Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 00313983 authored by Steve Wise's avatar Steve Wise Committed by Doug Ledford
Browse files

RDMA/nldev: provide detailed CM_ID information 



Implement RDMA nldev netlink interface to get detailed CM_ID information.

Because cm_id's are attached to rdma devices in various work queue
contexts, the pid and task information at restrak_add() time is sometimes
not useful.  For example, an nvme/f host connection cm_id ends up being
bound to a device in a work queue context and the resulting pid at attach
time no longer exists after connection setup.  So instead we mark all
cm_id's created via the rdma_ucm as "user", and all others as "kernel".
This required tweaking the restrack code a little.  It also required
wrapping some rdma_cm functions to allow passing the module name string.

Signed-off-by: default avatarSteve Wise <swise@opengridcomputing.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: default avatarDoug Ledford <dledford@redhat.com>
parent a3b641af

drivers/infiniband/core/cma.c

+40 −21
Original line number Diff line number Diff line
@@ -466,6 +466,8 @@ static void _cma_attach_to_dev(struct rdma_id_private *id_priv, 
	id_priv->id.route.addr.dev_addr.transport =

		rdma_node_get_transport(cma_dev->device->node_type);

	list_add_tail(&id_priv->list, &cma_dev->id_list);

	id_priv->res.type = RDMA_RESTRACK_CM_ID;

	rdma_restrack_add(&id_priv->res);

}



static void cma_attach_to_dev(struct rdma_id_private *id_priv,
@@ -738,10 +740,10 @@ static void cma_deref_id(struct rdma_id_private *id_priv) 
		complete(&id_priv->comp);

}



struct rdma_cm_id *rdma_create_id(struct net *net,

struct rdma_cm_id *__rdma_create_id(struct net *net,

				    rdma_cm_event_handler event_handler,

				    void *context, enum rdma_port_space ps,

				  enum ib_qp_type qp_type)

				    enum ib_qp_type qp_type, const char *caller)

{

	struct rdma_id_private *id_priv;
@@ -749,7 +751,10 @@ struct rdma_cm_id *rdma_create_id(struct net *net, 
	if (!id_priv)

		return ERR_PTR(-ENOMEM);



	id_priv->owner = task_pid_nr(current);

	if (caller)

		id_priv->res.kern_name = caller;

	else

		rdma_restrack_set_task(&id_priv->res, current);

	id_priv->state = RDMA_CM_IDLE;

	id_priv->id.context = context;

	id_priv->id.event_handler = event_handler;
@@ -769,7 +774,7 @@ struct rdma_cm_id *rdma_create_id(struct net *net, 


	return &id_priv->id;

}

EXPORT_SYMBOL(rdma_create_id);

EXPORT_SYMBOL(__rdma_create_id);



static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)

{
@@ -1629,6 +1634,7 @@ void rdma_destroy_id(struct rdma_cm_id *id) 
	mutex_unlock(&id_priv->handler_mutex);



	if (id_priv->cma_dev) {

		rdma_restrack_del(&id_priv->res);

		if (rdma_cap_ib_cm(id_priv->id.device, 1)) {

			if (id_priv->cm_id.ib)

				ib_destroy_cm_id(id_priv->cm_id.ib);
@@ -1778,6 +1784,7 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id, 
					       struct ib_cm_event *ib_event,

					       struct net_device *net_dev)

{

	struct rdma_id_private *listen_id_priv;

	struct rdma_id_private *id_priv;

	struct rdma_cm_id *id;

	struct rdma_route *rt;
@@ -1787,9 +1794,11 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id, 
		ib_event->param.req_rcvd.primary_path->service_id;

	int ret;



	id = rdma_create_id(listen_id->route.addr.dev_addr.net,

	listen_id_priv = container_of(listen_id, struct rdma_id_private, id);

	id = __rdma_create_id(listen_id->route.addr.dev_addr.net,

			    listen_id->event_handler, listen_id->context,

			    listen_id->ps, ib_event->param.req_rcvd.qp_type);

			    listen_id->ps, ib_event->param.req_rcvd.qp_type,

			    listen_id_priv->res.kern_name);

	if (IS_ERR(id))

		return NULL;
@@ -1838,14 +1847,17 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id, 
					      struct ib_cm_event *ib_event,

					      struct net_device *net_dev)

