[dpdk-dev] [PATCH v2 0/2] ethdev: abstraction layer for QoS hierarchical scheduler

[dpdk-dev] [PATCH v2 0/2] ethdev: abstraction layer for QoS hierarchical scheduler

[Cristian Dumitrescu]

This patch set introduces an ethdev-based abstraction layer for Quality of
Service (QoS) hierarchical scheduler. The goal is to provide a simple generic
API that is agnostic of the underlying HW, SW or mixed HW-SW implementation.

Patch 1 builds on the mechanism introduced by rte_flow in DPDK and generalizes
it to make it available for other ethdev features/capabilities (such as the
hierarchical scheduler). The goal is to define a plugin-like mechanism to extend
the ethdev functionality in a modular way as opposed to the current monolithic
approach.

Patch 2 introduces the generic ethdev API for hierarchical scheduler using the
above plugin-like mechanism for ethdev.

Cristian Dumitrescu (2):
  ethdev: add capability control API
  ethdev: add hierarchical scheduler API

 MAINTAINERS                            |    4 +
 lib/librte_ether/Makefile              |    5 +-
 lib/librte_ether/rte_ethdev.c          |   13 +
 lib/librte_ether/rte_ethdev.h          |   29 +
 lib/librte_ether/rte_ether_version.map |   37 +
 lib/librte_ether/rte_scheddev.c        |  781 ++++++++++++++++++
 lib/librte_ether/rte_scheddev.h        | 1416 ++++++++++++++++++++++++++++++++
 lib/librte_ether/rte_scheddev_driver.h |  365 ++++++++
 8 files changed, 2649 insertions(+), 1 deletion(-)
 create mode 100644 lib/librte_ether/rte_scheddev.c
 create mode 100644 lib/librte_ether/rte_scheddev.h
 create mode 100644 lib/librte_ether/rte_scheddev_driver.h

-- 
2.5.0

[dpdk-dev] [PATCH v2 1/2] ethdev: add capability control API

[Cristian Dumitrescu]

The rte_flow feature breaks the current monolithic approach for ethdev and
introduces the new generic flow API to ethdev using a plugin-like approach.

Basically, the rte_flow API is still logically part of ethdev:
- It extends the ethdev functionality: rte_flow is a new feature/capability
  of ethdev;
- all its functions work on an Ethernet device: the first parameter of the
  rte_flow functions is Ethernet device port ID.

At the same time, the rte_flow API is a sort of capability plugin for ethdev:
- the rte_flow API functions have their own name space: they are called
  rte_flow_operationXYZ() as opposed to rte_eth_dev_flow_operationXYZ());
- the rte_flow API functions are placed in separate files in the same
  librte_ether folder as opposed to rte_ethdev.[hc].

The way it works is by using the existing ethdev API function
rte_eth_dev_filter_ctrl() to query the current Ethernet device port ID for the
support of the rte_flow capability and return the pointer to the
rte_flow operations when supported and NULL otherwise:

struct rte_flow_ops *eth_flow_ops;
int rte = rte_eth_dev_filter_ctrl(eth_port_id,
	RTE_ETH_FILTER_GENERIC, RTE_ETH_FILTER_GET, &eth_flow_ops);

Unfortunately, the rte_flow opportunistically uses the rte_eth_dev_filter_ctrl()
API function, which is applicable just to RX-side filters as opposed to
introducing a mechanism that could be used by any capability in a generic way.

This is the gap that addressed by the current patch. This mechanism is intended
to be used to introduce new capabilities into ethdev in a modular plugin-like
approach, such as hierarchical scheduler. Over time, if agreed, it can also be
used for exposing the existing Ethernet device capabilities in a modular way,
such as: xstats, filters, multicast, mirroring, tunnels, time stamping, eeprom,
bypass, etc.

Changes in v2:
-Followed up on suggestion from Jerin and Hemant: renamed capability_control()
 to capability_ops_get()
-Added ACK from Keith, Jerin and Hemant

Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 lib/librte_ether/rte_ethdev.c          | 13 +++++++++++++
 lib/librte_ether/rte_ethdev.h          | 29 +++++++++++++++++++++++++++++
 lib/librte_ether/rte_ether_version.map |  7 +++++++
 3 files changed, 49 insertions(+)

diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index eb0a94a..674bbae 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -2802,6 +2802,19 @@ rte_eth_dev_filter_ctrl(uint8_t port_id, enum rte_filter_type filter_type,
 	return (*dev->dev_ops->filter_ctrl)(dev, filter_type, filter_op, arg);
 }
 
+int
+rte_eth_dev_capability_ops_get(uint8_t port_id, enum rte_eth_capability cap,
+	void *arg)
+{
+	struct rte_eth_dev *dev;
+
+	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+
+	dev = &rte_eth_devices[port_id];
+	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->cap_ops_get, -ENOTSUP);
+	return (*dev->dev_ops->cap_ops_get)(dev, cap, arg);
+}
+
 void *
 rte_eth_add_rx_callback(uint8_t port_id, uint16_t queue_id,
 		rte_rx_callback_fn fn, void *user_param)
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 97f3e2d..e56d160 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -1073,6 +1073,12 @@ TAILQ_HEAD(rte_eth_dev_cb_list, rte_eth_dev_callback);
  * structure associated with an Ethernet device.
  */
 
+enum rte_eth_capability {
+	RTE_ETH_CAPABILITY_FLOW = 0, /**< Flow */
+	RTE_ETH_CAPABILITY_SCHED, /**< Hierarchical Scheduler */
+	RTE_ETH_CAPABILITY_MAX
+};
+
 typedef int  (*eth_dev_configure_t)(struct rte_eth_dev *dev);
 /**< @internal Ethernet device configuration. */
 
@@ -1427,6 +1433,10 @@ typedef int (*eth_filter_ctrl_t)(struct rte_eth_dev *dev,
 				 void *arg);
 /**< @internal Take operations to assigned filter type on an Ethernet device */
 
+typedef int (*eth_capability_ops_get_t)(struct rte_eth_dev *dev,
+	enum rte_eth_capability cap, void *arg);
+/**< @internal Take capability operations on an Ethernet device */
+
 typedef int (*eth_get_dcb_info)(struct rte_eth_dev *dev,
 				 struct rte_eth_dcb_info *dcb_info);
 /**< @internal Get dcb information on an Ethernet device */
@@ -1548,6 +1558,8 @@ struct eth_dev_ops {
 	eth_timesync_adjust_time   timesync_adjust_time; /** Adjust the device clock. */
 	eth_timesync_read_time     timesync_read_time; /** Get the device clock time. */
 	eth_timesync_write_time    timesync_write_time; /** Set the device clock time. */
+
+	eth_capability_ops_get_t   cap_ops_get; /**< capability control. */
 };
 
 /**
@@ -3890,6 +3902,23 @@ int rte_eth_dev_filter_ctrl(uint8_t port_id, enum rte_filter_type filter_type,
 			enum rte_filter_op filter_op, void *arg);
 
 /**
+ * Take capability operations on an Ethernet device.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param cap
+ *   The capability of the Ethernet device
+ * @param arg
+ *   A pointer to arguments defined specifically for the operation.
+ * @return
+ *   - (0) if successful.
+ *   - (-ENOTSUP) if hardware doesn't support.
+ *   - (-ENODEV) if *port_id* invalid.
+ */
+int rte_eth_dev_capability_ops_get(uint8_t port_id,
+	enum rte_eth_capability cap, void *arg);
+
+/**
  * Get DCB information on an Ethernet device.
  *
  * @param port_id
diff --git a/lib/librte_ether/rte_ether_version.map b/lib/librte_ether/rte_ether_version.map
index c6c9d0d..637317c 100644
--- a/lib/librte_ether/rte_ether_version.map
+++ b/lib/librte_ether/rte_ether_version.map
@@ -154,3 +154,10 @@ DPDK_17.02 {
 	rte_flow_validate;
 
 } DPDK_16.11;
+
+DPDK_17.05 {
+	global:
+
+	rte_eth_dev_capability_ops_get;
+
+} DPDK_17.02;
-- 
2.5.0

[dpdk-dev] [PATCH v2 2/2] ethdev: add hierarchical scheduler API

[Cristian Dumitrescu]

This patch introduces the generic ethdev API for the hierarchical scheduler
capability.

