,
+			   dma_addr_t src, size_t len,
+			   void *call_back,
+			   void *param)
+{
+	struct fsl_qdma_comp *fsl_comp;
+
+	fsl_comp =
+	fsl_qdma_request_enqueue_desc((struct fsl_qdma_chan *)fsl_chan);
+	if (!fsl_comp)
+		return NULL;
+
+	fsl_comp->qchan = fsl_chan;
+	fsl_comp->call_back_func = call_back;
+	fsl_comp->params = param;
+
+	fsl_qdma_comp_fill_memcpy(fsl_comp, dst, src, len);
+
+	((struct fsl_qdma_chan *)fsl_chan)->status = DMA_IN_PREPAR;
+	return (void *)fsl_comp;
+}
+
+static int fsl_qdma_enqueue_desc(struct fsl_qdma_chan *fsl_chan,
+				  struct fsl_qdma_comp *fsl_comp)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	void *block = fsl_queue->block_base;
+	u32 reg;
+
+	if (!fsl_comp)
+		return -1;
+
+	reg = qdma_readl(fsl_chan->qdma, block +
+			 FSL_QDMA_BCQSR(fsl_queue->id));
+	if (reg & (FSL_QDMA_BCQSR_QF | FSL_QDMA_BCQSR_XOFF))
+		return -1;
+
+	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);
+
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BSQSR);
+	if (reg & FSL_QDMA_BSQSR_QF)
+		return -1;
+
+	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;
+	return 0;
+}
+
+static int fsl_qdma_issue_pending(void *fsl_chan_org, void *fsl_comp)
+{
+	struct fsl_qdma_chan *fsl_chan = fsl_chan_org;
+
+	return fsl_qdma_enqueue_desc(fsl_chan,
+				     (struct fsl_qdma_comp *)fsl_comp);
+}
+
+static int fsl_qdma_alloc_chan_resources(struct fsl_qdma_chan *fsl_chan)
+{
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	int ret;
+
+	if (fsl_queue->count++)
+		goto finally;
+
+	INIT_LIST_HEAD(&fsl_queue->comp_free);
+	INIT_LIST_HEAD(&fsl_queue->comp_used);
+
+	ret = fsl_qdma_pre_request_enqueue_comp_desc(fsl_queue,
+				FSL_QDMA_COMMAND_BUFFER_SIZE, 64);
+	if (ret) {
+		DPAA_QDMA_ERR(
+			"failed to alloc dma buffer for comp descriptor\n");
+		goto exit;
+	}
+
+	ret = fsl_qdma_pre_request_enqueue_sd_desc(fsl_queue,
+					FSL_QDMA_DESCRIPTOR_BUFFER_SIZE, 32);
+	if (ret) {
+		DPAA_QDMA_ERR(
+			"failed to alloc dma buffer for sd descriptor\n");
+		goto exit;
+	}
+
+finally:
+	return fsl_qdma->desc_allocated++;
+
+exit:
+	return -ENOMEM;
+}
+
+static int
+dpaa_get_channel(struct fsl_qdma_engine *fsl_qdma, uint32_t core)
+{
+	u32 i, start, end;
+
+	start = core * QDMA_QUEUES;
+
+	/* TODO: Currently, supporting 1 queue per core. In future,
+	 * if there is more queues requirement then we may need extra
+	 * layer of virtual queues on dequeue side as we have only one
+	 * status queue per block/core and then we can change below
+	 * statement as:
+	 * end = start + QDMA_QUEUES;
+	 */
+	end = start + 1;
+	for (i = start; i < end; i++) {
+		struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[i];
+
+		if (fsl_chan->free) {
+			fsl_chan->free = false;
+			fsl_qdma_alloc_chan_resources(fsl_chan);
+			return i;
+		}
+	}
+
+	return -1;
+}
+
+static void
+dma_release(void *fsl_chan)
+{
+	((struct fsl_qdma_chan *)fsl_chan)->free = true;
+	fsl_qdma_free_chan_resources((struct fsl_qdma_chan *)fsl_chan);
+}
+
+
+static int
+dpaa_qdma_configure(__rte_unused const struct rte_rawdev *rawdev,
+			__rte_unused  rte_rawdev_obj_t config)
+{
+	return 0;
+}
+
+static int
+dpaa_qdma_start(__rte_unused struct rte_rawdev *rawdev)
