[PATCH v3 iproute2-next 1/8] rdma: include rdma-core <rdma/rdma_cma.h>

[PATCH v3 iproute2-next 1/8] rdma: include rdma-core <rdma/rdma_cma.h>

[Steve Wise]

This avoids requiring rdma-core be installed on systems.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---
 rdma/include/rdma/rdma_cma.h | 728 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 728 insertions(+)
 create mode 100644 rdma/include/rdma/rdma_cma.h

diff --git a/rdma/include/rdma/rdma_cma.h b/rdma/include/rdma/rdma_cma.h
new file mode 100644
index 0000000..456aa4e
--- /dev/null
+++ b/rdma/include/rdma/rdma_cma.h
@@ -0,0 +1,728 @@
+/*
+ * Copyright (c) 2005 Voltaire Inc.  All rights reserved.
+ * Copyright (c) 2005-2014 Intel Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     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.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#if !defined(_RDMA_CMA_H)
+#define _RDMA_CMA_H
+
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <infiniband/verbs.h>
+#include <infiniband/sa.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+ * Upon receiving a device removal event, users must destroy the associated
+ * RDMA identifier and release all resources allocated with the device.
+ */
+enum rdma_cm_event_type {
+	RDMA_CM_EVENT_ADDR_RESOLVED,
+	RDMA_CM_EVENT_ADDR_ERROR,
+	RDMA_CM_EVENT_ROUTE_RESOLVED,
+	RDMA_CM_EVENT_ROUTE_ERROR,
+	RDMA_CM_EVENT_CONNECT_REQUEST,
+	RDMA_CM_EVENT_CONNECT_RESPONSE,
+	RDMA_CM_EVENT_CONNECT_ERROR,
+	RDMA_CM_EVENT_UNREACHABLE,
+	RDMA_CM_EVENT_REJECTED,
+	RDMA_CM_EVENT_ESTABLISHED,
+	RDMA_CM_EVENT_DISCONNECTED,
+	RDMA_CM_EVENT_DEVICE_REMOVAL,
+	RDMA_CM_EVENT_MULTICAST_JOIN,
+	RDMA_CM_EVENT_MULTICAST_ERROR,
+	RDMA_CM_EVENT_ADDR_CHANGE,
+	RDMA_CM_EVENT_TIMEWAIT_EXIT
+};
+
+enum rdma_port_space {
+	RDMA_PS_IPOIB = 0x0002,
+	RDMA_PS_TCP   = 0x0106,
+	RDMA_PS_UDP   = 0x0111,
+	RDMA_PS_IB    = 0x013F,
+};
+
+#define RDMA_IB_IP_PS_MASK   0xFFFFFFFFFFFF0000ULL
+#define RDMA_IB_IP_PORT_MASK 0x000000000000FFFFULL
+#define RDMA_IB_IP_PS_TCP    0x0000000001060000ULL
+#define RDMA_IB_IP_PS_UDP    0x0000000001110000ULL
+#define RDMA_IB_PS_IB        0x00000000013F0000ULL
+
+/*
+ * Global qkey value for UDP QPs and multicast groups created via the 
+ * RDMA CM.
+ */
+#define RDMA_UDP_QKEY 0x01234567
+
+struct rdma_ib_addr {
+	union ibv_gid	sgid;
+	union ibv_gid	dgid;
+	__be16		pkey;
+};
+
+struct rdma_addr {
+	union {
+		struct sockaddr		src_addr;
+		struct sockaddr_in	src_sin;
+		struct sockaddr_in6	src_sin6;
+		struct sockaddr_storage src_storage;
+	};
+	union {
+		struct sockaddr		dst_addr;
+		struct sockaddr_in	dst_sin;
+		struct sockaddr_in6	dst_sin6;
+		struct sockaddr_storage dst_storage;
+	};
+	union {
+		struct rdma_ib_addr	ibaddr;
+	} addr;
+};
+
+struct rdma_route {
+	struct rdma_addr	 addr;
+	struct ibv_sa_path_rec	*path_rec;
+	int			 num_paths;
+};
+
+struct rdma_event_channel {
+	int			fd;
+};
+
+struct rdma_cm_id {
+	struct ibv_context	*verbs;
+	struct rdma_event_channel *channel;
+	void			*context;
+	struct ibv_qp		*qp;
+	struct rdma_route	 route;
+	enum rdma_port_space	 ps;
+	uint8_t			 port_num;
+	struct rdma_cm_event	*event;
+	struct ibv_comp_channel *send_cq_channel;
+	struct ibv_cq		*send_cq;
+	struct ibv_comp_channel *recv_cq_channel;
+	struct ibv_cq		*recv_cq;
+	struct ibv_srq		*srq;
+	struct ibv_pd		*pd;
+	enum ibv_qp_type	qp_type;
+};
+
+enum {
+	RDMA_MAX_RESP_RES = 0xFF,
+	RDMA_MAX_INIT_DEPTH = 0xFF
+};
+
+struct rdma_conn_param {
+	const void *private_data;
+	uint8_t private_data_len;
+	uint8_t responder_resources;
+	uint8_t initiator_depth;
+	uint8_t flow_control;
+	uint8_t retry_count;		/* ignored when accepting */
+	uint8_t rnr_retry_count;
+	/* Fields below ignored if a QP is created on the rdma_cm_id. */
+	uint8_t srq;
+	uint32_t qp_num;
+};
+
+struct rdma_ud_param {
+	const void *private_data;
+	uint8_t private_data_len;
+	struct ibv_ah_attr ah_attr;
+	uint32_t qp_num;
+	uint32_t qkey;
+};
+
+struct rdma_cm_event {
+	struct rdma_cm_id	*id;
+	struct rdma_cm_id	*listen_id;
+	enum rdma_cm_event_type	 event;
+	int			 status;
+	union {
+		struct rdma_conn_param conn;
+		struct rdma_ud_param   ud;
+	} param;
+};
+
+#define RAI_PASSIVE		0x00000001
+#define RAI_NUMERICHOST		0x00000002
+#define RAI_NOROUTE		0x00000004
+#define RAI_FAMILY		0x00000008
+
+struct rdma_addrinfo {
+	int			ai_flags;
+	int			ai_family;
+	int			ai_qp_type;
+	int			ai_port_space;
+	socklen_t		ai_src_len;
+	socklen_t		ai_dst_len;
+	struct sockaddr		*ai_src_addr;
+	struct sockaddr		*ai_dst_addr;
+	char			*ai_src_canonname;
+	char			*ai_dst_canonname;
+	size_t			ai_route_len;
+	void			*ai_route;
+	size_t			ai_connect_len;
+	void			*ai_connect;
+	struct rdma_addrinfo	*ai_next;
+};
+
+/* Multicast join compatibility mask attributes */
+enum rdma_cm_join_mc_attr_mask {
+	RDMA_CM_JOIN_MC_ATTR_ADDRESS	= 1 << 0,
+	RDMA_CM_JOIN_MC_ATTR_JOIN_FLAGS	= 1 << 1,
+	RDMA_CM_JOIN_MC_ATTR_RESERVED	= 1 << 2,
+};
+
+/* Multicast join flags */
+enum rdma_cm_mc_join_flags {
+	RDMA_MC_JOIN_FLAG_FULLMEMBER,
+	RDMA_MC_JOIN_FLAG_SENDONLY_FULLMEMBER,
+	RDMA_MC_JOIN_FLAG_RESERVED,
+};
+
+struct rdma_cm_join_mc_attr_ex {
+	/* Bitwise OR between "rdma_cm_join_mc_attr_mask" enum */
+	uint32_t comp_mask;
+	/* Use a flag from "rdma_cm_mc_join_flags" enum */
+	uint32_t join_flags;
+	/* Multicast address identifying the group to join */
+	struct sockaddr *addr;
+};
+
+/**
+ * rdma_create_event_channel - Open a channel used to report communication events.
+ * Description:
+ *   Asynchronous events are reported to users through event channels.  Each
+ *   event channel maps to a file descriptor.
+ * Notes:
+ *   All created event channels must be destroyed by calling
+ *   rdma_destroy_event_channel.  Users should call rdma_get_cm_event to
+ *   retrieve events on an event channel.
+ * See also:
+ *   rdma_get_cm_event, rdma_destroy_event_channel
+ */
+struct rdma_event_channel *rdma_create_event_channel(void);
+
+/**
+ * rdma_destroy_event_channel - Close an event communication channel.
+ * @channel: The communication channel to destroy.
+ * Description:
+ *   Release all resources associated with an event channel and closes the
+ *   associated file descriptor.
+ * Notes:
+ *   All rdma_cm_id's associated with the event channel must be destroyed,
+ *   and all returned events must be acked before calling this function.
+ * See also:
+ *  rdma_create_event_channel, rdma_get_cm_event, rdma_ack_cm_event
+ */
+void rdma_destroy_event_channel(struct rdma_event_channel *channel);
+
+/**
+ * rdma_create_id - Allocate a communication identifier.