Main features:
- Exposed as ethdev plugin capability (similar to rte_flow approach)
- Capability query API per port, per hierarchy level and per hierarchy node
- Scheduling algorithms: Strict Priority (SP), Weighed Fair Queuing (WFQ),
  Weighted Round Robin (WRR)
- Traffic shaping: single/dual rate, private (per node) and shared (by multiple
  nodes) shapers
- Congestion management for hierarchy leaf nodes: algorithms of tail drop,
  head drop, WRED; private (per node) and shared (by multiple nodes) WRED
  contexts
- Packet marking: IEEE 802.1q (VLAN DEI), IETF RFC 3168 (IPv4/IPv6 ECN for
  TCP and SCTP), IETF RFC 2597 (IPv4 / IPv6 DSCP)

Changes in v2:
- Implemented feedback from Hemant [4]
- Improvements on the capability API
	- Added capability API for hierarchy level
	- Merged stats capability into the capability API
	- Added dynamic updates
	- Added non-leaf/leaf union to the node capability structure
	- Renamed sp_priority_min to sp_n_priorities_max, added clarifications
	- Fixed description for sp_n_children_max
- Clarified and enforced rule on node ID range for leaf and non-leaf nodes
	- Added API functions to get node type (i.e. leaf/non-leaf):
	  get_leaf_nodes(), node_type_get()
- Added clarification for the root node: its creation, its parent, its role
	- Macro NODE_ID_NULL as root node's parent
	- Description of the node_add() and node_parent_update() API functions
- Added clarification for the first time add vs. subsequent updates rule
	- Cleaned up the description for the node_add() function
- Statistics API improvements
	- Merged stats capability into the capability API
	- Added API function node_stats_update()
	- Added more stats per packet color
- Added more error types
- Fixed small Doxygen style issues

Changes in v1 (since RFC [1]):
- Implemented as ethdev plugin (similar to rte_flow) as opposed to more
  monolithic additions to ethdev itself
- Implemented feedback from Jerin [2] and Hemant [3]. Implemented all the
  suggested items with only one exception, see the long list below, hopefully
  nothing was forgotten.
    - The item not done (hopefully for a good reason): driver-generated object
      IDs. IMO the choice to have application-generated object IDs adds marginal
      complexity to the driver (search ID function required), but it provides
      huge simplification for the application. The app does not need to worry
      about building & managing tree-like structure for storing driver-generated
      object IDs, the app can use its own convention for node IDs depending on
      the specific hierarchy that it needs. Trivial example: identify all
      level-2 nodes with IDs like 100, 200, 300, … and the level-3 nodes based
      on their level-2 parents: 110, 120, 130, 140, …, 210, 220, 230, 240, …,
      310, 320, 330, … and level-4 nodes based on their level-3 parents: 111,
      112, 113, 114, …, 121, 122, 123, 124, …). Moreover, see the change log for
      the other related simplification that was implemented: leaf nodes now have
      predefined IDs that are the same with their Ethernet TX queue ID (
      therefore no translation is required for leaf nodes).
- Capability API. Done per port and per node as well.
- Dual rate shapers
- Added configuration of private shaper (per node) directly from the shaper
  profile as part of node API (no shaper ID needed for private shapers), while
  the shared shapers are configured outside of the node API using shaper profile
  and communicated to the node using shared shaper ID. So there is no
  configuration overhead for shared shapers if the app does not use any of them.
- Leaf nodes now have predefined IDs that are the same with their Ethernet TX
  queue ID (therefore no translation is required for leaf nodes). This is also
  used to differentiate between a leaf node and a non-leaf node.
- Domain-specific errors to give a precise indication of the error cause (same
  as done by rte_flow)
- Packet marking API
- Packet length optional adjustment for shapers, positive (e.g. for adding
  Ethernet framing overhead of 20 bytes) or negative (e.g. for rate limiting
  based on IP packet bytes)

Next steps:
- SW fallback based on librte_sched library (to be later introduced by
  standalone patch set)

[1] RFC: http://dpdk.org/ml/archives/dev/2016-November/050956.html
[2] Jerin’s feedback on RFC: http://www.dpdk.org/ml/archives/dev/2017-January/054484.html
[3] Hemant’s feedback on RFC: http://www.dpdk.org/ml/archives/dev/2017-January/054866.html
[4] Hemant's feedback on v1: http://www.dpdk.org/ml/archives/dev/2017-February/058033.html

Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
---
 MAINTAINERS                            |    4 +
 lib/librte_ether/Makefile              |    5 +-
 lib/librte_ether/rte_ether_version.map |   30 +
 lib/librte_ether/rte_scheddev.c        |  781 ++++++++++++++++++
 lib/librte_ether/rte_scheddev.h        | 1416 ++++++++++++++++++++++++++++++++
 lib/librte_ether/rte_scheddev_driver.h |  365 ++++++++
 6 files changed, 2600 insertions(+), 1 deletion(-)
 create mode 100644 lib/librte_ether/rte_scheddev.c
 create mode 100644 lib/librte_ether/rte_scheddev.h
 create mode 100644 lib/librte_ether/rte_scheddev_driver.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 24e0eff..8a8719f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -247,6 +247,10 @@ Flow API
 M: Adrien Mazarguil <adrien.mazarguil@6wind.com>
 F: lib/librte_ether/rte_flow*
 
+SchedDev API
+M: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
+F: lib/librte_ether/rte_scheddev*
+
 Crypto API
 M: Declan Doherty <declan.doherty@intel.com>
 F: lib/librte_cryptodev/
diff --git a/lib/librte_ether/Makefile b/lib/librte_ether/Makefile
index 1d095a9..7e0527f 100644
--- a/lib/librte_ether/Makefile
+++ b/lib/librte_ether/Makefile
@@ -1,6 +1,6 @@
 #   BSD LICENSE
 #
-#   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+#   Copyright(c) 2010-2017 Intel Corporation. All rights reserved.
 #   All rights reserved.
 #
 #   Redistribution and use in source and binary forms, with or without
@@ -45,6 +45,7 @@ LIBABIVER := 6
 
 SRCS-y += rte_ethdev.c
 SRCS-y += rte_flow.c
+SRCS-y += rte_scheddev.c
 
 #
 # Export include files
@@ -54,6 +55,8 @@ SYMLINK-y-include += rte_eth_ctrl.h
 SYMLINK-y-include += rte_dev_info.h
 SYMLINK-y-include += rte_flow.h
 SYMLINK-y-include += rte_flow_driver.h
+SYMLINK-y-include += rte_scheddev.h
+SYMLINK-y-include += rte_scheddev_driver.h
 
 # this lib depends upon:
 DEPDIRS-y += lib/librte_net lib/librte_eal lib/librte_mempool lib/librte_ring lib/librte_mbuf
diff --git a/lib/librte_ether/rte_ether_version.map b/lib/librte_ether/rte_ether_version.map
index 637317c..4d67eee 100644
--- a/lib/librte_ether/rte_ether_version.map
+++ b/lib/librte_ether/rte_ether_version.map
@@ -159,5 +159,35 @@ DPDK_17.05 {
 	global:
 
 	rte_eth_dev_capability_ops_get;
+	rte_scheddev_get_leaf_nodes;
+	rte_scheddev_node_type_get;
+	rte_scheddev_capabilities_get;
+	rte_scheddev_level_capabilities_get;
+	rte_scheddev_node_capabilities_get;
+	rte_scheddev_wred_profile_add;
+	rte_scheddev_wred_profile_delete;
+	rte_scheddev_shared_wred_context_add_update;
+	rte_scheddev_shared_wred_context_delete;
+	rte_scheddev_shaper_profile_add;
+	rte_scheddev_shaper_profile_delete;
+	rte_scheddev_shared_shaper_add_update;
+	rte_scheddev_shared_shaper_delete;
+	rte_scheddev_node_add;
+	rte_scheddev_node_delete;
+	rte_scheddev_node_suspend;
+	rte_scheddev_node_resume;
+	rte_scheddev_hierarchy_set;
+	rte_scheddev_node_parent_update;
+	rte_scheddev_node_shaper_update;
+	rte_scheddev_node_shared_shaper_update;
+	rte_scheddev_node_stats_update;
+	rte_scheddev_node_scheduling_mode_update;
+	rte_scheddev_node_cman_update;
+	rte_scheddev_node_wred_context_update;
+	rte_scheddev_node_shared_wred_context_update;
+	rte_scheddev_node_stats_read;
+	rte_scheddev_mark_vlan_dei;
+	rte_scheddev_mark_ip_ecn;
+	rte_scheddev_mark_ip_dscp;
 
