[RFC PATCH] ethdev: add flow item for RoCE infiniband BTH

[RFC PATCH] ethdev: add flow item for RoCE infiniband BTH

[dong zhou]

From: Dong Zhou <dongzhou@nvidia.com>

IB(InfiniBand) is one type of networking used in high-performance
computing with high throughput and low latency. Like Ethernet,
IB defines a layered protocol (Physical, Link, Network, Transport
Layers). IB provides native support for RDMA(Remote DMA), an
extension of the DMA that allows direct access to remote host
memory without CPU intervention. IB network requires NICs and
switches to support the IB protocol.

RoCE(RDMA over Converged Ethernet) is a network protocol that
allows RDMA to run on Ethernet. RoCE encapsulates IB packets on
ethernet and has two versions, RoCEv1 and RoCEv2. RoCEv1 is an
ethernet link layer protocol, IB packets are encapsulated in the
ethernet layer and use ethernet type 0x8915. RoCEv2 is an internet
layer protocol, IB packets are encapsulated in UDP payload and
use a destination port 4791, The format of the RoCEv2 packet is
as follows:
  ETH + IP + UDP(dport 4791) + IB(BTH + ExtHDR + PAYLOAD + CRC)

BTH(Base Transport Header) is the IB transport layer header, RoCEv1
and RoCEv2 both contain this header. This patch introduces a new
RTE item to match the IB BTH in RoCE packets. One use of this match
is that the user can monitor RoCEv2's CNP(Congestion Notification
Packet) by matching BTH opcode 0x81.

This patch also adds the testpmd command line to match the RoCEv2
BTH. Usage example:

  testpmd> flow create 0 group 1 ingress pattern
           eth / ipv4 / udp dst is 4791 / ib_bth opcode is 0x81
           dst_qp is 0xd3 / end actions queue index 0 / end

Signed-off-by: Dong Zhou <dongzhou@nvidia.com>
---
 app/test-pmd/cmdline_flow.c                 | 58 ++++++++++++++++++
 doc/guides/nics/features/default.ini        |  1 +
 doc/guides/prog_guide/rte_flow.rst          |  7 +++
 doc/guides/testpmd_app_ug/testpmd_funcs.rst |  6 ++
 lib/ethdev/rte_flow.c                       |  1 +
 lib/ethdev/rte_flow.h                       | 27 ++++++++
 lib/net/rte_ib.h                            | 68 +++++++++++++++++++++
 7 files changed, 168 insertions(+)
 create mode 100644 lib/net/rte_ib.h

diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdline_flow.c
index 5fbc450849..3ff33b281d 100644
--- a/app/test-pmd/cmdline_flow.c
+++ b/app/test-pmd/cmdline_flow.c
@@ -531,6 +531,11 @@ enum index {
 	ITEM_QUOTA_STATE_NAME,
 	ITEM_PORT_AFFINITY,
 	ITEM_PORT_AFFINITY_VALUE,
+	ITEM_IB_BTH,
+	ITEM_IB_BTH_OPCODE,
+	ITEM_IB_BTH_PKEY,
+	ITEM_IB_BTH_DST_QPN,
+	ITEM_IB_BTH_PSN,
 
 	/* Validate/create actions. */
 	ACTIONS,
@@ -1517,6 +1522,7 @@ static const enum index next_item[] = {
 	ITEM_QUOTA,
 	ITEM_PORT_AFFINITY,
 	ITEM_IPSEC_SYNDROME,
+	ITEM_IB_BTH,
 	END_SET,
 	ZERO,
 };
@@ -2025,6 +2031,15 @@ static const enum index item_ipsec_syndrome[] = {
 	ZERO,
 };
 
