X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fraw%2Fdpaa2_qdma%2Fdpaa2_qdma.c;h=530ee156d21e808aeda67754e213c7f85eb5d269;hb=1c540f29de0d845baf18e497fcb6685ab2d11d39;hp=b38a282581fcc6976a8d791ea6e5df76fef7646c;hpb=c22fab9a6c349ba5fcf3f809c1d78a81424719f4;p=dpdk.git

diff --git a/drivers/raw/dpaa2_qdma/dpaa2_qdma.c b/drivers/raw/dpaa2_qdma/dpaa2_qdma.c
index b38a282581..530ee156d2 100644
--- a/drivers/raw/dpaa2_qdma/dpaa2_qdma.c
+++ b/drivers/raw/dpaa2_qdma/dpaa2_qdma.c
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright 2018 NXP
+ * Copyright 2018-2020 NXP
  */
 
 #include <string.h>
@@ -13,20 +13,24 @@
 #include <rte_malloc.h>
 #include <rte_ring.h>
 #include <rte_mempool.h>
+#include <rte_prefetch.h>
+#include <rte_kvargs.h>
 
 #include <mc/fsl_dpdmai.h>
 #include <portal/dpaa2_hw_pvt.h>
 #include <portal/dpaa2_hw_dpio.h>
 
+#include "rte_pmd_dpaa2_qdma.h"
 #include "dpaa2_qdma.h"
 #include "dpaa2_qdma_logs.h"
-#include "rte_pmd_dpaa2_qdma.h"
 
-/* Dynamic log type identifier */
-int dpaa2_qdma_logtype;
+#define DPAA2_QDMA_NO_PREFETCH "no_prefetch"
+
+uint32_t dpaa2_coherent_no_alloc_cache;
+uint32_t dpaa2_coherent_alloc_cache;
 
 /* QDMA device */
-static struct qdma_device qdma_dev;
+static struct qdma_device q_dev;
 
 /* QDMA H/W queues list */
 TAILQ_HEAD(qdma_hw_queue_list, qdma_hw_queue);
@@ -34,10 +38,287 @@ static struct qdma_hw_queue_list qdma_queue_list
 	= TAILQ_HEAD_INITIALIZER(qdma_queue_list);
 
 /* QDMA Virtual Queues */
-struct qdma_virt_queue *qdma_vqs;
+static struct qdma_virt_queue *qdma_vqs;
 
