raw/dpaa2_qdma: introduce the DPAA2 QDMA driver

DPAA2 QDMA driver uses MC DPDMAI object. This driver enables
the user (app) to perform data DMA without involving CPU in
the DMA process

Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>

MAINTAINERS

@@ -843,6 +843,14 @@ F: drivers/event/opdl/
 F: doc/guides/eventdevs/opdl.rst
 
 
+Rawdev Drivers
+--------------
+
+NXP DPAA2 QDMA
+M: Nipun Gupta <nipun.gupta@nxp.com>
+F: drivers/raw/dpaa2_qdma/
+
+
 Packet processing
 -----------------
 

config/common_base

@@ -617,6 +617,11 @@ CONFIG_RTE_LIBRTE_RAWDEV=y
 CONFIG_RTE_RAWDEV_MAX_DEVS=10
 CONFIG_RTE_LIBRTE_PMD_SKELETON_RAWDEV=y
 
+#
+# Compile PMD for NXP DPAA2 QDMA raw device
+#
+CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV=n
+
 #
 # Compile librte_ring
 #

config/common_linuxapp

@@ -38,3 +38,4 @@ CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL=y
 CONFIG_RTE_LIBRTE_DPAA2_PMD=y
 CONFIG_RTE_LIBRTE_PMD_DPAA2_EVENTDEV=y
 CONFIG_RTE_LIBRTE_PMD_DPAA2_SEC=y
+CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV=y

drivers/raw/Makefile

@@ -5,5 +5,8 @@ include $(RTE_SDK)/mk/rte.vars.mk
 
 # DIRS-$(<configuration>) += <directory>
 DIRS-$(CONFIG_RTE_LIBRTE_PMD_SKELETON_RAWDEV) += skeleton_rawdev
+ifeq ($(CONFIG_RTE_EAL_VFIO)$(CONFIG_RTE_LIBRTE_FSLMC_BUS),yy)
+DIRS-$(CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV) += dpaa2_qdma
+endif
 
 include $(RTE_SDK)/mk/rte.subdir.mk

drivers/raw/dpaa2_qdma/Makefile

@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright 2018 NXP
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+#
+# library name
+#
+LIB = librte_pmd_dpaa2_qdma.a
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+CFLAGS += -O3
+CFLAGS += $(WERROR_FLAGS)
+
+CFLAGS += -I$(RTE_SDK)/lib/librte_eal/linuxapp/eal
+CFLAGS += -I$(RTE_SDK)/drivers/bus/fslmc
+CFLAGS += -I$(RTE_SDK)/drivers/bus/fslmc/qbman/include
+
+LDLIBS += -lrte_bus_fslmc
+LDLIBS += -lrte_eal
+LDLIBS += -lrte_mempool
+LDLIBS += -lrte_mempool_dpaa2
+LDLIBS += -lrte_rawdev
+LDLIBS += -lrte_ring
+
+EXPORT_MAP := rte_pmd_dpaa2_qdma_version.map
+
+LIBABIVER := 1
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV) += dpaa2_qdma.c
+
+include $(RTE_SDK)/mk/rte.lib.mk

