[v2,2/6] dma/dpaa: add device probe and remove functionality

diff --git a/drivers/dma/dpaa/dpaa_qdma.c b/drivers/dma/dpaa/dpaa_qdma.c
index 2ef3ee0c35..3ad23513e9 100644
--- a/drivers/dma/dpaa/dpaa_qdma.c
+++ b/drivers/dma/dpaa/dpaa_qdma.c
@@ -3,17 +3,447 @@ 
  */
 
 #include <rte_dpaa_bus.h>
+#include <rte_dmadev_pmd.h>
+
+#include "dpaa_qdma.h"
+
+static inline int ilog2(int x)
+{
+	int log = 0;
+
+	x >>= 1;
+
+	while (x) {
+		log++;
+		x >>= 1;
+	}
+	return log;
+}
+
+static u32 qdma_readl(void *addr)
+{
+	return QDMA_IN(addr);
+}
+
+static void qdma_writel(u32 val, void *addr)
+{
+	QDMA_OUT(addr, val);
+}
+
+static void *dma_pool_alloc(int size, int aligned, dma_addr_t *phy_addr)
+{
+	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;
+}
+
+static void dma_pool_free(void *addr)
+{
+	rte_free(addr);
+}
+
+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);
+		dma_pool_free(comp_temp->virt_addr);
+		dma_pool_free(comp_temp->desc_virt_addr);
+		rte_free(comp_temp);
+	}
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_free, list) {
+		list_del(&comp_temp->list);
+		dma_pool_free(comp_temp->virt_addr);
+		dma_pool_free(comp_temp->desc_virt_addr);
+		rte_free(comp_temp);
+	}
+
+finally:
+	fsl_qdma->desc_allocated--;
+}
+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) {
+				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) {
+		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(ctrl + FSL_QDMA_DMR);
+	reg |= FSL_QDMA_DMR_DQD;
+	qdma_writel(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(0, block + FSL_QDMA_BCQMR(i));
+	}
+	while (true) {
+		reg = qdma_readl(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(0, block + FSL_QDMA_BSQMR);
+
+		/*
+		 * clear the command queue interrupt detect register for
+		 * all queues.
+		 */
+		qdma_writel(0xffffffff, block + FSL_QDMA_BCQIDR(0));
+	}
+
+	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 *ctrl = fsl_qdma->ctrl_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) {
+		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(lower_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQDPA_SADDR(i));
+			qdma_writel(upper_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQEDPA_SADDR(i));
+			qdma_writel(lower_32_bits(temp->bus_addr),
+				    block + FSL_QDMA_BCQEPA_SADDR(i));
+			qdma_writel(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(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_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(
+			    upper_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEEPAR);
+		qdma_writel(
+			    lower_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEPAR);
+		qdma_writel(
+			    upper_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQEDPAR);
+		qdma_writel(
+			    lower_32_bits(fsl_qdma->status[j]->bus_addr),
+			    block + FSL_QDMA_SQDPAR);
+		/* Desiable status queue interrupt. */
+
+		qdma_writel(0x0, block + FSL_QDMA_BCQIER(0));
+		qdma_writel(0x0, block + FSL_QDMA_BSQICR);
+		qdma_writel(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(reg, block + FSL_QDMA_BSQMR);
+	}
+
+	reg = qdma_readl(ctrl + FSL_QDMA_DMR);
+	reg &= ~FSL_QDMA_DMR_DQD;
+	qdma_writel(reg, ctrl + FSL_QDMA_DMR);
+
+	return 0;
+}
+
+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_init(struct rte_dma_dev *dmadev)
+{
+	struct fsl_qdma_engine *fsl_qdma = dmadev->data->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)) {
+		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) {
+		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;
+	}
+
+	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) {
+		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(__rte_unused struct rte_dpaa_driver *dpaa_drv,
-		__rte_unused struct rte_dpaa_device *dpaa_dev)
+		struct rte_dpaa_device *dpaa_dev)
 {
+	struct rte_dma_dev *dmadev;
+	int ret;
+
+	dmadev = rte_dma_pmd_allocate(dpaa_dev->device.name,
+				      rte_socket_id(),
+				      sizeof(struct fsl_qdma_engine));
+	if (!dmadev) {
+		return -EINVAL;
+	}
+
+	dpaa_dev->dmadev = dmadev;
+
+	/* Invoke PMD device initialization function */
+	ret = dpaa_qdma_init(dmadev);
+	if (ret) {
+		(void)rte_dma_pmd_release(dpaa_dev->device.name);
+		return ret;
+	}
+
+	dmadev->state = RTE_DMA_DEV_READY;
 	return 0;
 }
 