 } DPDK_17.02;
diff --git a/lib/librte_ether/rte_scheddev.c b/lib/librte_ether/rte_scheddev.c
new file mode 100644
index 0000000..d9c7dfe
--- /dev/null
+++ b/lib/librte_ether/rte_scheddev.c
@@ -0,0 +1,781 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <stdint.h>
+
+#include <rte_errno.h>
+#include <rte_branch_prediction.h>
+#include "rte_ethdev.h"
+#include "rte_scheddev_driver.h"
+#include "rte_scheddev.h"
+
+/* Get generic scheduler operations structure from a port. */
+const struct rte_scheddev_ops *
+rte_scheddev_ops_get(uint8_t port_id, struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops;
+
+	if (!rte_eth_dev_is_valid_port(port_id)) {
+		rte_scheddev_error_set(error,
+			ENODEV,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENODEV));
+		return NULL;
+	}
+
+	if ((dev->dev_ops->cap_ops_get == NULL) ||
+		(dev->dev_ops->cap_ops_get(dev, RTE_ETH_CAPABILITY_SCHED,
+		&ops) != 0) || (ops == NULL)) {
+		rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+		return NULL;
+	}
+
+	return ops;
+}
+
+/* Get number of leaf nodes */
+int
+rte_scheddev_get_leaf_nodes(uint8_t port_id,
+	uint32_t *n_leaf_nodes,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (n_leaf_nodes == NULL) {
+		rte_scheddev_error_set(error,
+			EINVAL,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(EINVAL));
+		return -rte_errno;
+	}
+
+	*n_leaf_nodes = dev->data->nb_tx_queues;
+	return 0;
+}
+
+/* Check node ID type (leaf or non-leaf) */
+int
+rte_scheddev_node_type_get(uint8_t port_id,
+	uint32_t node_id,
+	int *is_leaf,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_type_get == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_type_get(dev, node_id, is_leaf, error);
+}
+
+/* Get capabilities */
+int rte_scheddev_capabilities_get(uint8_t port_id,
+	struct rte_scheddev_capabilities *cap,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->capabilities_get == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->capabilities_get(dev, cap, error);
+}
+
+/* Get level capabilities */
+int rte_scheddev_level_capabilities_get(uint8_t port_id,
+	uint32_t level_id,
+	struct rte_scheddev_level_capabilities *cap,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->level_capabilities_get == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->level_capabilities_get(dev, level_id, cap, error);
+}
+
+/* Get node capabilities */
+int rte_scheddev_node_capabilities_get(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_node_capabilities *cap,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_capabilities_get == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_capabilities_get(dev, node_id, cap, error);
+}
+
+/* Add WRED profile */
+int rte_scheddev_wred_profile_add(uint8_t port_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_wred_params *profile,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->wred_profile_add == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->wred_profile_add(dev, wred_profile_id, profile, error);
+}
+
+/* Delete WRED profile */
+int rte_scheddev_wred_profile_delete(uint8_t port_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->wred_profile_delete == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->wred_profile_delete(dev, wred_profile_id, error);
+}
+
+/* Add/update shared WRED context */
+int rte_scheddev_shared_wred_context_add_update(uint8_t port_id,
+	uint32_t shared_wred_context_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shared_wred_context_add_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shared_wred_context_add_update(dev, shared_wred_context_id,
+		wred_profile_id, error);
+}
+
+/* Delete shared WRED context */
+int rte_scheddev_shared_wred_context_delete(uint8_t port_id,
+	uint32_t shared_wred_context_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shared_wred_context_delete == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shared_wred_context_delete(dev, shared_wred_context_id,
+		error);
+}
+
+/* Add shaper profile */
+int rte_scheddev_shaper_profile_add(uint8_t port_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_shaper_params *profile,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shaper_profile_add == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shaper_profile_add(dev, shaper_profile_id, profile, error);
+}
+
+/* Delete WRED profile */
+int rte_scheddev_shaper_profile_delete(uint8_t port_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shaper_profile_delete == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shaper_profile_delete(dev, shaper_profile_id, error);
+}
+
+/* Add shared shaper */
+int rte_scheddev_shared_shaper_add_update(uint8_t port_id,
+	uint32_t shared_shaper_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shared_shaper_add_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shared_shaper_add_update(dev, shared_shaper_id,
+		shaper_profile_id, error);
+}
+
+/* Delete shared shaper */
+int rte_scheddev_shared_shaper_delete(uint8_t port_id,
+	uint32_t shared_shaper_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->shared_shaper_delete == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->shared_shaper_delete(dev, shared_shaper_id, error);
+}
+
+/* Add node to port scheduler hierarchy */
+int rte_scheddev_node_add(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_node_params *params,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_add == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_add(dev, node_id, parent_node_id, priority, weight,
+		params, error);
+}
+
+/* Delete node from scheduler hierarchy */
+int rte_scheddev_node_delete(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_delete == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_delete(dev, node_id, error);
+}
+
+/* Suspend node */
+int rte_scheddev_node_suspend(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_suspend == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_suspend(dev, node_id, error);
+}
+
+/* Resume node */
+int rte_scheddev_node_resume(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_resume == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_resume(dev, node_id, error);
+}
+
+/* Set the initial port scheduler hierarchy */
+int rte_scheddev_hierarchy_set(uint8_t port_id,
+	int clear_on_fail,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->hierarchy_set == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->hierarchy_set(dev, clear_on_fail, error);
+}
+
+/* Update node parent  */
+int rte_scheddev_node_parent_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_parent_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_parent_update(dev, node_id, parent_node_id, priority,
+		weight, error);
+}
+
+/* Update node private shaper */
+int rte_scheddev_node_shaper_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_shaper_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_shaper_update(dev, node_id, shaper_profile_id,
+		error);
+}
+
+/* Update node shared shapers */
+int rte_scheddev_node_shared_shaper_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shared_shaper_id,
+	int add,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_shared_shaper_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_shared_shaper_update(dev, node_id, shared_shaper_id,
+		add, error);
+}
+
+/* Update node stats */
+int rte_scheddev_node_stats_update(uint8_t port_id,
+	uint32_t node_id,
+	uint64_t stats_mask,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_stats_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_stats_update(dev, node_id, stats_mask, error);
+}
+
+/* Update scheduling mode */
+int rte_scheddev_node_scheduling_mode_update(uint8_t port_id,
+	uint32_t node_id,
+	int *scheduling_mode_per_priority,
+	uint32_t n_priorities,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_scheduling_mode_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_scheduling_mode_update(dev, node_id,
+		scheduling_mode_per_priority, n_priorities, error);
+}
+
+/* Update node congestion management mode */
+int rte_scheddev_node_cman_update(uint8_t port_id,
+	uint32_t node_id,
+	enum rte_scheddev_cman_mode cman,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_cman_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_cman_update(dev, node_id, cman, error);
+}
+
+/* Update node private WRED context */
+int rte_scheddev_node_wred_context_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_wred_context_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_wred_context_update(dev, node_id, wred_profile_id,
+		error);
+}
+
+/* Update node shared WRED context */
+int rte_scheddev_node_shared_wred_context_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shared_wred_context_id,
+	int add,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_shared_wred_context_update == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_shared_wred_context_update(dev, node_id,
+		shared_wred_context_id, add, error);
+}
+
+/* Read and/or clear stats counters for specific node */
+int rte_scheddev_node_stats_read(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_node_stats *stats,
+	uint64_t *stats_mask,
+	int clear,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->node_stats_read == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->node_stats_read(dev, node_id, stats, stats_mask, clear,
+		error);
+}
+
+/* Packet marking - VLAN DEI */
+int rte_scheddev_mark_vlan_dei(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->mark_vlan_dei == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->mark_vlan_dei(dev, mark_green, mark_yellow, mark_red,
+		error);
+}
+
+/* Packet marking - IPv4/IPv6 ECN */
+int rte_scheddev_mark_ip_ecn(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->mark_ip_ecn == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->mark_ip_ecn(dev, mark_green, mark_yellow, mark_red, error);
+}
+
+/* Packet marking - IPv4/IPv6 DSCP */
+int rte_scheddev_mark_ip_dscp(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	const struct rte_scheddev_ops *ops =
+		rte_scheddev_ops_get(port_id, error);
+
+	if (ops == NULL)
+		return -rte_errno;
+
+	if (ops->mark_ip_dscp == NULL)
+		return -rte_scheddev_error_set(error,
+			ENOSYS,
+			RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED,
+			NULL,
+			rte_strerror(ENOSYS));
+
+	return ops->mark_ip_dscp(dev, mark_green, mark_yellow, mark_red,
+		error);
+}
diff --git a/lib/librte_ether/rte_scheddev.h b/lib/librte_ether/rte_scheddev.h