drivers/raw/dpaa2_qdma/dpaa2_qdma.c

@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 NXP
+ */
+
+#include <string.h>
+
+#include <rte_eal.h>
+#include <rte_fslmc.h>
+#include <rte_atomic.h>
+#include <rte_lcore.h>
+#include <rte_rawdev.h>
+#include <rte_rawdev_pmd.h>
+#include <rte_malloc.h>
+#include <rte_ring.h>
+#include <rte_mempool.h>
+
+#include <mc/fsl_dpdmai.h>
+#include <portal/dpaa2_hw_pvt.h>
+#include <portal/dpaa2_hw_dpio.h>
+
+#include "dpaa2_qdma.h"
+#include "dpaa2_qdma_logs.h"
+
+/* Dynamic log type identifier */
+int dpaa2_qdma_logtype;
+
+/* QDMA device */
+static struct qdma_device qdma_dev;
+
+/* QDMA H/W queues list */
+TAILQ_HEAD(qdma_hw_queue_list, qdma_hw_queue);
+static struct qdma_hw_queue_list qdma_queue_list
+	= TAILQ_HEAD_INITIALIZER(qdma_queue_list);
+
+static const struct rte_rawdev_ops dpaa2_qdma_ops;
+
+static int
+add_hw_queues_to_list(struct dpaa2_dpdmai_dev *dpdmai_dev)
+{
+	struct qdma_hw_queue *queue;
+	int i;
+
+	DPAA2_QDMA_FUNC_TRACE();
+
+	for (i = 0; i < dpdmai_dev->num_queues; i++) {
+		queue = rte_zmalloc(NULL, sizeof(struct qdma_hw_queue), 0);
+		if (!queue) {
+			DPAA2_QDMA_ERR(
+				"Memory allocation failed for QDMA queue");
+			return -ENOMEM;
+		}
+
+		queue->dpdmai_dev = dpdmai_dev;
+		queue->queue_id = i;
+
+		TAILQ_INSERT_TAIL(&qdma_queue_list, queue, next);
+		qdma_dev.num_hw_queues++;
+	}
+
+	return 0;
+}
+
+static void
+remove_hw_queues_from_list(struct dpaa2_dpdmai_dev *dpdmai_dev)
+{
+	struct qdma_hw_queue *queue = NULL;
+	struct qdma_hw_queue *tqueue = NULL;
+
+	DPAA2_QDMA_FUNC_TRACE();
+
+	TAILQ_FOREACH_SAFE(queue, &qdma_queue_list, next, tqueue) {
+		if (queue->dpdmai_dev == dpdmai_dev) {
+			TAILQ_REMOVE(&qdma_queue_list, queue, next);
+			rte_free(queue);
+			queue = NULL;
+		}
+	}
+}
+
+static int
+dpaa2_dpdmai_dev_uninit(struct rte_rawdev *rawdev)
+{
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	int ret, i;
+
+	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);
+
+	ret = dpdmai_disable(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
+			     dpdmai_dev->token);
+	if (ret)
+		DPAA2_QDMA_ERR("dmdmai disable failed");
+
+	/* Set up the DQRR storage for Rx */
+	for (i = 0; i < DPDMAI_PRIO_NUM; i++) {
+		struct dpaa2_queue *rxq = &(dpdmai_dev->rx_queue[i]);
+
+		if (rxq->q_storage) {
+			dpaa2_free_dq_storage(rxq->q_storage);
+			rte_free(rxq->q_storage);
+		}
+	}
+
+	/* Close the device at underlying layer*/
+	ret = dpdmai_close(&dpdmai_dev->dpdmai, CMD_PRI_LOW, dpdmai_dev->token);
+	if (ret)
+		DPAA2_QDMA_ERR("Failure closing dpdmai device");
+
+	return 0;
+}
+
+static int
+dpaa2_dpdmai_dev_init(struct rte_rawdev *rawdev, int dpdmai_id)
+{
+	struct dpaa2_dpdmai_dev *dpdmai_dev = rawdev->dev_private;
+	struct dpdmai_rx_queue_cfg rx_queue_cfg;
+	struct dpdmai_attr attr;
+	struct dpdmai_rx_queue_attr rx_attr;
+	struct dpdmai_tx_queue_attr tx_attr;
+	int ret, i;
+
+	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];
+	ret = dpdmai_open(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
+			  dpdmai_dev->dpdmai_id, &dpdmai_dev->token);
+	if (ret) {
+		DPAA2_QDMA_ERR("dpdmai_open() failed with err: %d", ret);
+		return ret;
+	}
+
+	/* Get DPDMAI attributes */
+	ret = dpdmai_get_attributes(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
+				    dpdmai_dev->token, &attr);
+	if (ret) {
+		DPAA2_QDMA_ERR("dpdmai get attributes failed with err: %d",
+			       ret);
+		goto init_err;
+	}
+	dpdmai_dev->num_queues = attr.num_of_priorities;
+
+	/* Set up Rx Queues */
+	for (i = 0; i < attr.num_of_priorities; 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);
+		if (ret) {
+			DPAA2_QDMA_ERR("Setting Rx queue failed with err: %d",
+				       ret);
+			goto init_err;
+		}
+
+		/* Allocate DQ storage for the DPDMAI Rx queues */
+		rxq = &(dpdmai_dev->rx_queue[i]);
+		rxq->q_storage = rte_malloc("dq_storage",
+					    sizeof(struct queue_storage_info_t),
+					    RTE_CACHE_LINE_SIZE);
+		if (!rxq->q_storage) {
+			DPAA2_QDMA_ERR("q_storage allocation failed");
+			ret = -ENOMEM;
+			goto init_err;
+		}
+
+		memset(rxq->q_storage, 0, sizeof(struct queue_storage_info_t));
+		ret = dpaa2_alloc_dq_storage(rxq->q_storage);
+		if (ret) {
+			DPAA2_QDMA_ERR("dpaa2_alloc_dq_storage failed");
+			goto init_err;
+		}
+	}
+
+	/* Get Rx and Tx queues FQID's */
+	for (i = 0; i < DPDMAI_PRIO_NUM; i++) {
+		ret = dpdmai_get_rx_queue(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
+					  dpdmai_dev->token, i, &rx_attr);
+		if (ret) {
+			DPAA2_QDMA_ERR("Reading device failed with err: %d",
+				       ret);
+			goto init_err;
+		}
+		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);
+		if (ret) {
+			DPAA2_QDMA_ERR("Reading device failed with err: %d",
+				       ret);
+			goto init_err;
+		}
+		dpdmai_dev->tx_queue[i].fqid = tx_attr.fqid;
+	}
+
+	/* Enable the device */
+	ret = dpdmai_enable(&dpdmai_dev->dpdmai, CMD_PRI_LOW,
+			    dpdmai_dev->token);
+	if (ret) {
+		DPAA2_QDMA_ERR("Enabling device failed with err: %d", ret);
+		goto init_err;
+	}
+
+	/* Add the HW queue to the global list */
+	ret = add_hw_queues_to_list(dpdmai_dev);
+	if (ret) {
+		DPAA2_QDMA_ERR("Adding H/W queue to list failed");
+		goto init_err;
+	}
+	DPAA2_QDMA_DEBUG("Initialized dpdmai object successfully");
+
+	return 0;
+init_err:
+	dpaa2_dpdmai_dev_uninit(rawdev);
+	return ret;
+}
+
+static int
+rte_dpaa2_qdma_probe(struct rte_dpaa2_driver *dpaa2_drv,
+		     struct rte_dpaa2_device *dpaa2_dev)
+{
+	struct rte_rawdev *rawdev;
+	int ret;
+
+	DPAA2_QDMA_FUNC_TRACE();
+
+	rawdev = rte_rawdev_pmd_allocate(dpaa2_dev->device.name,
+			sizeof(struct dpaa2_dpdmai_dev),
+			rte_socket_id());
+	if (!rawdev) {
+		DPAA2_QDMA_ERR("Unable to allocate rawdevice");
+		return -EINVAL;
+	}
+
+	dpaa2_dev->rawdev = rawdev;
+	rawdev->dev_ops = &dpaa2_qdma_ops;
+	rawdev->device = &dpaa2_dev->device;
+	rawdev->driver_name = dpaa2_drv->driver.name;
+
+	/* Invoke PMD device initialization function */
+	ret = dpaa2_dpdmai_dev_init(rawdev, dpaa2_dev->object_id);
+	if (ret) {
+		rte_rawdev_pmd_release(rawdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+rte_dpaa2_qdma_remove(struct rte_dpaa2_device *dpaa2_dev)
+{
+	struct rte_rawdev *rawdev = dpaa2_dev->rawdev;
+	int ret;
+
+	DPAA2_QDMA_FUNC_TRACE();
+
+	dpaa2_dpdmai_dev_uninit(rawdev);
+
+	ret = rte_rawdev_pmd_release(rawdev);
+	if (ret)
+		DPAA2_QDMA_ERR("Device cleanup failed");
+
+	return 0;
+}
+
+static struct rte_dpaa2_driver rte_dpaa2_qdma_pmd = {
+	.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);
+}

