Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A very quiet cycle with few notable changes. Mostly the usual list of
  one or two patches to drivers changing something that isn't quite rc
  worthy. The subsystem seems to be seeing a larger number of rework and
  cleanup style patches right now, I feel that several vendors are
  prepping their drivers for new silicon.

  Summary:

   - Driver updates and cleanup for qedr, bnxt_re, hns, siw, mlx5, mlx4,
     rxe, i40iw

   - Larger series doing cleanup and rework for hns and hfi1.

   - Some general reworking of the CM code to make it a little more
     understandable

   - Unify the different code paths connected to the uverbs FD scheme

   - New UAPI ioctls conversions for get context and get async fd

   - Trace points for CQ and CM portions of the RDMA stack

   - mlx5 driver support for virtio-net formatted rings as RDMA raw
     ethernet QPs

   - verbs support for setting the PCI-E relaxed ordering bit on DMA
     traffic connected to a MR

   - A couple of bug fixes that came too late to make rc7"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (108 commits)
  RDMA/core: Make the entire API tree static
  RDMA/efa: Mask access flags with the correct optional range
  RDMA/cma: Fix unbalanced cm_id reference count during address resolve
  RDMA/umem: Fix ib_umem_find_best_pgsz()
  IB/mlx4: Fix leak in id_map_find_del
  IB/opa_vnic: Spelling correction of 'erorr' to 'error'
  IB/hfi1: Fix logical condition in msix_request_irq
  RDMA/cm: Remove CM message structs
  RDMA/cm: Use IBA functions for complex structure members
  RDMA/cm: Use IBA functions for simple structure members
  RDMA/cm: Use IBA functions for swapping get/set acessors
  RDMA/cm: Use IBA functions for simple get/set acessors
  RDMA/cm: Add SET/GET implementations to hide IBA wire format
  RDMA/cm: Add accessors for CM_REQ transport_type
  IB/mlx5: Return the administrative GUID if exists
  RDMA/core: Ensure that rdma_user_mmap_entry_remove() is a fence
  IB/mlx4: Fix memory leak in add_gid error flow
  IB/mlx5: Expose RoCE accelerator counters
  RDMA/mlx5: Set relaxed ordering when requested
  RDMA/core: Add the core support field to METHOD_GET_CONTEXT
  ...

1 files changed, 68 insertions, 22 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 43a6f07e0afe..72f032160c4b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -36,6 +36,7 @@
 
 #include "core_priv.h"
 #include "cma_priv.h"
+#include "cma_trace.h"
 
 MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("Generic RDMA CM Agent");
@@ -877,6 +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);
@@ -928,27 +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);
@@ -958,6 +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;
@@ -1811,6 +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);
 
@@ -1863,6 +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;
@@ -1871,6 +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;
@@ -1890,6 +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)
 {
@@ -1912,8 +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 :
@@ -1958,7 +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;
@@ -2119,6 +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;
@@ -2161,7 +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;
 	/*
@@ -2170,8 +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);
@@ -2286,7 +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;
@@ -2363,7 +2392,7 @@ 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;
@@ -2435,6 +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);
 }
 
@@ -2611,7 +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;
 	}
@@ -2634,7 +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;
 	}
@@ -3089,7 +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);
@@ -3118,6 +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;
@@ -3144,6 +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;
@@ -3736,7 +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) {
@@ -3800,6 +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);
@@ -3873,6 +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)) {
@@ -3986,6 +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;
@@ -4035,6 +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);
 }
 
@@ -4120,13 +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);
@@ -4151,8 +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
@@ -4218,7 +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) {
@@ -4623,6 +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:
@@ -4653,7 +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;
@@ -4691,6 +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;