 /* QDMA per core data */
-struct qdma_per_core_info qdma_core_info[RTE_MAX_LCORE];
+static struct qdma_per_core_info qdma_core_info[RTE_MAX_LCORE];
+
+typedef int (dpdmai_dev_dequeue_multijob_t)(struct dpaa2_dpdmai_dev *dpdmai_dev,
+					    uint16_t rxq_id,
+					    uint16_t *vq_id,
+					    struct rte_qdma_job **job,
+					    uint16_t nb_jobs);
+
+dpdmai_dev_dequeue_multijob_t *dpdmai_dev_dequeue_multijob;
+
+typedef uint16_t (dpdmai_dev_get_job_t)(struct qdma_device *qdma_dev,
+					const struct qbman_fd *fd,
+					struct rte_qdma_job **job);
+typedef int (dpdmai_dev_set_fd_t)(struct qdma_device *qdma_dev,
+				  struct qbman_fd *fd,
+				  struct rte_qdma_job *job,
+				  struct rte_qdma_rbp *rbp,
+				  uint16_t vq_id);
+dpdmai_dev_get_job_t *dpdmai_dev_get_job;
+dpdmai_dev_set_fd_t *dpdmai_dev_set_fd;
+
+static inline int
+qdma_populate_fd_pci(phys_addr_t src, phys_addr_t dest,
+			uint32_t len, struct qbman_fd *fd,
+			struct rte_qdma_rbp *rbp)
+{
+	fd->simple_pci.saddr_lo = lower_32_bits((uint64_t) (src));
+	fd->simple_pci.saddr_hi = upper_32_bits((uint64_t) (src));
+
+	fd->simple_pci.len_sl = len;
+
+	fd->simple_pci.bmt = 1;
+	fd->simple_pci.fmt = 3;
+	fd->simple_pci.sl = 1;
+	fd->simple_pci.ser = 1;
+
+	fd->simple_pci.sportid = rbp->sportid;	/*pcie 3 */
+	fd->simple_pci.srbp = rbp->srbp;
+	if (rbp->srbp)
+		fd->simple_pci.rdttype = 0;
+	else
+		fd->simple_pci.rdttype = dpaa2_coherent_alloc_cache;
+
+	/*dest is pcie memory */
+	fd->simple_pci.dportid = rbp->dportid;	/*pcie 3 */
+	fd->simple_pci.drbp = rbp->drbp;
+	if (rbp->drbp)
+		fd->simple_pci.wrttype = 0;
+	else
+		fd->simple_pci.wrttype = dpaa2_coherent_no_alloc_cache;
+
+	fd->simple_pci.daddr_lo = lower_32_bits((uint64_t) (dest));
+	fd->simple_pci.daddr_hi = upper_32_bits((uint64_t) (dest));
+
+	return 0;
+}
+
+static inline int
+qdma_populate_fd_ddr(phys_addr_t src, phys_addr_t dest,
+			uint32_t len, struct qbman_fd *fd)
+{
+	fd->simple_ddr.saddr_lo = lower_32_bits((uint64_t) (src));
+	fd->simple_ddr.saddr_hi = upper_32_bits((uint64_t) (src));
+
+	fd->simple_ddr.len = len;
+
+	fd->simple_ddr.bmt = 1;
+	fd->simple_ddr.fmt = 3;
+	fd->simple_ddr.sl = 1;
+	fd->simple_ddr.ser = 1;
+	/**
+	 * src If RBP=0 {NS,RDTTYPE[3:0]}: 0_1011
+	 * Coherent copy of cacheable memory,
+	 * lookup in downstream cache, no allocate
+	 * on miss
+	 */
+	fd->simple_ddr.rns = 0;
+	fd->simple_ddr.rdttype = dpaa2_coherent_alloc_cache;
+	/**
+	 * dest If RBP=0 {NS,WRTTYPE[3:0]}: 0_0111
+	 * Coherent write of cacheable memory,
+	 * lookup in downstream cache, no allocate on miss
+	 */
+	fd->simple_ddr.wns = 0;
+	fd->simple_ddr.wrttype = dpaa2_coherent_no_alloc_cache;
+
+	fd->simple_ddr.daddr_lo = lower_32_bits((uint64_t) (dest));
+	fd->simple_ddr.daddr_hi = upper_32_bits((uint64_t) (dest));
+
+	return 0;
+}
+
+static void
+dpaa2_qdma_populate_fle(struct qbman_fle *fle,
+			struct rte_qdma_rbp *rbp,
+			uint64_t src, uint64_t dest,
+			size_t len, uint32_t flags)
+{
+	struct qdma_sdd *sdd;
+
+	sdd = (struct qdma_sdd *)((uint8_t *)(fle) +
+		(DPAA2_QDMA_MAX_FLE * sizeof(struct qbman_fle)));
+
+	/* first frame list to source descriptor */
+	DPAA2_SET_FLE_ADDR(fle, DPAA2_VADDR_TO_IOVA(sdd));
+	DPAA2_SET_FLE_LEN(fle, (2 * (sizeof(struct qdma_sdd))));
+
+	/* source and destination descriptor */
+	if (rbp && rbp->enable) {
+		/* source */
+		sdd->read_cmd.portid = rbp->sportid;
+		sdd->rbpcmd_simple.pfid = rbp->spfid;
+		sdd->rbpcmd_simple.vfid = rbp->svfid;
+
+		if (rbp->srbp) {
+			sdd->read_cmd.rbp = rbp->srbp;
+			sdd->read_cmd.rdtype = DPAA2_RBP_MEM_RW;
+		} else {
+			sdd->read_cmd.rdtype = dpaa2_coherent_no_alloc_cache;
+		}
+		sdd++;
+		/* destination */
+		sdd->write_cmd.portid = rbp->dportid;
+		sdd->rbpcmd_simple.pfid = rbp->dpfid;
+		sdd->rbpcmd_simple.vfid = rbp->dvfid;
+
+		if (rbp->drbp) {
+			sdd->write_cmd.rbp = rbp->drbp;
+			sdd->write_cmd.wrttype = DPAA2_RBP_MEM_RW;
+		} else {
+			sdd->write_cmd.wrttype = dpaa2_coherent_alloc_cache;
+		}
+
+	} else {
+		sdd->read_cmd.rdtype = dpaa2_coherent_no_alloc_cache;
+		sdd++;
+		sdd->write_cmd.wrttype = dpaa2_coherent_alloc_cache;
+	}
+	fle++;
+	/* source frame list to source buffer */
+	if (flags & RTE_QDMA_JOB_SRC_PHY) {
+		DPAA2_SET_FLE_ADDR(fle, src);
+		DPAA2_SET_FLE_BMT(fle);
+	} else {
+		DPAA2_SET_FLE_ADDR(fle, DPAA2_VADDR_TO_IOVA(src));
+	}
+	DPAA2_SET_FLE_LEN(fle, len);
+
+	fle++;
+	/* destination frame list to destination buffer */
+	if (flags & RTE_QDMA_JOB_DEST_PHY) {
+		DPAA2_SET_FLE_BMT(fle);
+		DPAA2_SET_FLE_ADDR(fle, dest);
+	} else {
+		DPAA2_SET_FLE_ADDR(fle, DPAA2_VADDR_TO_IOVA(dest));
+	}
+	DPAA2_SET_FLE_LEN(fle, len);
+
+	/* Final bit: 1, for last frame list */
+	DPAA2_SET_FLE_FIN(fle);
+}
+
+static inline int dpdmai_dev_set_fd_us(
+				struct qdma_device *qdma_dev __rte_unused,
+				struct qbman_fd *fd,
+				struct rte_qdma_job *job,
+				struct rte_qdma_rbp *rbp,
+				uint16_t vq_id)
+{
+	struct rte_qdma_job **ppjob;
+	size_t iova;
+	int ret = 0;
+
+	if (job->src & QDMA_RBP_UPPER_ADDRESS_MASK)
+		iova = (size_t)job->dest;
+	else
+		iova = (size_t)job->src;
+
+	/* Set the metadata */
+	job->vq_id = vq_id;
+	ppjob = (struct rte_qdma_job **)DPAA2_IOVA_TO_VADDR(iova) - 1;
+	*ppjob = job;
+
+	if ((rbp->drbp == 1) || (rbp->srbp == 1))
+		ret = qdma_populate_fd_pci((phys_addr_t) job->src,
+					   (phys_addr_t) job->dest,
+					   job->len, fd, rbp);
+	else
+		ret = qdma_populate_fd_ddr((phys_addr_t) job->src,
+					   (phys_addr_t) job->dest,
+					   job->len, fd);
+	return ret;
+}
+static inline int dpdmai_dev_set_fd_lf(struct qdma_device *qdma_dev,
+					struct qbman_fd *fd,
+					struct rte_qdma_job *job,
+					struct rte_qdma_rbp *rbp,
+					uint16_t vq_id)
+{
+	struct rte_qdma_job **ppjob;
+	struct qbman_fle *fle;
+	int ret = 0;
+	/*
+	 * Get an FLE/SDD from FLE pool.
+	 * Note: IO metadata is before the FLE and SDD memory.
+	 */
+	ret = rte_mempool_get(qdma_dev->fle_pool, (void **)(&ppjob));
+	if (ret) {
+		DPAA2_QDMA_DP_DEBUG("Memory alloc failed for FLE");
+		return ret;
+	}
+
+	/* Set the metadata */
+	job->vq_id = vq_id;
+	*ppjob = job;
+
+	fle = (struct qbman_fle *)(ppjob + 1);
+
+	DPAA2_SET_FD_ADDR(fd, DPAA2_VADDR_TO_IOVA(fle));
+	DPAA2_SET_FD_COMPOUND_FMT(fd);
+	DPAA2_SET_FD_FRC(fd, QDMA_SER_CTX);
+
+	/* Populate FLE */
+	memset(fle, 0, QDMA_FLE_POOL_SIZE);
+	dpaa2_qdma_populate_fle(fle, rbp, job->src, job->dest,
+				job->len, job->flags);
+
+	return 0;
+}
+
+static inline uint16_t dpdmai_dev_get_job_us(
+				struct qdma_device *qdma_dev __rte_unused,
+				const struct qbman_fd *fd,
+				struct rte_qdma_job **job)
+{
+	uint16_t vqid;
+	size_t iova;
+	struct rte_qdma_job **ppjob;
+
+	if (fd->simple_pci.saddr_hi & (QDMA_RBP_UPPER_ADDRESS_MASK >> 32))
+		iova = (size_t) (((uint64_t)fd->simple_pci.daddr_hi) << 32
+				| (uint64_t)fd->simple_pci.daddr_lo);
+	else
+		iova = (size_t)(((uint64_t)fd->simple_pci.saddr_hi) << 32
+				| (uint64_t)fd->simple_pci.saddr_lo);
+
+	ppjob = (struct rte_qdma_job **)DPAA2_IOVA_TO_VADDR(iova) - 1;
+	*job = (struct rte_qdma_job *)*ppjob;
+	(*job)->status = (fd->simple_pci.acc_err << 8) | (fd->simple_pci.error);
+	vqid = (*job)->vq_id;
+
+	return vqid;
+}
+
+static inline uint16_t dpdmai_dev_get_job_lf(struct qdma_device *qdma_dev,
+					     const struct qbman_fd *fd,
+					     struct rte_qdma_job **job)
+{
+	struct rte_qdma_job **ppjob;
+	uint16_t vqid;
+	/*
+	 * Fetch metadata from FLE. job and vq_id were set
+	 * in metadata in the enqueue operation.
+	 */
+	ppjob = (struct rte_qdma_job **)
+			DPAA2_IOVA_TO_VADDR(DPAA2_GET_FD_ADDR(fd));
+	ppjob -= 1;
+
+	*job = (struct rte_qdma_job *)*ppjob;
+	(*job)->status = (DPAA2_GET_FD_ERR(fd) << 8) |
+			 (DPAA2_GET_FD_FRC(fd) & 0xFF);
+	vqid = (*job)->vq_id;
+
+	/* Free FLE to the pool */
+	rte_mempool_put(qdma_dev->fle_pool, (void *)ppjob);
+
+	return vqid;
+}
 
