1 files changed, 144 insertions, 65 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 19f1730a4f24..72f032160c4b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1,36 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * Copyright (c) 2005 Voltaire Inc.  All rights reserved.
  * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved.
- * Copyright (c) 1999-2005, Mellanox Technologies, Inc. All rights reserved.
+ * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved.
  * Copyright (c) 2005-2006 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.
  */
 
 #include <linux/completion.h>
@@ -63,6 +36,7 @@
 
 #include "core_priv.h"
 #include "cma_priv.h"
+#include "cma_trace.h"
 
 MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("Generic RDMA CM Agent");
@@ -904,6 +878,7 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
 	id_priv->seq_num &= 0x00ffffff;
 
+	trace_cm_id_create(id_priv);
 	return &id_priv->id;
 }
 EXPORT_SYMBOL(__rdma_create_id);
@@ -955,27 +930,34 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
 	int ret;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
-	if (id->device != pd->device)
-		return -EINVAL;
+	if (id->device != pd->device) {
+		ret = -EINVAL;
+		goto out_err;
+	}
 
 	qp_init_attr->port_num = id->port_num;
 	qp = ib_create_qp(pd, qp_init_attr);
-	if (IS_ERR(qp))
-		return PTR_ERR(qp);
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
+		goto out_err;
+	}
 
 	if (id->qp_type == IB_QPT_UD)
 		ret = cma_init_ud_qp(id_priv, qp);
 	else
 		ret = cma_init_conn_qp(id_priv, qp);
 	if (ret)
-		goto err;
+		goto out_destroy;
 
 	id->qp = qp;
 	id_priv->qp_num = qp->qp_num;
 	id_priv->srq = (qp->srq != NULL);
+	trace_cm_qp_create(id_priv, pd, qp_init_attr, 0);
 	return 0;
-err:
+out_destroy:
 	ib_destroy_qp(qp);
+out_err:
+	trace_cm_qp_create(id_priv, pd, qp_init_attr, ret);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_create_qp);
@@ -985,6 +967,7 @@ void rdma_destroy_qp(struct rdma_cm_id *id)
 	struct rdma_id_private *id_priv;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	trace_cm_qp_destroy(id_priv);
 	mutex_lock(&id_priv->qp_mutex);
 	ib_destroy_qp(id_priv->id.qp);
 	id_priv->id.qp = NULL;
@@ -1838,6 +1821,7 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 	enum rdma_cm_state state;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	trace_cm_id_destroy(id_priv);
 	state = cma_exch(id_priv, RDMA_CM_DESTROYING);
 	cma_cancel_operation(id_priv, state);
 
@@ -1890,6 +1874,7 @@ static int cma_rep_recv(struct rdma_id_private *id_priv)
 	if (ret)
 		goto reject;
 
+	trace_cm_send_rtu(id_priv);
 	ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0);
 	if (ret)
 		goto reject;
@@ -1898,6 +1883,7 @@ static int cma_rep_recv(struct rdma_id_private *id_priv)
 reject:
 	pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret);
 	cma_modify_qp_err(id_priv);
+	trace_cm_send_rej(id_priv);
 	ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED,
 		       NULL, 0, NULL, 0);
 	return ret;
@@ -1917,6 +1903,17 @@ static void cma_set_rep_event_data(struct rdma_cm_event *event,
 	event->param.conn.qp_num = rep_data->remote_qpn;
 }
 