+ * @channel: The communication channel that events associated with the
+ *   allocated rdma_cm_id will be reported on.
+ * @id: A reference where the allocated communication identifier will be
+ *   returned.
+ * @context: User specified context associated with the rdma_cm_id.
+ * @ps: RDMA port space.
+ * Description:
+ *   Creates an identifier that is used to track communication information.
+ * Notes:
+ *   Rdma_cm_id's are conceptually equivalent to a socket for RDMA
+ *   communication.  The difference is that RDMA communication requires
+ *   explicitly binding to a specified RDMA device before communication
+ *   can occur, and most operations are asynchronous in nature.  Communication
+ *   events on an rdma_cm_id are reported through the associated event
+ *   channel.  Users must release the rdma_cm_id by calling rdma_destroy_id.
+ * See also:
+ *   rdma_create_event_channel, rdma_destroy_id, rdma_get_devices,
+ *   rdma_bind_addr, rdma_resolve_addr, rdma_connect, rdma_listen,
+ */
+int rdma_create_id(struct rdma_event_channel *channel,
+		   struct rdma_cm_id **id, void *context,
+		   enum rdma_port_space ps);
+
+/**
+ * rdma_create_ep - Allocate a communication identifier and qp.
+ * @id: A reference where the allocated communication identifier will be
+ *   returned.
+ * @res: Result from rdma_getaddrinfo, which specifies the source and
+ *   destination addresses, plus optional routing and connection information.
+ * @pd: Optional protection domain.  This parameter is ignored if qp_init_attr
+ *   is NULL.
+ * @qp_init_attr: Optional attributes for a QP created on the rdma_cm_id.
+ * Description:
+ *   Create an identifier and option QP used for communication.
+ * Notes:
+ *   If qp_init_attr is provided, then a queue pair will be allocated and
+ *   associated with the rdma_cm_id.  If a pd is provided, the QP will be
+ *   created on that PD.  Otherwise, the QP will be allocated on a default
+ *   PD.
+ *   The rdma_cm_id will be set to use synchronous operations (connect,
+ *   listen, and get_request).  To convert to asynchronous operation, the
+ *   rdma_cm_id should be migrated to a user allocated event channel.
+ * See also:
+ *   rdma_create_id, rdma_create_qp, rdma_migrate_id, rdma_connect,
+ *   rdma_listen
+ */
+int rdma_create_ep(struct rdma_cm_id **id, struct rdma_addrinfo *res,
+		   struct ibv_pd *pd, struct ibv_qp_init_attr *qp_init_attr);
+
+/**
+ * rdma_destroy_ep - Deallocates a communication identifier and qp.
+ * @id: The communication identifier to destroy.
+ * Description:
+ *   Destroys the specified rdma_cm_id and any associated QP created
+ *   on that id.
+ * See also:
+ *   rdma_create_ep
+ */
+void rdma_destroy_ep(struct rdma_cm_id *id);
+
+/**
+ * rdma_destroy_id - Release a communication identifier.
+ * @id: The communication identifier to destroy.
+ * Description:
+ *   Destroys the specified rdma_cm_id and cancels any outstanding
+ *   asynchronous operation.
+ * Notes:
+ *   Users must free any associated QP with the rdma_cm_id before
+ *   calling this routine and ack an related events.
+ * See also:
+ *   rdma_create_id, rdma_destroy_qp, rdma_ack_cm_event
+ */
+int rdma_destroy_id(struct rdma_cm_id *id);
+
+/**
+ * rdma_bind_addr - Bind an RDMA identifier to a source address.
+ * @id: RDMA identifier.
+ * @addr: Local address information.  Wildcard values are permitted.
+ * Description:
+ *   Associates a source address with an rdma_cm_id.  The address may be
+ *   wildcarded.  If binding to a specific local address, the rdma_cm_id
+ *   will also be bound to a local RDMA device.
+ * Notes:
+ *   Typically, this routine is called before calling rdma_listen to bind
+ *   to a specific port number, but it may also be called on the active side
+ *   of a connection before calling rdma_resolve_addr to bind to a specific
+ *   address.
+ * See also:
+ *   rdma_create_id, rdma_listen, rdma_resolve_addr, rdma_create_qp
+ */
+int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr);
+
+/**
+ * rdma_resolve_addr - Resolve destination and optional source addresses.
+ * @id: RDMA identifier.
+ * @src_addr: Source address information.  This parameter may be NULL.
+ * @dst_addr: Destination address information.
+ * @timeout_ms: Time to wait for resolution to complete.
+ * Description:
+ *   Resolve destination and optional source addresses from IP addresses
+ *   to an RDMA address.  If successful, the specified rdma_cm_id will
+ *   be bound to a local device.
+ * Notes:
+ *   This call is used to map a given destination IP address to a usable RDMA
+ *   address.  If a source address is given, the rdma_cm_id is bound to that
+ *   address, the same as if rdma_bind_addr were called.  If no source
+ *   address is given, and the rdma_cm_id has not yet been bound to a device,
+ *   then the rdma_cm_id will be bound to a source address based on the
+ *   local routing tables.  After this call, the rdma_cm_id will be bound to
+ *   an RDMA device.  This call is typically made from the active side of a
+ *   connection before calling rdma_resolve_route and rdma_connect.
+ * See also:
+ *   rdma_create_id, rdma_resolve_route, rdma_connect, rdma_create_qp,
+ *   rdma_get_cm_event, rdma_bind_addr
+ */
+int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
+		      struct sockaddr *dst_addr, int timeout_ms);
+
+/**
+ * rdma_resolve_route - Resolve the route information needed to establish a connection.
+ * @id: RDMA identifier.
+ * @timeout_ms: Time to wait for resolution to complete.
+ * Description:
+ *   Resolves an RDMA route to the destination address in order to establish
+ *   a connection.  The destination address must have already been resolved
+ *   by calling rdma_resolve_addr.
+ * Notes:
+ *   This is called on the client side of a connection after calling
+ *   rdma_resolve_addr, but before calling rdma_connect.
+ * See also:
+ *   rdma_resolve_addr, rdma_connect, rdma_get_cm_event
+ */
+int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms);
+
+/**
+ * rdma_create_qp - Allocate a QP.
+ * @id: RDMA identifier.
+ * @pd: Optional protection domain for the QP.
+ * @qp_init_attr: initial QP attributes.
+ * Description:
+ *  Allocate a QP associated with the specified rdma_cm_id and transition it
+ *  for sending and receiving.
+ * Notes:
+ *   The rdma_cm_id must be bound to a local RDMA device before calling this
+ *   function, and the protection domain must be for that same device.
+ *   QPs allocated to an rdma_cm_id are automatically transitioned by the
+ *   librdmacm through their states.  After being allocated, the QP will be