+{
+	return 0;
+}
+
+static int
+dpaa_qdma_reset(__rte_unused struct rte_rawdev *rawdev)
+{
+	return 0;
+}
+
+static int
+dpaa_qdma_close(__rte_unused struct rte_rawdev *rawdev)
+{
+	return 0;
+}
+
+
+static int
+dpaa_qdma_queue_setup(struct rte_rawdev *rawdev,
+		      __rte_unused uint16_t queue_id,
+		      rte_rawdev_obj_t queue_conf)
+{
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	struct rte_qdma_queue_config *q_config =
+		(struct rte_qdma_queue_config *)queue_conf;
+
+	return dpaa_get_channel(fsl_qdma, q_config->lcore_id);
+}
+
+static int
+dpaa_qdma_queue_release(struct rte_rawdev *rawdev,
+			uint16_t vq_id)
+{
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[vq_id];
+
+	dma_release(fsl_chan);
+	return 0;
+}
+
+static int
+dpaa_qdma_enqueue(__rte_unused struct rte_rawdev *rawdev,
+		  __rte_unused struct rte_rawdev_buf **buffers,
+		  unsigned int nb_jobs,
+		  rte_rawdev_obj_t context)
+{
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	struct rte_qdma_enqdeq *e_context = (struct rte_qdma_enqdeq *)context;
+	struct rte_qdma_job **job = e_context->job;
+	struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[e_context->vq_id];
+	unsigned int i = 0, ret;
+
+	for (i = 0; i < nb_jobs; i++) {
+		void *fsl_comp = NULL;
+
+		fsl_comp = fsl_qdma_prep_memcpy(fsl_chan,
+				(dma_addr_t)job[i]->dest,
+				(dma_addr_t)job[i]->src,
+				job[i]->len, NULL, job[i]);
+		if (!fsl_comp) {
+			DPAA_QDMA_DP_DEBUG("fsl_comp is NULL\n");
+			return i;
+		}
+		ret = fsl_qdma_issue_pending(fsl_chan, fsl_comp);
+		if (ret)
+			return i;
+	}
+
+	return i;
+}
+
+static int
+dpaa_qdma_dequeue(struct rte_rawdev *rawdev,
+		   __rte_unused struct rte_rawdev_buf **buffers,
+		   __rte_unused unsigned int nb_jobs,
+		   rte_rawdev_obj_t cntxt)
+{
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	struct rte_qdma_enqdeq *e_context = (struct rte_qdma_enqdeq *)cntxt;
+	int id = (int)((e_context->vq_id) / QDMA_QUEUES);
+	void *block;
+	void *ctrl = fsl_qdma->ctrl_base;
+	unsigned int reg;
+	int intr;
+	void *status = fsl_qdma->status_base;
+
+	intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
+	if (intr) {
+		DPAA_QDMA_ERR("DMA transaction error! %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW0R);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECFDW0R %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW1R);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECFDW1R %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW2R);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECFDW2R %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW3R);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECFDW3R %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFQIDR);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECFQIDR %x\n", intr);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DECBR);
+		DPAA_QDMA_INFO("reg FSL_QDMA_DECBR %x\n", intr);
+		qdma_writel(fsl_qdma, 0xffffffff,
+			    status + FSL_QDMA_DEDR);
+		intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
+	}
+
+	block = fsl_qdma->block_base +
+		FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, id);
+
