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

Pull rdma updates from Jason Gunthorpe:
 "A usual cycle for RDMA with a typical mix of driver and core subsystem
  updates:

   - Driver minor changes and bug fixes for mlx5, efa, rxe, vmw_pvrdma,
     hns, usnic, qib, qedr, cxgb4, hns, bnxt_re

   - Various rtrs fixes and updates

   - Bug fix for mlx4 CM emulation for virtualization scenarios where
     MRA wasn't working right

   - Use tracepoints instead of pr_debug in the CM code

   - Scrub the locking in ucma and cma to close more syzkaller bugs

   - Use tasklet_setup in the subsystem

   - Revert the idea that 'destroy' operations are not allowed to fail
     at the driver level. This proved unworkable from a HW perspective.

   - Revise how the umem API works so drivers make fewer mistakes using
     it

   - XRC support for qedr

   - Convert uverbs objects RWQ and MW to new the allocation scheme

   - Large queue entry sizes for hns

   - Use hmm_range_fault() for mlx5 On Demand Paging

   - uverbs APIs to inspect the GID table instead of sysfs

   - Move some of the RDMA code for building large page SGLs into
     lib/scatterlist"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (191 commits)
  RDMA/ucma: Fix use after free in destroy id flow
  RDMA/rxe: Handle skb_clone() failure in rxe_recv.c
  RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI
  RDMA: Explicitly pass in the dma_device to ib_register_device
  lib/scatterlist: Do not limit max_segment to PAGE_ALIGNED values
  IB/mlx4: Convert rej_tmout radix-tree to XArray
  RDMA/rxe: Fix bug rejecting all multicast packets
  RDMA/rxe: Fix skb lifetime in rxe_rcv_mcast_pkt()
  RDMA/rxe: Remove duplicate entries in struct rxe_mr
  IB/hfi,rdmavt,qib,opa_vnic: Update MAINTAINERS
  IB/rdmavt: Fix sizeof mismatch
  MAINTAINERS: CISCO VIC LOW LATENCY NIC DRIVER
  RDMA/bnxt_re: Fix sizeof mismatch for allocation of pbl_tbl.
  RDMA/bnxt_re: Use rdma_umem_for_each_dma_block()
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test
  RDMA/ipoib: Set rtnl_link_ops for ipoib interfaces
  RDMA/uverbs: Expose the new GID query API to user space
  ...

.clang-format

@@ -429,6 +429,7 @@ ForEachMacros:
   - 'rbtree_postorder_for_each_entry_safe'
   - 'rdma_for_each_block'
   - 'rdma_for_each_port'
+  - 'rdma_umem_for_each_dma_block'
   - 'resource_list_for_each_entry'
   - 'resource_list_for_each_entry_safe'
   - 'rhl_for_each_entry_rcu'

Documentation/ABI/stable/sysfs-class-infiniband

@@ -258,23 +258,6 @@ Description:
 		userspace ABI compatibility of umad & issm devices.
 
 
-What:		/sys/class/infiniband_cm/ucmN/ibdev
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	linux-rdma@vger.kernel.org
-Description:
-		(RO) Display Infiniband (IB) device name
-
-
-What:		/sys/class/infiniband_cm/abi_version
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	linux-rdma@vger.kernel.org
-Description:
-		(RO) Value is incremented if any changes are made that break
-		userspace ABI compatibility of ucm devices.
-
-
 What:		/sys/class/infiniband_verbs/uverbsN/ibdev
 What:		/sys/class/infiniband_verbs/uverbsN/abi_version
 Date:		Sept, 2005

MAINTAINERS

@@ -4256,7 +4256,6 @@ F:	drivers/net/ethernet/cisco/enic/
 CISCO VIC LOW LATENCY NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
 M:	Nelson Escobar <neescoba@cisco.com>
-M:	Parvi Kaustubhi <pkaustub@cisco.com>
 S:	Supported
 F:	drivers/infiniband/hw/usnic/
 
@@ -7793,8 +7792,8 @@ F:	include/linux/cciss*.h
 F:	include/uapi/linux/cciss*.h
 
 HFI1 DRIVER
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/hfi1
@@ -12999,8 +12998,8 @@ S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
 
 OPA-VNIC DRIVER
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/ulp/opa_vnic
@@ -14301,8 +14300,8 @@ F:	drivers/firmware/qemu_fw_cfg.c
 F:	include/uapi/linux/qemu_fw_cfg.h
 
 QIB DRIVER
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/qib/
@@ -14727,8 +14726,8 @@ S:	Maintained
 F:	drivers/net/ethernet/rdc/r6040.c
 