new file mode 100644
index 0000000..1741f7a
--- /dev/null
+++ b/lib/librte_ether/rte_scheddev.h
@@ -0,0 +1,1416 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __INCLUDE_RTE_SCHEDDEV_H__
+#define __INCLUDE_RTE_SCHEDDEV_H__
+
+/**
+ * @file
+ * RTE Generic Hierarchical Scheduler API
+ *
+ * This interface provides the ability to configure the hierarchical scheduler
+ * feature in a generic way.
+ */
+
+#include <stdint.h>
+
+#include <rte_red.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/** Ethernet framing overhead
+ *
+ * Overhead fields per Ethernet frame:
+ * 1. Preamble:                                            7 bytes;
+ * 2. Start of Frame Delimiter (SFD):                      1 byte;
+ * 3. Inter-Frame Gap (IFG):                              12 bytes.
+ */
+#define RTE_SCHEDDEV_ETH_FRAMING_OVERHEAD                  20
+
+/**
+ * Ethernet framing overhead plus Frame Check Sequence (FCS). Useful when FCS
+ * is generated and added at the end of the Ethernet frame on TX side without
+ * any SW intervention.
+ */
+#define RTE_SCHEDDEV_ETH_FRAMING_OVERHEAD_FCS              24
+
+/**< Invalid WRED profile ID */
+#define RTE_SCHEDDEV_WRED_PROFILE_ID_NONE                  UINT32_MAX
+
+/**< Invalid shaper profile ID */
+#define RTE_SCHEDDEV_SHAPER_PROFILE_ID_NONE                UINT32_MAX
+
+/**< Node ID for the parent of the root node */
+#define RTE_SCHEDDEV_NODE_ID_NULL                          UINT32_MAX
+
+/**
+ * Color
+ */
+enum rte_scheddev_color {
+	e_RTE_SCHEDDEV_GREEN = 0, /**< Green */
+	e_RTE_SCHEDDEV_YELLOW, /**< Yellow */
+	e_RTE_SCHEDDEV_RED, /**< Red */
+	e_RTE_SCHEDDEV_COLORS /**< Number of colors */
+};
+
+/**
+ * Node statistics counter type
+ */
+enum rte_scheddev_stats_type {
+	/**< Number of packets scheduled from current node. */
+	RTE_SCHEDDEV_STATS_N_PKTS = 1 << 0,
+
+	/**< Number of bytes scheduled from current node. */
+	RTE_SCHEDDEV_STATS_N_BYTES = 1 << 1,
+
+	/**< Number of green packets dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_PKTS_GREEN_DROPPED = 1 << 2,
+
+	/**< Number of yellow packets dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_PKTS_YELLOW_DROPPED = 1 << 3,
+
+	/**< Number of red packets dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_PKTS_RED_DROPPED = 1 << 4,
+
+	/**< Number of green bytes dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_BYTES_GREEN_DROPPED = 1 << 5,
+
+	/**< Number of yellow bytes dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_BYTES_YELLOW_DROPPED = 1 << 6,
+
+	/**< Number of red bytes dropped by current leaf node.  */
+	RTE_SCHEDDEV_STATS_N_BYTES_RED_DROPPED = 1 << 7,
+
+	/**< Number of packets currently waiting in the packet queue of current
+	 * leaf node.
+	 */
+	RTE_SCHEDDEV_STATS_N_PKTS_QUEUED = 1 << 8,
+
+	/**< Number of bytes currently waiting in the packet queue of current
+	 * leaf node.
+	 */
+	RTE_SCHEDDEV_STATS_N_BYTES_QUEUED = 1 << 9,
+};
+
+/**
+ * Node statistics counters
+ */
+struct rte_scheddev_node_stats {
+	/**< Number of packets scheduled from current node. */
+	uint64_t n_pkts;
+
+	/**< Number of bytes scheduled from current node. */
+	uint64_t n_bytes;
+
+	/**< Statistics counters for leaf nodes only. */
+	struct {
+		/**< Number of packets dropped by current leaf node per each
+		 * color.
+		 */
+		uint64_t n_pkts_dropped[e_RTE_SCHEDDEV_COLORS];
+
+		/**< Number of bytes dropped by current leaf node per each
+		 * color.
+		 */
+		uint64_t n_bytes_dropped[e_RTE_SCHEDDEV_COLORS];
+
+		/**< Number of packets currently waiting in the packet queue of
+		 * current leaf node.
+		 */
+		uint64_t n_pkts_queued;
+
+		/**< Number of bytes currently waiting in the packet queue of
+		 * current leaf node.
+		 */
+		uint64_t n_bytes_queued;
+	} leaf;
+};
+
+/**
+ * Scheduler dynamic updates
+ */
+enum rte_scheddev_dynamic_update_type {
+	/**< Dynamic parent node update. */
+	RTE_SCHEDDEV_UPDATE_NODE_PARENT = 1 << 0,
+
+	/**< Dynamic node add/delete. */
+	RTE_SCHEDDEV_UPDATE_NODE_ADD_DELETE = 1 << 1,
+
+	/**< Suspend/resume nodes. */
+	RTE_SCHEDDEV_UPDATE_NODE_SUSPEND_RESUME = 1 << 2,
+
+	/**< Dynamic switch between WFQ and WRR per node SP priority level. */
+	RTE_SCHEDDEV_UPDATE_NODE_SCHEDULING_MODE = 1 << 3,
+
+	/**< Dynamic update of the set of enabled stats counter types. */
+	RTE_SCHEDDEV_UPDATE_NODE_STATS = 1 << 4,
+
+	/**< Dynamic update of congestion management mode for leaf nodes. */
+	RTE_SCHEDDEV_UPDATE_NODE_CMAN = 1 << 5,
+};
+
+/**
+ * Scheduler node capabilities
+ */
+struct rte_scheddev_node_capabilities {
+	/**< Private shaper support. */
+	int shaper_private_supported;
+
+	/**< Dual rate shaping support for private shaper. Valid only when
+	 * private shaper is supported.
+	 */
+	int shaper_private_dual_rate_supported;
+
+	/**< Minimum committed/peak rate (bytes per second) for private
+	 * shaper. Valid only when private shaper is supported.
+	 */
+	uint64_t shaper_private_rate_min;
+
+	/**< Maximum committed/peak rate (bytes per second) for private
+	 * shaper. Valid only when private shaper is supported.
+	 */
+	uint64_t shaper_private_rate_max;
+
+	/**< Maximum number of supported shared shapers. The value of zero
+	 * indicates that shared shapers are not supported.
+	 */
+	uint32_t shaper_shared_n_max;
+
+	/**< Mask of supported statistics counter types. */
+	uint64_t stats_mask;
+
+	union {
+		/**< Items valid only for non-leaf nodes. */
+		struct {
+			/**< Maximum number of children nodes. */
+			uint32_t n_children_max;
+
+			/**< Maximum number of supported priority levels. The
+			 * value of zero is invalid. The value of 1 indicates
+			 * that only priority 0 is supported, which essentially
+			 * means that Strict Priority (SP) algorithm is not
+			 * supported.
+			 */
+			uint32_t sp_n_priorities_max;
+
+			/**< Maximum number of sibling nodes that can have the
+			 * same priority at any given time. The value of zero is
+			 * invalid. The value of 1 indicates that WFQ/WRR
+			 * algorithms are not supported. The maximum value is
+			 * *n_children_max*.
+			 */
+			uint32_t sp_n_children_max;
+
+			/**< WFQ algorithm support. */
+			int wfq_supported;
+
+			/**< WRR algorithm support. */
+			int wrr_supported;
+
+			/**< Maximum WFQ/WRR weight. */
+			uint32_t wfq_wrr_weight_max;
+		} nonleaf;
+
+		/**< Items valid only for leaf nodes. */
+		struct {
+			/**< Head drop algorithm support. */
+			int cman_head_drop_supported;
+
+			/**< Private WRED context support. */
+			int cman_wred_context_private_supported;
+
+			/**< Maximum number of shared WRED contexts supported.
+			 * The value of zero indicates that shared WRED contexts
+			 * are not supported.
+			 */
+			uint32_t cman_wred_context_shared_n_max;
+		} leaf;
+	};
+};
+
+/**
+ * Scheduler level capabilities
+ */
+struct rte_scheddev_level_capabilities {
+	/**< Maximum number of nodes for the current hierarchy level. */
+	uint32_t n_nodes_max;
+
+	/**< Maximum number of non-leaf nodes for the current hierarchy level.
+	 * The value of 0 indicates that current level only supports leaf nodes.
+	 * The maximum value is *n_nodes_max*.
+	 */
+	uint32_t n_nodes_nonleaf_max;
+
+	/**< Maximum number of leaf nodes for the current hierarchy level. The
+	 * value of 0 indicates that current level only supports non-leaf nodes.
+	 * The maximum value is *n_nodes_max*.
+	 */
+	uint32_t n_nodes_leaf_max;
+
+	/**< Summary of node-level capabilities across all the non-leaf nodes
+	 * of the current hierarchy level. Valid only when *n_nodes_nonleaf_max*
+	 * is greater than 0.
+	 */
+	struct rte_scheddev_node_capabilities nonleaf;
+
+	/**< Summary of node-level capabilities across all the leaf nodes of the
+	 * current hierarchy level. Valid only when *n_nodes_leaf_max* is
+	 * greater than 0.
+	 */
+	struct rte_scheddev_node_capabilities leaf;
+};
+
+/**
+ * Scheduler capabilities
+ */
+struct rte_scheddev_capabilities {
+	/**< Maximum number of nodes. */
+	uint32_t n_nodes_max;
+
+	/**< Maximum number of levels (i.e. number of nodes connecting the root
+	 * node with any leaf node, including the root and the leaf).
+	 */
+	uint32_t n_levels_max;
+
+	/**< Maximum number of shapers, either private or shared. In case the
+	 * implementation does not share any resource between private and
+	 * shared shapers, it is typically equal to the sum between
+	 * *shaper_private_n_max* and *shaper_shared_n_max*.
+	 */
+	uint32_t shaper_n_max;
+
+	/**< Maximum number of private shapers. Indicates the maximum number of
+	 * nodes that can concurrently have the private shaper enabled.
+	 */
+	uint32_t shaper_private_n_max;
+
+	/**< Maximum number of shared shapers. The value of zero indicates that
+	 * shared shapers are not supported.
+	 */
+	uint32_t shaper_shared_n_max;
+
+	/**< Maximum number of nodes that can share the same shared shaper. Only
+	 * valid when shared shapers are supported.
+	 */
+	uint32_t shaper_shared_n_nodes_max;
+
+	/**< Maximum number of shared shapers that can be configured with dual
+	 * rate shaping. The value of zero indicates that dual rate shaping
+	 * support is not available for shared shapers.
+	 */
+	uint32_t shaper_shared_dual_rate_n_max;
+
+	/**< Minimum committed/peak rate (bytes per second) for shared
+	 * shapers. Only valid when shared shapers are supported.
+	 */
+	uint64_t shaper_shared_rate_min;
+
+	/**< Maximum committed/peak rate (bytes per second) for shared
+	 * shaper. Only valid when shared shapers are supported.
+	 */
+	uint64_t shaper_shared_rate_max;
+
+	/**< Minimum value allowed for packet length adjustment for
+	 * private/shared shapers.
+	 */
+	int shaper_pkt_length_adjust_min;
+
+	/**< Maximum value allowed for packet length adjustment for
+	 * private/shared shapers.
+	 */
+	int shaper_pkt_length_adjust_max;
+
+	/**< Maximum number of WRED contexts. */
+	uint32_t cman_wred_context_n_max;
+
+	/**< Maximum number of private WRED contexts. Indicates the maximum
+	 * number of leaf nodes that can concurrently have the private WRED
+	 * context enabled.
+	 */
+	uint32_t cman_wred_context_private_n_max;
+
+	/**< Maximum number of shared WRED contexts. The value of zero indicates
+	 * that shared WRED contexts are not supported.
+	 */
+	uint32_t cman_wred_context_shared_n_max;
+
+	/**< Maximum number of leaf nodes that can share the same WRED context.
+	 * Only valid when shared WRED contexts are supported.
+	 */
+	uint32_t cman_wred_context_shared_n_nodes_max;
+