+static int cma_cm_event_handler(struct rdma_id_private *id_priv,
+				struct rdma_cm_event *event)
+{
+	int ret;
+
+	trace_cm_event_handler(id_priv, event);
+	ret = id_priv->id.event_handler(&id_priv->id, event);
+	trace_cm_event_done(id_priv, event, ret);
+	return ret;
+}
+
 static int cma_ib_handler(struct ib_cm_id *cm_id,
 			  const struct ib_cm_event *ib_event)
 {
@@ -1939,8 +1936,10 @@ static int cma_ib_handler(struct ib_cm_id *cm_id,
 		break;
 	case IB_CM_REP_RECEIVED:
 		if (cma_comp(id_priv, RDMA_CM_CONNECT) &&
-		    (id_priv->id.qp_type != IB_QPT_UD))
+		    (id_priv->id.qp_type != IB_QPT_UD)) {
+			trace_cm_send_mra(id_priv);
 			ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
+		}
 		if (id_priv->id.qp) {
 			event.status = cma_rep_recv(id_priv);
 			event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR :
@@ -1985,7 +1984,7 @@ static int cma_ib_handler(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 	if (ret) {
 		/* Destroy the CM ID by returning a non-zero value. */
 		id_priv->cm_id.ib = NULL;
@@ -2146,6 +2145,7 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	if (IS_ERR(listen_id))
 		return PTR_ERR(listen_id);
 
+	trace_cm_req_handler(listen_id, ib_event->event);
 	if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) {
 		ret = -EINVAL;
 		goto net_dev_put;
@@ -2188,7 +2188,7 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	 * until we're done accessing it.
 	 */
 	atomic_inc(&conn_id->refcount);
-	ret = conn_id->id.event_handler(&conn_id->id, &event);
+	ret = cma_cm_event_handler(conn_id, &event);
 	if (ret)
 		goto err3;
 	/*
@@ -2197,8 +2197,10 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	 */
 	mutex_lock(&lock);
 	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
-	    (conn_id->id.qp_type != IB_QPT_UD))
+	    (conn_id->id.qp_type != IB_QPT_UD)) {
+		trace_cm_send_mra(cm_id->context);
 		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
+	}
 	mutex_unlock(&lock);
 	mutex_unlock(&conn_id->handler_mutex);
 	mutex_unlock(&listen_id->handler_mutex);
@@ -2313,7 +2315,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 	event.status = iw_event->status;
 	event.param.conn.private_data = iw_event->private_data;
 	event.param.conn.private_data_len = iw_event->private_data_len;
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 	if (ret) {
 		/* Destroy the CM ID by returning a non-zero value. */
 		id_priv->cm_id.iw = NULL;
@@ -2390,15 +2392,16 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	 * until we're done accessing it.
 	 */
 	atomic_inc(&conn_id->refcount);
-	ret = conn_id->id.event_handler(&conn_id->id, &event);
+	ret = cma_cm_event_handler(conn_id, &event);
 	if (ret) {
 		/* User wants to destroy the CM ID */
 		conn_id->cm_id.iw = NULL;
 		cma_exch(conn_id, RDMA_CM_DESTROYING);
 		mutex_unlock(&conn_id->handler_mutex);
+		mutex_unlock(&listen_id->handler_mutex);
 		cma_deref_id(conn_id);
 		rdma_destroy_id(&conn_id->id);
-		goto out;
+		return ret;
 	}
 
 	mutex_unlock(&conn_id->handler_mutex);
@@ -2461,6 +2464,7 @@ static int cma_listen_handler(struct rdma_cm_id *id,
 
 	id->context = id_priv->id.context;
 	id->event_handler = id_priv->id.event_handler;
+	trace_cm_event_handler(id_priv, event);
 	return id_priv->id.event_handler(id, event);
 }
 
@@ -2530,7 +2534,9 @@ EXPORT_SYMBOL(rdma_set_service_type);
  * This function should be called before rdma_connect() on active side,
  * and on passive side before rdma_accept(). It is applicable to primary
  * path only. The timeout will affect the local side of the QP, it is not
- * negotiated with remote side and zero disables the timer.
+ * negotiated with remote side and zero disables the timer. In case it is
+ * set before rdma_resolve_route, the value will also be used to determine
+ * PacketLifeTime for RoCE.
  *
  * Return: 0 for success
  */
@@ -2635,7 +2641,7 @@ static void cma_work_handler(struct work_struct *_work)
 	if (!cma_comp_exch(id_priv, work->old_state, work->new_state))
 		goto out;
 