 static struct qdma_hw_queue *
 alloc_hw_queue(uint32_t lcore_id)
@@ -68,7 +349,7 @@ free_hw_queue(struct qdma_hw_queue *queue)
 
 
 static struct qdma_hw_queue *
-get_hw_queue(uint32_t lcore_id)
+get_hw_queue(struct qdma_device *qdma_dev, uint32_t lcore_id)
 {
 	struct qdma_per_core_info *core_info;
 	struct qdma_hw_queue *queue, *temp;
@@ -84,7 +365,7 @@ get_hw_queue(uint32_t lcore_id)
 	 * Allocate a HW queue if there are less queues
 	 * than maximum per core queues configured
 	 */
-	if (num_hw_queues < qdma_dev.max_hw_queues_per_core) {
+	if (num_hw_queues < qdma_dev->max_hw_queues_per_core) {
 		queue = alloc_hw_queue(lcore_id);
 		if (queue) {
 			core_info->hw_queues[num_hw_queues] = queue;
@@ -143,45 +424,46 @@ put_hw_queue(struct qdma_hw_queue *queue)
 	}
 }
 
-int __rte_experimental
-rte_qdma_init(void)
+static int
+dpaa2_qdma_attr_get(struct rte_rawdev *rawdev,
+		    __rte_unused const char *attr_name,
+		    uint64_t *attr_value)
 {
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
+	struct rte_qdma_attr *qdma_attr = (struct rte_qdma_attr *)attr_value;
+
 	DPAA2_QDMA_FUNC_TRACE();
 
-	rte_spinlock_init(&qdma_dev.lock);
+	qdma_attr->num_hw_queues = qdma_dev->num_hw_queues;
 
 	return 0;
 }
 
-void __rte_experimental
-rte_qdma_attr_get(struct rte_qdma_attr *qdma_attr)
-{
-	DPAA2_QDMA_FUNC_TRACE();
-
-	qdma_attr->num_hw_queues = qdma_dev.num_hw_queues;
-}
-
-int __rte_experimental
-rte_qdma_reset(void)
+static int
+dpaa2_qdma_reset(struct rte_rawdev *rawdev)
 {
 	struct qdma_hw_queue *queue;
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
 	int i;
 
 	DPAA2_QDMA_FUNC_TRACE();
 
 	/* In case QDMA device is not in stopped state, return -EBUSY */
-	if (qdma_dev.state == 1) {
+	if (qdma_dev->state == 1) {
 		DPAA2_QDMA_ERR(
 			"Device is in running state. Stop before reset.");
 		return -EBUSY;
 	}
 
 	/* In case there are pending jobs on any VQ, return -EBUSY */
-	for (i = 0; i < qdma_dev.max_vqs; i++) {
+	for (i = 0; i < qdma_dev->max_vqs; i++) {
 		if (qdma_vqs[i].in_use && (qdma_vqs[i].num_enqueues !=
-		    qdma_vqs[i].num_dequeues))
+		    qdma_vqs[i].num_dequeues)) {
 			DPAA2_QDMA_ERR("Jobs are still pending on VQ: %d", i);
 			return -EBUSY;
+		}
 	}
 
 	/* Reset HW queues */
@@ -189,7 +471,7 @@ rte_qdma_reset(void)
 		queue->num_users = 0;
 
 	/* Reset and free virtual queues */
-	for (i = 0; i < qdma_dev.max_vqs; i++) {
+	for (i = 0; i < qdma_dev->max_vqs; i++) {
 		if (qdma_vqs[i].status_ring)
 			rte_ring_free(qdma_vqs[i].status_ring);
 	}
@@ -202,42 +484,43 @@ rte_qdma_reset(void)
 		sizeof(struct qdma_per_core_info) * RTE_MAX_LCORE);
 
 	/* Free the FLE pool */
-	if (qdma_dev.fle_pool)
-		rte_mempool_free(qdma_dev.fle_pool);
+	if (qdma_dev->fle_pool)
+		rte_mempool_free(qdma_dev->fle_pool);
 
 	/* Reset QDMA device structure */
-	qdma_dev.mode = RTE_QDMA_MODE_HW;
-	qdma_dev.max_hw_queues_per_core = 0;
-	qdma_dev.fle_pool = NULL;
-	qdma_dev.fle_pool_count = 0;
-	qdma_dev.max_vqs = 0;
+	qdma_dev->mode = RTE_QDMA_MODE_HW;
+	qdma_dev->max_hw_queues_per_core = 0;
+	qdma_dev->fle_pool = NULL;
+	qdma_dev->fle_pool_count = 0;
+	qdma_dev->max_vqs = 0;
 
 	return 0;
 }
 
-int __rte_experimental
-rte_qdma_configure(struct rte_qdma_config *qdma_config)
+static int
+dpaa2_qdma_configure(const struct rte_rawdev *rawdev,
+			 rte_rawdev_obj_t config,
+			 size_t config_size)
 {
-	int ret;
+	char fle_pool_name[32]; /* RTE_MEMZONE_NAMESIZE = 32 */
+	struct rte_qdma_config *qdma_config = (struct rte_qdma_config *)config;
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
 
 	DPAA2_QDMA_FUNC_TRACE();
 
+	if (config_size != sizeof(*qdma_config))
+		return -EINVAL;
+
 	/* In case QDMA device is not in stopped state, return -EBUSY */
-	if (qdma_dev.state == 1) {
+	if (qdma_dev->state == 1) {
 		DPAA2_QDMA_ERR(
 			"Device is in running state. Stop before config.");
 		return -1;
 	}
 
-	/* Reset the QDMA device */
-	ret = rte_qdma_reset();
-	if (ret) {
-		DPAA2_QDMA_ERR("Resetting QDMA failed");
-		return ret;
-	}
-
 	/* Set mode */
-	qdma_dev.mode = qdma_config->mode;
+	qdma_dev->mode = qdma_config->mode;
 
 	/* Set max HW queue per core */
 	if (qdma_config->max_hw_queues_per_core > MAX_HW_QUEUE_PER_CORE) {
@@ -245,7 +528,7 @@ rte_qdma_configure(struct rte_qdma_config *qdma_config)
 			       MAX_HW_QUEUE_PER_CORE);
 		return -EINVAL;
 	}
-	qdma_dev.max_hw_queues_per_core =
+	qdma_dev->max_hw_queues_per_core =
 		qdma_config->max_hw_queues_per_core;
 