+	reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQSR);
+	if (reg & FSL_QDMA_BSQSR_QE)
+		return 0;
+
+	intr = fsl_qdma_queue_transfer_complete(fsl_qdma, block, id, e_context);
+	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));
+		DPAA_QDMA_ERR("QDMA: status err!\n");
+	}
+
+	return intr;
+}
+
+static int
+dpaa_qdma_attr_get(__rte_unused struct rte_rawdev *rawdev,
+		    __rte_unused const char *attr_name,
+		    __rte_unused uint64_t *attr_value)
+{
+	return 0;
+}
+
+static struct rte_rawdev_ops dpaa_qdma_ops = {
+	.dev_configure            = dpaa_qdma_configure,
+	.dev_start                = dpaa_qdma_start,
+	.dev_reset                = dpaa_qdma_reset,
+	.dev_close                = dpaa_qdma_close,
+	.queue_setup		  = dpaa_qdma_queue_setup,
+	.queue_release		  = dpaa_qdma_queue_release,
+	.attr_get		  = dpaa_qdma_attr_get,
+	.enqueue_bufs		  = dpaa_qdma_enqueue,
+	.dequeue_bufs		  = dpaa_qdma_dequeue,
+};
+
+static int
+dpaa_qdma_init(struct rte_rawdev *rawdev)
+{
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	struct fsl_qdma_chan *fsl_chan;
+	uint64_t phys_addr;
+	unsigned int len;
+	int ccsr_qdma_fd;
+	int regs_size;
+	int ret;
+	u32 i;
+
+	fsl_qdma->desc_allocated = 0;
+	fsl_qdma->n_chans = VIRT_CHANNELS;
+	fsl_qdma->n_queues = QDMA_QUEUES;
+	fsl_qdma->num_blocks = QDMA_BLOCKS;
+	fsl_qdma->block_offset = QDMA_BLOCK_OFFSET;
+
+	len = sizeof(*fsl_chan) * fsl_qdma->n_chans;
+	fsl_qdma->chans = rte_zmalloc("qdma: fsl chans", len, 0);
+	if (!fsl_qdma->chans)
+		return -1;
+
+	len = sizeof(struct fsl_qdma_queue *) * fsl_qdma->num_blocks;
+	fsl_qdma->status = rte_zmalloc("qdma: fsl status", len, 0);
+	if (!fsl_qdma->status) {
+		rte_free(fsl_qdma->chans);
+		return -1;
+	}
+
+	for (i = 0; i < fsl_qdma->num_blocks; i++) {
+		rte_atomic32_init(&wait_task[i]);
+		fsl_qdma->status[i] = fsl_qdma_prep_status_queue();
+		if (!fsl_qdma->status[i])
+			goto err;
+	}
+
+	ccsr_qdma_fd = open("/dev/mem", O_RDWR);
+	if (unlikely(ccsr_qdma_fd < 0)) {
+		DPAA_QDMA_ERR("Can not open /dev/mem for qdma CCSR map");
+		goto err;
+	}
+
+	regs_size = fsl_qdma->block_offset * (fsl_qdma->num_blocks + 2);
+	phys_addr = QDMA_CCSR_BASE;
+	fsl_qdma->ctrl_base = mmap(NULL, regs_size, PROT_READ |
+					 PROT_WRITE, MAP_SHARED,
+					 ccsr_qdma_fd, phys_addr);
+
+	close(ccsr_qdma_fd);
+	if (fsl_qdma->ctrl_base == MAP_FAILED) {
+		DPAA_QDMA_ERR("Can not map CCSR base qdma: Phys: 0x%lx "
+		       "size %d\n", phys_addr, regs_size);
+		goto err;
+	}
+
+	fsl_qdma->status_base = fsl_qdma->ctrl_base + QDMA_BLOCK_OFFSET;
+	fsl_qdma->block_base = fsl_qdma->status_base + QDMA_BLOCK_OFFSET;
+
+	fsl_qdma->queue = fsl_qdma_alloc_queue_resources(fsl_qdma);
+	if (!fsl_qdma->queue) {
+		munmap(fsl_qdma->ctrl_base, regs_size);
+		goto err;
+	}
+
+	fsl_qdma->big_endian = QDMA_BIG_ENDIAN;
+	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_qdma->num_blocks);
+		fsl_chan->free = true;
+	}
+
+	ret = fsl_qdma_reg_init(fsl_qdma);
+	if (ret) {
+		DPAA_QDMA_ERR("Can't Initialize the qDMA engine.\n");
+		munmap(fsl_qdma->ctrl_base, regs_size);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	rte_free(fsl_qdma->chans);
+	rte_free(fsl_qdma->status);
+