+static const enum index item_ib_bth[] = {
+	ITEM_IB_BTH_OPCODE,
+	ITEM_IB_BTH_PKEY,
+	ITEM_IB_BTH_DST_QPN,
+	ITEM_IB_BTH_PSN,
+	ITEM_NEXT,
+	ZERO,
+};
+
 static const enum index next_action[] = {
 	ACTION_END,
 	ACTION_VOID,
@@ -5750,6 +5765,46 @@ static const struct token token_list[] = {
 		.args = ARGS(ARGS_ENTRY(struct mlx5_flow_item_ipsec_syndrome,
 					syndrome)),
 	},
+	[ITEM_IB_BTH] = {
+		.name = "ib_bth",
+		.help = "match ib bth fields",
+		.priv = PRIV_ITEM(IB_BTH,
+				  sizeof(struct rte_flow_item_ib_bth)),
+		.next = NEXT(item_ib_bth),
+		.call = parse_vc,
+	},
+	[ITEM_IB_BTH_OPCODE] = {
+		.name = "opcode",
+		.help = "match ib bth opcode",
+		.next = NEXT(item_ib_bth, NEXT_ENTRY(COMMON_UNSIGNED),
+				 item_param),
+		.args = ARGS(ARGS_ENTRY_HTON(struct rte_flow_item_ib_bth,
+						 hdr.opcode)),
+	},
+	[ITEM_IB_BTH_PKEY] = {
+		.name = "pkey",
+		.help = "partition key",
+		.next = NEXT(item_ib_bth, NEXT_ENTRY(COMMON_UNSIGNED),
+				 item_param),
+		.args = ARGS(ARGS_ENTRY_HTON(struct rte_flow_item_ib_bth,
+						 hdr.pkey)),
+	},
+	[ITEM_IB_BTH_DST_QPN] = {
+		.name = "dst_qp",
+		.help = "destination qp",
+		.next = NEXT(item_ib_bth, NEXT_ENTRY(COMMON_UNSIGNED),
+				 item_param),
+		.args = ARGS(ARGS_ENTRY_HTON(struct rte_flow_item_ib_bth,
+						 hdr.dst_qp)),
+	},
+	[ITEM_IB_BTH_PSN] = {
+		.name = "psn",
+		.help = "packet sequence number",
+		.next = NEXT(item_ib_bth, NEXT_ENTRY(COMMON_UNSIGNED),
+				 item_param),
+		.args = ARGS(ARGS_ENTRY_HTON(struct rte_flow_item_ib_bth,
+						 hdr.psn)),
+	},
 	/* Validate/create actions. */
 	[ACTIONS] = {
 		.name = "actions",
@@ -12634,6 +12689,9 @@ flow_item_default_mask(const struct rte_flow_item *item)
 	case RTE_FLOW_ITEM_TYPE_IPV6_ROUTING_EXT:
 		mask = &ipv6_routing_ext_default_mask;
 		break;
+	case RTE_FLOW_ITEM_TYPE_IB_BTH:
+		mask = &rte_flow_item_ib_bth_mask;
+		break;
 	default:
 		break;
 	}
diff --git a/doc/guides/nics/features/default.ini b/doc/guides/nics/features/default.ini
index 510cc6679d..54045a29a0 100644
--- a/doc/guides/nics/features/default.ini
+++ b/doc/guides/nics/features/default.ini
@@ -103,6 +103,7 @@ gtpc                 =
 gtpu                 =
 gtp_psc              =
 higig2               =
+ib_bth               =
 icmp                 =
 icmp6                =
 icmp6_nd_na          =
diff --git a/doc/guides/prog_guide/rte_flow.rst b/doc/guides/prog_guide/rte_flow.rst
index 1d81334e96..363bbdd5d8 100644
--- a/doc/guides/prog_guide/rte_flow.rst
+++ b/doc/guides/prog_guide/rte_flow.rst
@@ -1574,6 +1574,13 @@ Matches ipv6 routing extension header.
 - ``type``: IPv6 routing extension header type.
 - ``segments_left``: How many IPv6 destination addresses carries on
 
