[dpdk-dev] [PATCH v10 1/5] raw/ntb: introduce ntb rawdev driver

[Xiaoyun Li <xiaoyun.li@intel.com>]

Introduce rawdev driver support for NTB (Non-transparent Bridge) which
can help to connect two separate hosts with each other.

Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
---
 MAINTAINERS                                   |   5 +
 config/common_base                            |   5 +
 doc/guides/rawdevs/index.rst                  |   1 +
 doc/guides/rawdevs/ntb_rawdev.rst             |  22 +
 doc/guides/rel_notes/release_19_08.rst        |   5 +
 drivers/raw/Makefile                          |   1 +
 drivers/raw/meson.build                       |   2 +-
 drivers/raw/ntb_rawdev/Makefile               |  27 +
 drivers/raw/ntb_rawdev/meson.build            |   7 +
 drivers/raw/ntb_rawdev/ntb_rawdev.c           | 488 ++++++++++++++++++
 drivers/raw/ntb_rawdev/ntb_rawdev.h           | 164 ++++++
 .../ntb_rawdev/rte_pmd_ntb_rawdev_version.map |   4 +
 mk/rte.app.mk                                 |   1 +
 13 files changed, 731 insertions(+), 1 deletion(-)
 create mode 100644 doc/guides/rawdevs/ntb_rawdev.rst
 create mode 100644 drivers/raw/ntb_rawdev/Makefile
 create mode 100644 drivers/raw/ntb_rawdev/meson.build
 create mode 100644 drivers/raw/ntb_rawdev/ntb_rawdev.c
 create mode 100644 drivers/raw/ntb_rawdev/ntb_rawdev.h
 create mode 100644 drivers/raw/ntb_rawdev/rte_pmd_ntb_rawdev_version.map

diff --git a/MAINTAINERS b/MAINTAINERS
index 97a009e43..9303624c6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1094,6 +1094,11 @@ M: Nipun Gupta <nipun.gupta@nxp.com>
 F: drivers/raw/dpaa2_cmdif/
 F: doc/guides/rawdevs/dpaa2_cmdif.rst
 
+NTB Rawdev
+M: Xiaoyun Li <xiaoyun.li@intel.com>
+M: Jingjing Wu <jingjing.wu@intel.com>
+F: drivers/raw/ntb_rawdev/
+F: doc/guides/rawdevs/ntb_rawdev.rst
 
 Packet processing
 -----------------
diff --git a/config/common_base b/config/common_base
index e700bf1e7..d3f2b941a 100644
--- a/config/common_base
+++ b/config/common_base
@@ -752,6 +752,11 @@ CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV=n
 #
 CONFIG_RTE_LIBRTE_PMD_IFPGA_RAWDEV=y
 
+#
+# Compile PMD for NTB raw device
+#
+CONFIG_RTE_LIBRTE_PMD_NTB_RAWDEV=y
+
 #
 # Compile librte_ring
 #
diff --git a/doc/guides/rawdevs/index.rst b/doc/guides/rawdevs/index.rst
index 7c3bd9586..cf6fcb06b 100644
--- a/doc/guides/rawdevs/index.rst
+++ b/doc/guides/rawdevs/index.rst
@@ -14,3 +14,4 @@ application through rawdev API.
     dpaa2_cmdif
     dpaa2_qdma
     ifpga_rawdev
+    ntb_rawdev
diff --git a/doc/guides/rawdevs/ntb_rawdev.rst b/doc/guides/rawdevs/ntb_rawdev.rst
new file mode 100644
index 000000000..ebc4dbc1e
--- /dev/null
+++ b/doc/guides/rawdevs/ntb_rawdev.rst
@@ -0,0 +1,22 @@
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright(c) 2018 Intel Corporation.
+
+NTB Rawdev Driver
+=================
+
+The ``ntb`` rawdev driver provides a non-transparent bridge between two
+separate hosts so that they can communicate with each other. Thus, many
+user cases can benefit from this, such as fault tolerance and visual
+acceleration.