drivers/raw/dpaa2_qdma/dpaa2_qdma.h

@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 NXP
+ */
+
+#ifndef __DPAA2_QDMA_H__
+#define __DPAA2_QDMA_H__
+
+/**
+ * Represents a QDMA device.
+ * A single QDMA device exists which is combination of multiple DPDMAI rawdev's.
+ */
+struct qdma_device {
+	/** total number of hw queues. */
+	uint16_t num_hw_queues;
+	/**
+	 * Maximum number of hw queues to be alocated per core.
+	 * This is limited by MAX_HW_QUEUE_PER_CORE
+	 */
+	uint16_t max_hw_queues_per_core;
+	/** Maximum number of VQ's */
+	uint16_t max_vqs;
+	/** mode of operation - physical(h/w) or virtual */
+	uint8_t mode;
+	/** Device state - started or stopped */
+	uint8_t state;
+	/** FLE pool for the device */
+	struct rte_mempool *fle_pool;
+	/** FLE pool size */
+	int fle_pool_count;
+	/** A lock to QDMA device whenever required */
+	rte_spinlock_t lock;
+};
+
+/** Represents a QDMA H/W queue */
+struct qdma_hw_queue {
+	/** Pointer to Next instance */
+	TAILQ_ENTRY(qdma_hw_queue) next;
+	/** DPDMAI device to communicate with HW */
+	struct dpaa2_dpdmai_dev *dpdmai_dev;
+	/** queue ID to communicate with HW */
+	uint16_t queue_id;
+	/** Associated lcore id */
+	uint32_t lcore_id;
+	/** Number of users of this hw queue */
+	uint32_t num_users;
+};
+
+/** Represents a DPDMAI raw device */
+struct dpaa2_dpdmai_dev {
+	/** Pointer to Next device instance */
+	TAILQ_ENTRY(dpaa2_qdma_device) next;
+	/** handle to DPDMAI object */
+	struct fsl_mc_io dpdmai;
+	/** HW ID for DPDMAI object */
+	uint32_t dpdmai_id;
+	/** Tocken of this device */
+	uint16_t token;
+	/** Number of queue in this DPDMAI device */
+	uint8_t num_queues;
+	/** RX queues */
+	struct dpaa2_queue rx_queue[DPDMAI_PRIO_NUM];
+	/** TX queues */
+	struct dpaa2_queue tx_queue[DPDMAI_PRIO_NUM];
+};
+
+#endif /* __DPAA2_QDMA_H__ */