 RDMAVT - RDMA verbs software
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/sw/rdmavt

drivers/gpu/drm/drm_prime.c

@@ -806,30 +806,27 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
 struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
 				       struct page **pages, unsigned int nr_pages)
 {
-	struct sg_table *sg = NULL;
+	struct sg_table *sg;
+	struct scatterlist *sge;
 	size_t max_segment = 0;
-	int ret;
 
 	sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
-	if (!sg) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!sg)
+		return ERR_PTR(-ENOMEM);
 
 	if (dev)
 		max_segment = dma_max_mapping_size(dev->dev);
 	if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT)
 		max_segment = SCATTERLIST_MAX_SEGMENT;
-	ret = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
+	sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
 					  nr_pages << PAGE_SHIFT,
-					  max_segment, GFP_KERNEL);
-	if (ret)
-		goto out;
-
+					  max_segment,
+					  NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sge)) {
+		kfree(sg);
+		sg = ERR_CAST(sge);
+	}
 	return sg;
-out:
-	kfree(sg);
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(drm_prime_pages_to_sg);
 

drivers/gpu/drm/i915/gem/i915_gem_userptr.c

@@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
+	struct scatterlist *sg;
 	int ret;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
@@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 		return ERR_PTR(-ENOMEM);
 
 alloc_table:
-	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
-					  0, num_pages << PAGE_SHIFT,
-					  max_segment,
-					  GFP_KERNEL);
-	if (ret) {
+	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
+					 num_pages << PAGE_SHIFT, max_segment,
+					 NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ERR_CAST(sg);
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);

drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c

@@ -432,6 +432,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	int ret = 0;
 	static size_t sgl_size;
 	static size_t sgt_size;
+	struct scatterlist *sg;
 
 	if (vmw_tt->mapped)
 		return 0;
@@ -454,13 +455,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = __sg_alloc_table_from_pages
-			(&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
-			 (unsigned long) vsgt->num_pages << PAGE_SHIFT,
-			 dma_get_max_seg_size(dev_priv->dev->dev),
-			 GFP_KERNEL);
-		if (unlikely(ret != 0))
+		sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
+				vsgt->num_pages, 0,
+				(unsigned long) vsgt->num_pages << PAGE_SHIFT,
+				dma_get_max_seg_size(dev_priv->dev->dev),
+				NULL, 0, GFP_KERNEL);
+		if (IS_ERR(sg)) {
+			ret = PTR_ERR(sg);
 			goto out_sg_alloc_fail;
+		}
 
 		if (vsgt->num_pages > vmw_tt->sgt.orig_nents) {
 			uint64_t over_alloc =

drivers/infiniband/Kconfig

@@ -48,6 +48,7 @@ config INFINIBAND_ON_DEMAND_PAGING
 	depends on INFINIBAND_USER_MEM
 	select MMU_NOTIFIER
 	select INTERVAL_TREE
+	select HMM_MIRROR
 	default y
 	help
 	  On demand paging support for the InfiniBand subsystem.

drivers/infiniband/core/Makefile

@@ -17,7 +17,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
 
-ib_cm-y :=			cm.o
+ib_cm-y :=			cm.o cm_trace.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
 

drivers/infiniband/core/addr.c

@@ -647,13 +647,12 @@ static void process_one_req(struct work_struct *_work)
 	req->callback = NULL;
 
 	spin_lock_bh(&lock);
+	/*
+	 * Although the work will normally have been canceled by the workqueue,
+	 * it can still be requeued as long as it is on the req_list.
+	 */
+	cancel_delayed_work(&req->work);
 	if (!list_empty(&req->list)) {
-		/*
-		 * Although the work will normally have been canceled by the
-		 * workqueue, it can still be requeued as long as it is on the
-		 * req_list.
-		 */
-		cancel_delayed_work(&req->work);
 		list_del_init(&req->list);
 		kfree(req);
 	}

drivers/infiniband/core/cache.c

@@ -133,7 +133,11 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 }
 
 static const char * const gid_type_str[] = {
+	/* IB/RoCE v1 value is set for IB_GID_TYPE_IB and IB_GID_TYPE_ROCE for
+	 * user space compatibility reasons.
+	 */
 	[IB_GID_TYPE_IB]	= "IB/RoCE v1",
+	[IB_GID_TYPE_ROCE]	= "IB/RoCE v1",
 	[IB_GID_TYPE_ROCE_UDP_ENCAP]	= "RoCE v2",
 };
 
@@ -1220,7 +1224,7 @@ EXPORT_SYMBOL(ib_get_cached_port_state);
 const struct ib_gid_attr *
 rdma_get_gid_attr(struct ib_device *device, u8 port_num, int index)
 {
-	const struct ib_gid_attr *attr = ERR_PTR(-EINVAL);
+	const struct ib_gid_attr *attr = ERR_PTR(-ENODATA);
 	struct ib_gid_table *table;
 	unsigned long flags;
 