+
+Build Options
+-------------
+
+- ``CONFIG_RTE_LIBRTE_PMD_NTB_RAWDEV`` (default ``y``)
+
+   Toggle compilation of the ``ntb_rawdev`` driver.
+
+Limitation
+----------
+
+- The FIFO hasn't been introduced and will come in 19.11 release.
diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst
index 8e0b13e05..4c07a0210 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -126,6 +126,11 @@ New Features
   Added telemetry mode to l3fwd-power application to report
   application level busyness, empty and full polls of rte_eth_rx_burst().
 
+* **Introduced NTB PMD.**
+
+  Added a PMD for Intel NTB (Non-transparent Bridge). This PMD implemented
+  handshake between two seperate hosts and can share local memory for peer
+  host to directly access.
 
 Removed Items
 -------------
diff --git a/drivers/raw/Makefile b/drivers/raw/Makefile
index 8e29b4a56..efe61f451 100644
--- a/drivers/raw/Makefile
+++ b/drivers/raw/Makefile
@@ -10,5 +10,6 @@ DIRS-$(CONFIG_RTE_LIBRTE_PMD_DPAA2_CMDIF_RAWDEV) += dpaa2_cmdif
 DIRS-$(CONFIG_RTE_LIBRTE_PMD_DPAA2_QDMA_RAWDEV) += dpaa2_qdma
 endif
 DIRS-$(CONFIG_RTE_LIBRTE_PMD_IFPGA_RAWDEV) += ifpga_rawdev
+DIRS-$(CONFIG_RTE_LIBRTE_PMD_NTB_RAWDEV) += ntb_rawdev
 
 include $(RTE_SDK)/mk/rte.subdir.mk
diff --git a/drivers/raw/meson.build b/drivers/raw/meson.build
index a61cdccef..6abf659d0 100644
--- a/drivers/raw/meson.build
+++ b/drivers/raw/meson.build
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright 2018 NXP
 
-drivers = ['skeleton_rawdev', 'dpaa2_cmdif', 'dpaa2_qdma', 'ifpga_rawdev']
+drivers = ['skeleton_rawdev', 'dpaa2_cmdif', 'dpaa2_qdma', 'ifpga_rawdev', 'ntb_rawdev']
 std_deps = ['rawdev']
 config_flag_fmt = 'RTE_LIBRTE_PMD_@0@_RAWDEV'
 driver_name_fmt = 'rte_pmd_@0@'
diff --git a/drivers/raw/ntb_rawdev/Makefile b/drivers/raw/ntb_rawdev/Makefile
new file mode 100644
index 000000000..da87a4610
--- /dev/null
+++ b/drivers/raw/ntb_rawdev/Makefile
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2019 Intel Corporation
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+#
+# library name
+#
+LIB = librte_pmd_ntb_rawdev.a
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+CFLAGS += -O3
+CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool
+LDLIBS += -lrte_pci -lrte_bus_pci
+LDLIBS += -lrte_rawdev
+
+EXPORT_MAP := rte_pmd_ntb_rawdev_version.map
+
+LIBABIVER := 1
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_NTB_RAWDEV) += ntb_rawdev.c
+
+include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/raw/ntb_rawdev/meson.build b/drivers/raw/ntb_rawdev/meson.build
new file mode 100644
index 000000000..ca905049d
--- /dev/null
+++ b/drivers/raw/ntb_rawdev/meson.build
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2019 Intel Corporation.
+
+deps += ['rawdev', 'mbuf', 'mempool',
+	 'pci', 'bus_pci']
+sources = files('ntb_rawdev.c')
+allow_experimental_apis = true
diff --git a/drivers/raw/ntb_rawdev/ntb_rawdev.c b/drivers/raw/ntb_rawdev/ntb_rawdev.c
new file mode 100644
index 000000000..07ad81d44
--- /dev/null
+++ b/drivers/raw/ntb_rawdev/ntb_rawdev.c
@@ -0,0 +1,488 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation.