+ *   ready to handle posting of receives.  If the QP is unconnected, it will
+ *   be ready to post sends.
+ *   If pd is NULL, then the QP will be allocated using a default protection
+ *   domain associated with the underlying RDMA device.
+ * See also:
+ *   rdma_bind_addr, rdma_resolve_addr, rdma_destroy_qp, ibv_create_qp,
+ *   ibv_modify_qp
+ */
+int rdma_create_qp(struct rdma_cm_id *id, struct ibv_pd *pd,
+		   struct ibv_qp_init_attr *qp_init_attr);
+int rdma_create_qp_ex(struct rdma_cm_id *id,
+		      struct ibv_qp_init_attr_ex *qp_init_attr);
+
+/**
+ * rdma_destroy_qp - Deallocate a QP.
+ * @id: RDMA identifier.
+ * Description:
+ *   Destroy a QP allocated on the rdma_cm_id.
+ * Notes:
+ *   Users must destroy any QP associated with an rdma_cm_id before
+ *   destroying the ID.
+ * See also:
+ *   rdma_create_qp, rdma_destroy_id, ibv_destroy_qp
+ */
+void rdma_destroy_qp(struct rdma_cm_id *id);
+
+/**
+ * rdma_connect - Initiate an active connection request.
+ * @id: RDMA identifier.
+ * @conn_param: optional connection parameters.
+ * Description:
+ *   For a connected rdma_cm_id, this call initiates a connection request
+ *   to a remote destination.  For an unconnected rdma_cm_id, it initiates
+ *   a lookup of the remote QP providing the datagram service.
+ * Notes:
+ *   Users must have resolved a route to the destination address
+ *   by having called rdma_resolve_route before calling this routine.
+ *   A user may override the default connection parameters and exchange
+ *   private data as part of the connection by using the conn_param parameter.
+ * See also:
+ *   rdma_resolve_route, rdma_disconnect, rdma_listen, rdma_get_cm_event
+ */
+int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+
+/**
+ * rdma_listen - Listen for incoming connection requests.
+ * @id: RDMA identifier.
+ * @backlog: backlog of incoming connection requests.
+ * Description:
+ *   Initiates a listen for incoming connection requests or datagram service
+ *   lookup.  The listen will be restricted to the locally bound source
+ *   address.
+ * Notes:
+ *   Users must have bound the rdma_cm_id to a local address by calling
+ *   rdma_bind_addr before calling this routine.  If the rdma_cm_id is
+ *   bound to a specific IP address, the listen will be restricted to that
+ *   address and the associated RDMA device.  If the rdma_cm_id is bound
+ *   to an RDMA port number only, the listen will occur across all RDMA
+ *   devices.
+ * See also:
+ *   rdma_bind_addr, rdma_connect, rdma_accept, rdma_reject, rdma_get_cm_event
+ */
+int rdma_listen(struct rdma_cm_id *id, int backlog);
+
+/**
+ * rdma_get_request
+ */
+int rdma_get_request(struct rdma_cm_id *listen, struct rdma_cm_id **id);
+
+/**
+ * rdma_accept - Called to accept a connection request.
+ * @id: Connection identifier associated with the request.
+ * @conn_param: Optional information needed to establish the connection.
+ * Description:
+ *   Called from the listening side to accept a connection or datagram
+ *   service lookup request.
+ * Notes:
+ *   Unlike the socket accept routine, rdma_accept is not called on a
+ *   listening rdma_cm_id.  Instead, after calling rdma_listen, the user
+ *   waits for a connection request event to occur.  Connection request
+ *   events give the user a newly created rdma_cm_id, similar to a new
+ *   socket, but the rdma_cm_id is bound to a specific RDMA device.
+ *   rdma_accept is called on the new rdma_cm_id.
+ *   A user may override the default connection parameters and exchange
+ *   private data as part of the connection by using the conn_param parameter.
+ * See also:
+ *   rdma_listen, rdma_reject, rdma_get_cm_event
+ */
+int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+
+/**
+ * rdma_reject - Called to reject a connection request.
+ * @id: Connection identifier associated with the request.
+ * @private_data: Optional private data to send with the reject message.
+ * @private_data_len: Size of the private_data to send, in bytes.
+ * Description:
+ *   Called from the listening side to reject a connection or datagram
+ *   service lookup request.
+ * Notes:
+ *   After receiving a connection request event, a user may call rdma_reject
+ *   to reject the request.  If the underlying RDMA transport supports
+ *   private data in the reject message, the specified data will be passed to
+ *   the remote side.
+ * See also:
+ *   rdma_listen, rdma_accept, rdma_get_cm_event
+ */
+int rdma_reject(struct rdma_cm_id *id, const void *private_data,
+		uint8_t private_data_len);
+
+/**
+ * rdma_notify - Notifies the librdmacm of an asynchronous event.
+ * @id: RDMA identifier.
+ * @event: Asynchronous event.
+ * Description:
+ *   Used to notify the librdmacm of asynchronous events that have occurred
+ *   on a QP associated with the rdma_cm_id.
+ * Notes:
+ *   Asynchronous events that occur on a QP are reported through the user's
+ *   device event handler.  This routine is used to notify the librdmacm of
+ *   communication events.  In most cases, use of this routine is not
+ *   necessary, however if connection establishment is done out of band
+ *   (such as done through Infiniband), it's possible to receive data on a
+ *   QP that is not yet considered connected.  This routine forces the
+ *   connection into an established state in this case in order to handle
+ *   the rare situation where the connection never forms on its own.
+ *   Events that should be reported to the CM are: IB_EVENT_COMM_EST.
+ * See also:
+ *   rdma_connect, rdma_accept, rdma_listen
+ */
+int rdma_notify(struct rdma_cm_id *id, enum ibv_event_type event);
+
+/**
+ * rdma_disconnect - This function disconnects a connection.
+ * @id: RDMA identifier.
+ * Description:
+ *   Disconnects a connection and transitions any associated QP to the
+ *   error state.
+ * See also:
+ *   rdma_connect, rdma_listen, rdma_accept
+ */
+int rdma_disconnect(struct rdma_cm_id *id);
+
+/**
+ * rdma_join_multicast - Joins a multicast group.
+ * @id: Communication identifier associated with the request.
+ * @addr: Multicast address identifying the group to join.
+ * @context: User-defined context associated with the join request.
+ * Description:
+ *   Joins a multicast group and attaches an associated QP to the group.
+ * Notes:
+ *   Before joining a multicast group, the rdma_cm_id must be bound to
+ *   an RDMA device by calling rdma_bind_addr or rdma_resolve_addr.  Use of
+ *   rdma_resolve_addr requires the local routing tables to resolve the