@@ -1243,6 +1247,67 @@ done:
 }
 EXPORT_SYMBOL(rdma_get_gid_attr);
 
+/**
+ * rdma_query_gid_table - Reads GID table entries of all the ports of a device up to max_entries.
+ * @device: The device to query.
+ * @entries: Entries where GID entries are returned.
+ * @max_entries: Maximum number of entries that can be returned.
+ * Entries array must be allocated to hold max_entries number of entries.
+ * @num_entries: Updated to the number of entries that were successfully read.
+ *
+ * Returns number of entries on success or appropriate error code.
+ */
+ssize_t rdma_query_gid_table(struct ib_device *device,
+			     struct ib_uverbs_gid_entry *entries,
+			     size_t max_entries)
+{
+	const struct ib_gid_attr *gid_attr;
+	ssize_t num_entries = 0, ret;
+	struct ib_gid_table *table;
+	unsigned int port_num, i;
+	struct net_device *ndev;
+	unsigned long flags;
+
+	rdma_for_each_port(device, port_num) {
+		if (!rdma_ib_or_roce(device, port_num))
+			continue;
+
+		table = rdma_gid_table(device, port_num);
+		read_lock_irqsave(&table->rwlock, flags);
+		for (i = 0; i < table->sz; i++) {
+			if (!is_gid_entry_valid(table->data_vec[i]))
+				continue;
+			if (num_entries >= max_entries) {
+				ret = -EINVAL;
+				goto err;
+			}
+
+			gid_attr = &table->data_vec[i]->attr;
+
+			memcpy(&entries->gid, &gid_attr->gid,
+			       sizeof(gid_attr->gid));
+			entries->gid_index = gid_attr->index;
+			entries->port_num = gid_attr->port_num;
+			entries->gid_type = gid_attr->gid_type;
+			ndev = rcu_dereference_protected(
+				gid_attr->ndev,
+				lockdep_is_held(&table->rwlock));
+			if (ndev)
+				entries->netdev_ifindex = ndev->ifindex;
+
+			num_entries++;
+			entries++;
+		}
+		read_unlock_irqrestore(&table->rwlock, flags);
+	}
+
+	return num_entries;
+err:
+	read_unlock_irqrestore(&table->rwlock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_query_gid_table);
+
 /**
  * rdma_put_gid_attr - Release reference to the GID attribute
  * @attr:		Pointer to the GID attribute whose reference
@@ -1299,7 +1364,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	struct ib_gid_table_entry *entry =
 			container_of(attr, struct ib_gid_table_entry, attr);
 	struct ib_device *device = entry->attr.device;
-	struct net_device *ndev = ERR_PTR(-ENODEV);
+	struct net_device *ndev = ERR_PTR(-EINVAL);
 	u8 port_num = entry->attr.port_num;
 	struct ib_gid_table *table;
 	unsigned long flags;
@@ -1311,8 +1376,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	valid = is_gid_entry_valid(table->data_vec[attr->index]);
 	if (valid) {
 		ndev = rcu_dereference(attr->ndev);
-		if (!ndev ||
-		    (ndev && ((READ_ONCE(ndev->flags) & IFF_UP) == 0)))
+		if (!ndev)
 			ndev = ERR_PTR(-ENODEV);
 	}
 	read_unlock_irqrestore(&table->rwlock, flags);

drivers/infiniband/core/cm.c

@@ -27,6 +27,7 @@
 #include <rdma/ib_cm.h>
 #include "cm_msgs.h"
 #include "core_priv.h"
+#include "cm_trace.h"
 
 MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("InfiniBand CM");
@@ -201,7 +202,6 @@ static struct attribute *cm_counter_default_attrs[] = {
 struct cm_port {
 	struct cm_device *cm_dev;
 	struct ib_mad_agent *mad_agent;
-	struct kobject port_obj;
 	u8 port_num;
 	struct list_head cm_priv_prim_list;
 	struct list_head cm_priv_altr_list;
@@ -1563,6 +1563,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
 	cm_id_priv->local_qpn = cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
 	cm_id_priv->rq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
 
+	trace_icm_send_req(&cm_id_priv->id);
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
 	ret = ib_post_send_mad(cm_id_priv->msg, NULL);
 	if (ret) {
@@ -1610,6 +1611,9 @@ static int cm_issue_rej(struct cm_port *port,
 		IBA_SET_MEM(CM_REJ_ARI, rej_msg, ari, ari_length);
 	}
 