+ */
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+
+#include <rte_common.h>
+#include <rte_lcore.h>
+#include <rte_cycles.h>
+#include <rte_eal.h>
+#include <rte_log.h>
+#include <rte_pci.h>
+#include <rte_bus_pci.h>
+#include <rte_memzone.h>
+#include <rte_memcpy.h>
+#include <rte_rawdev.h>
+#include <rte_rawdev_pmd.h>
+
+#include "ntb_rawdev.h"
+
+int ntb_logtype;
+
+static const struct rte_pci_id pci_id_ntb_map[] = {
+	{ .vendor_id = 0, /* sentinel */ },
+};
+
+static void
+ntb_queue_conf_get(struct rte_rawdev *dev __rte_unused,
+		   uint16_t queue_id __rte_unused,
+		   rte_rawdev_obj_t queue_conf __rte_unused)
+{
+}
+
+static int
+ntb_queue_setup(struct rte_rawdev *dev __rte_unused,
+		uint16_t queue_id __rte_unused,
+		rte_rawdev_obj_t queue_conf __rte_unused)
+{
+	return 0;
+}
+
+static int
+ntb_queue_release(struct rte_rawdev *dev __rte_unused,
+		  uint16_t queue_id __rte_unused)
+{
+	return 0;
+}
+
+static uint16_t
+ntb_queue_count(struct rte_rawdev *dev)
+{
+	struct ntb_hw *hw = dev->dev_private;
+	return hw->queue_pairs;
+}
+
+static int
+ntb_enqueue_bufs(struct rte_rawdev *dev,
+		 struct rte_rawdev_buf **buffers,
+		 unsigned int count,
+		 rte_rawdev_obj_t context)
+{
+	RTE_SET_USED(dev);
+	RTE_SET_USED(buffers);
+	RTE_SET_USED(count);
+	RTE_SET_USED(context);
+
+	return 0;
+}
+
+static int
+ntb_dequeue_bufs(struct rte_rawdev *dev,
+		 struct rte_rawdev_buf **buffers,
+		 unsigned int count,
+		 rte_rawdev_obj_t context)
+{
+	RTE_SET_USED(dev);
+	RTE_SET_USED(buffers);
+	RTE_SET_USED(count);
+	RTE_SET_USED(context);
+
+	return 0;
+}
+
+static void
+ntb_dev_info_get(struct rte_rawdev *dev, rte_rawdev_obj_t dev_info)
+{
+	struct ntb_hw *hw = dev->dev_private;
+	struct ntb_attr *ntb_attrs = dev_info;
+
+	strncpy(ntb_attrs[NTB_TOPO_ID].name, NTB_TOPO_NAME, NTB_ATTR_NAME_LEN);
+	switch (hw->topo) {
+	case NTB_TOPO_B2B_DSD:
+		strncpy(ntb_attrs[NTB_TOPO_ID].value, "B2B DSD",
+			NTB_ATTR_VAL_LEN);
+		break;
+	case NTB_TOPO_B2B_USD:
+		strncpy(ntb_attrs[NTB_TOPO_ID].value, "B2B USD",
+			NTB_ATTR_VAL_LEN);
+		break;
+	default:
+		strncpy(ntb_attrs[NTB_TOPO_ID].value, "Unsupported",
+			NTB_ATTR_VAL_LEN);
+	}
+
+	strncpy(ntb_attrs[NTB_LINK_STATUS_ID].name, NTB_LINK_STATUS_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_LINK_STATUS_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->link_status);
+
+	strncpy(ntb_attrs[NTB_SPEED_ID].name, NTB_SPEED_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_SPEED_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->link_speed);
+
+	strncpy(ntb_attrs[NTB_WIDTH_ID].name, NTB_WIDTH_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_WIDTH_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->link_width);
+