+ *   multicast address to an RDMA device.  The user must call
+ *   rdma_leave_multicast to leave the multicast group and release any
+ *   multicast resources.  The context is returned to the user through
+ *   the private_data field in the rdma_cm_event.
+ * See also:
+ *   rdma_leave_multicast, rdma_bind_addr, rdma_resolve_addr, rdma_create_qp
+ */
+int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
+			void *context);
+
+/**
+ * rdma_leave_multicast - Leaves a multicast group.
+ * @id: Communication identifier associated with the request.
+ * @addr: Multicast address identifying the group to leave.
+ * Description:
+ *   Leaves a multicast group and detaches an associated QP from the group.
+ * Notes:
+ *   Calling this function before a group has been fully joined results in
+ *   canceling the join operation.  Users should be aware that messages
+ *   received from the multicast group may stilled be queued for
+ *   completion processing immediately after leaving a multicast group.
+ *   Destroying an rdma_cm_id will automatically leave all multicast groups.
+ * See also:
+ *   rdma_join_multicast, rdma_destroy_qp
+ */
+int rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr);
+
+/**
+ * rdma_multicast_ex - Joins a multicast group with options.
+ * @id: Communication identifier associated with the request.
+ * @mc_join_attr: Extensive struct containing multicast join parameters.
+ * @context: User-defined context associated with the join request.
+ * Description:
+ *  Joins a multicast group with options. Currently supporting MC join flags.
+ *  The QP will be attached based on the given join flag.
+ *  Join message will be sent according to the join flag.
+ * Notes:
+ *  Before joining a multicast group, the rdma_cm_id must be bound to
+ *  an RDMA device by calling rdma_bind_addr or rdma_resolve_addr.  Use of
+ *  rdma_resolve_addr requires the local routing tables to resolve the
+ *  multicast address to an RDMA device.  The user must call
+ *  rdma_leave_multicast to leave the multicast group and release any
+ *  multicast resources.  The context is returned to the user through
+ *  the private_data field in the rdma_cm_event.
+ * See also:
+ *  rdma_leave_multicast, rdma_bind_addr, rdma_resolve_addr, rdma_create_qp
+ */
+int rdma_join_multicast_ex(struct rdma_cm_id *id,
+			   struct rdma_cm_join_mc_attr_ex *mc_join_attr,
+			   void *context);
+
+/**
+ * rdma_get_cm_event - Retrieves the next pending communication event.
+ * @channel: Event channel to check for events.
+ * @event: Allocated information about the next communication event.
+ * Description:
+ *   Retrieves a communication event.  If no events are pending, by default,
+ *   the call will block until an event is received.
+ * Notes:
+ *   The default synchronous behavior of this routine can be changed by
+ *   modifying the file descriptor associated with the given channel.  All
+ *   events that are reported must be acknowledged by calling rdma_ack_cm_event.
+ *   Destruction of an rdma_cm_id will block until related events have been
+ *   acknowledged.
+ * See also:
+ *   rdma_ack_cm_event, rdma_create_event_channel, rdma_event_str
+ */
+int rdma_get_cm_event(struct rdma_event_channel *channel,
+		      struct rdma_cm_event **event);
+
+/**
+ * rdma_ack_cm_event - Free a communication event.
+ * @event: Event to be released.
+ * Description:
+ *   All events which are allocated by rdma_get_cm_event must be released,
+ *   there should be a one-to-one correspondence between successful gets
+ *   and acks.
+ * See also:
+ *   rdma_get_cm_event, rdma_destroy_id
+ */
+int rdma_ack_cm_event(struct rdma_cm_event *event);
+
+__be16 rdma_get_src_port(struct rdma_cm_id *id);
+__be16 rdma_get_dst_port(struct rdma_cm_id *id);
+
+static inline struct sockaddr *rdma_get_local_addr(struct rdma_cm_id *id)
+{
+	return &id->route.addr.src_addr;
+}
+
+static inline struct sockaddr *rdma_get_peer_addr(struct rdma_cm_id *id)
+{
+	return &id->route.addr.dst_addr;
+}
+
+/**
+ * rdma_get_devices - Get list of RDMA devices currently available.
+ * @num_devices: If non-NULL, set to the number of devices returned.
+ * Description:
+ *   Return a NULL-terminated array of opened RDMA devices.  Callers can use
+ *   this routine to allocate resources on specific RDMA devices that will be
+ *   shared across multiple rdma_cm_id's.
+ * Notes:
+ *   The returned array must be released by calling rdma_free_devices.  Devices
+ *   remain opened while the librdmacm is loaded.
+ * See also:
+ *   rdma_free_devices
+ */
+struct ibv_context **rdma_get_devices(int *num_devices);
+
+/**
+ * rdma_free_devices - Frees the list of devices returned by rdma_get_devices.
+ * @list: List of devices returned from rdma_get_devices.
+ * Description:
+ *   Frees the device array returned by rdma_get_devices.
+ * See also:
+ *   rdma_get_devices
+ */
+void rdma_free_devices(struct ibv_context **list);
+
+/**
+ * rdma_event_str - Returns a string representation of an rdma cm event.
+ * @event: Asynchronous event.
+ * Description:
+ *   Returns a string representation of an asynchronous event.
+ * See also:
+ *   rdma_get_cm_event
+ */
+const char *rdma_event_str(enum rdma_cm_event_type event);
+
+/* Option levels */
+enum {
+	RDMA_OPTION_ID		= 0,
+	RDMA_OPTION_IB		= 1
+};
+
+/* Option details */
+enum {
+	RDMA_OPTION_ID_TOS	 = 0,	/* uint8_t: RFC 2474 */
+	RDMA_OPTION_ID_REUSEADDR = 1,   /* int: ~SO_REUSEADDR */
+	RDMA_OPTION_ID_AFONLY	 = 2,   /* int: ~IPV6_V6ONLY */
+	RDMA_OPTION_IB_PATH	 = 1	/* struct ibv_path_data[] */
+};
+
+/**
+ * rdma_set_option - Set options for an rdma_cm_id.
+ * @id: Communication identifier to set option for.
+ * @level: Protocol level of the option to set.
+ * @optname: Name of the option to set.
+ * @optval: Reference to the option data.
+ * @optlen: The size of the %optval buffer.
+ */
+int rdma_set_option(struct rdma_cm_id *id, int level, int optname,
+		    void *optval, size_t optlen);
+
+/**
+ * rdma_migrate_id - Move an rdma_cm_id to a new event channel.
+ * @id: Communication identifier to migrate.
+ * @channel: New event channel for rdma_cm_id events.
+ */
+int rdma_migrate_id(struct rdma_cm_id *id, struct rdma_event_channel *channel);
+
+/**
+ * rdma_getaddrinfo - RDMA address and route resolution service.
+ */
+int rdma_getaddrinfo(const char *node, const char *service,
+		     const struct rdma_addrinfo *hints,
+		     struct rdma_addrinfo **res);
+
+void rdma_freeaddrinfo(struct rdma_addrinfo *res);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RDMA_CMA_H */
-- 
1.8.3.1