drivers/raw/dpaa2_qdma/dpaa2_qdma_logs.h

@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 NXP
+ */
+
+#ifndef __DPAA2_QDMA_LOGS_H__
+#define __DPAA2_QDMA_LOGS_H__
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern int dpaa2_qdma_logtype;
+
+#define DPAA2_QDMA_LOG(level, fmt, args...) \
+	rte_log(RTE_LOG_ ## level, dpaa2_qdma_logtype, "dpaa2_qdma: " \
+		fmt "\n", ## args)
+
+#define DPAA2_QDMA_DEBUG(fmt, args...) \
+	rte_log(RTE_LOG_DEBUG, dpaa2_qdma_logtype, "dpaa2_qdma: %s(): " \
+		fmt "\n", __func__, ## args)
+
+#define DPAA2_QDMA_FUNC_TRACE() DPAA2_QDMA_LOG(DEBUG, ">>")
+
+#define DPAA2_QDMA_INFO(fmt, args...) \
+	DPAA2_QDMA_LOG(INFO, fmt, ## args)
+#define DPAA2_QDMA_ERR(fmt, args...) \
+	DPAA2_QDMA_LOG(ERR, fmt, ## args)
+#define DPAA2_QDMA_WARN(fmt, args...) \
+	DPAA2_QDMA_LOG(WARNING, fmt, ## args)
+
+/* DP Logs, toggled out at compile time if level lower than current level */
+#define DPAA2_QDMA_DP_LOG(level, fmt, args...) \
+	RTE_LOG_DP(level, PMD, "dpaa2_qdma: " fmt "\n", ## args)
+
+#define DPAA2_QDMA_DP_DEBUG(fmt, args...) \
+	DPAA2_QDMA_DP_LOG(DEBUG, fmt, ## args)
+#define DPAA2_QDMA_DP_INFO(fmt, args...) \
+	DPAA2_QDMA_DP_LOG(INFO, fmt, ## args)
+#define DPAA2_QDMA_DP_WARN(fmt, args...) \
+	DPAA2_QDMA_DP_LOG(WARNING, fmt, ## args)
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __DPAA2_QDMA_LOGS_H__ */

drivers/raw/dpaa2_qdma/meson.build

@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright 2018 NXP
+
+deps += ['rawdev', 'mempool_dpaa2', 'ring']
+sources = files('dpaa2_qdma.c')
+
+allow_experimental_apis = true

drivers/raw/dpaa2_qdma/rte_pmd_dpaa2_qdma_version.map

@@ -0,0 +1,4 @@
+EXPERIMENTAL {
+
+	local: *;
+};

drivers/raw/meson.build

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright 2018 NXP
 
-drivers = ['skeleton_rawdev']
+drivers = ['skeleton_rawdev', 'dpaa2_qdma']
 std_deps = ['rawdev']
 config_flag_fmt = 'RTE_LIBRTE_PMD_@0@_RAWDEV'
 driver_name_fmt = 'rte_pmd_@0@'

mk/rte.app.mk

@@ -251,6 +251,9 @@ endif # CONFIG_RTE_LIBRTE_EVENTDEV
 
 ifeq ($(CONFIG_RTE_LIBRTE_RAWDEV),y)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_SKELETON_RAWDEV) += -lrte_pmd_skeleton_rawdev
+ifeq ($(CONFIG_RTE_EAL_VFIO)$(CONFIG_RTE_LIBRTE_FSLMC_BUS),yy)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV) += -lrte_pmd_dpaa2_qdma
+endif # CONFIG_RTE_LIBRTE_FSLMC_BUS
 endif # CONFIG_RTE_LIBRTE_RAWDEV