+	strncpy(ntb_attrs[NTB_MW_CNT_ID].name, NTB_MW_CNT_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_MW_CNT_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->mw_cnt);
+
+	strncpy(ntb_attrs[NTB_DB_CNT_ID].name, NTB_DB_CNT_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_DB_CNT_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->db_cnt);
+
+	strncpy(ntb_attrs[NTB_SPAD_CNT_ID].name, NTB_SPAD_CNT_NAME,
+		NTB_ATTR_NAME_LEN);
+	snprintf(ntb_attrs[NTB_SPAD_CNT_ID].value, NTB_ATTR_VAL_LEN,
+		 "%d", hw->spad_cnt);
+}
+
+static int
+ntb_dev_configure(const struct rte_rawdev *dev __rte_unused,
+		  rte_rawdev_obj_t config __rte_unused)
+{
+	return 0;
+}
+
+static int
+ntb_dev_start(struct rte_rawdev *dev)
+{
+	/* TODO: init queues and start queues. */
+	dev->started = 1;
+
+	return 0;
+}
+
+static void
+ntb_dev_stop(struct rte_rawdev *dev)
+{
+	/* TODO: stop rx/tx queues. */
+	dev->started = 0;
+}
+
+static int
+ntb_dev_close(struct rte_rawdev *dev)
+{
+	int ret = 0;
+
+	if (dev->started)
+		ntb_dev_stop(dev);
+
+	/* TODO: free queues. */
+
+	return ret;
+}
+
+static int
+ntb_dev_reset(struct rte_rawdev *rawdev __rte_unused)
+{
+	return 0;
+}
+
+static int
+ntb_attr_set(struct rte_rawdev *dev, const char *attr_name,
+				 uint64_t attr_value)
+{
+	struct ntb_hw *hw = dev->dev_private;
+	int index = 0;
+
+	if (dev == NULL || attr_name == NULL) {
+		NTB_LOG(ERR, "Invalid arguments for setting attributes");
+		return -EINVAL;
+	}
+
+	if (!strncmp(attr_name, NTB_SPAD_USER, NTB_SPAD_USER_LEN)) {
+		if (hw->ntb_ops->spad_write == NULL)
+			return -ENOTSUP;
+		index = atoi(&attr_name[NTB_SPAD_USER_LEN]);
+		(*hw->ntb_ops->spad_write)(dev, hw->spad_user_list[index],
+					   1, attr_value);
+		NTB_LOG(INFO, "Set attribute (%s) Value (%" PRIu64 ")",
+			attr_name, attr_value);
+		return 0;
+	}
+
+	/* Attribute not found. */
+	NTB_LOG(ERR, "Attribute not found.");
+	return -EINVAL;
+}
+
+static int
+ntb_attr_get(struct rte_rawdev *dev, const char *attr_name,
+				 uint64_t *attr_value)
+{
+	struct ntb_hw *hw = dev->dev_private;
+	int index = 0;
+
+	if (dev == NULL || attr_name == NULL || attr_value == NULL) {
+		NTB_LOG(ERR, "Invalid arguments for getting attributes");
+		return -EINVAL;
+	}
+
+	if (!strncmp(attr_name, NTB_TOPO_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->topo;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_LINK_STATUS_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->link_status;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_SPEED_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->link_speed;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_WIDTH_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->link_width;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_MW_CNT_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->mw_cnt;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_DB_CNT_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->db_cnt;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_SPAD_CNT_NAME, NTB_ATTR_NAME_LEN)) {