[PATCH v3 iproute2-next 2/8] rdma: Makefile change to find <rdma/rdma_cma.h>

[Steve Wise]

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---
 rdma/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rdma/Makefile b/rdma/Makefile
index 819fcbe..2cb46b6 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -4,7 +4,7 @@ include ../config.mk
 TARGETS :=
 
 ifeq ($(HAVE_MNL),y)
-CFLAGS += -I./include/uapi/
+CFLAGS += -I./include/uapi/ -I./include/
 
 RDMA_OBJ = rdma.o utils.o dev.o link.o res.o
 
-- 
1.8.3.1

[PATCH v3 iproute2-next 3/8] rdma: update rdma_netlink.h

[Steve Wise]

From: Steve Wise <swise@opengridcomputing.com>

Pull in the latest rdma_netlink.h which has support for
the rdma nldev resource tracking objects being added
with this patch series.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---
 rdma/include/uapi/rdma/rdma_netlink.h | 38 +++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/rdma/include/uapi/rdma/rdma_netlink.h b/rdma/include/uapi/rdma/rdma_netlink.h
index dbac3b8..9446a72 100644
--- a/rdma/include/uapi/rdma/rdma_netlink.h
+++ b/rdma/include/uapi/rdma/rdma_netlink.h
@@ -238,6 +238,14 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_QP_GET, /* can dump */
 
+	RDMA_NLDEV_CMD_RES_CM_ID_GET, /* can dump */
+
+	RDMA_NLDEV_CMD_RES_CQ_GET, /* can dump */
+
+	RDMA_NLDEV_CMD_RES_MR_GET, /* can dump */
+
+	RDMA_NLDEV_CMD_RES_PD_GET, /* can dump */
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -350,6 +358,36 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_RES_KERN_NAME,		/* string */
 
+	RDMA_NLDEV_ATTR_RES_CM_ID,		/* nested table */
+	RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY,	/* nested table */
+	/*
+	 * rdma_cm_id port space.
+	 */
+	RDMA_NLDEV_ATTR_RES_PS,			/* u32 */
+	/*
+	 * Source and destination socket addresses
+	 */
+	RDMA_NLDEV_ATTR_RES_SRC_ADDR,		/* __kernel_sockaddr_storage */
+	RDMA_NLDEV_ATTR_RES_DST_ADDR,		/* __kernel_sockaddr_storage */
+
+	RDMA_NLDEV_ATTR_RES_CQ,			/* nested table */
+	RDMA_NLDEV_ATTR_RES_CQ_ENTRY,		/* nested table */
+	RDMA_NLDEV_ATTR_RES_CQE,		/* u32 */
+	RDMA_NLDEV_ATTR_RES_USECNT,		/* u64 */
+	RDMA_NLDEV_ATTR_RES_POLL_CTX,		/* u8 */
+
+	RDMA_NLDEV_ATTR_RES_MR,			/* nested table */
+	RDMA_NLDEV_ATTR_RES_MR_ENTRY,		/* nested table */
+	RDMA_NLDEV_ATTR_RES_RKEY,		/* u32 */
+	RDMA_NLDEV_ATTR_RES_LKEY,		/* u32 */
+	RDMA_NLDEV_ATTR_RES_IOVA,		/* u64 */
+	RDMA_NLDEV_ATTR_RES_MRLEN,		/* u64 */
+
+	RDMA_NLDEV_ATTR_RES_PD,			/* nested table */
+	RDMA_NLDEV_ATTR_RES_PD_ENTRY,		/* nested table */
+	RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY,	/* u32 */
+	RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY,	/* u32 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _RDMA_NETLINK_H */
-- 
1.8.3.1

[PATCH v3 iproute2-next 4/8] rdma: initialize the rd struct

[Steve Wise]

Initialize the rd struct so port_idx is 0 unless set otherwise.
Otherwise, strict_port queries end up passing an uninitialized PORT
nlattr.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rdma/rdma.c b/rdma/rdma.c
index ab2c960..b43e538 100644
--- a/rdma/rdma.c
+++ b/rdma/rdma.c
@@ -135,7 +135,7 @@ int main(int argc, char **argv)
 	bool json_output = false;
 	bool force = false;
 	char *filename;
-	struct rd rd;
+	struct rd rd = {};
 	int opt;
 	int err;
 
-- 
1.8.3.1

[PATCH v3 iproute2-next 5/8] rdma: Add CM_ID resource tracking information

[Steve Wise]

Sample output:

# rdma resource
2: cxgb4_0: pd 5 cq 2 qp 2 cm_id 3 mr 7
3: mlx4_0: pd 7 cq 3 qp 3 cm_id 3 mr 7

# rdma resource show cm_id
link cxgb4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
link cxgb4_0/2 lqpn 1048 qp-type RC state CONNECT ps TCP pid 30503 comm rping src-addr 172.16.2.1:7174 dst-addr 172.16.2.1:38246
link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
link mlx4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
link mlx4_0/1 lqpn 539 qp-type RC state CONNECT ps TCP pid 30494 comm rping src-addr 172.16.99.1:7174 dst-addr 172.16.99.1:43670
link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174

# rdma resource show cm_id dst-port 7174
link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/rdma.h  |   2 +
 rdma/res.c   | 262 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 rdma/utils.c |   5 ++
 3 files changed, 268 insertions(+), 1 deletion(-)

diff --git a/rdma/rdma.h b/rdma/rdma.h
index 5809f70..e55205b 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -18,10 +18,12 @@
 #include <libmnl/libmnl.h>
 #include <rdma/rdma_netlink.h>
 #include <time.h>
+#include <net/if_arp.h>
 
 #include "list.h"
 #include "utils.h"
 #include "json_writer.h"
+#include <rdma/rdma_cma.h>
 
 #define pr_err(args...) fprintf(stderr, ##args)
 #define pr_out(args...) fprintf(stdout, ##args)
diff --git a/rdma/res.c b/rdma/res.c
index 62f5c54..5506cf3 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -16,9 +16,11 @@ static int res_help(struct rd *rd)
 {
 	pr_out("Usage: %s resource\n", rd->filename);
 	pr_out("          resource show [DEV]\n");
-	pr_out("          resource show [qp]\n");
+	pr_out("          resource show [qp|cm_id]\n");
 	pr_out("          resource show qp link [DEV/PORT]\n");
 	pr_out("          resource show qp link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
+	pr_out("          resource show cm_id link [DEV/PORT]\n");
+	pr_out("          resource show cm_id link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
 	return 0;
 }
 