{

	struct rdma_id_private *listen_id_priv;

	struct rdma_id_private *id_priv;

	struct rdma_cm_id *id;

	const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family;

	struct net *net = listen_id->route.addr.dev_addr.net;

	int ret;



	id = rdma_create_id(net, listen_id->event_handler, listen_id->context,

			    listen_id->ps, IB_QPT_UD);

	listen_id_priv = container_of(listen_id, struct rdma_id_private, id);

	id = __rdma_create_id(net, listen_id->event_handler, listen_id->context,

			      listen_id->ps, IB_QPT_UD,

			      listen_id_priv->res.kern_name);

	if (IS_ERR(id))

		return NULL;
@@ -2111,10 +2123,11 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, 
		goto out;



	/* Create a new RDMA id for the new IW CM ID */

	new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,

	new_cm_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net,

				     listen_id->id.event_handler,

				     listen_id->id.context,

				   RDMA_PS_TCP, IB_QPT_RC);

				     RDMA_PS_TCP, IB_QPT_RC,

				     listen_id->res.kern_name);

	if (IS_ERR(new_cm_id)) {

		ret = -ENOMEM;

		goto out;
@@ -2239,8 +2252,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, 
	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))

		return;



	id = rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps,

			    id_priv->id.qp_type);

	id = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps,

			      id_priv->id.qp_type, id_priv->res.kern_name);

	if (IS_ERR(id))

		return;
@@ -3348,8 +3361,10 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) 


	return 0;

err2:

	if (id_priv->cma_dev)

	if (id_priv->cma_dev) {

		rdma_restrack_del(&id_priv->res);

		cma_release_dev(id_priv);

	}

err1:

	cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE);

	return ret;
@@ -3732,14 +3747,18 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv, 
	return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep);

}



int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)

int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,

		  const char *caller)

{

	struct rdma_id_private *id_priv;

	int ret;



	id_priv = container_of(id, struct rdma_id_private, id);



	id_priv->owner = task_pid_nr(current);

	if (caller)

		id_priv->res.kern_name = caller;

	else

		rdma_restrack_set_task(&id_priv->res, current);



	if (!cma_comp(id_priv, RDMA_CM_CONNECT))

		return -EINVAL;
@@ -3779,7 +3798,7 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) 
	rdma_reject(id, NULL, 0);

	return ret;

}

EXPORT_SYMBOL(rdma_accept);

EXPORT_SYMBOL(__rdma_accept);



int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event)

{
@@ -4457,7 +4476,7 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb) 
					  RDMA_NL_RDMA_CM_ATTR_DST_ADDR))

				goto out;



			id_stats->pid		= id_priv->owner;

			id_stats->pid	= task_pid_vnr(id_priv->res.task);

			id_stats->port_space	= id->ps;

			id_stats->cm_state	= id_priv->state;

			id_stats->qp_num	= id_priv->qp_num;

drivers/infiniband/core/cma_priv.h

+5 −1
Original line number Diff line number Diff line
@@ -67,7 +67,6 @@ struct rdma_id_private { 
	u32			seq_num;

	u32			qkey;

	u32			qp_num;

	pid_t			owner;

	u32			options;

	u8			srq;

	u8			tos;
@@ -75,5 +74,10 @@ struct rdma_id_private { 
	u8			reuseaddr;

	u8			afonly;

	enum ib_gid_type	gid_type;



	/*

	 * Internal to RDMA/core, don't use in the drivers

	 */

	struct rdma_restrack_entry     res;

};

#endif /* _CMA_PRIV_H */

drivers/infiniband/core/nldev.c

+98 −9
Original line number Diff line number Diff line
@@ -34,9 +34,11 @@ 
#include <linux/pid.h>

#include <linux/pid_namespace.h>

#include <net/netlink.h>

#include <rdma/rdma_cm.h>

#include <rdma/rdma_netlink.h>



#include "core_priv.h"

#include "cma_priv.h"



static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {

	[RDMA_NLDEV_ATTR_DEV_INDEX]     = { .type = NLA_U32 },
@@ -71,6 +73,13 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = { 
	[RDMA_NLDEV_ATTR_RES_PID]		= { .type = NLA_U32 },

	[RDMA_NLDEV_ATTR_RES_KERN_NAME]		= { .type = NLA_NUL_STRING,

						    .len = TASK_COMM_LEN },

	[RDMA_NLDEV_ATTR_RES_CM_ID]		= { .type = NLA_NESTED },

	[RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY]	= { .type = NLA_NESTED },