+		*attr_value = hw->spad_cnt;
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	if (!strncmp(attr_name, NTB_SPAD_USER, NTB_SPAD_USER_LEN)) {
+		if (hw->ntb_ops->spad_read == NULL)
+			return -ENOTSUP;
+		index = atoi(&attr_name[NTB_SPAD_USER_LEN]);
+		*attr_value = (*hw->ntb_ops->spad_read)(dev,
+				hw->spad_user_list[index], 0);
+		NTB_LOG(INFO, "Attribute (%s) Value (%" PRIu64 ")",
+			attr_name, *attr_value);
+		return 0;
+	}
+
+	/* Attribute not found. */
+	NTB_LOG(ERR, "Attribute not found.");
+	return -EINVAL;
+}
+
+static int
+ntb_xstats_get(const struct rte_rawdev *dev __rte_unused,
+	       const unsigned int ids[] __rte_unused,
+	       uint64_t values[] __rte_unused,
+	       unsigned int n __rte_unused)
+{
+	return 0;
+}
+
+static int
+ntb_xstats_get_names(const struct rte_rawdev *dev __rte_unused,
+		     struct rte_rawdev_xstats_name *xstats_names __rte_unused,
+		     unsigned int size __rte_unused)
+{
+	return 0;
+}
+
+static uint64_t
+ntb_xstats_get_by_name(const struct rte_rawdev *dev __rte_unused,
+		       const char *name __rte_unused,
+		       unsigned int *id __rte_unused)
+{
+	return 0;
+}
+
+static int
+ntb_xstats_reset(struct rte_rawdev *dev __rte_unused,
+		 const uint32_t ids[] __rte_unused,
+		 uint32_t nb_ids __rte_unused)
+{
+	return 0;
+}
+
+static const struct rte_rawdev_ops ntb_rawdev_ops = {
+	.dev_info_get         = ntb_dev_info_get,
+	.dev_configure        = ntb_dev_configure,
+	.dev_start            = ntb_dev_start,
+	.dev_stop             = ntb_dev_stop,
+	.dev_close            = ntb_dev_close,
+	.dev_reset            = ntb_dev_reset,
+
+	.queue_def_conf       = ntb_queue_conf_get,
+	.queue_setup          = ntb_queue_setup,
+	.queue_release        = ntb_queue_release,
+	.queue_count          = ntb_queue_count,
+
+	.enqueue_bufs         = ntb_enqueue_bufs,
+	.dequeue_bufs         = ntb_dequeue_bufs,
+
+	.attr_get             = ntb_attr_get,
+	.attr_set             = ntb_attr_set,
+
+	.xstats_get           = ntb_xstats_get,
+	.xstats_get_names     = ntb_xstats_get_names,
+	.xstats_get_by_name   = ntb_xstats_get_by_name,
+	.xstats_reset         = ntb_xstats_reset,
+};
+
+static int
+ntb_init_hw(struct rte_rawdev *dev, struct rte_pci_device *pci_dev)
+{
+	struct ntb_hw *hw = dev->dev_private;
+	int ret;
+
+	hw->pci_dev = pci_dev;
+	hw->peer_dev_up = 0;
+	hw->link_status = NTB_LINK_DOWN;
+	hw->link_speed = NTB_SPEED_NONE;
+	hw->link_width = NTB_WIDTH_NONE;
+
+	switch (pci_dev->id.device_id) {
+	default:
+		NTB_LOG(ERR, "Not supported device.");
+		return -EINVAL;
+	}
+
+	if (hw->ntb_ops->ntb_dev_init == NULL)
+		return -ENOTSUP;
+	ret = (*hw->ntb_ops->ntb_dev_init)(dev);
+	if (ret) {
+		NTB_LOG(ERR, "Unable to init ntb dev.");
+		return ret;
+	}
+
+	if (hw->ntb_ops->set_link == NULL)
+		return -ENOTSUP;
+	ret = (*hw->ntb_ops->set_link)(dev, 1);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int
+ntb_rawdev_create(struct rte_pci_device *pci_dev, int socket_id)
+{
+	char name[RTE_RAWDEV_NAME_MAX_LEN];
+	struct rte_rawdev *rawdev = NULL;
+	int ret;
+
+	if (pci_dev == NULL) {
+		NTB_LOG(ERR, "Invalid pci_dev.");
+		ret = -EINVAL;
+	}
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, RTE_RAWDEV_NAME_MAX_LEN, "NTB:%x:%02x.%x",
+		 pci_dev->addr.bus, pci_dev->addr.devid,
+		 pci_dev->addr.function);
+
+	NTB_LOG(INFO, "Init %s on NUMA node %d", name, socket_id);
+
+	/* Allocate device structure. */
+	rawdev = rte_rawdev_pmd_allocate(name, sizeof(struct ntb_hw),
+					 socket_id);
+	if (rawdev == NULL) {
+		NTB_LOG(ERR, "Unable to allocate rawdev.");
+		ret = -EINVAL;
+	}
+
+	rawdev->dev_ops = &ntb_rawdev_ops;
+	rawdev->device = &pci_dev->device;
+	rawdev->driver_name = pci_dev->driver->driver.name;
+
+	ret = ntb_init_hw(rawdev, pci_dev);
+	if (ret < 0) {
+		NTB_LOG(ERR, "Unable to init ntb hw.");
+		goto fail;
+	}
+
+	return ret;
+
+fail:
+	if (rawdev)
+		rte_rawdev_pmd_release(rawdev);
+
+	return ret;
+}
+
+static int
+ntb_rawdev_destroy(struct rte_pci_device *pci_dev)
+{
+	char name[RTE_RAWDEV_NAME_MAX_LEN];
+	struct rte_rawdev *rawdev;
+	int ret;
+
+	if (pci_dev == NULL) {
+		NTB_LOG(ERR, "Invalid pci_dev.");
+		ret = -EINVAL;
+		return ret;
+	}
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, RTE_RAWDEV_NAME_MAX_LEN, "NTB:%x:%02x.%x",
+		 pci_dev->addr.bus, pci_dev->addr.devid,
+		 pci_dev->addr.function);
+
+	NTB_LOG(INFO, "Closing %s on NUMA node %d", name, rte_socket_id());
+
+	rawdev = rte_rawdev_pmd_get_named_dev(name);
+	if (rawdev == NULL) {
+		NTB_LOG(ERR, "Invalid device name (%s)", name);
+		ret = -EINVAL;
+		return ret;
+	}
+
+	ret = rte_rawdev_pmd_release(rawdev);
+	if (ret)
+		NTB_LOG(ERR, "Failed to destroy ntb rawdev.");
+
+	return ret;
+}
+
+static int
+ntb_rawdev_probe(struct rte_pci_driver *pci_drv __rte_unused,
+	struct rte_pci_device *pci_dev)
+{
+	return ntb_rawdev_create(pci_dev, rte_socket_id());
+}
+
+static int
+ntb_rawdev_remove(struct rte_pci_device *pci_dev)
+{
+	return ntb_rawdev_destroy(pci_dev);
+}
+
+
+static struct rte_pci_driver rte_ntb_pmd = {
+	.id_table = pci_id_ntb_map,
+	.drv_flags = RTE_PCI_DRV_NEED_MAPPING,
+	.probe = ntb_rawdev_probe,
+	.remove = ntb_rawdev_remove,
+};
+
+RTE_PMD_REGISTER_PCI(raw_ntb, rte_ntb_pmd);
+RTE_PMD_REGISTER_PCI_TABLE(raw_ntb, pci_id_ntb_map);