@@ -433,6 +435,245 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
+static void print_qp_type(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_string_field(rd->jw, "qp-type",
+				   qp_types_to_str(val));
+	else
+		pr_out("qp-type %s ", qp_types_to_str(val));
+}
+
+static const char *cm_id_state_to_str(uint8_t idx)
+{
+	static const char * const cm_id_states_str[] = {
+		"IDLE", "ADDR_QUERY", "ADDR_RESOLVED", "ROUTE_QUERY",
+		"ROUTE_RESOLVED", "CONNECT", "DISCONNECT", "ADDR_BOUND",
+		"LISTEN", "DEVICE_REMOVAL", "DESTROYING" };
+
+	if (idx < ARRAY_SIZE(cm_id_states_str))
+		return cm_id_states_str[idx];
+	return "UNKNOWN";
+}
+
+static const char *cm_id_ps_to_str(uint32_t ps)
+{
+	switch (ps) {
+	case RDMA_PS_IPOIB:
+		return "IPoIB";
+	case RDMA_PS_IB:
+		return "IPoIB";
+	case RDMA_PS_TCP:
+		return "TCP";
+	case RDMA_PS_UDP:
+		return "UDP";
+	default:
+		return "---";
+	}
+}
+
+static void print_cm_id_state(struct rd *rd, uint8_t state)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "state", cm_id_state_to_str(state));
+		return;
+	}
+	pr_out("state %s ", cm_id_state_to_str(state));
+}
+
+static void print_ps(struct rd *rd, uint32_t ps)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "ps", cm_id_ps_to_str(ps));
+		return;
+	}
+	pr_out("ps %s ", cm_id_ps_to_str(ps));
+}
+
+static void print_ipaddr(struct rd *rd, const char *key, char *addrstr,
+			 uint16_t port)
+{
+	if (rd->json_output) {
+		int name_size = INET6_ADDRSTRLEN+strlen(":65535");
+		char json_name[name_size];
+
+		snprintf(json_name, name_size, "%s:%u", addrstr, port);
+		jsonw_string_field(rd->jw, key, json_name);
+		return;
+	}
+	pr_out("%s %s:%u ", key, addrstr, port);
+}
+
+static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
+{
+	struct __kernel_sockaddr_storage *addr;
+
+	addr = (struct __kernel_sockaddr_storage *)
+						mnl_attr_get_payload(nla_line);
+	switch (addr->ss_family) {
+	case AF_INET: {
+		struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+
+		if (!inet_ntop(AF_INET, (const void *)&sin->sin_addr, addr_str,
+			       INET6_ADDRSTRLEN))
+			return -EINVAL;
+		*port = ntohs(sin->sin_port);
+		break;
+	}
+	case AF_INET6: {
+		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+
+		if (!inet_ntop(AF_INET6, (const void *)&sin6->sin6_addr,
+			       addr_str, INET6_ADDRSTRLEN))
+			return -EINVAL;
+		*port = ntohs(sin6->sin6_port);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	int idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_CM_ID])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char src_addr_str[INET6_ADDRSTRLEN];
+		char dst_addr_str[INET6_ADDRSTRLEN];
+		uint16_t src_port, dst_port;
+		uint32_t port = 0, pid = 0;
+		uint8_t type = 0, state;
+		uint32_t lqpn = 0, ps;
+		char *comm = NULL;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+			port = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+		if (port && port != rd->port_idx)
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
+			lqpn = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+			if (rd_check_is_filtered(rd, "lqpn", lqpn))
+				continue;
+		}
+		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
+			type = mnl_attr_get_u8(
+					nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+			if (rd_check_is_string_filtered(rd, "qp-type",
+							qp_types_to_str(type)))
+				continue;
+		}
+
+		ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
+		if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
+			continue;
+
+		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+		if (rd_check_is_string_filtered(rd, "state",
+						cm_id_state_to_str(state)))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
+			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
+				    src_addr_str, &src_port))
+				continue;
+			if (rd_check_is_string_filtered(rd, "src-addr",
+							src_addr_str))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
+			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
+				    dst_addr_str, &dst_port))
+				continue;
+			if (rd_check_is_string_filtered(rd, "dst-addr",
+							dst_addr_str))
+				continue;
+		}
+
+		if (rd_check_is_filtered(rd, "src-port", src_port))
+			continue;
+
+		if (rd_check_is_filtered(rd, "dst-port", dst_port))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+		}
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, port, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
+			print_lqpn(rd, lqpn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
+			print_qp_type(rd, type);
+		print_cm_id_state(rd, state);
+		print_ps(rd, ps);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
+			print_ipaddr(rd, "src-addr", src_addr_str, src_port);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
+			print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		if (rd->json_output)
+			jsonw_end_array(rd->jw);
+		else
+			pr_out("\n");
+	}
+	return MNL_CB_OK;
+}
+
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -457,11 +698,30 @@ filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {{ .name = "link",
 
 RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
 
+static const
+struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "lqpn", .is_number = true },
+	{ .name = "qp-type", .is_number = false },
+	{ .name = "state", .is_number = false },
+	{ .name = "ps", .is_number = false },
+	{ .name = "dev-type", .is_number = false },
+	{ .name = "transport-type", .is_number = false },
+	{ .name = "pid", .is_number = true },
+	{ .name = "src-addr", .is_number = false },
+	{ .name = "src-port", .is_number = true },
+	{ .name = "dst-addr", .is_number = false },
+	{ .name = "dst-port", .is_number = true }
+};
+
+RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
+
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
 		{ NULL,		res_no_args	},
 		{ "qp",		res_qp		},
+		{ "cm_id",	res_cm_id	},
 		{ 0 }
 	};
 
diff --git a/rdma/utils.c b/rdma/utils.c
index f946016..ec81737 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -375,6 +375,11 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_RES_STATE]		= MNL_TYPE_U8,
 	[RDMA_NLDEV_ATTR_RES_PID]		= MNL_TYPE_U32,
 	[RDMA_NLDEV_ATTR_RES_KERN_NAME]	= MNL_TYPE_NUL_STRING,
+	[RDMA_NLDEV_ATTR_RES_CM_ID]		= MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY]	= MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_PS]		= MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_RES_SRC_ADDR]		= MNL_TYPE_UNSPEC,
+	[RDMA_NLDEV_ATTR_RES_DST_ADDR]		= MNL_TYPE_UNSPEC,
 };
 
 int rd_attr_cb(const struct nlattr *attr, void *data)
-- 
1.8.3.1

[PATCH v3 iproute2-next 6/8] rdma: Add CQ resource tracking information

[Steve Wise]

Sample output:

# rdma resource show cq
link cxgb4_0/- cqe 46 users 2 pid 30503 comm rping
link cxgb4_0/- cqe 46 users 2 pid 30498 comm rping
link mlx4_0/- cqe 63 users 2 pid 30494 comm rping
link mlx4_0/- cqe 63 users 2 pid 30489 comm rping
link mlx4_0/- cqe 1023 users 2 poll_ctx WORKQUEUE pid 0 comm [ib_core]

# rdma resource show cq pid 30489
link mlx4_0/- cqe 63 users 2 pid 30489 comm rping

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/res.c   | 139 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/utils.c |   5 +++
 2 files changed, 144 insertions(+)

diff --git a/rdma/res.c b/rdma/res.c
index 5506cf3..f1a90d3 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -21,6 +21,8 @@ static int res_help(struct rd *rd)
 	pr_out("          resource show qp link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
 	pr_out("          resource show cm_id link [DEV/PORT]\n");
 	pr_out("          resource show cm_id link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
+	pr_out("          resource show cq link [DEV/PORT]\n");
+	pr_out("          resource show cq link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
 	return 0;
 }
 