-	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
+	if (cma_cm_event_handler(id_priv, &work->event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		destroy = 1;
 	}
@@ -2658,7 +2664,7 @@ static void cma_ndev_work_handler(struct work_struct *_work)
 	    id_priv->state == RDMA_CM_DEVICE_REMOVAL)
 		goto out;
 
-	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
+	if (cma_cm_event_handler(id_priv, &work->event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		destroy = 1;
 	}
@@ -2827,22 +2833,65 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv)
 	return 0;
 }
 
-static int iboe_tos_to_sl(struct net_device *ndev, int tos)
+static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio)
 {
-	int prio;
 	struct net_device *dev;
 
-	prio = rt_tos2priority(tos);
-	dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
+	dev = vlan_dev_real_dev(vlan_ndev);
 	if (dev->num_tc)
 		return netdev_get_prio_tc_map(dev, prio);
 
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
+	return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) &
+		VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+}
+
+struct iboe_prio_tc_map {
+	int input_prio;
+	int output_tc;
+	bool found;
+};
+
+static int get_lower_vlan_dev_tc(struct net_device *dev, void *data)
+{
+	struct iboe_prio_tc_map *map = data;
+
+	if (is_vlan_dev(dev))
+		map->output_tc = get_vlan_ndev_tc(dev, map->input_prio);
+	else if (dev->num_tc)
+		map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio);
+	else
+		map->output_tc = 0;
+	/* We are interested only in first level VLAN device, so always
+	 * return 1 to stop iterating over next level devices.
+	 */
+	map->found = true;
+	return 1;
+}
+
+static int iboe_tos_to_sl(struct net_device *ndev, int tos)
+{
+	struct iboe_prio_tc_map prio_tc_map = {};
+	int prio = rt_tos2priority(tos);
+
+	/* If VLAN device, get it directly from the VLAN netdev */
 	if (is_vlan_dev(ndev))
-		return (vlan_dev_get_egress_qos_mask(ndev, prio) &
-			VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-#endif
-	return 0;
+		return get_vlan_ndev_tc(ndev, prio);
+
+	prio_tc_map.input_prio = prio;
+	rcu_read_lock();
+	netdev_walk_all_lower_dev_rcu(ndev,
+				      get_lower_vlan_dev_tc,
+				      &prio_tc_map);
+	rcu_read_unlock();
+	/* If map is found from lower device, use it; Otherwise
+	 * continue with the current netdevice to get priority to tc map.
+	 */
+	if (prio_tc_map.found)
+		return prio_tc_map.output_tc;
+	else if (ndev->num_tc)
+		return netdev_get_prio_tc_map(ndev, prio);
+	else
+		return 0;
 }
 
 static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
@@ -2896,7 +2945,16 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	route->path_rec->rate = iboe_get_rate(ndev);
 	dev_put(ndev);
 	route->path_rec->packet_life_time_selector = IB_SA_EQ;
-	route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME;
+	/* In case ACK timeout is set, use this value to calculate
+	 * PacketLifeTime.  As per IBTA 12.7.34,
+	 * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay).
+	 * Assuming a negligible local ACK delay, we can use
+	 * PacketLifeTime = local ACK timeout/2
+	 * as a reasonable approximation for RoCE networks.
+	 */
+	route->path_rec->packet_life_time = id_priv->timeout_set ?
+		id_priv->timeout - 1 : CMA_IBOE_PACKET_LIFETIME;
+
 	if (!route->path_rec->mtu) {
 		ret = -EINVAL;
 		goto err2;
@@ -3046,7 +3104,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 		if (status)
 			pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n",
 					     status);
-	} else {
+	} else if (status) {
 		pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status);
 	}
 
@@ -3061,7 +3119,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 	} else
 		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
 
-	if (id_priv->id.event_handler(&id_priv->id, &event)) {
+	if (cma_cm_event_handler(id_priv, &event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		mutex_unlock(&id_priv->handler_mutex);
 		rdma_destroy_id(&id_priv->id);
@@ -3090,6 +3148,7 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
 	rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3116,6 +3175,7 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv)
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)
 		&(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr));
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3708,7 +3768,7 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 
 	rdma_destroy_ah_attr(&event.param.ud.ah_attr);
 	if (ret) {
@@ -3772,6 +3832,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 	req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8);
 	req.max_cm_retries = CMA_MAX_CM_RETRIES;
 