 	/* Allocate Virtual Queues */
@@ -256,74 +539,100 @@ rte_qdma_configure(struct rte_qdma_config *qdma_config)
 		DPAA2_QDMA_ERR("qdma_virtual_queues allocation failed");
 		return -ENOMEM;
 	}
-	qdma_dev.max_vqs = qdma_config->max_vqs;
+	qdma_dev->max_vqs = qdma_config->max_vqs;
 
-	/* Allocate FLE pool */
-	qdma_dev.fle_pool = rte_mempool_create("qdma_fle_pool",
+	/* Allocate FLE pool; just append PID so that in case of
+	 * multiprocess, the pool's don't collide.
+	 */
+	snprintf(fle_pool_name, sizeof(fle_pool_name), "qdma_fle_pool%u",
+		 getpid());
+	qdma_dev->fle_pool = rte_mempool_create(fle_pool_name,
 			qdma_config->fle_pool_count, QDMA_FLE_POOL_SIZE,
 			QDMA_FLE_CACHE_SIZE(qdma_config->fle_pool_count), 0,
 			NULL, NULL, NULL, NULL, SOCKET_ID_ANY, 0);
-	if (!qdma_dev.fle_pool) {
+	if (!qdma_dev->fle_pool) {
 		DPAA2_QDMA_ERR("qdma_fle_pool create failed");
 		rte_free(qdma_vqs);
 		qdma_vqs = NULL;
 		return -ENOMEM;
 	}
-	qdma_dev.fle_pool_count = qdma_config->fle_pool_count;
+	qdma_dev->fle_pool_count = qdma_config->fle_pool_count;
 
+	if (qdma_config->format == RTE_QDMA_ULTRASHORT_FORMAT) {
+		dpdmai_dev_get_job = dpdmai_dev_get_job_us;
+		dpdmai_dev_set_fd = dpdmai_dev_set_fd_us;
+	} else {
+		dpdmai_dev_get_job = dpdmai_dev_get_job_lf;
+		dpdmai_dev_set_fd = dpdmai_dev_set_fd_lf;
+	}
 	return 0;
 }
 
-int __rte_experimental
-rte_qdma_start(void)
+static int
+dpaa2_qdma_start(struct rte_rawdev *rawdev)
 {
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
+
 	DPAA2_QDMA_FUNC_TRACE();
 
-	qdma_dev.state = 1;
+	qdma_dev->state = 1;
 
 	return 0;
 }
 
-int __rte_experimental
-rte_qdma_vq_create(uint32_t lcore_id, uint32_t flags)
+static int
+dpaa2_qdma_queue_setup(struct rte_rawdev *rawdev,
+			  __rte_unused uint16_t queue_id,
+			  rte_rawdev_obj_t queue_conf,
+			  size_t conf_size)
 {
 	char ring_name[32];
 	int i;
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
+	struct rte_qdma_queue_config *q_config =
+		(struct rte_qdma_queue_config *)queue_conf;
 
 	DPAA2_QDMA_FUNC_TRACE();
 
-	rte_spinlock_lock(&qdma_dev.lock);
+	if (conf_size != sizeof(*q_config))
+		return -EINVAL;
+
+	rte_spinlock_lock(&qdma_dev->lock);
 
 	/* Get a free Virtual Queue */
-	for (i = 0; i < qdma_dev.max_vqs; i++) {
+	for (i = 0; i < qdma_dev->max_vqs; i++) {
 		if (qdma_vqs[i].in_use == 0)
 			break;
 	}
 
 	/* Return in case no VQ is free */
-	if (i == qdma_dev.max_vqs) {
-		rte_spinlock_unlock(&qdma_dev.lock);
+	if (i == qdma_dev->max_vqs) {
+		rte_spinlock_unlock(&qdma_dev->lock);
+		DPAA2_QDMA_ERR("Unable to get lock on QDMA device");
 		return -ENODEV;
 	}
 
-	if (qdma_dev.mode == RTE_QDMA_MODE_HW ||
-			(flags & RTE_QDMA_VQ_EXCLUSIVE_PQ)) {
+	if (qdma_dev->mode == RTE_QDMA_MODE_HW ||
+			(q_config->flags & RTE_QDMA_VQ_EXCLUSIVE_PQ)) {
 		/* Allocate HW queue for a VQ */
-		qdma_vqs[i].hw_queue = alloc_hw_queue(lcore_id);
+		qdma_vqs[i].hw_queue = alloc_hw_queue(q_config->lcore_id);
 		qdma_vqs[i].exclusive_hw_queue = 1;
 	} else {
 		/* Allocate a Ring for Virutal Queue in VQ mode */
-		sprintf(ring_name, "status ring %d", i);
+		snprintf(ring_name, sizeof(ring_name), "status ring %d", i);
 		qdma_vqs[i].status_ring = rte_ring_create(ring_name,
-			qdma_dev.fle_pool_count, rte_socket_id(), 0);
+			qdma_dev->fle_pool_count, rte_socket_id(), 0);
 		if (!qdma_vqs[i].status_ring) {
 			DPAA2_QDMA_ERR("Status ring creation failed for vq");
-			rte_spinlock_unlock(&qdma_dev.lock);
+			rte_spinlock_unlock(&qdma_dev->lock);
 			return rte_errno;
 		}
 
 		/* Get a HW queue (shared) for a VQ */
-		qdma_vqs[i].hw_queue = get_hw_queue(lcore_id);
+		qdma_vqs[i].hw_queue = get_hw_queue(qdma_dev,
+						    q_config->lcore_id);
 		qdma_vqs[i].exclusive_hw_queue = 0;
 	}
 
@@ -332,26 +641,464 @@ rte_qdma_vq_create(uint32_t lcore_id, uint32_t flags)
 		if (qdma_vqs[i].status_ring)
 			rte_ring_free(qdma_vqs[i].status_ring);
 		qdma_vqs[i].status_ring = NULL;
-		rte_spinlock_unlock(&qdma_dev.lock);
+		rte_spinlock_unlock(&qdma_dev->lock);
 		return -ENODEV;
 	}
 
 	qdma_vqs[i].in_use = 1;
-	qdma_vqs[i].lcore_id = lcore_id;
+	qdma_vqs[i].lcore_id = q_config->lcore_id;
+	memset(&qdma_vqs[i].rbp, 0, sizeof(struct rte_qdma_rbp));
+	rte_spinlock_unlock(&qdma_dev->lock);
 