+	return -1;
+}
+
+static int
+dpaa_qdma_probe(struct rte_dpaa_driver *dpaa_drv,
+		     struct rte_dpaa_device *dpaa_dev)
+{
+	struct rte_rawdev *rawdev;
+	int ret;
+
+	rawdev = rte_rawdev_pmd_allocate(dpaa_dev->device.name,
+			sizeof(struct fsl_qdma_engine),
+			rte_socket_id());
+	if (!rawdev) {
+		DPAA_QDMA_ERR("Unable to allocate rawdevice");
+		return -EINVAL;
+	}
+
+	dpaa_dev->rawdev = rawdev;
+	rawdev->dev_ops = &dpaa_qdma_ops;
+	rawdev->device = &dpaa_dev->device;
+	rawdev->driver_name = dpaa_drv->driver.name;
+
+	/* Invoke PMD device initialization function */
+	ret = dpaa_qdma_init(rawdev);
+	if (ret) {
+		rte_rawdev_pmd_release(rawdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+dpaa_qdma_remove(struct rte_dpaa_device *dpaa_dev)
+{
+	struct rte_rawdev *rawdev = dpaa_dev->rawdev;
+	struct fsl_qdma_engine *fsl_qdma = rawdev->dev_private;
+	int ret;
+
+	rte_free(fsl_qdma->status);
+	rte_free(fsl_qdma->chans);
+	ret = rte_rawdev_pmd_release(rawdev);
+	if (ret)
+		DPAA_QDMA_ERR("Device cleanup failed\n");
+
+	return 0;
+}
+
+static struct rte_dpaa_driver rte_dpaa_qdma_pmd;
+
+static struct rte_dpaa_driver rte_dpaa_qdma_pmd = {
+	.drv_type = FSL_DPAA_QDMA,
+	.probe = dpaa_qdma_probe,
+	.remove = dpaa_qdma_remove,
+};
+
+RTE_PMD_REGISTER_DPAA(dpaa_qdma, rte_dpaa_qdma_pmd);
+
+RTE_INIT(dpaa_qdma_init_log)
+{
+	dpaa_qdma_logtype = rte_log_register("pmd.raw.dpaa.qdma");
+	if (dpaa_qdma_logtype >= 0)
+		rte_log_set_level(dpaa_qdma_logtype, RTE_LOG_INFO);
+}
diff --git a/drivers/raw/dpaa_qdma/dpaa_qdma.h b/drivers/raw/dpaa_qdma/dpaa_qdma.h
new file mode 100644
index 0000000..a60fdcb
--- /dev/null
+++ b/drivers/raw/dpaa_qdma/dpaa_qdma.h
@@ -0,0 +1,275 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 NXP
+ */
+
+#ifndef _FSL_QDMA_H_
+#define _FSL_QDMA_H_
+
+#include <dpaa_list.h>
+#include <rte_atomic.h>
+
+#define u64	uint64_t
+#define u32	uint32_t
+#define u16	uint16_t
+#define u8	uint8_t
+
+#ifdef DEBUG
+#define debug printf
+#else
+#define debug
+#endif
+#ifndef BIT
+#define BIT(nr)		(1UL << (nr))
+#endif
+
+#define CORE_NUMBER 4
+#define RETRIES	5
+
+#ifndef GENMASK
+#define BITS_PER_LONG	(__SIZEOF_LONG__ * 8)
+#define GENMASK(h, l) \
+		(((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+#endif
+
+#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_SQEDPAR		0x808
+#define FSL_QDMA_SQDPAR			0x80c
+#define FSL_QDMA_SQEEPAR		0x810
+#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_BSQSR_QF		0x10000
+
+#define FSL_QDMA_DMR_DQD		0x40000000
+#define FSL_QDMA_DSR_DB			0x80000000
+
+#define FSL_QDMA_COMMAND_BUFFER_SIZE	64
+#define FSL_QDMA_DESCRIPTOR_BUFFER_SIZE 32
+#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 QDMA_CCDF_STATUS		20
+#define QDMA_CCDF_OFFSET		20
+#define QDMA_CCDF_MASK			GENMASK(28, 20)
+#define QDMA_CCDF_FOTMAT		BIT(29)
+#define QDMA_CCDF_SER			BIT(30)
+
+#define QDMA_SG_FIN			BIT(30)
+#define QDMA_SG_EXT			BIT(31)
+#define QDMA_SG_LEN_MASK		GENMASK(29, 0)
+
+#define QDMA_BIG_ENDIAN			0x00000001
+#define COMP_TIMEOUT			100000
+#define COMMAND_QUEUE_OVERFLLOW		10
+
+/* qdma engine attribute */
+#define QDMA_QUEUE_SIZE 64
+#define QDMA_STATUS_SIZE 64
+#define QDMA_CCSR_BASE 0x8380000