@@ -674,6 +676,132 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
+static void print_cqe(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "cqe", val);
+	else
+		pr_out("cqe %u ", val);
+}
+
+static void print_users(struct rd *rd, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "users", val);
+	else
+		pr_out("users %" PRIu64 " ", val);
+}
+
+static const char *poll_ctx_to_str(uint8_t idx)
+{
+	static const char * const cm_id_states_str[] = {
+		"DIRECT", "SOFTIRQ", "WORKQUEUE"};
+
+	if (idx < ARRAY_SIZE(cm_id_states_str))
+		return cm_id_states_str[idx];
+	return "UNKNOWN";
+}
+
+static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "poll-ctx",
+				   poll_ctx_to_str(poll_ctx));
+		return;
+	}
+	pr_out("poll-ctx %s ", poll_ctx_to_str(poll_ctx));
+}
+
+static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_CQ])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char *comm = NULL;
+		uint32_t pid = 0;
+		uint8_t poll_ctx = 0;
+		uint64_t users;
+		uint32_t cqe;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
+
+		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+		if (rd_check_is_filtered(rd, "users", users))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
+			poll_ctx = mnl_attr_get_u8(
+					nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
+			if (rd_check_is_string_filtered(rd, "poll-ctx",
+						poll_ctx_to_str(poll_ctx)))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, 0, nla_line);
+		print_cqe(rd, cqe);
+		print_users(rd, users);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
+			print_poll_ctx(rd, poll_ctx);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		if (rd->json_output)
+			jsonw_end_array(rd->jw);
+		else
+			pr_out("\n");
+	}
+	return MNL_CB_OK;
+}
+
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -716,12 +844,23 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
 
+static const
+struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "users", .is_number = true },
+	{ .name = "poll-ctx", .is_number = false },
+	{ .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
+
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
 		{ NULL,		res_no_args	},
 		{ "qp",		res_qp		},
 		{ "cm_id",	res_cm_id	},
+		{ "cq",		res_cq		},
 		{ 0 }
 	};
 
diff --git a/rdma/utils.c b/rdma/utils.c
index ec81737..5e79b62 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -380,6 +380,11 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_RES_PS]		= MNL_TYPE_U32,
 	[RDMA_NLDEV_ATTR_RES_SRC_ADDR]		= MNL_TYPE_UNSPEC,
 	[RDMA_NLDEV_ATTR_RES_DST_ADDR]		= MNL_TYPE_UNSPEC,
+	[RDMA_NLDEV_ATTR_RES_CQ] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_CQE] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_RES_USECNT] = MNL_TYPE_U64,
+	[RDMA_NLDEV_ATTR_RES_POLL_CTX] = MNL_TYPE_U8,
 };
 
 int rd_attr_cb(const struct nlattr *attr, void *data)
-- 
1.8.3.1

[PATCH v3 iproute2-next 7/8] rdma: Add MR resource tracking information

[Steve Wise]

Sample output:

Without CAP_NET_ADMIN:

$ rdma resource show mr mrlen 65536
link mlx4_0/- mrlen 65536 pid 0 comm [nvme_rdma]
link cxgb4_0/- mrlen 65536 pid 0 comm [nvme_rdma]

With CAP_NET_ADMIN:

# rdma resource show mr mrlen 65536
link mlx4_0/- rkey 0x12702 lkey 0x12702 iova 0x85724a000 mrlen 65536 pid 0 comm [nvme_rdma]
link cxgb4_0/- rkey 0x68fe4e9 lkey 0x68fe4e9 iova 0x835b91000 mrlen 65536 pid 0 comm [nvme_rdma]

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 include/json_writer.h |   2 +
 lib/json_writer.c     |  11 +++++
 rdma/res.c            | 127 ++++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/utils.c          |   6 +++
 4 files changed, 146 insertions(+)

diff --git a/include/json_writer.h b/include/json_writer.h
index 45459fa..4b4dec2 100644
--- a/include/json_writer.h
+++ b/include/json_writer.h
@@ -35,6 +35,7 @@ void jsonw_bool(json_writer_t *self, bool value);
 void jsonw_float(json_writer_t *self, double number);
 void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
 void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_xint(json_writer_t *self, uint64_t number);
 void jsonw_hu(json_writer_t *self, unsigned short number);
 void jsonw_int(json_writer_t *self, int64_t number);
 void jsonw_null(json_writer_t *self);
@@ -45,6 +46,7 @@ void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
 void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
 void jsonw_float_field(json_writer_t *self, const char *prop, double num);
 void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_xint_field(json_writer_t *self, const char *prop, uint64_t num);
 void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
 void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
 void jsonw_null_field(json_writer_t *self, const char *prop);
diff --git a/lib/json_writer.c b/lib/json_writer.c
index 68401ae..0ad0421 100644
--- a/lib/json_writer.c
+++ b/lib/json_writer.c
@@ -225,6 +225,11 @@ void jsonw_uint(json_writer_t *self, uint64_t num)
 	jsonw_printf(self, "%"PRIu64, num);
 }
 
+void jsonw_xint(json_writer_t *self, uint64_t num)
+{
+	jsonw_printf(self, "%"PRIx64, num);
+}
+
 void jsonw_lluint(json_writer_t *self, unsigned long long int num)
 {
 	jsonw_printf(self, "%llu", num);
@@ -269,6 +274,12 @@ void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
 	jsonw_uint(self, num);
 }
 
+void jsonw_xint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+	jsonw_name(self, prop);
+	jsonw_xint(self, num);
+}
+
 void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num)
 {
 	jsonw_name(self, prop);
diff --git a/rdma/res.c b/rdma/res.c
index f1a90d3..aa61e73 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -802,6 +802,121 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
+static void print_key(struct rd *rd, const char *name, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_xint_field(rd->jw, name, val);
+	else
+		pr_out("%s 0x%x ", name, val);
+}
+
+static void print_iova(struct rd *rd, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_xint_field(rd->jw, "iova", val);
+	else
+		pr_out("iova 0x%" PRIx64 " ", val);
+}
+
+static void print_mrlen(struct rd *rd, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "mrlen", val);
+	else
+		pr_out("mrlen %" PRIu64 " ", val);
+}
+
+static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_MR])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		uint32_t rkey = 0, lkey = 0;
+		uint64_t iova = 0, mrlen;
+		char *comm = NULL;
+		uint32_t pid = 0;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+			rkey = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+			lkey = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+			iova = mnl_attr_get_u64(
+					nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
+
+		mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
+		if (rd_check_is_filtered(rd, "mrlen", mrlen)) 
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, 0, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+			print_key(rd, "rkey", rkey);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+			print_key(rd, "lkey", lkey);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+			print_iova(rd, iova);
+		print_mrlen(rd, mrlen);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		if (rd->json_output)
+			jsonw_end_array(rd->jw);
+		else
+			pr_out("\n");
+	}
+	return MNL_CB_OK;
+}
+
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -854,6 +969,17 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
 