 static int
-dpaa_qdma_remove(__rte_unused struct rte_dpaa_device *dpaa_dev)
+dpaa_qdma_remove(struct rte_dpaa_device *dpaa_dev)
 {
+	struct rte_dma_dev *dmadev = dpaa_dev->dmadev;
+	struct fsl_qdma_engine *fsl_qdma = dmadev->data->dev_private;
+	int i = 0, max = QDMA_QUEUES * QDMA_BLOCKS;
+
+	for (i = 0; i < max; i++) {
+		struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[i];
+
+		if (fsl_chan->free == false)
+			dma_release(fsl_chan);
+	}
+
+	rte_free(fsl_qdma->status);
+	rte_free(fsl_qdma->chans);
+
 	return 0;
 }
 
diff --git a/drivers/dma/dpaa/dpaa_qdma.h b/drivers/dma/dpaa/dpaa_qdma.h
new file mode 100644
index 0000000000..cc0d1f114e
--- /dev/null
+++ b/drivers/dma/dpaa/dpaa_qdma.h
@@ -0,0 +1,247 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2021 NXP
+ */
+
+#ifndef _DPAA_QDMA_H_
+#define _DPAA_QDMA_H_
+
+#define CORE_NUMBER 4
+#define RETRIES	5
+
+#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_EI_BE           0x40
+#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_BCQSR_QF_XOFF_BE      0x1000100
+
+#define FSL_QDMA_BSQMR_EN		0x80000000
+#define FSL_QDMA_BSQMR_DI		0x40000000
+#define FSL_QDMA_BSQMR_DI_BE		0x40
+#define FSL_QDMA_BSQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BSQSR_QE		0x20000
+#define FSL_QDMA_BSQSR_QE_BE		0x200
+#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			1
+#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 readq32(c) \
+	({ u32 __v = __arch_getq32(c); rte_io_rmb(); __v; })
+#define writeq32(v, c) \
+	({ u32 __v = v; __arch_putq32(__v, c); __v; })
+#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)
+
+#ifdef QDMA_BIG_ENDIAN
+#define QDMA_IN(addr)		ioread32be(addr)
+#define QDMA_OUT(addr, val)	iowrite32be(val, addr)
+#define QDMA_IN_BE(addr)	ioread32(addr)
+#define QDMA_OUT_BE(addr, val)	iowrite32(val, addr)
+#else
+#define QDMA_IN(addr)		ioread32(addr)
+#define QDMA_OUT(addr, val)	iowrite32(val, addr)
+#define QDMA_IN_BE(addr)	ioread32be(addr)
+#define QDMA_OUT_BE(addr, val)	iowrite32be(val, addr)
+#endif
+
+#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 Formats */
+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;
+	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;
+	int			index;
+	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;
+	struct fsl_qdma_queue	*queue;
+	struct fsl_qdma_queue	**status;
+	struct fsl_qdma_chan	*chans;
+	u32			num_blocks;
+	u8			free_block_id;
+	u32			vchan_map[4];
+	int			block_offset;
+};
+
+static rte_atomic32_t wait_task[CORE_NUMBER];
+
+#endif /* _DPAA_QDMA_H_ */