+	/**< Support for VLAN DEI packet marking. */
+	int mark_vlan_dei_supported;
+
+	/**< Support for IPv4/IPv6 ECN marking of TCP packets. */
+	int mark_ip_ecn_tcp_supported;
+
+	/**< Support for IPv4/IPv6 ECN marking of SCTP packets. */
+	int mark_ip_ecn_sctp_supported;
+
+	/**< Support for IPv4/IPv6 DSCP packet marking. */
+	int mark_ip_dscp_supported;
+
+	/**< Set of supported dynamic update operations
+	 * (see enum rte_scheddev_dynamic_update_type).
+	 */
+	uint64_t dynamic_update_mask;
+
+	/**< Summary of node-level capabilities across all non-leaf nodes. */
+	struct rte_scheddev_node_capabilities nonleaf;
+
+	/**< Summary of node-level capabilities across all leaf nodes. */
+	struct rte_scheddev_node_capabilities leaf;
+};
+
+/**
+ * Congestion management (CMAN) mode
+ *
+ * This is used for controlling the admission of packets into a packet queue or
+ * group of packet queues on congestion. On request of writing a new packet
+ * into the current queue while the queue is full, the *tail drop* algorithm
+ * drops the new packet while leaving the queue unmodified, as opposed to *head
+ * drop* algorithm, which drops the packet at the head of the queue (the oldest
+ * packet waiting in the queue) and admits the new packet at the tail of the
+ * queue.
+ *
+ * The *Random Early Detection (RED)* algorithm works by proactively dropping
+ * more and more input packets as the queue occupancy builds up. When the queue
+ * is full or almost full, RED effectively works as *tail drop*. The *Weighted
+ * RED* algorithm uses a separate set of RED thresholds for each packet color.
+ */
+enum rte_scheddev_cman_mode {
+	RTE_SCHEDDEV_CMAN_TAIL_DROP = 0, /**< Tail drop */
+	RTE_SCHEDDEV_CMAN_HEAD_DROP, /**< Head drop */
+	RTE_SCHEDDEV_CMAN_WRED, /**< Weighted Random Early Detection (WRED) */
+};
+
+/**
+ * WRED profile
+ *
+ * Multiple WRED contexts can share the same WRED profile. Each leaf node with
+ * WRED enabled as its congestion management mode has zero or one private WRED
+ * context (only one leaf node using it) and/or zero, one or several shared
+ * WRED contexts (multiple leaf nodes use the same WRED context). A private
+ * WRED context is used to perform congestion management for a single leaf
+ * node, while a shared WRED context is used to perform congestion management
+ * for a group of leaf nodes.
+ */
+struct rte_scheddev_wred_params {
+	/**< One set of RED parameters per packet color */
+	struct rte_red_params red_params[e_RTE_SCHEDDEV_COLORS];
+};
+
+/**
+ * Token bucket
+ */
+struct rte_scheddev_token_bucket {
+	/**< Token bucket rate (bytes per second) */
+	uint64_t rate;
+
+	/**< Token bucket size (bytes), a.k.a. max burst size */
+	uint64_t size;
+};
+
+/**
+ * Shaper (rate limiter) profile
+ *
+ * Multiple shaper instances can share the same shaper profile. Each node has
+ * zero or one private shaper (only one node using it) and/or zero, one or
+ * several shared shapers (multiple nodes use the same shaper instance).
+ * A private shaper is used to perform traffic shaping for a single node, while
+ * a shared shaper is used to perform traffic shaping for a group of nodes.
+ *
+ * Single rate shapers use a single token bucket. A single rate shaper can be
+ * configured by setting the rate of the committed bucket to zero, which
+ * effectively disables this bucket. The peak bucket is used to limit the rate
+ * and the burst size for the current shaper.
+ *
+ * Dual rate shapers use both the committed and the peak token buckets. The
+ * rate of the committed bucket has to be less than or equal to the rate of the
+ * peak bucket.
+ */
+struct rte_scheddev_shaper_params {
+	/**< Committed token bucket */
+	struct rte_scheddev_token_bucket committed;
+
+	/**< Peak token bucket */
+	struct rte_scheddev_token_bucket peak;
+
+	/**< Signed value to be added to the length of each packet for the
+	 * purpose of shaping. Can be used to correct the packet length with
+	 * the framing overhead bytes that are also consumed on the wire (e.g.
+	 * RTE_SCHEDDEV_ETH_FRAMING_OVERHEAD_FCS).
+	 */
+	int32_t pkt_length_adjust;
+};
+
+/**
+ * Node parameters
+ *
+ * Each scheduler hierarchy node has multiple inputs (children nodes of the
+ * current parent node) and a single output (which is input to its parent
+ * node). The current node arbitrates its inputs using Strict Priority (SP),
+ * Weighted Fair Queuing (WFQ) and Weighted Round Robin (WRR) algorithms to
+ * schedule input packets on its output while observing its shaping (rate
+ * limiting) constraints.
+ *
+ * Algorithms such as byte-level WRR, Deficit WRR (DWRR), etc are considered
+ * approximations of the ideal of WFQ and are assimilated to WFQ, although
+ * an associated implementation-dependent trade-off on accuracy, performance
+ * and resource usage might exist.
+ *
+ * Children nodes with different priorities are scheduled using the SP
+ * algorithm, based on their priority, with zero (0) as the highest priority.
+ * Children with same priority are scheduled using the WFQ or WRR algorithm,
+ * based on their weight, which is relative to the sum of the weights of all
+ * siblings with same priority, with one (1) as the lowest weight.
+ *
+ * Each leaf node sits on on top of a TX queue of the current Ethernet port.
+ * Therefore, the leaf nodes are predefined with the node IDs of 0 .. (N-1),
+ * where N is the number of TX queues configured for the current Ethernet port.
+ * The non-leaf nodes have their IDs generated by the application.
+ */
+struct rte_scheddev_node_params {
+	/**< Shaper profile for the private shaper. The absence of the private
+	 * shaper for the current node is indicated by setting this parameter
+	 * to RTE_SCHEDDEV_SHAPER_PROFILE_ID_NONE.
+	 */
+	uint32_t shaper_profile_id;
+
+	/**< User allocated array of valid shared shaper IDs. */
+	uint32_t *shared_shaper_id;
+
+	/**< Number of shared shaper IDs in the *shared_shaper_id* array. */
+	uint32_t n_shared_shapers;
+
+	/**< Mask of statistics counter types to be enabled for this node. This
+	 * needs to be a subset of the statistics counter types available for
+	 * the current node. Any statistics counter type not included in this
+	 * set is to be disabled for the current node.
+	 */
+	uint64_t stats_mask;
+
+	union {
+		/**< Parameters only valid for non-leaf nodes. */
+		struct {
+			/**< For each priority, indicates whether the children
+			 * nodes sharing the same priority are to be scheduled
+			 * by WFQ or by WRR. When NULL, it indicates that WFQ
+			 * is to be used for all priorities. When non-NULL, it
+			 * points to a pre-allocated array of *n_priority*
+			 * elements, with a non-zero value element indicating
+			 * WFQ and a zero value element for WRR.
+			 */
+			int *scheduling_mode_per_priority;
+
+			/**< Number of priorities. */
+			uint32_t n_priorities;
+		} nonleaf;
+
+		/**< Parameters only valid for leaf nodes. */
+		struct {
+			/**< Congestion management mode */
+			enum rte_scheddev_cman_mode cman;
+
+			/**< WRED parameters (valid when *cman* is WRED). */
+			struct {
+				/**< WRED profile for private WRED context. */
+				uint32_t wred_profile_id;
+
+				/**< User allocated array of shared WRED context
+				 * IDs. The absence of a private WRED context
+				 * for current leaf node is indicated by value
+				 * RTE_SCHEDDEV_WRED_PROFILE_ID_NONE.
+				 */
+				uint32_t *shared_wred_context_id;
+
+				/**< Number of shared WRED context IDs in the
+				 * *shared_wred_context_id* array.
+				 */
+				uint32_t n_shared_wred_contexts;
+			} wred;
+		} leaf;
+	};
+};
+
+/**
+ * Verbose error types.
+ *
+ * Most of them provide the type of the object referenced by struct
+ * rte_scheddev_error::cause.
+ */
+enum rte_scheddev_error_type {
+	RTE_SCHEDDEV_ERROR_TYPE_NONE, /**< No error. */
+	RTE_SCHEDDEV_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */
+	RTE_SCHEDDEV_ERROR_TYPE_CAPABILITIES,
+	RTE_SCHEDDEV_ERROR_TYPE_LEVEL_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_WRED_PROFILE,
+	RTE_SCHEDDEV_ERROR_TYPE_WRED_PROFILE_GREEN,
+	RTE_SCHEDDEV_ERROR_TYPE_WRED_PROFILE_YELLOW,
+	RTE_SCHEDDEV_ERROR_TYPE_WRED_PROFILE_RED,
+	RTE_SCHEDDEV_ERROR_TYPE_WRED_PROFILE_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_SHARED_WRED_CONTEXT_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_COMMITTED_RATE,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_COMMITTED_SIZE,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_PEAK_RATE,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_PEAK_SIZE,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_PKT_ADJUST_LEN,
+	RTE_SCHEDDEV_ERROR_TYPE_SHAPER_PROFILE_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_SHARED_SHAPER_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARENT_NODE_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PRIORITY,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_WEIGHT,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_SHAPER_PROFILE_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_SHARED_SHAPER_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_N_SHARED_SHAPERS,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_STATS,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_SCHEDULING_MODE,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_N_PRIORITIES,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_CMAN,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_WRED_PROFILE_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_SHARED_WRED_CONTEXT_ID,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_PARAMS_N_SHARED_WRED_CONTEXTS,
+	RTE_SCHEDDEV_ERROR_TYPE_NODE_ID,
+};
+
+/**
+ * Verbose error structure definition.
+ *
+ * This object is normally allocated by applications and set by PMDs, the
+ * message points to a constant string which does not need to be freed by
+ * the application, however its pointer can be considered valid only as long
+ * as its associated DPDK port remains configured. Closing the underlying
+ * device or unloading the PMD invalidates it.
+ *
+ * Both cause and message may be NULL regardless of the error type.
+ */
+struct rte_scheddev_error {
+	enum rte_scheddev_error_type type; /**< Cause field and error type. */
+	const void *cause; /**< Object responsible for the error. */
+	const char *message; /**< Human-readable error message. */
+};
+
+/**
+ * Scheduler get number of leaf nodes
+ *
+ * Each leaf node sits on on top of a TX queue of the current Ethernet port.