-	rte_spinlock_unlock(&qdma_dev.lock);
+	if (q_config->rbp != NULL)
+		memcpy(&qdma_vqs[i].rbp, q_config->rbp,
+		       sizeof(struct rte_qdma_rbp));
 
 	return i;
 }
 
-void __rte_experimental
+static int
+dpdmai_dev_enqueue_multi(struct dpaa2_dpdmai_dev *dpdmai_dev,
+			uint16_t txq_id,
+			uint16_t vq_id,
+			struct rte_qdma_rbp *rbp,
+			struct rte_qdma_job **job,
+			uint16_t nb_jobs)
+{
+	struct qbman_fd fd[RTE_QDMA_BURST_NB_MAX];
+	struct dpaa2_queue *txq;
+	struct qbman_eq_desc eqdesc;
+	struct qbman_swp *swp;
+	int ret;
+	uint32_t num_to_send = 0;
+	uint16_t num_tx = 0;
+
+	if (unlikely(!DPAA2_PER_LCORE_DPIO)) {
+		ret = dpaa2_affine_qbman_swp();
+		if (ret) {
+			DPAA2_QDMA_ERR(
+				"Failed to allocate IO portal, tid: %d\n",
+				rte_gettid());
+			return 0;
+		}
+	}
+	swp = DPAA2_PER_LCORE_PORTAL;
+
+	txq = &(dpdmai_dev->tx_queue[txq_id]);
+
+	/* Prepare enqueue descriptor */
+	qbman_eq_desc_clear(&eqdesc);
+	qbman_eq_desc_set_fq(&eqdesc, txq->fqid);
+	qbman_eq_desc_set_no_orp(&eqdesc, 0);
+	qbman_eq_desc_set_response(&eqdesc, 0, 0);
+
+	memset(fd, 0, RTE_QDMA_BURST_NB_MAX * sizeof(struct qbman_fd));
+
+	while (nb_jobs > 0) {
+		uint32_t loop;
+
+		num_to_send = (nb_jobs > dpaa2_eqcr_size) ?
+			dpaa2_eqcr_size : nb_jobs;
+
+		for (loop = 0; loop < num_to_send; loop++) {
+			ret = dpdmai_dev_set_fd(dpdmai_dev->qdma_dev, &fd[loop],
+						job[num_tx], rbp, vq_id);
+			if (ret < 0) {
+				/* Set nb_jobs to loop, so outer while loop
+				 * breaks out.
+				 */
+				nb_jobs = loop;
+				break;
+			}
+
+			num_tx++;
+		}
+
+		/* Enqueue the packet to the QBMAN */
+		uint32_t enqueue_loop = 0, retry_count = 0;
+		while (enqueue_loop < loop) {
+			ret = qbman_swp_enqueue_multiple(swp,
+						&eqdesc,
+						&fd[enqueue_loop],
+						NULL,
+						loop - enqueue_loop);
+			if (unlikely(ret < 0)) {
+				retry_count++;
+				if (retry_count > DPAA2_MAX_TX_RETRY_COUNT)
+					return num_tx - (loop - enqueue_loop);
+			} else {
+				enqueue_loop += ret;
+				retry_count = 0;
+			}
+		}
+		nb_jobs -= loop;
+	}
+	return num_tx;
+}
+
+static int
+dpaa2_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 rte_qdma_enqdeq *e_context = (struct rte_qdma_enqdeq *)context;
+	struct qdma_virt_queue *qdma_vq = &qdma_vqs[e_context->vq_id];
+	struct qdma_hw_queue *qdma_pq = qdma_vq->hw_queue;
+	struct dpaa2_dpdmai_dev *dpdmai_dev = qdma_pq->dpdmai_dev;
+	int ret;
+
+	/* Return error in case of wrong lcore_id */
+	if (rte_lcore_id() != qdma_vq->lcore_id) {
+		DPAA2_QDMA_ERR("QDMA enqueue for vqid %d on wrong core",
+				e_context->vq_id);
+		return -EINVAL;
+	}
+
+	ret = dpdmai_dev_enqueue_multi(dpdmai_dev,
+				 qdma_pq->queue_id,
+				 e_context->vq_id,
+				 &qdma_vq->rbp,
+				 e_context->job,
+				 nb_jobs);
+	if (ret < 0) {
+		DPAA2_QDMA_ERR("DPDMAI device enqueue failed: %d", ret);
+		return ret;
+	}
+
+	qdma_vq->num_enqueues += ret;
+
+	return ret;
+}
+
+/* Function to receive a QDMA job for a given device and queue*/
+static int
+dpdmai_dev_dequeue_multijob_prefetch(
+			struct dpaa2_dpdmai_dev *dpdmai_dev,
+			uint16_t rxq_id,
+			uint16_t *vq_id,
+			struct rte_qdma_job **job,
+			uint16_t nb_jobs)
+{
+	struct dpaa2_queue *rxq;
+	struct qbman_result *dq_storage, *dq_storage1 = NULL;
+	struct qbman_pull_desc pulldesc;
+	struct qbman_swp *swp;
+	struct queue_storage_info_t *q_storage;
+	uint32_t fqid;
+	uint8_t status, pending;
+	uint8_t num_rx = 0;
+	const struct qbman_fd *fd;
+	uint16_t vqid;
+	int ret, pull_size;
+
+	if (unlikely(!DPAA2_PER_LCORE_DPIO)) {
+		ret = dpaa2_affine_qbman_swp();
+		if (ret) {
+			DPAA2_QDMA_ERR(
+				"Failed to allocate IO portal, tid: %d\n",
+				rte_gettid());
+			return 0;
+		}
+	}
+	swp = DPAA2_PER_LCORE_PORTAL;
+
+	pull_size = (nb_jobs > dpaa2_dqrr_size) ? dpaa2_dqrr_size : nb_jobs;
+	rxq = &(dpdmai_dev->rx_queue[rxq_id]);
+	fqid = rxq->fqid;
+	q_storage = rxq->q_storage;
+
+	if (unlikely(!q_storage->active_dqs)) {
+		q_storage->toggle = 0;
+		dq_storage = q_storage->dq_storage[q_storage->toggle];
+		q_storage->last_num_pkts = pull_size;
+		qbman_pull_desc_clear(&pulldesc);
+		qbman_pull_desc_set_numframes(&pulldesc,
+					      q_storage->last_num_pkts);
+		qbman_pull_desc_set_fq(&pulldesc, fqid);
+		qbman_pull_desc_set_storage(&pulldesc, dq_storage,
+				(size_t)(DPAA2_VADDR_TO_IOVA(dq_storage)), 1);
+		if (check_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index)) {
+			while (!qbman_check_command_complete(
+			       get_swp_active_dqs(
+			       DPAA2_PER_LCORE_DPIO->index)))
+				;
+			clear_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index);
+		}
+		while (1) {
+			if (qbman_swp_pull(swp, &pulldesc)) {
+				DPAA2_QDMA_DP_WARN(
+					"VDQ command not issued.QBMAN busy\n");
+					/* Portal was busy, try again */
+				continue;
+			}
+			break;
+		}
+		q_storage->active_dqs = dq_storage;
+		q_storage->active_dpio_id = DPAA2_PER_LCORE_DPIO->index;
+		set_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index,
+				   dq_storage);
+	}
+
+	dq_storage = q_storage->active_dqs;
+	rte_prefetch0((void *)(size_t)(dq_storage));
+	rte_prefetch0((void *)(size_t)(dq_storage + 1));
+
+	/* Prepare next pull descriptor. This will give space for the
+	 * prefething done on DQRR entries
+	 */
+	q_storage->toggle ^= 1;
+	dq_storage1 = q_storage->dq_storage[q_storage->toggle];
+	qbman_pull_desc_clear(&pulldesc);
+	qbman_pull_desc_set_numframes(&pulldesc, pull_size);
+	qbman_pull_desc_set_fq(&pulldesc, fqid);
+	qbman_pull_desc_set_storage(&pulldesc, dq_storage1,
+		(size_t)(DPAA2_VADDR_TO_IOVA(dq_storage1)), 1);
+
+	/* Check if the previous issued command is completed.
+	 * Also seems like the SWP is shared between the Ethernet Driver
+	 * and the SEC driver.
+	 */
+	while (!qbman_check_command_complete(dq_storage))
+		;
+	if (dq_storage == get_swp_active_dqs(q_storage->active_dpio_id))
+		clear_swp_active_dqs(q_storage->active_dpio_id);
+
+	pending = 1;
+
+	do {
+		/* Loop until the dq_storage is updated with
+		 * new token by QBMAN
+		 */
+		while (!qbman_check_new_result(dq_storage))
+			;
+		rte_prefetch0((void *)((size_t)(dq_storage + 2)));
+		/* Check whether Last Pull command is Expired and
+		 * setting Condition for Loop termination