+RTE_PMD_REGISTER_KMOD_DEP(raw_ntb, "* igb_uio | uio_pci_generic | vfio-pci");
+
+RTE_INIT(ntb_init_log)
+{
+	ntb_logtype = rte_log_register("pmd.raw.ntb");
+	if (ntb_logtype >= 0)
+		rte_log_set_level(ntb_logtype, RTE_LOG_DEBUG);
+}
diff --git a/drivers/raw/ntb_rawdev/ntb_rawdev.h b/drivers/raw/ntb_rawdev/ntb_rawdev.h
new file mode 100644
index 000000000..d355231b0
--- /dev/null
+++ b/drivers/raw/ntb_rawdev/ntb_rawdev.h
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef _NTB_RAWDEV_H_
+#define _NTB_RAWDEV_H_
+
+#include <stdbool.h>
+
+extern int ntb_logtype;
+
+#define NTB_LOG(level, fmt, args...) \
+	rte_log(RTE_LOG_ ## level, ntb_logtype,	"%s(): " fmt "\n", \
+		__func__, ##args)
+
+/* Vendor ID */
+#define NTB_INTEL_VENDOR_ID         0x8086
+
+/* Device IDs */
+#define NTB_INTEL_DEV_ID_B2B_SKX    0x201C
+
+#define NTB_TOPO_NAME               "topo"
+#define NTB_LINK_STATUS_NAME        "link_status"
+#define NTB_SPEED_NAME              "speed"
+#define NTB_WIDTH_NAME              "width"
+#define NTB_MW_CNT_NAME             "mw_count"
+#define NTB_DB_CNT_NAME             "db_count"
+#define NTB_SPAD_CNT_NAME           "spad_count"
+/* Reserved to app to use. */
+#define NTB_SPAD_USER               "spad_user_"
+#define NTB_SPAD_USER_LEN           (sizeof(NTB_SPAD_USER) - 1)
+#define NTB_SPAD_USER_MAX_NUM       10
+#define NTB_ATTR_NAME_LEN           30
+#define NTB_ATTR_VAL_LEN            30
+#define NTB_ATTR_MAX                20
+
+/* NTB Attributes */
+struct ntb_attr {
+	/**< Name of the attribute */
+	char name[NTB_ATTR_NAME_LEN];
+	/**< Value or reference of value of attribute */
+	char value[NTB_ATTR_NAME_LEN];
+};
+
+enum ntb_attr_idx {
+	NTB_TOPO_ID = 0,
+	NTB_LINK_STATUS_ID,
+	NTB_SPEED_ID,
+	NTB_WIDTH_ID,
+	NTB_MW_CNT_ID,
+	NTB_DB_CNT_ID,
+	NTB_SPAD_CNT_ID,
+};
+
+enum ntb_topo {
+	NTB_TOPO_NONE = 0,
+	NTB_TOPO_B2B_USD,
+	NTB_TOPO_B2B_DSD,
+};
+
+enum ntb_link {
+	NTB_LINK_DOWN = 0,
+	NTB_LINK_UP,
+};
+
+enum ntb_speed {
+	NTB_SPEED_NONE = 0,
+	NTB_SPEED_GEN1 = 1,
+	NTB_SPEED_GEN2 = 2,
+	NTB_SPEED_GEN3 = 3,
+	NTB_SPEED_GEN4 = 4,
+};
+
+enum ntb_width {
+	NTB_WIDTH_NONE = 0,
+	NTB_WIDTH_1 = 1,
+	NTB_WIDTH_2 = 2,
+	NTB_WIDTH_4 = 4,
+	NTB_WIDTH_8 = 8,
+	NTB_WIDTH_12 = 12,
+	NTB_WIDTH_16 = 16,
+	NTB_WIDTH_32 = 32,
+};
+
+/* Define spad registers usage. 0 is reserved. */
+enum ntb_spad_idx {
+	SPAD_NUM_MWS = 1,
+	SPAD_NUM_QPS,
+	SPAD_Q_SZ,
+	SPAD_MW0_SZ_H,
+	SPAD_MW0_SZ_L,
+	SPAD_MW1_SZ_H,
+	SPAD_MW1_SZ_L,
+};
+
+/**
+ * NTB device operations
+ * @ntb_dev_init: Init ntb dev.
+ * @get_peer_mw_addr: To get the addr of peer mw[mw_idx].
+ * @mw_set_trans: Set translation of internal memory that remote can access.
+ * @get_link_status: get link status, link speed and link width.