+#define VIRT_CHANNELS 32
+#define QDMA_BLOCK_OFFSET 0x10000
+#define QDMA_BLOCKS 4
+#define QDMA_QUEUES 8
+#define QDMA_DELAY 1000
+
+#define __arch_getq(a)		(*(volatile u64 *)(a))
+#define __arch_putq(v, a)	(*(volatile u64 *)(a) = (v))
+#define __arch_getq32(a)	(*(volatile u32 *)(a))
+#define __arch_putq32(v, a)	(*(volatile u32 *)(a) = (v))
+#define readq(c) \
+	({ u64 __v = __arch_getq(c); rte_io_rmb(); __v; })
+#define writeq(v, c) \
+	({ u64 __v = v; rte_io_wmb(); __arch_putq(__v, c); __v; })
+#define readq32(c) \
+	({ u32 __v = __arch_getq32(c); rte_io_rmb(); __v; })
+#define writeq32(v, c) \
+	({ u32 __v = v; rte_io_wmb(); __arch_putq32(__v, c); __v; })
+#define ioread64(_p)		readq(_p)
+#define iowrite64(_v, _p)	writeq(_v, _p)
+#define ioread32(_p)		readq32(_p)
+#define iowrite32(_v, _p)	writeq32(_v, _p)
+
+#define ioread32be(_p)          be32_to_cpu(readq32(_p))
+#define iowrite32be(_v, _p)	writeq32(be32_to_cpu(_v), _p)
+
+#define QDMA_IN(fsl_qdma_engine, addr)					\
+	(((fsl_qdma_engine)->big_endian & QDMA_BIG_ENDIAN) ?		\
+		ioread32be(addr) : ioread32(addr))
+#define QDMA_OUT(fsl_qdma_engine, addr, val)				\
+	(((fsl_qdma_engine)->big_endian & QDMA_BIG_ENDIAN) ?		\
+		iowrite32be(val, addr) : iowrite32(val, addr))
+
+#define FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma_engine, x)			\
+	(((fsl_qdma_engine)->block_offset) * (x))
+
+typedef void (*dma_call_back)(void *params);
+
+/* qDMA Command Descriptor Fotmats */
+struct fsl_qdma_format {
+	__le32 status; /* ser, status */
+	__le32 cfg;	/* format, offset */
+	union {
+		struct {
+			__le32 addr_lo;	/* low 32-bits of 40-bit address */
+			u8 addr_hi;	/* high 8-bits of 40-bit address */
+			u8 __reserved1[2];
+			u8 cfg8b_w1; /* dd, queue */
+		};
+		__le64 data;
+	};
+};
+
+/* qDMA Source Descriptor Format */
+struct fsl_qdma_sdf {
+	__le32 rev3;
+	__le32 cfg; /* rev4, bit[0-11] - ssd, bit[12-23] sss */
+	__le32 rev5;
+	__le32 cmd;
+};
+
+/* qDMA Destination Descriptor Format */
+struct fsl_qdma_ddf {
+	__le32 rev1;
+	__le32 cfg; /* rev2, bit[0-11] - dsd, bit[12-23] - dss */
+	__le32 rev3;
+	__le32 cmd;
+};
+
+enum dma_status {
+	DMA_COMPLETE,
+	DMA_IN_PROGRESS,
+	DMA_IN_PREPAR,
+	DMA_PAUSED,
+	DMA_ERROR,
+};
+
+struct fsl_qdma_chan {
+	struct fsl_qdma_engine	*qdma;
+	struct fsl_qdma_queue	*queue;
+	enum dma_status         status;
+	bool			free;
+	struct list_head	list;
+};
+
+struct fsl_qdma_list {
+	struct list_head	dma_list;
+};
+
+struct fsl_qdma_queue {
+	struct fsl_qdma_format	*virt_head;
+	struct list_head	comp_used;
+	struct list_head	comp_free;
+	dma_addr_t		bus_addr;
+	u32                     n_cq;
+	u32			id;
+	u32			count;
+	struct fsl_qdma_format	*cq;
+	void			*block_base;
+};
+
+struct fsl_qdma_comp {
+	dma_addr_t              bus_addr;
+	dma_addr_t              desc_bus_addr;
+	void			*virt_addr;
+	void			*desc_virt_addr;
+	struct fsl_qdma_chan	*qchan;
+	dma_call_back		call_back_func;
+	void			*params;
+	struct list_head	list;
+};
+
+struct fsl_qdma_engine {
+	int			desc_allocated;
+	void			*ctrl_base;
+	void			*status_base;
+	void			*block_base;
+	u32			n_chans;
+	u32			n_queues;
+	int			error_irq;
+	bool			big_endian;