	[RDMA_NLDEV_ATTR_RES_PS]		= { .type = NLA_U32 },

	[RDMA_NLDEV_ATTR_RES_SRC_ADDR]	= {

			.len = sizeof(struct __kernel_sockaddr_storage) },

	[RDMA_NLDEV_ATTR_RES_DST_ADDR]	= {

			.len = sizeof(struct __kernel_sockaddr_storage) },

};



static int fill_nldev_handle(struct sk_buff *msg, struct ib_device *device)
@@ -182,6 +191,7 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device) 
		[RDMA_RESTRACK_PD] = "pd",

		[RDMA_RESTRACK_CQ] = "cq",

		[RDMA_RESTRACK_QP] = "qp",

		[RDMA_RESTRACK_CM_ID] = "cm_id",

	};



	struct rdma_restrack_root *res = &device->res;
@@ -212,6 +222,25 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device) 
	return ret;

}



static int fill_res_name_pid(struct sk_buff *msg,

			     struct rdma_restrack_entry *res)

{

	/*

	 * For user resources, user is should read /proc/PID/comm to get the

	 * name of the task file.

	 */

	if (rdma_is_kernel_res(res)) {

		if (nla_put_string(msg, RDMA_NLDEV_ATTR_RES_KERN_NAME,

		    res->kern_name))

			return -EMSGSIZE;

	} else {

		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PID,

		    task_pid_vnr(res->task)))

			return -EMSGSIZE;

	}

	return 0;

}



static int fill_res_qp_entry(struct sk_buff *msg, struct netlink_callback *cb,

			     struct rdma_restrack_entry *res, uint32_t port)

{
@@ -262,19 +291,65 @@ static int fill_res_qp_entry(struct sk_buff *msg, struct netlink_callback *cb, 
	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_STATE, qp_attr.qp_state))

		goto err;



	/*

	 * Existence of task means that it is user QP and netlink

	 * user is invited to go and read /proc/PID/comm to get name

	 * of the task file and res->task_com should be NULL.

	 */

	if (rdma_is_kernel_res(res)) {

		if (nla_put_string(msg, RDMA_NLDEV_ATTR_RES_KERN_NAME, res->kern_name))

	if (fill_res_name_pid(msg, res))

		goto err;

	} else {

		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PID, task_pid_vnr(res->task)))



	nla_nest_end(msg, entry_attr);

	return 0;



err:

	nla_nest_cancel(msg, entry_attr);

out:

	return -EMSGSIZE;

}



static int fill_res_cm_id_entry(struct sk_buff *msg,

				struct netlink_callback *cb,

				struct rdma_restrack_entry *res, uint32_t port)

{

	struct rdma_id_private *id_priv =

				container_of(res, struct rdma_id_private, res);

	struct rdma_cm_id *cm_id = &id_priv->id;

	struct nlattr *entry_attr;



	if (port && port != cm_id->port_num)

		return 0;



	entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY);

	if (!entry_attr)

		goto out;



	if (cm_id->port_num &&

	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, cm_id->port_num))

		goto err;



	if (id_priv->qp_num) {

		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, id_priv->qp_num))

			goto err;

		if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, cm_id->qp_type))

			goto err;

	}



	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PS, cm_id->ps))

		goto err;



	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_STATE, id_priv->state))

		goto err;



	if (cm_id->route.addr.src_addr.ss_family &&

	    nla_put(msg, RDMA_NLDEV_ATTR_RES_SRC_ADDR,

		    sizeof(cm_id->route.addr.src_addr),

		    &cm_id->route.addr.src_addr))

		goto err;

	if (cm_id->route.addr.dst_addr.ss_family &&

	    nla_put(msg, RDMA_NLDEV_ATTR_RES_DST_ADDR,

		    sizeof(cm_id->route.addr.dst_addr),

		    &cm_id->route.addr.dst_addr))

		goto err;



	if (fill_res_name_pid(msg, res))

		goto err;



	nla_nest_end(msg, entry_attr);

	return 0;
@@ -571,6 +646,11 @@ static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = { 
		.nldev_cmd = RDMA_NLDEV_CMD_RES_QP_GET,