+		 */
+		if (qbman_result_DQ_is_pull_complete(dq_storage)) {
+			pending = 0;
+			/* Check for valid frame. */
+			status = qbman_result_DQ_flags(dq_storage);
+			if (unlikely((status & QBMAN_DQ_STAT_VALIDFRAME) == 0))
+				continue;
+		}
+		fd = qbman_result_DQ_fd(dq_storage);
+
+		vqid = dpdmai_dev_get_job(dpdmai_dev->qdma_dev, fd,
+					  &job[num_rx]);
+		if (vq_id)
+			vq_id[num_rx] = vqid;
+
+		dq_storage++;
+		num_rx++;
+	} while (pending);
+
+	if (check_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index)) {
+		while (!qbman_check_command_complete(
+		       get_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index)))
+			;
+		clear_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index);
+	}
+	/* issue a volatile dequeue command for next pull */
+	while (1) {
+		if (qbman_swp_pull(swp, &pulldesc)) {
+			DPAA2_QDMA_DP_WARN("VDQ command is not issued."
+					  "QBMAN is busy (2)\n");
+			continue;
+		}
+		break;
+	}
+
+	q_storage->active_dqs = dq_storage1;
+	q_storage->active_dpio_id = DPAA2_PER_LCORE_DPIO->index;
+	set_swp_active_dqs(DPAA2_PER_LCORE_DPIO->index, dq_storage1);
+
+	return num_rx;
+}
+
+static int
+dpdmai_dev_dequeue_multijob_no_prefetch(
+		struct dpaa2_dpdmai_dev *dpdmai_dev,
+		uint16_t rxq_id,
+		uint16_t *vq_id,
+		struct rte_qdma_job **job,
+		uint16_t nb_jobs)
+{
+	struct dpaa2_queue *rxq;
+	struct qbman_result *dq_storage;
+	struct qbman_pull_desc pulldesc;
+	struct qbman_swp *swp;
+	uint32_t fqid;
+	uint8_t status, pending;
+	uint8_t num_rx = 0;
+	const struct qbman_fd *fd;
+	uint16_t vqid;
+	int ret, next_pull = nb_jobs, num_pulled = 0;
+
+	if (unlikely(!DPAA2_PER_LCORE_DPIO)) {
+		ret = dpaa2_affine_qbman_swp();
+		if (ret) {
+			DPAA2_QDMA_ERR(
+				"Failed to allocate IO portal, tid: %d\n",
+				rte_gettid());
+			return 0;
+		}
+	}
+	swp = DPAA2_PER_LCORE_PORTAL;
+
+	rxq = &(dpdmai_dev->rx_queue[rxq_id]);
+	fqid = rxq->fqid;
+
+	do {
+		dq_storage = rxq->q_storage->dq_storage[0];
+		/* Prepare dequeue descriptor */
+		qbman_pull_desc_clear(&pulldesc);
+		qbman_pull_desc_set_fq(&pulldesc, fqid);
+		qbman_pull_desc_set_storage(&pulldesc, dq_storage,
+			(uint64_t)(DPAA2_VADDR_TO_IOVA(dq_storage)), 1);
+
+		if (next_pull > dpaa2_dqrr_size) {
+			qbman_pull_desc_set_numframes(&pulldesc,
+					dpaa2_dqrr_size);
+			next_pull -= dpaa2_dqrr_size;
+		} else {
+			qbman_pull_desc_set_numframes(&pulldesc, next_pull);
+			next_pull = 0;
+		}
+
+		while (1) {
+			if (qbman_swp_pull(swp, &pulldesc)) {
+				DPAA2_QDMA_DP_WARN("VDQ command not issued. QBMAN busy");
+				/* Portal was busy, try again */
+				continue;
+			}
+			break;
+		}
+
+		rte_prefetch0((void *)((size_t)(dq_storage + 1)));
+		/* Check if the previous issued command is completed. */
+		while (!qbman_check_command_complete(dq_storage))
+			;
+
+		num_pulled = 0;
+		pending = 1;
+
+		do {
+			/* Loop until dq_storage is updated
+			 * with new token by QBMAN
+			 */
+			while (!qbman_check_new_result(dq_storage))
+				;
+			rte_prefetch0((void *)((size_t)(dq_storage + 2)));
+
+			if (qbman_result_DQ_is_pull_complete(dq_storage)) {
+				pending = 0;
+				/* Check for valid frame. */
+				status = qbman_result_DQ_flags(dq_storage);
+				if (unlikely((status &
+					QBMAN_DQ_STAT_VALIDFRAME) == 0))
+					continue;
+			}
+			fd = qbman_result_DQ_fd(dq_storage);
+
+			vqid = dpdmai_dev_get_job(dpdmai_dev->qdma_dev, fd,
+						  &job[num_rx]);
+			if (vq_id)
+				vq_id[num_rx] = vqid;
+
+			dq_storage++;
+			num_rx++;
+			num_pulled++;
+
+		} while (pending);
+	/* Last VDQ provided all packets and more packets are requested */
+	} while (next_pull && num_pulled == dpaa2_dqrr_size);
+
+	return num_rx;
+}
+
+static int
+dpaa2_qdma_dequeue(__rte_unused struct rte_rawdev *rawdev,
+		   __rte_unused struct rte_rawdev_buf **buffers,
+		   unsigned int nb_jobs,
+		   rte_rawdev_obj_t cntxt)
+{
+	struct rte_qdma_enqdeq *context = (struct rte_qdma_enqdeq *)cntxt;
+	struct qdma_virt_queue *qdma_vq = &qdma_vqs[context->vq_id];
+	struct qdma_hw_queue *qdma_pq = qdma_vq->hw_queue;
+	struct qdma_virt_queue *temp_qdma_vq;
+	struct dpaa2_dpdmai_dev *dpdmai_dev = qdma_pq->dpdmai_dev;
+	int ret = 0, i;
+	unsigned int ring_count;
+
+	/* Return error in case of wrong lcore_id */
+	if (rte_lcore_id() != (unsigned int)(qdma_vq->lcore_id)) {
+		DPAA2_QDMA_WARN("QDMA dequeue for vqid %d on wrong core",
+				context->vq_id);
+		return -1;
+	}
+
+	/* Only dequeue when there are pending jobs on VQ */
+	if (qdma_vq->num_enqueues == qdma_vq->num_dequeues)
+		return 0;
+
+	if (qdma_vq->num_enqueues < (qdma_vq->num_dequeues + nb_jobs))
+		nb_jobs = (qdma_vq->num_enqueues -  qdma_vq->num_dequeues);
+
+	if (qdma_vq->exclusive_hw_queue) {
+		/* In case of exclusive queue directly fetch from HW queue */
+		ret = dpdmai_dev_dequeue_multijob(dpdmai_dev, qdma_pq->queue_id,
+					 NULL, context->job, nb_jobs);
+		if (ret < 0) {
+			DPAA2_QDMA_ERR(
+				"Dequeue from DPDMAI device failed: %d", ret);
+			return ret;
+		}
+		qdma_vq->num_dequeues += ret;
+	} else {
+		uint16_t temp_vq_id[RTE_QDMA_BURST_NB_MAX];
+		/*
+		 * Get the QDMA completed jobs from the software ring.
+		 * In case they are not available on the ring poke the HW
+		 * to fetch completed jobs from corresponding HW queues
+		 */
+		ring_count = rte_ring_count(qdma_vq->status_ring);
+		if (ring_count < nb_jobs) {
+			/* TODO - How to have right budget */
+			ret = dpdmai_dev_dequeue_multijob(dpdmai_dev,
+					qdma_pq->queue_id,
+					temp_vq_id, context->job, nb_jobs);
+			for (i = 0; i < ret; i++) {
+				temp_qdma_vq = &qdma_vqs[temp_vq_id[i]];
+				rte_ring_enqueue(temp_qdma_vq->status_ring,
+					(void *)(context->job[i]));
+			}
+			ring_count = rte_ring_count(
+					qdma_vq->status_ring);
+		}
+
+		if (ring_count) {
+			/* Dequeue job from the software ring
+			 * to provide to the user
+			 */
+			ret = rte_ring_dequeue_bulk(qdma_vq->status_ring,
+						    (void **)context->job,
+						    ring_count, NULL);
+			if (ret)
+				qdma_vq->num_dequeues += ret;
+		}
+	}
+
+	return ret;
+}
+
+void
 rte_qdma_vq_stats(uint16_t vq_id,
 		  struct rte_qdma_vq_stats *vq_status)
 {
 	struct qdma_virt_queue *qdma_vq = &qdma_vqs[vq_id];
 