+Item: ``IB_BTH``
+^^^^^^^^^^^^^^^^
+
+Matches an InfiniBand base transport header in RoCE packet.
+
+- ``hdr``: InfiniBand base transport header definition (``rte_ib.h``).
+
 Actions
 ~~~~~~~
 
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index 0c3317ee06..de90958596 100644
--- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
+++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
@@ -3741,6 +3741,12 @@ This section lists supported pattern items and their attributes, if any.
 
 - ``send_to_kernel``: send packets to kernel.
 
+- ``ib_bth``: match InfiniBand BTH(base transport header).
+
+  - ``opcode {unsigned}``: Opcode.
+  - ``pkey {unsigned}``: Partition key.
+  - ``dst_qp {unsigned}``: Destination Queue Pair.
+  - ``psn {unsigned}``: Packet Sequence Number.
 
 Actions list
 ^^^^^^^^^^^^
diff --git a/lib/ethdev/rte_flow.c b/lib/ethdev/rte_flow.c
index 515edb0c01..61066aa615 100644
--- a/lib/ethdev/rte_flow.c
+++ b/lib/ethdev/rte_flow.c
@@ -179,6 +179,7 @@ static const struct rte_flow_desc_data rte_flow_desc_item[] = {
 	MK_FLOW_ITEM(PORT_AFFINITY, sizeof(struct rte_flow_item_port_affinity)),
 	MK_FLOW_ITEM_FN(IPV6_ROUTING_EXT, sizeof(struct rte_flow_item_ipv6_routing_ext),
 			rte_flow_item_ipv6_routing_ext_conv),
+	MK_FLOW_ITEM(IB_BTH, sizeof(struct rte_flow_item_ib_bth)),
 };
 
 /** Generate flow_action[] entry. */
diff --git a/lib/ethdev/rte_flow.h b/lib/ethdev/rte_flow.h
index 1590cd0498..d78bcf17cd 100644
--- a/lib/ethdev/rte_flow.h
+++ b/lib/ethdev/rte_flow.h
@@ -38,6 +38,7 @@
 #include <rte_ppp.h>
 #include <rte_gre.h>
 #include <rte_macsec.h>
+#include <rte_ib.h>
 
 #ifdef __cplusplus
 extern "C" {
@@ -691,6 +692,13 @@ enum rte_flow_item_type {
 	 * See struct rte_flow_item_ipv6_routing_ext.
 	 */
 	RTE_FLOW_ITEM_TYPE_IPV6_ROUTING_EXT,
+
+	/**
+	 * Matches an InfiniBand base transport header in RoCE packet.
+	 *
+	 * See struct rte_flow_item_ib_bth.
+	 */
+	RTE_FLOW_ITEM_TYPE_IB_BTH,
 };
 
 /**
@@ -2284,6 +2292,25 @@ rte_flow_item_port_affinity_mask = {
 };
 #endif
 
+/**
+ * RTE_FLOW_ITEM_TYPE_IB_BTH.
+ *
+ * Matches an InfiniBand base transport header in RoCE packet.
+ */
+struct rte_flow_item_ib_bth {
+	struct rte_ib_bth hdr; /**< InfiniBand base transport header definition. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_IB_BTH. */
+#ifndef __cplusplus
+static const struct rte_flow_item_ib_bth rte_flow_item_ib_bth_mask = {
+	.hdr = {
+		.opcode = 0xff,
+		.dst_qp = "\xff\xff\xff",
+	},
+};
+#endif
+
 /**
  * Action types.
  *
diff --git a/lib/net/rte_ib.h b/lib/net/rte_ib.h
new file mode 100644
index 0000000000..c1b2797815
--- /dev/null
+++ b/lib/net/rte_ib.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2023 NVIDIA Corporation & Affiliates
+ */
+
+#ifndef RTE_IB_H
+#define RTE_IB_H
+
+/**
+ * @file
+ *
+ * InfiniBand headers definitions
+ *
+ * The infiniBand headers are used by RoCE (RDMA over Converged Ethernet).
+ */
+
+#include <stdint.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * InfiniBand Base Transport Header according to
+ * IB Specification Vol 1-Release-1.4.
+ */
+__extension__
+struct rte_ib_bth {
+	uint8_t	opcode;		/**< Opcode. */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	uint8_t	tver:4;		/**< Transport Header Version. */
+	uint8_t	padcnt:2;	/**< Pad Count. */
+	uint8_t	m:1;		/**< MigReq. */
+	uint8_t	se:1;		/**< Solicited Event. */
+#elif RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	uint8_t	se:1;		/**< Solicited Event. */
+	uint8_t	m:1;		/**< MigReq. */
+	uint8_t	padcnt:2;	/**< Pad Count. */
+	uint8_t	tver:4;		/**< Transport Header Version. */
+#endif
+	rte_be16_t pkey;	/**< Partition key. */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	uint8_t	rsvd0:6;	/**< Reserved. */
+	uint8_t	b:1;		/**< BECN. */
+	uint8_t	f:1;		/**< FECN. */
+#elif RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	uint8_t	f:1;		/**< FECN. */
+	uint8_t	b:1;		/**< BECN. */
+	uint8_t	rsvd0:6;	/**< Reserved. */
+#endif
+	uint8_t	dst_qp[3];	/**< Destination QP */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	uint8_t	rsvd1:7;	/**< Reserved. */
+	uint8_t	a:1;		/**< Acknowledge Request. */
+#elif RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	uint8_t	a:1;		/**< Acknowledge Request. */
+	uint8_t	rsvd1:7;	/**< Reserved. */
+#endif
+	uint8_t	psn[3];		/**< Packet Sequence Number */
+} __rte_packed;
+
+/** RoCEv2 default port. */
+#define RTE_ROCEV2_DEFAULT_PORT 4791
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_IB_H */
-- 
2.27.0