+ * Therefore, the set of leaf nodes is predefined, their number is always equal
+ * to N (where N is the number of TX queues configured for the current port) and
+ * their IDs are 0 .. (N-1).
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param n_leaf_nodes
+ *   Number of leaf nodes for the current port.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_get_leaf_nodes(uint8_t port_id,
+	uint32_t *n_leaf_nodes,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node type (i.e. leaf or non-leaf) get
+ *
+ * The leaf nodes have predefined IDs in the range of 0 .. (N-1), where N is the
+ * number of TX queues of the current Ethernet port. The non-leaf nodes have
+ * their IDs generated by the application outside of the above range, which is
+ * reserved for leaf nodes.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID value. Needs to be valid.
+ * @param is_leaf
+ *   Set to non-zero value when node is leaf and to zero otherwise (non-leaf).
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_type_get(uint8_t port_id,
+	uint32_t node_id,
+	int *is_leaf,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler capabilities get
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param cap
+ *   Scheduler capabilities. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_capabilities_get(uint8_t port_id,
+	struct rte_scheddev_capabilities *cap,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler level capabilities get
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param level_id
+ *   The scheduler hierarchy level identifier. The value of 0 identifies the
+ *   level of the root node.
+ * @param cap
+ *   Scheduler level capabilities. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_level_capabilities_get(uint8_t port_id,
+	uint32_t level_id,
+	struct rte_scheddev_level_capabilities *cap,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node capabilities get
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param cap
+ *   Scheduler node capabilities. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_capabilities_get(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_node_capabilities *cap,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler WRED profile add
+ *
+ * Create a new WRED profile with ID set to *wred_profile_id*. The new profile
+ * is used to create one or several WRED contexts.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param wred_profile_id
+ *   WRED profile ID for the new profile. Needs to be unused.
+ * @param profile
+ *   WRED profile parameters. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_wred_profile_add(uint8_t port_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_wred_params *profile,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler WRED profile delete
+ *
+ * Delete an existing WRED profile. This operation fails when there is currently
+ * at least one user (i.e. WRED context) of this WRED profile.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param wred_profile_id
+ *   WRED profile ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_wred_profile_delete(uint8_t port_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shared WRED context add or update
+ *
+ * When *shared_wred_context_id* is invalid, a new WRED context with this ID is
+ * created by using the WRED profile identified by *wred_profile_id*.
+ *
+ * When *shared_wred_context_id* is valid, this WRED context is no longer using
+ * the profile previously assigned to it and is updated to use the profile
+ * identified by *wred_profile_id*.
+ *
+ * A valid shared WRED context can be assigned to several scheduler hierarchy
+ * leaf nodes configured to use WRED as the congestion management mode.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shared_wred_context_id
+ *   Shared WRED context ID
+ * @param wred_profile_id
+ *   WRED profile ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shared_wred_context_add_update(uint8_t port_id,
+	uint32_t shared_wred_context_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shared WRED context delete
+ *
+ * Delete an existing shared WRED context. This operation fails when there is
+ * currently at least one user (i.e. scheduler hierarchy leaf node) of this
+ * shared WRED context.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shared_wred_context_id
+ *   Shared WRED context ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shared_wred_context_delete(uint8_t port_id,
+	uint32_t shared_wred_context_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shaper profile add
+ *
+ * Create a new shaper profile with ID set to *shaper_profile_id*. The new
+ * shaper profile is used to create one or several shapers.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shaper_profile_id
+ *   Shaper profile ID for the new profile. Needs to be unused.
+ * @param profile
+ *   Shaper profile parameters. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shaper_profile_add(uint8_t port_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_shaper_params *profile,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shaper profile delete
+ *
+ * Delete an existing shaper profile. This operation fails when there is
+ * currently at least one user (i.e. shaper) of this shaper profile.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shaper_profile_id
+ *   Shaper profile ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shaper_profile_delete(uint8_t port_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shared shaper add or update
+ *
+ * When *shared_shaper_id* is not a valid shared shaper ID, a new shared shaper
+ * with this ID is created using the shaper profile identified by
+ * *shaper_profile_id*.
+ *
+ * When *shared_shaper_id* is a valid shared shaper ID, this shared shaper is no
+ * longer using the shaper profile previously assigned to it and is updated to
+ * use the shaper profile identified by *shaper_profile_id*.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shared_shaper_id
+ *   Shared shaper ID
+ * @param shaper_profile_id
+ *   Shaper profile ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shared_shaper_add_update(uint8_t port_id,
+	uint32_t shared_shaper_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler shared shaper delete
+ *
+ * Delete an existing shared shaper. This operation fails when there is
+ * currently at least one user (i.e. scheduler hierarchy node) of this shared
+ * shaper.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param shared_shaper_id
+ *   Shared shaper ID. Needs to be the valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_shared_shaper_delete(uint8_t port_id,
+	uint32_t shared_shaper_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node add
+ *
+ * Create new node and connect it as child of an existing node. The new node is
+ * further identified by *node_id*, which needs to be unused by any of the
+ * existing nodes. The parent node is identified by *parent_node_id*, which
+ * needs to be the valid ID of an existing non-leaf node. The parent node is
+ * going to use the provided SP *priority* and WFQ/WRR *weight* to schedule its
+ * new child node.
+ *
+ * This function has to be called for both leaf and non-leaf nodes. In the case
+ * of leaf nodes (i.e. *node_id* is within the range of 0 .. (N-1), with N as
+ * the number of configured TX queues of the current port), the leaf node is
+ * configured rather than created (as the set of leaf nodes is predefined) and
+ * it is also connected as child of an existing node.
+ *
+ * The first node that is added becomes the root node and all the nodes that are
+ * subsequently added have to be added as descendants of the root node. The
+ * parent of the root node has to be specified as RTE_SCHEDDEV_NODE_ID_NULL and
+ * there can only be one node with this parent ID (i.e. the root node).
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be unused by any of the existing nodes.
+ * @param parent_node_id
+ *   Parent node ID. Needs to be the valid.
+ * @param priority
+ *   Node priority. The highest node priority is zero. Used by the SP algorithm
+ *   running on the parent of the current node for scheduling this child node.
+ * @param weight
+ *   Node weight. The node weight is relative to the weight sum of all siblings
+ *   that have the same priority. The lowest weight is one. Used by the WFQ/WRR
+ *   algorithm running on the parent of the current node for scheduling this
+ *   child node.
+ * @param params
+ *   Node parameters. Needs to be pre-allocated and valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_add(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_node_params *params,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node delete
+ *
+ * Delete an existing node. This operation fails when this node currently has at
+ * least one user (i.e. child node).
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_delete(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node suspend
+ *
+ * Suspend an existing node.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_suspend(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node resume
+ *
+ * Resume an existing node that was previously suspended.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_resume(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler hierarchy set
+ *
+ * This function is called during the port initialization phase (before the
+ * Ethernet port is started) to freeze the scheduler start-up hierarchy.
+ *
+ * This function fails when the currently configured scheduler hierarchy is not
+ * supported by the Ethernet port, in which case the user can abort or try out
+ * another hierarchy configuration (e.g. a hierarchy with less leaf nodes),
+ * which can be build from scratch (when *clear_on_fail* is enabled) or by
+ * modifying the existing hierarchy configuration (when *clear_on_fail* is
+ * disabled).
+ *
+ * Note that, even when the configured scheduler hierarchy is supported (so this
+ * function is successful), the Ethernet port start might still fail due to e.g.
+ * not enough memory being available in the system, etc.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param clear_on_fail
+ *   On function call failure, hierarchy is cleared when this parameter is
+ *   non-zero and preserved when this parameter is equal to zero.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_hierarchy_set(uint8_t port_id,