+	trace_cm_send_sidr_req(id_priv);
 	ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req);
 	if (ret) {
 		ib_destroy_cm_id(id_priv->cm_id.ib);
@@ -3845,6 +3906,7 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
 	req.max_cm_retries = CMA_MAX_CM_RETRIES;
 	req.srq = id_priv->srq ? 1 : 0;
 
+	trace_cm_send_req(id_priv);
 	ret = ib_send_cm_req(id_priv->cm_id.ib, &req);
 out:
 	if (ret && !IS_ERR(id)) {
@@ -3958,6 +4020,7 @@ static int cma_accept_ib(struct rdma_id_private *id_priv,
 	rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count);
 	rep.srq = id_priv->srq ? 1 : 0;
 
+	trace_cm_send_rep(id_priv);
 	ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep);
 out:
 	return ret;
@@ -4007,6 +4070,7 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
 	rep.private_data = private_data;
 	rep.private_data_len = private_data_len;
 
+	trace_cm_send_sidr_rep(id_priv);
 	return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep);
 }
 
@@ -4092,13 +4156,15 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 		return -EINVAL;
 
 	if (rdma_cap_ib_cm(id->device, id->port_num)) {
-		if (id->qp_type == IB_QPT_UD)
+		if (id->qp_type == IB_QPT_UD) {
 			ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0,
 						private_data, private_data_len);
-		else
+		} else {
+			trace_cm_send_rej(id_priv);
 			ret = ib_send_cm_rej(id_priv->cm_id.ib,
 					     IB_CM_REJ_CONSUMER_DEFINED, NULL,
 					     0, private_data, private_data_len);
+		}
 	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_reject(id_priv->cm_id.iw,
 				   private_data, private_data_len);
@@ -4123,8 +4189,13 @@ int rdma_disconnect(struct rdma_cm_id *id)
 		if (ret)
 			goto out;
 		/* Initiate or respond to a disconnect. */
-		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0))
-			ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0);
+		trace_cm_disconnect(id_priv);
+		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) {
+			if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0))
+				trace_cm_sent_drep(id_priv);
+		} else {
+			trace_cm_sent_dreq(id_priv);
+		}
 	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
 	} else
@@ -4190,7 +4261,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 	} else
 		event.event = RDMA_CM_EVENT_MULTICAST_ERROR;
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 
 	rdma_destroy_ah_attr(&event.param.ud.ah_attr);
 	if (ret) {
@@ -4595,6 +4666,7 @@ static void cma_add_one(struct ib_device *device)
 		cma_listen_on_dev(id_priv, cma_dev);
 	mutex_unlock(&lock);
 
+	trace_cm_add_one(device);
 	return;
 
 free_gid_type:
@@ -4625,7 +4697,7 @@ static int cma_remove_id_dev(struct rdma_id_private *id_priv)
 		goto out;
 
 	event.event = RDMA_CM_EVENT_DEVICE_REMOVAL;
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
@@ -4663,6 +4735,8 @@ static void cma_remove_one(struct ib_device *device, void *client_data)
 {
 	struct cma_device *cma_dev = client_data;
 
+	trace_cm_remove_one(device);
+
 	if (!cma_dev)
 		return;
 
@@ -4724,13 +4798,18 @@ static int __init cma_init(void)
 	if (ret)
 		goto err;
 
-	cma_configfs_init();
+	ret = cma_configfs_init();
+	if (ret)
+		goto err_ib;
 
 	return 0;
 
+err_ib:
+	ib_unregister_client(&cma_client);
 err:
 	unregister_netdevice_notifier(&cma_nb);
 	ib_sa_unregister_client(&sa_client);
+	unregister_pernet_subsys(&cma_pernet_operations);
 err_wq:
 	destroy_workqueue(cma_wq);
 	return ret;