-	DPAA2_QDMA_FUNC_TRACE();
-
 	if (qdma_vq->in_use) {
 		vq_status->exclusive_hw_queue = qdma_vq->exclusive_hw_queue;
 		vq_status->lcore_id = qdma_vq->lcore_id;
@@ -362,9 +1109,13 @@ rte_qdma_vq_stats(uint16_t vq_id,
 	}
 }
 
-int __rte_experimental
-rte_qdma_vq_destroy(uint16_t vq_id)
+static int
+dpaa2_qdma_queue_release(struct rte_rawdev *rawdev,
+			 uint16_t vq_id)
 {
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
+
 	struct qdma_virt_queue *qdma_vq = &qdma_vqs[vq_id];
 
 	DPAA2_QDMA_FUNC_TRACE();
@@ -373,7 +1124,7 @@ rte_qdma_vq_destroy(uint16_t vq_id)
 	if (qdma_vq->num_enqueues != qdma_vq->num_dequeues)
 		return -EBUSY;
 
-	rte_spinlock_lock(&qdma_dev.lock);
+	rte_spinlock_lock(&qdma_dev->lock);
 
 	if (qdma_vq->exclusive_hw_queue)
 		free_hw_queue(qdma_vq->hw_queue);
@@ -386,28 +1137,44 @@ rte_qdma_vq_destroy(uint16_t vq_id)
 
 	memset(qdma_vq, 0, sizeof(struct qdma_virt_queue));
 
-	rte_spinlock_lock(&qdma_dev.lock);
+	rte_spinlock_unlock(&qdma_dev->lock);
 
 	return 0;
 }
 
-void __rte_experimental
-rte_qdma_stop(void)
+static void
+dpaa2_qdma_stop(struct rte_rawdev *rawdev)
 {
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct qdma_device *qdma_dev = dpdmai_dev->qdma_dev;
+
 	DPAA2_QDMA_FUNC_TRACE();
 
-	qdma_dev.state = 0;
+	qdma_dev->state = 0;
 }
 
-void __rte_experimental
-rte_qdma_destroy(void)
+static int
+dpaa2_qdma_close(struct rte_rawdev *rawdev)
 {
 	DPAA2_QDMA_FUNC_TRACE();
 
-	rte_qdma_reset();
+	dpaa2_qdma_reset(rawdev);
+
+	return 0;
 }
 
-static const struct rte_rawdev_ops dpaa2_qdma_ops;
+static struct rte_rawdev_ops dpaa2_qdma_ops = {
+	.dev_configure            = dpaa2_qdma_configure,
+	.dev_start                = dpaa2_qdma_start,
+	.dev_stop                 = dpaa2_qdma_stop,
+	.dev_reset                = dpaa2_qdma_reset,
+	.dev_close                = dpaa2_qdma_close,
+	.queue_setup		  = dpaa2_qdma_queue_setup,
+	.queue_release		  = dpaa2_qdma_queue_release,
+	.attr_get		  = dpaa2_qdma_attr_get,
+	.enqueue_bufs		  = dpaa2_qdma_enqueue,
+	.dequeue_bufs		  = dpaa2_qdma_dequeue,
+};
 
 static int
 add_hw_queues_to_list(struct dpaa2_dpdmai_dev *dpdmai_dev)
@@ -429,7 +1196,7 @@ add_hw_queues_to_list(struct dpaa2_dpdmai_dev *dpdmai_dev)
 		queue->queue_id = i;
 
 		TAILQ_INSERT_TAIL(&qdma_queue_list, queue, next);
-		qdma_dev.num_hw_queues++;
+		dpdmai_dev->qdma_dev->num_hw_queues++;
 	}
 
 	return 0;
@@ -460,9 +1227,6 @@ dpaa2_dpdmai_dev_uninit(struct rte_rawdev *rawdev)
 
 	DPAA2_QDMA_FUNC_TRACE();
 
-	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return 0;
-
 	/* Remove HW queues from global list */
 	remove_hw_queues_from_list(dpdmai_dev);
 
@@ -472,7 +1236,7 @@ dpaa2_dpdmai_dev_uninit(struct rte_rawdev *rawdev)
 		DPAA2_QDMA_ERR("dmdmai disable failed");
 
 	/* Set up the DQRR storage for Rx */
-	for (i = 0; i < DPDMAI_PRIO_NUM; i++) {
+	for (i = 0; i < dpdmai_dev->num_queues; i++) {
 		struct dpaa2_queue *rxq = &(dpdmai_dev->rx_queue[i]);
 
 		if (rxq->q_storage) {
@@ -489,6 +1253,43 @@ dpaa2_dpdmai_dev_uninit(struct rte_rawdev *rawdev)
 	return 0;
 }
 