+ * @set_link: Set local side up/down.
+ * @spad_read: Read local/peer spad register val.
+ * @spad_write: Write val to local/peer spad register.
+ * @db_read: Read doorbells status.
+ * @db_clear: Clear local doorbells.
+ * @db_set_mask: Set bits in db mask, preventing db interrpts generated
+ * for those db bits.
+ * @peer_db_set: Set doorbell bit to generate peer interrupt for that bit.
+ * @vector_bind: Bind vector source [intr] to msix vector [msix].
+ */
+struct ntb_dev_ops {
+	int (*ntb_dev_init)(struct rte_rawdev *dev);
+	void *(*get_peer_mw_addr)(struct rte_rawdev *dev, int mw_idx);
+	int (*mw_set_trans)(struct rte_rawdev *dev, int mw_idx,
+			    uint64_t addr, uint64_t size);
+	int (*get_link_status)(struct rte_rawdev *dev);
+	int (*set_link)(struct rte_rawdev *dev, bool up);
+	uint32_t (*spad_read)(struct rte_rawdev *dev, int spad, bool peer);
+	int (*spad_write)(struct rte_rawdev *dev, int spad,
+			  bool peer, uint32_t spad_v);
+	uint64_t (*db_read)(struct rte_rawdev *dev);
+	int (*db_clear)(struct rte_rawdev *dev, uint64_t db_bits);
+	int (*db_set_mask)(struct rte_rawdev *dev, uint64_t db_mask);
+	int (*peer_db_set)(struct rte_rawdev *dev, uint8_t db_bit);
+	int (*vector_bind)(struct rte_rawdev *dev, uint8_t intr, uint8_t msix);
+};
+
+/* ntb private data. */
+struct ntb_hw {
+	uint8_t mw_cnt;
+	uint8_t peer_mw_cnt;
+	uint8_t db_cnt;
+	uint8_t spad_cnt;
+
+	uint64_t db_valid_mask;
+	uint64_t db_mask;
+
+	enum ntb_topo topo;
+
+	enum ntb_link link_status;
+	enum ntb_speed link_speed;
+	enum ntb_width link_width;
+
+	const struct ntb_dev_ops *ntb_ops;
+
+	struct rte_pci_device *pci_dev;
+	char *hw_addr;
+
+	uint64_t *mw_size;
+	uint64_t *peer_mw_size;
+	uint8_t peer_dev_up;
+
+	uint16_t queue_pairs;
+	uint16_t queue_size;
+
+	/**< mem zone to populate RX ring. */
+	const struct rte_memzone **mz;
+
+	/* Reserve several spad for app to use. */
+	int spad_user_list[NTB_SPAD_USER_MAX_NUM];
+};
+
+#endif /* _NTB_RAWDEV_H_ */
diff --git a/drivers/raw/ntb_rawdev/rte_pmd_ntb_rawdev_version.map b/drivers/raw/ntb_rawdev/rte_pmd_ntb_rawdev_version.map
new file mode 100644
index 000000000..8861484fb
--- /dev/null
+++ b/drivers/raw/ntb_rawdev/rte_pmd_ntb_rawdev_version.map
@@ -0,0 +1,4 @@
+DPDK_19.08 {
+
+        local: *;
+};
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 2b5696a27..ead42ee3a 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -307,6 +307,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_IFPGA_BUS),y)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_IFPGA_RAWDEV)   += -lrte_pmd_ifpga_rawdev
 _LDLIBS-$(CONFIG_RTE_LIBRTE_IPN3KE_PMD)       += -lrte_pmd_ipn3ke
 endif # CONFIG_RTE_LIBRTE_IFPGA_BUS
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_NTB_RAWDEV) += -lrte_pmd_ntb_rawdev
 endif # CONFIG_RTE_LIBRTE_RAWDEV
 
 endif # !CONFIG_RTE_BUILD_SHARED_LIBS
-- 
2.17.1