		.nldev_attr = RDMA_NLDEV_ATTR_RES_QP,

	},

	[RDMA_RESTRACK_CM_ID] = {

		.fill_res_func = fill_res_cm_id_entry,

		.nldev_cmd = RDMA_NLDEV_CMD_RES_CM_ID_GET,

		.nldev_attr = RDMA_NLDEV_ATTR_RES_CM_ID,

	},

};



static int res_get_common_dumpit(struct sk_buff *skb,
@@ -713,6 +793,12 @@ static int nldev_res_get_qp_dumpit(struct sk_buff *skb, 
	return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_QP);

}



static int nldev_res_get_cm_id_dumpit(struct sk_buff *skb,

				      struct netlink_callback *cb)

{

	return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_CM_ID);

}



static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {

	[RDMA_NLDEV_CMD_GET] = {

		.doit = nldev_get_doit,
@@ -739,6 +825,9 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { 
		 * too.

		 */

	},

	[RDMA_NLDEV_CMD_RES_CM_ID_GET] = {

		.dump = nldev_res_get_cm_id_dumpit,

	},

};



void __init nldev_init(void)

drivers/infiniband/core/restrack.c

+11 −3
Original line number Diff line number Diff line
@@ -3,12 +3,15 @@ 
 * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.

 */



#include <rdma/rdma_cm.h>

#include <rdma/ib_verbs.h>

#include <rdma/restrack.h>

#include <linux/mutex.h>

#include <linux/sched/task.h>

#include <linux/pid_namespace.h>



#include "cma_priv.h"



void rdma_restrack_init(struct rdma_restrack_root *res)

{

	init_rwsem(&res->rwsem);
@@ -44,7 +47,7 @@ static void set_kern_name(struct rdma_restrack_entry *res) 
	struct ib_qp *qp;



	if (type != RDMA_RESTRACK_QP)

		/* PD and CQ types already have this name embedded in */

		/* Other types already have this name embedded in */

		return;



	qp = container_of(res, struct ib_qp, res);
@@ -67,6 +70,9 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res) 
		return container_of(res, struct ib_cq, res)->device;

	case RDMA_RESTRACK_QP:

		return container_of(res, struct ib_qp, res)->device;

	case RDMA_RESTRACK_CM_ID:

		return container_of(res, struct rdma_id_private,

				    res)->id.device;

	default:

		WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);

		return NULL;
@@ -82,6 +88,8 @@ static bool res_is_user(struct rdma_restrack_entry *res) 
		return container_of(res, struct ib_cq, res)->uobject;

	case RDMA_RESTRACK_QP:

		return container_of(res, struct ib_qp, res)->uobject;

	case RDMA_RESTRACK_CM_ID:

		return !res->kern_name;

	default:

		WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);

		return false;
@@ -96,8 +104,8 @@ void rdma_restrack_add(struct rdma_restrack_entry *res) 
		return;



	if (res_is_user(res)) {

		get_task_struct(current);

		res->task = current;

		if (!res->task)

			rdma_restrack_set_task(res, current);

		res->kern_name = NULL;

	} else {

		set_kern_name(res);

drivers/infiniband/core/ucma.c

+4 −4
Original line number Diff line number Diff line
@@ -476,8 +476,8 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, 
		return -ENOMEM;



	ctx->uid = cmd.uid;

	ctx->cm_id = rdma_create_id(current->nsproxy->net_ns,

				    ucma_event_handler, ctx, cmd.ps, qp_type);

	ctx->cm_id = __rdma_create_id(current->nsproxy->net_ns,

			      ucma_event_handler, ctx, cmd.ps, qp_type, NULL);

	if (IS_ERR(ctx->cm_id)) {

		ret = PTR_ERR(ctx->cm_id);

		goto err1;
@@ -1084,12 +1084,12 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, 
	if (cmd.conn_param.valid) {

		ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param);

		mutex_lock(&file->mut);

		ret = rdma_accept(ctx->cm_id, &conn_param);

		ret = __rdma_accept(ctx->cm_id, &conn_param, NULL);

		if (!ret)

			ctx->uid = cmd.uid;

		mutex_unlock(&file->mut);

	} else

		ret = rdma_accept(ctx->cm_id, NULL);

		ret = __rdma_accept(ctx->cm_id, NULL, NULL);



	ucma_put_ctx(ctx);

	return ret;