+	int clear_on_fail,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node parent update
+ *
+ * The parent of the root node cannot be changed.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param parent_node_id
+ *   Node ID for the new parent. Needs to be valid.
+ * @param priority
+ *   Node priority. The highest node priority is zero. Used by the SP algorithm
+ *   running on the parent of the current node for scheduling this child node.
+ * @param weight
+ *   Node weight. The node weight is relative to the weight sum of all siblings
+ *   that have the same priority. The lowest weight is zero. Used by the WFQ/WRR
+ *   algorithm running on the parent of the current node for scheduling this
+ *   child node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_parent_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node private shaper update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param shaper_profile_id
+ *   Shaper profile ID for the private shaper of the current node. Needs to be
+ *   either valid shaper profile ID or RTE_SCHEDDEV_SHAPER_PROFILE_ID_NONE, with
+ *   the latter disabling the private shaper of the current node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_shaper_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node shared shapers update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param shared_shaper_id
+ *   Shared shaper ID. Needs to be valid.
+ * @param add
+ *   Set to non-zero value to add this shared shaper to current node or to zero
+ *   to delete this shared shaper from current node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_shared_shaper_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shared_shaper_id,
+	int add,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node enabled statistics counters update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param stats_mask
+ *   Mask of statistics counter types to be enabled for the current node. This
+ *   needs to be a subset of the statistics counter types available for the
+ *   current node. Any statistics counter type not included in this set is to be
+ *   disabled for the current node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_stats_update(uint8_t port_id,
+	uint32_t node_id,
+	uint64_t stats_mask,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node scheduling mode update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid leaf node ID.
+ * @param scheduling_mode_per_priority
+ *   For each priority, indicates whether the children nodes sharing the same
+ *   priority are to be scheduled by WFQ or by WRR. When NULL, it indicates that
+ *   WFQ is to be used for all priorities. When non-NULL, it points to a
+ *   pre-allocated array of *n_priority* elements, with a non-zero value element
+ *   indicating WFQ and a zero value element for WRR.
+ * @param n_priorities
+ *   Number of priorities.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_scheduling_mode_update(uint8_t port_id,
+	uint32_t node_id,
+	int *scheduling_mode_per_priority,
+	uint32_t n_priorities,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node congestion management mode update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid leaf node ID.
+ * @param cman
+ *   Congestion management mode.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_cman_update(uint8_t port_id,
+	uint32_t node_id,
+	enum rte_scheddev_cman_mode cman,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node private WRED context update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid leaf node ID.
+ * @param wred_profile_id
+ *   WRED profile ID for the private WRED context of the current node. Needs to
+ *   be either valid WRED profile ID or RTE_SCHEDDEV_WRED_PROFILE_ID_NONE, with
+ *   the latter disabling the private WRED context of the current node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_wred_context_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node shared WRED context update
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid leaf node ID.
+ * @param shared_wred_context_id
+ *   Shared WRED context ID. Needs to be valid.
+ * @param add
+ *   Set to non-zero value to add this shared WRED context to current node or to
+ *   zero to delete this shared WRED context from current node.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_shared_wred_context_update(uint8_t port_id,
+	uint32_t node_id,
+	uint32_t shared_wred_context_id,
+	int add,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler node statistics counters read
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param node_id
+ *   Node ID. Needs to be valid.
+ * @param stats
+ *   When non-NULL, it contains the current value for the statistics counters
+ *   enabled for the current node.
+ * @param stats_mask
+ *   When non-NULL, it contains the mask of statistics counter types that are
+ *   currently enabled for this node, indicating which of the counters retrieved
+ *   with the *stats* structure are valid.
+ * @param clear
+ *   When this parameter has a non-zero value, the statistics counters are
+ *   cleared (i.e. set to zero) immediately after they have been read, otherwise
+ *   the statistics counters are left untouched.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_node_stats_read(uint8_t port_id,
+	uint32_t node_id,
+	struct rte_scheddev_node_stats *stats,
+	uint64_t *stats_mask,
+	int clear,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler packet marking - VLAN DEI (IEEE 802.1Q)
+ *
+ * IEEE 802.1p maps the traffic class to the VLAN Priority Code Point (PCP)
+ * field (3 bits), while IEEE 802.1q maps the drop priority to the VLAN Drop
+ * Eligible Indicator (DEI) field (1 bit), which was previously named Canonical
+ * Format Indicator (CFI).
+ *
+ * All VLAN frames of a given color get their DEI bit set if marking is enabled
+ * for this color; otherwise, their DEI bit is left as is (either set or not).
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param mark_green
+ *   Set to non-zero value to enable marking of green packets and to zero to
+ *   disable it.
+ * @param mark_yellow
+ *   Set to non-zero value to enable marking of yellow packets and to zero to
+ *   disable it.
+ * @param mark_red
+ *   Set to non-zero value to enable marking of red packets and to zero to
+ *   disable it.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_mark_vlan_dei(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler packet marking - IPv4 / IPv6 ECN (IETF RFC 3168)
+ *
+ * IETF RFCs 2474 and 3168 reorganize the IPv4 Type of Service (TOS) field
+ * (8 bits) and the IPv6 Traffic Class (TC) field (8 bits) into Differentiated
+ * Services Codepoint (DSCP) field (6 bits) and Explicit Congestion Notification
+ * (ECN) field (2 bits). The DSCP field is typically used to encode the traffic
+ * class and/or drop priority (RFC 2597), while the ECN field is used by RFC
+ * 3168 to implement a congestion notification mechanism to be leveraged by
+ * transport layer protocols such as TCP and SCTP that have congestion control
+ * mechanisms.
+ *
+ * When congestion is experienced, as alternative to dropping the packet,
+ * routers can change the ECN field of input packets from 2'b01 or 2'b10 (values
+ * indicating that source endpoint is ECN-capable) to 2'b11 (meaning that
+ * congestion is experienced). The destination endpoint can use the ECN-Echo
+ * (ECE) TCP flag to relay the congestion indication back to the source
+ * endpoint, which acknowledges it back to the destination endpoint with the
+ * Congestion Window Reduced (CWR) TCP flag.
+ *
+ * All IPv4/IPv6 packets of a given color with ECN set to 2’b01 or 2’b10
+ * carrying TCP or SCTP have their ECN set to 2’b11 if the marking feature is
+ * enabled for the current color, otherwise the ECN field is left as is.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param mark_green
+ *   Set to non-zero value to enable marking of green packets and to zero to
+ *   disable it.
+ * @param mark_yellow
+ *   Set to non-zero value to enable marking of yellow packets and to zero to
+ *   disable it.
+ * @param mark_red
+ *   Set to non-zero value to enable marking of red packets and to zero to
+ *   disable it.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_mark_ip_ecn(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+
+/**
+ * Scheduler packet marking - IPv4 / IPv6 DSCP (IETF RFC 2597)
+ *
+ * IETF RFC 2597 maps the traffic class and the drop priority to the IPv4/IPv6
+ * Differentiated Services Codepoint (DSCP) field (6 bits). Here are the DSCP
+ * values proposed by this RFC:
+ *
+ *                       Class 1    Class 2    Class 3    Class 4
+ *                     +----------+----------+----------+----------+
+ *    Low Drop Prec    |  001010  |  010010  |  011010  |  100010  |
+ *    Medium Drop Prec |  001100  |  010100  |  011100  |  100100  |
+ *    High Drop Prec   |  001110  |  010110  |  011110  |  100110  |
+ *                     +----------+----------+----------+----------+
+ *
+ * There are 4 traffic classes (classes 1 .. 4) encoded by DSCP bits 1 and 2, as
+ * well as 3 drop priorities (low/medium/high) encoded by DSCP bits 3 and 4.
+ *
+ * All IPv4/IPv6 packets have their color marked into DSCP bits 3 and 4 as
+ * follows: green mapped to Low Drop Precedence (2’b01), yellow to Medium
+ * (2’b10) and red to High (2’b11). Marking needs to be explicitly enabled
+ * for each color; when not enabled for a given color, the DSCP field of all
+ * packets with that color is left as is.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param mark_green
+ *   Set to non-zero value to enable marking of green packets and to zero to
+ *   disable it.
+ * @param mark_yellow
+ *   Set to non-zero value to enable marking of yellow packets and to zero to
+ *   disable it.
+ * @param mark_red
+ *   Set to non-zero value to enable marking of red packets and to zero to
+ *   disable it.
+ * @param error
+ *   Error details. Filled in only on error, when not NULL.
+ * @return
+ *   0 on success, non-zero error code otherwise.
+ */
+int
+rte_scheddev_mark_ip_dscp(uint8_t port_id,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __INCLUDE_RTE_SCHEDDEV_H__ */
diff --git a/lib/librte_ether/rte_scheddev_driver.h b/lib/librte_ether/rte_scheddev_driver.h
new file mode 100644
index 0000000..d245aea