+	struct fsl_qdma_queue	*queue;
+	struct fsl_qdma_queue	**status;
+	struct fsl_qdma_chan	*chans;
+	u32			num_blocks;
+	int			block_offset;
+};
+
+static u64 pre_addr[CORE_NUMBER];
+static u64 pre_queue[CORE_NUMBER];
+static rte_atomic32_t wait_task[CORE_NUMBER];
+
+#ifndef QDMA_MEMZONE
+/* Array of memzone pointers */
+static const struct rte_memzone *qdma_mz_mapping[RTE_MAX_MEMZONE];
+/* Counter to track current memzone allocated */
+static uint16_t qdma_mz_count;
+#endif
+
+#endif /* _FSL_QDMA_H_ */
diff --git a/drivers/raw/dpaa_qdma/dpaa_qdma_logs.h b/drivers/raw/dpaa_qdma/dpaa_qdma_logs.h
new file mode 100644
index 0000000..7c11815
--- /dev/null
+++ b/drivers/raw/dpaa_qdma/dpaa_qdma_logs.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 NXP
+ */
+
+#ifndef __DPAA_QDMA_LOGS_H__
+#define __DPAA_QDMA_LOGS_H__
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern int dpaa_qdma_logtype;
+
+#define DPAA_QDMA_LOG(level, fmt, args...) \
+	rte_log(RTE_LOG_ ## level, dpaa_qdma_logtype, "dpaa_qdma: " \
+		fmt "\n", ## args)
+
+#define DPAA_QDMA_DEBUG(fmt, args...) \
+	rte_log(RTE_LOG_DEBUG, dpaa_qdma_logtype, "dpaa_qdma: %s(): " \
+		fmt "\n", __func__, ## args)
+
+#define DPAA_QDMA_FUNC_TRACE() DPAA_QDMA_DEBUG(">>")
+
+#define DPAA_QDMA_INFO(fmt, args...) \
+	DPAA_QDMA_LOG(INFO, fmt, ## args)
+#define DPAA_QDMA_ERR(fmt, args...) \
+	DPAA_QDMA_LOG(ERR, fmt, ## args)
+#define DPAA_QDMA_WARN(fmt, args...) \
+	DPAA_QDMA_LOG(WARNING, fmt, ## args)
+
+/* DP Logs, toggled out at compile time if level lower than current level */
+#define DPAA_QDMA_DP_LOG(level, fmt, args...) \
+	RTE_LOG_DP(level, PMD, "dpaa_qdma: " fmt "\n", ## args)
+
+#define DPAA_QDMA_DP_DEBUG(fmt, args...) \
+	DPAA_QDMA_DP_LOG(DEBUG, fmt, ## args)
+#define DPAA_QDMA_DP_INFO(fmt, args...) \
+	DPAA_QDMA_DP_LOG(INFO, fmt, ## args)
+#define DPAA_QDMA_DP_WARN(fmt, args...) \
+	DPAA_QDMA_DP_LOG(WARNING, fmt, ## args)
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __DPAA_QDMA_LOGS_H__ */
diff --git a/drivers/raw/dpaa_qdma/meson.build b/drivers/raw/dpaa_qdma/meson.build
new file mode 100644
index 0000000..ce2ac33
--- /dev/null
+++ b/drivers/raw/dpaa_qdma/meson.build
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright 2020 NXP
+
+if not is_linux
+	build = false
+	reason = 'only supported on linux'
+endif
+
+deps += ['rawdev', 'bus_dpaa']
+sources = files('dpaa_qdma.c')
+includes += include_directories('../dpaa2_qdma')
+
+if cc.has_argument('-Wno-pointer-arith')
+	cflags += '-Wno-pointer-arith'
+endif
diff --git a/drivers/raw/dpaa_qdma/rte_rawdev_dpaa_qdma_version.map b/drivers/raw/dpaa_qdma/rte_rawdev_dpaa_qdma_version.map
new file mode 100644
index 0000000..f9f17e4
--- /dev/null
+++ b/drivers/raw/dpaa_qdma/rte_rawdev_dpaa_qdma_version.map
@@ -0,0 +1,3 @@
+DPDK_20.0 {
+	local: *;
+};
diff --git a/drivers/raw/meson.build b/drivers/raw/meson.build
index 2c1e65e..0e310ac 100644
--- a/drivers/raw/meson.build
+++ b/drivers/raw/meson.build
@@ -5,7 +5,7 @@ if is_windows
 	subdir_done()
 endif
 
-drivers = ['dpaa2_cmdif', 'dpaa2_qdma',
+drivers = ['dpaa_qdma', 'dpaa2_cmdif', 'dpaa2_qdma',
 	'ifpga', 'ioat', 'ntb',
 	'octeontx2_dma',
 	'octeontx2_ep',
-- 
2.7.4