+static int
+check_devargs_handler(__rte_unused const char *key, const char *value,
+		      __rte_unused void *opaque)
+{
+	if (strcmp(value, "1"))
+		return -1;
+
+	return 0;
+}
+
+static int
+dpaa2_get_devargs(struct rte_devargs *devargs, const char *key)
+{
+	struct rte_kvargs *kvlist;
+
+	if (!devargs)
+		return 0;
+
+	kvlist = rte_kvargs_parse(devargs->args, NULL);
+	if (!kvlist)
+		return 0;
+
+	if (!rte_kvargs_count(kvlist, key)) {
+		rte_kvargs_free(kvlist);
+		return 0;
+	}
+
+	if (rte_kvargs_process(kvlist, key,
+			       check_devargs_handler, NULL) < 0) {
+		rte_kvargs_free(kvlist);
+		return 0;
+	}
+	rte_kvargs_free(kvlist);
+
+	return 1;
+}
+
 static int
 dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 {
@@ -501,13 +1302,10 @@ dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 
 	DPAA2_QDMA_FUNC_TRACE();
 
-	/* For secondary processes, the primary has done all the work */
-	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return 0;
-
 	/* Open DPDMAI device */
 	dpdmai_dev->dpdmai_id = dpdmai_id;
-	dpdmai_dev->dpdmai.regs = rte_mcp_ptr_list[MC_PORTAL_INDEX];
+	dpdmai_dev->dpdmai.regs = dpaa2_get_mcp_ptr(MC_PORTAL_INDEX);
+	dpdmai_dev->qdma_dev = &q_dev;
 	ret = dpdmai_open(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
 			  dpdmai_dev->dpdmai_id, &dpdmai_dev->token);
 	if (ret) {
@@ -523,17 +1321,17 @@ dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 			       ret);
 		goto init_err;
 	}
-	dpdmai_dev->num_queues = attr.num_of_priorities;
+	dpdmai_dev->num_queues = attr.num_of_queues;
 
 	/* Set up Rx Queues */
-	for (i = 0; i < attr.num_of_priorities; i++) {
+	for (i = 0; i < dpdmai_dev->num_queues; i++) {
 		struct dpaa2_queue *rxq;
 
 		memset(&rx_queue_cfg, 0, sizeof(struct dpdmai_rx_queue_cfg));
 		ret = dpdmai_set_rx_queue(&dpdmai_dev->dpdmai,
 					  CMD_PRI_LOW,
 					  dpdmai_dev->token,
-					  i, &rx_queue_cfg);
+					  i, 0, &rx_queue_cfg);
 		if (ret) {
 			DPAA2_QDMA_ERR("Setting Rx queue failed with err: %d",
 				       ret);
@@ -560,9 +1358,9 @@ dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 	}
 
 	/* Get Rx and Tx queues FQID's */
-	for (i = 0; i < DPDMAI_PRIO_NUM; i++) {
+	for (i = 0; i < dpdmai_dev->num_queues; i++) {
 		ret = dpdmai_get_rx_queue(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
-					  dpdmai_dev->token, i, &rx_attr);
+					  dpdmai_dev->token, i, 0, &rx_attr);
 		if (ret) {
 			DPAA2_QDMA_ERR("Reading device failed with err: %d",
 				       ret);
@@ -571,7 +1369,7 @@ dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 		dpdmai_dev->rx_queue[i].fqid = rx_attr.fqid;
 
 		ret = dpdmai_get_tx_queue(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
-					  dpdmai_dev->token, i, &tx_attr);
+					  dpdmai_dev->token, i, 0, &tx_attr);
 		if (ret) {
 			DPAA2_QDMA_ERR("Reading device failed with err: %d",
 				       ret);
@@ -594,8 +1392,36 @@ dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
 		DPAA2_QDMA_ERR("Adding H/W queue to list failed");
 		goto init_err;
 	}
+
+	if (dpaa2_get_devargs(rawdev->device->devargs,
+		DPAA2_QDMA_NO_PREFETCH)) {
+		/* If no prefetch is configured. */
+		dpdmai_dev_dequeue_multijob =
+				dpdmai_dev_dequeue_multijob_no_prefetch;
+		DPAA2_QDMA_INFO("No Prefetch RX Mode enabled");
+	} else {
+		dpdmai_dev_dequeue_multijob =
+			dpdmai_dev_dequeue_multijob_prefetch;
+	}
+
+	if (!dpaa2_coherent_no_alloc_cache) {
+		if (dpaa2_svr_family == SVR_LX2160A) {
+			dpaa2_coherent_no_alloc_cache =
+				DPAA2_LX2_COHERENT_NO_ALLOCATE_CACHE;
+			dpaa2_coherent_alloc_cache =
+				DPAA2_LX2_COHERENT_ALLOCATE_CACHE;
+		} else {
+			dpaa2_coherent_no_alloc_cache =
+				DPAA2_COHERENT_NO_ALLOCATE_CACHE;
+			dpaa2_coherent_alloc_cache =
+				DPAA2_COHERENT_ALLOCATE_CACHE;
+		}
+	}
+
 	DPAA2_QDMA_DEBUG("Initialized dpdmai object successfully");
 
+	rte_spinlock_init(&dpdmai_dev->qdma_dev->lock);
+
 	return 0;
 init_err:
 	dpaa2_dpdmai_dev_uninit(rawdev);
@@ -631,6 +1457,13 @@ rte_dpaa2_qdma_probe(struct rte_dpaa2_driver *dpaa2_drv,
 		return ret;
 	}
 
+	/* Reset the QDMA device */
+	ret = dpaa2_qdma_reset(rawdev);
+	if (ret) {
+		DPAA2_QDMA_ERR("Resetting QDMA failed");
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -652,18 +1485,13 @@ rte_dpaa2_qdma_remove(struct rte_dpaa2_device *dpaa2_dev)
 }
 
 static struct rte_dpaa2_driver rte_dpaa2_qdma_pmd = {
+	.drv_flags = RTE_DPAA2_DRV_IOVA_AS_VA,
 	.drv_type = DPAA2_QDMA,
 	.probe = rte_dpaa2_qdma_probe,
 	.remove = rte_dpaa2_qdma_remove,
 };
 
 RTE_PMD_REGISTER_DPAA2(dpaa2_qdma, rte_dpaa2_qdma_pmd);
-
-RTE_INIT(dpaa2_qdma_init_log);
-static void
-dpaa2_qdma_init_log(void)
-{
-	dpaa2_qdma_logtype = rte_log_register("pmd.raw.dpaa2.qdma");
-	if (dpaa2_qdma_logtype >= 0)
-		rte_log_set_level(dpaa2_qdma_logtype, RTE_LOG_INFO);
-}
+RTE_PMD_REGISTER_PARAM_STRING(dpaa2_qdma,
+	"no_prefetch=<int> ");
+RTE_LOG_REGISTER(dpaa2_qdma_logtype, pmd.raw.dpaa2.qdma, INFO);