--- /dev/null
+++ b/lib/librte_ether/rte_scheddev_driver.h
@@ -0,0 +1,365 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __INCLUDE_RTE_SCHEDDEV_DRIVER_H__
+#define __INCLUDE_RTE_SCHEDDEV_DRIVER_H__
+
+/**
+ * @file
+ * RTE Generic Hierarchical Scheduler API (Driver Side)
+ *
+ * This file provides implementation helpers for internal use by PMDs, they
+ * are not intended to be exposed to applications and are not subject to ABI
+ * versioning.
+ */
+
+#include <stdint.h>
+
+#include <rte_errno.h>
+#include "rte_ethdev.h"
+#include "rte_scheddev.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef int (*rte_scheddev_node_type_get_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	int *is_leaf,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node type get */
+
+typedef int (*rte_scheddev_capabilities_get_t)(struct rte_eth_dev *dev,
+	struct rte_scheddev_capabilities *cap,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler capabilities get */
+
+typedef int (*rte_scheddev_level_capabilities_get_t)(struct rte_eth_dev *dev,
+	uint32_t level_id,
+	struct rte_scheddev_level_capabilities *cap,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler level capabilities get */
+
+typedef int (*rte_scheddev_node_capabilities_get_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	struct rte_scheddev_node_capabilities *cap,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node capabilities get */
+
+typedef int (*rte_scheddev_wred_profile_add_t)(struct rte_eth_dev *dev,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_wred_params *profile,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler WRED profile add */
+
+typedef int (*rte_scheddev_wred_profile_delete_t)(struct rte_eth_dev *dev,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler WRED profile delete */
+
+typedef int (*rte_scheddev_shared_wred_context_add_update_t)(
+	struct rte_eth_dev *dev,
+	uint32_t shared_wred_context_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shared WRED context add */
+
+typedef int (*rte_scheddev_shared_wred_context_delete_t)(
+	struct rte_eth_dev *dev,
+	uint32_t shared_wred_context_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shared WRED context delete */
+
+typedef int (*rte_scheddev_shaper_profile_add_t)(struct rte_eth_dev *dev,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_shaper_params *profile,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shaper profile add */
+
+typedef int (*rte_scheddev_shaper_profile_delete_t)(struct rte_eth_dev *dev,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shaper profile delete */
+
+typedef int (*rte_scheddev_shared_shaper_add_update_t)(struct rte_eth_dev *dev,
+	uint32_t shared_shaper_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shared shaper add/update */
+
+typedef int (*rte_scheddev_shared_shaper_delete_t)(struct rte_eth_dev *dev,
+	uint32_t shared_shaper_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler shared shaper delete */
+
+typedef int (*rte_scheddev_node_add_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_node_params *params,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node add */
+
+typedef int (*rte_scheddev_node_delete_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node delete */
+
+typedef int (*rte_scheddev_node_suspend_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node suspend */
+
+typedef int (*rte_scheddev_node_resume_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node resume */
+
+typedef int (*rte_scheddev_hierarchy_set_t)(struct rte_eth_dev *dev,
+	int clear_on_fail,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler hierarchy set */
+
+typedef int (*rte_scheddev_node_parent_update_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t parent_node_id,
+	uint32_t priority,
+	uint32_t weight,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node parent update */
+
+typedef int (*rte_scheddev_node_shaper_update_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t shaper_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node shaper update */
+
+typedef int (*rte_scheddev_node_shared_shaper_update_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t shared_shaper_id,
+	int32_t add,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node shaper update */
+
+typedef int (*rte_scheddev_node_stats_update_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint64_t stats_mask,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node stats update */
+
+typedef int (*rte_scheddev_node_scheduling_mode_update_t)(
+	struct rte_eth_dev *dev,
+	uint32_t node_id,
+	int *scheduling_mode_per_priority,
+	uint32_t n_priorities,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node scheduling mode update */
+
+typedef int (*rte_scheddev_node_cman_update_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	enum rte_scheddev_cman_mode cman,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node congestion management mode update */
+
+typedef int (*rte_scheddev_node_wred_context_update_t)(
+	struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t wred_profile_id,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node WRED context update */
+
+typedef int (*rte_scheddev_node_shared_wred_context_update_t)(
+	struct rte_eth_dev *dev,
+	uint32_t node_id,
+	uint32_t shared_wred_context_id,
+	int add,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler node WRED context update */
+
+typedef int (*rte_scheddev_node_stats_read_t)(struct rte_eth_dev *dev,
+	uint32_t node_id,
+	struct rte_scheddev_node_stats *stats,
+	uint64_t *stats_mask,
+	int clear,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler read stats counters for specific node */
+
+typedef int (*rte_scheddev_mark_vlan_dei_t)(struct rte_eth_dev *dev,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler packet marking - VLAN DEI */
+
+typedef int (*rte_scheddev_mark_ip_ecn_t)(struct rte_eth_dev *dev,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler packet marking - IPv4/IPv6 ECN */
+
+typedef int (*rte_scheddev_mark_ip_dscp_t)(struct rte_eth_dev *dev,
+	int mark_green,
+	int mark_yellow,
+	int mark_red,
+	struct rte_scheddev_error *error);
+/**< @internal Scheduler packet marking - IPv4/IPv6 DSCP */
+
+struct rte_scheddev_ops {
+	/** Scheduler node type get */
+	rte_scheddev_node_type_get_t node_type_get;
+
+	/** Scheduler capabilities_get */
+	rte_scheddev_capabilities_get_t capabilities_get;
+	/** Scheduler level capabilities_get */
+	rte_scheddev_level_capabilities_get_t level_capabilities_get;
+	/** Scheduler node capabilities get */
+	rte_scheddev_node_capabilities_get_t node_capabilities_get;
+
+	/** Scheduler WRED profile add */
+	rte_scheddev_wred_profile_add_t wred_profile_add;
+	/** Scheduler WRED profile delete */
+	rte_scheddev_wred_profile_delete_t wred_profile_delete;
+	/** Scheduler shared WRED context add/update */
+	rte_scheddev_shared_wred_context_add_update_t
+		shared_wred_context_add_update;
+	/** Scheduler shared WRED context delete */
+	rte_scheddev_shared_wred_context_delete_t
+		shared_wred_context_delete;
+
+	/** Scheduler shaper profile add */
+	rte_scheddev_shaper_profile_add_t shaper_profile_add;
+	/** Scheduler shaper profile delete */
+	rte_scheddev_shaper_profile_delete_t shaper_profile_delete;
+	/** Scheduler shared shaper add/update */
+	rte_scheddev_shared_shaper_add_update_t shared_shaper_add_update;
+	/** Scheduler shared shaper delete */
+	rte_scheddev_shared_shaper_delete_t shared_shaper_delete;
+
+	/** Scheduler node add */
+	rte_scheddev_node_add_t node_add;
+	/** Scheduler node delete */
+	rte_scheddev_node_delete_t node_delete;
+	/** Scheduler node suspend */
+	rte_scheddev_node_suspend_t node_suspend;
+	/** Scheduler node resume */
+	rte_scheddev_node_resume_t node_resume;
+	/** Scheduler hierarchy set */
+	rte_scheddev_hierarchy_set_t hierarchy_set;
+
+	/** Scheduler node parent update */
+	rte_scheddev_node_parent_update_t node_parent_update;
+	/** Scheduler node shaper update */
+	rte_scheddev_node_shaper_update_t node_shaper_update;
+	/** Scheduler node shared shaper update */
+	rte_scheddev_node_shared_shaper_update_t node_shared_shaper_update;
+	/** Scheduler node stats update */
+	rte_scheddev_node_stats_update_t node_stats_update;
+	/** Scheduler node scheduling mode update */
+	rte_scheddev_node_scheduling_mode_update_t node_scheduling_mode_update;
+	/** Scheduler node congestion management mode update */
+	rte_scheddev_node_cman_update_t node_cman_update;
+	/** Scheduler node WRED context update */
+	rte_scheddev_node_wred_context_update_t node_wred_context_update;
+	/** Scheduler node shared WRED context update */
+	rte_scheddev_node_shared_wred_context_update_t
+		node_shared_wred_context_update;
+	/** Scheduler read statistics counters for current node */
+	rte_scheddev_node_stats_read_t node_stats_read;
+
+	/** Scheduler packet marking - VLAN DEI */
+	rte_scheddev_mark_vlan_dei_t mark_vlan_dei;
+	/** Scheduler packet marking - IPv4/IPv6 ECN */
+	rte_scheddev_mark_ip_ecn_t mark_ip_ecn;
+	/** Scheduler packet marking - IPv4/IPv6 DSCP */
+	rte_scheddev_mark_ip_dscp_t mark_ip_dscp;
+};
+
+/**
+ * Initialize generic error structure.
+ *
+ * This function also sets rte_errno to a given value.
+ *
+ * @param error
+ *   Pointer to error structure (may be NULL).
+ * @param code
+ *   Related error code (rte_errno).
+ * @param type
+ *   Cause field and error type.
+ * @param cause
+ *   Object responsible for the error.
+ * @param message
+ *   Human-readable error message.
+ *
+ * @return
+ *   Error code.
+ */
+static inline int
+rte_scheddev_error_set(struct rte_scheddev_error *error,
+		   int code,
+		   enum rte_scheddev_error_type type,
+		   const void *cause,
+		   const char *message)
+{
+	if (error) {
+		*error = (struct rte_scheddev_error){
+			.type = type,
+			.cause = cause,
+			.message = message,
+		};
+	}
+	rte_errno = code;
+	return code;
+}
+
+/**
+ * Get generic hierarchical scheduler operations structure from a port
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param error
+ *   Error details
+ *
+ * @return
+ *   The hierarchical scheduler operations structure associated with port_id on
+ *   success, NULL otherwise.
+ */
+const struct rte_scheddev_ops *
+rte_scheddev_ops_get(uint8_t port_id, struct rte_scheddev_error *error);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __INCLUDE_RTE_SCHEDDEV_DRIVER_H__ */
-- 
2.5.0