+static const
+struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "rkey", .is_number = true },
+	{ .name = "lkey", .is_number = true },
+	{ .name = "mrlen", .is_number = true },
+	{ .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
+
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
@@ -861,6 +987,7 @@ static int res_show(struct rd *rd)
 		{ "qp",		res_qp		},
 		{ "cm_id",	res_cm_id	},
 		{ "cq",		res_cq		},
+		{ "mr",		res_mr		},
 		{ 0 }
 	};
 
diff --git a/rdma/utils.c b/rdma/utils.c
index 5e79b62..a2e08e9 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -385,6 +385,12 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_RES_CQE] = MNL_TYPE_U32,
 	[RDMA_NLDEV_ATTR_RES_USECNT] = MNL_TYPE_U64,
 	[RDMA_NLDEV_ATTR_RES_POLL_CTX] = MNL_TYPE_U8,
+	[RDMA_NLDEV_ATTR_RES_MR] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_MR_ENTRY] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_RES_RKEY] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_RES_LKEY] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_RES_IOVA] = MNL_TYPE_U64,
+	[RDMA_NLDEV_ATTR_RES_MRLEN] = MNL_TYPE_U64,
 };
 
 int rd_attr_cb(const struct nlattr *attr, void *data)
-- 
1.8.3.1

[PATCH v3 iproute2-next 8/8] rdma: Add PD resource tracking information

[Steve Wise]

Sample output:

Without CAP_NET_ADMIN capability:

link mlx4_0/- users 0 pid 0 comm [ib_srpt]
link mlx4_0/- users 0 pid 0 comm [ib_srp]
link mlx4_0/- users 1 pid 0 comm [ib_core]
link cxgb4_0/- users 0 pid 0 comm [ib_srp]

With CAP_NET_ADMIN capability:
link mlx4_0/- local_dma_lkey 0x8000 users 0 pid 0 comm [ib_srpt]
link mlx4_0/- local_dma_lkey 0x8000 users 0 pid 0 comm [ib_srp]
link mlx4_0/- local_dma_lkey 0x8000 users 1 pid 0 comm [ib_core]
link cxgb4_0/- local_dma_lkey 0x0 users 0 pid 0 comm [ib_srp]

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/res.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

diff --git a/rdma/res.c b/rdma/res.c
index aa61e73..6177e46 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -917,6 +917,91 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
+static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_PD])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char *comm = NULL;
+		uint32_t pid = 0;
+		uint64_t users;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+			local_dma_lkey = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
+
+		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+		if (rd_check_is_filtered(rd, "users", users))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+			unsafe_global_rkey = mnl_attr_get_u32(
+			      nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, 0, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+			print_key(rd, "local_dma_lkey", local_dma_lkey);
+		print_users(rd, users);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		if (rd->json_output)
+			jsonw_end_array(rd->jw);
+		else
+			pr_out("\n");
+	}
+	return MNL_CB_OK;
+}
+
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -980,6 +1065,15 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
 
+static const
+struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "users", .is_number = true },
+	{ .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
+
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
@@ -988,6 +1082,7 @@ static int res_show(struct rd *rd)
 		{ "cm_id",	res_cm_id	},
 		{ "cq",		res_cq		},
 		{ "mr",		res_mr		},
+		{ "pd",		res_pd		},
 		{ 0 }
 	};
 
-- 
1.8.3.1

[PATCH v3 iproute2-next 0/8] cm_id, cq, mr, and pd resource tracking

[Steve Wise]

Hello,

This series enhances the iproute2 rdma tool to include dumping of
connection manager id (cm_id), completion queue (cq), memory region (mr),
and protection domain (pd) rdma resources.  It is the user-space part
of the kernel resource tracking series merged into rdma-next for 4.17 [1].

Changes since v2:
- pull in rdma-core include/rdma/rdma_cma.h
- update the new local rdma/include/uapi/rdma/rdma_netlink.h
- 80 column reformat
- add reviewed-by tags

Changes since v1/RFC:
- removed RFC tag
- initialize rd properly to avoid passing a garbage port number
- revert accidental change to qp_valid_filters 
- removed cm_id dev/network/transport types
- cm_id ip addrs now passed up as __kernel_sockaddr_storage
- cm_id ip address ports printed as "address:port" strings
- only parse/display memory keys and iova if available
- filter on "users" for cqs and pds
- fixed memory leaks 
- removed PD_FLAGS attribute
- filter on "mrlen" for mrs
- filter on "poll-ctx" for cqs
- don't require addrs or qp_type for parsing cm_ids
- only filter optional attrs if they are present
- remove PGSIZE MR attr to match kernel 

[1] https://www.spinics.net/lists/linux-rdma/msg61720.html

---

Steve Wise (8):
  rdma: include rdma-core <rdma/rdma_cma.h>
  rdma: Makefile change to find <rdma/rdma_cma.h>
  rdma: update rdma_netlink.h
  rdma: initialize the rd struct
  rdma: Add CM_ID resource tracking information
  rdma: Add CQ resource tracking information
  rdma: Add MR resource tracking information
  rdma: Add PD resource tracking information

 include/json_writer.h                 |   2 +
 lib/json_writer.c                     |  11 +
 rdma/Makefile                         |   2 +-
 rdma/include/rdma/rdma_cma.h          | 728 ++++++++++++++++++++++++++++++++++
 rdma/include/uapi/rdma/rdma_netlink.h |  38 ++
 rdma/rdma.c                           |   2 +-
 rdma/rdma.h                           |   2 +
 rdma/res.c                            | 623 ++++++++++++++++++++++++++++-
 rdma/utils.c                          |  16 +
 9 files changed, 1421 insertions(+), 3 deletions(-)
 create mode 100644 rdma/include/rdma/rdma_cma.h

-- 
1.8.3.1

Re: [PATCH v3 iproute2-next 1/8] rdma: include rdma-core <rdma/rdma_cma.h>

[Leon Romanovsky]

[-- Attachment #1: Type: text/plain, Size: 535 bytes --]

On Mon, Mar 26, 2018 at 01:57:32PM -0700, Steve Wise wrote:
> This avoids requiring rdma-core be installed on systems.
>
> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
> ---
>  rdma/include/rdma/rdma_cma.h | 728 +++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 728 insertions(+)
>  create mode 100644 rdma/include/rdma/rdma_cma.h
>

Steve,

Sorry for not spotting it before, you actually need only 3 enums for the
cm_id_ps_to_str() from rdma_cma.h.

Simply copy/paste that enum into cm_id_ps_to_str().

Thanks

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v3 iproute2-next 1/8] rdma: include rdma-core <rdma/rdma_cma.h>

[David Ahern]

On 3/26/18 11:46 PM, Leon Romanovsky wrote:
> On Mon, Mar 26, 2018 at 01:57:32PM -0700, Steve Wise wrote:
>> This avoids requiring rdma-core be installed on systems.
>>
>> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
>> ---
>>  rdma/include/rdma/rdma_cma.h | 728 +++++++++++++++++++++++++++++++++++++++++++
>>  1 file changed, 728 insertions(+)
>>  create mode 100644 rdma/include/rdma/rdma_cma.h
>>
> 
> Steve,
> 
> Sorry for not spotting it before, you actually need only 3 enums for the
> cm_id_ps_to_str() from rdma_cma.h.
> 
> Simply copy/paste that enum into cm_id_ps_to_str().
> 
> Thanks
> 

I think this is Jason's point: if that enum is part of the UAPI why
isn't it part of a uapi header file?

We definitely do not want that entire header file brought in to iproute2