+	trace_icm_issue_rej(
+		IBA_GET(CM_REJ_LOCAL_COMM_ID, rcv_msg),
+		IBA_GET(CM_REJ_REMOTE_COMM_ID, rcv_msg));
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret)
 		cm_free_msg(msg);
@@ -1961,6 +1965,7 @@ static void cm_dup_req_handler(struct cm_work *work,
 	}
 	spin_unlock_irq(&cm_id_priv->lock);
 
+	trace_icm_send_dup_req(&cm_id_priv->id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret)
 		goto free;
@@ -2124,8 +2129,7 @@ static int cm_req_handler(struct cm_work *work)
 
 	listen_cm_id_priv = cm_match_req(work, cm_id_priv);
 	if (!listen_cm_id_priv) {
-		pr_debug("%s: local_id %d, no listen_cm_id_priv\n", __func__,
-			 be32_to_cpu(cm_id_priv->id.local_id));
+		trace_icm_no_listener_err(&cm_id_priv->id);
 		cm_id_priv->id.state = IB_CM_IDLE;
 		ret = -EINVAL;
 		goto destroy;
@@ -2274,8 +2278,7 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
 	if (cm_id->state != IB_CM_REQ_RCVD &&
 	    cm_id->state != IB_CM_MRA_REQ_SENT) {
-		pr_debug("%s: local_comm_id %d, cm_id->state: %d\n", __func__,
-			 be32_to_cpu(cm_id_priv->id.local_id), cm_id->state);
+		trace_icm_send_rep_err(cm_id_priv->id.local_id, cm_id->state);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -2289,6 +2292,7 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
 	msg->timeout_ms = cm_id_priv->timeout_ms;
 	msg->context[1] = (void *) (unsigned long) IB_CM_REP_SENT;
 
+	trace_icm_send_rep(cm_id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -2348,8 +2352,7 @@ int ib_send_cm_rtu(struct ib_cm_id *cm_id,
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
 	if (cm_id->state != IB_CM_REP_RCVD &&
 	    cm_id->state != IB_CM_MRA_REP_SENT) {
-		pr_debug("%s: local_id %d, cm_id->state %d\n", __func__,
-			 be32_to_cpu(cm_id->local_id), cm_id->state);
+		trace_icm_send_cm_rtu_err(cm_id);
 		ret = -EINVAL;
 		goto error;
 	}
@@ -2361,6 +2364,7 @@ int ib_send_cm_rtu(struct ib_cm_id *cm_id,
 	cm_format_rtu((struct cm_rtu_msg *) msg->mad, cm_id_priv,
 		      private_data, private_data_len);
 
+	trace_icm_send_rtu(cm_id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -2442,6 +2446,7 @@ static void cm_dup_rep_handler(struct cm_work *work)
 		goto unlock;
 	spin_unlock_irq(&cm_id_priv->lock);
 
+	trace_icm_send_dup_rep(&cm_id_priv->id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret)
 		goto free;
@@ -2465,7 +2470,7 @@ static int cm_rep_handler(struct cm_work *work)
 		cpu_to_be32(IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg)), 0);
 	if (!cm_id_priv) {
 		cm_dup_rep_handler(work);
-		pr_debug("%s: remote_comm_id %d, no cm_id_priv\n", __func__,
+		trace_icm_remote_no_priv_err(
 			 IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 		return -EINVAL;
 	}
@@ -2479,11 +2484,10 @@ static int cm_rep_handler(struct cm_work *work)
 		break;
 	default:
 		ret = -EINVAL;
-		pr_debug(
-			"%s: cm_id_priv->id.state: %d, local_comm_id %d, remote_comm_id %d\n",
-			__func__, cm_id_priv->id.state,
+		trace_icm_rep_unknown_err(
 			IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
-			IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
+			IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg),
+			cm_id_priv->id.state);
 		spin_unlock_irq(&cm_id_priv->lock);
 		goto error;
 	}
@@ -2500,7 +2504,7 @@ static int cm_rep_handler(struct cm_work *work)
 		spin_unlock(&cm.lock);
 		spin_unlock_irq(&cm_id_priv->lock);
 		ret = -EINVAL;
-		pr_debug("%s: Failed to insert remote id %d\n", __func__,
+		trace_icm_insert_failed_err(
 			 IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 		goto error;
 	}
@@ -2517,9 +2521,8 @@ static int cm_rep_handler(struct cm_work *work)
 			     IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
 			     NULL, 0);
 		ret = -EINVAL;
-		pr_debug(
-			"%s: Stale connection. local_comm_id %d, remote_comm_id %d\n",
-			__func__, IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
+		trace_icm_staleconn_err(
+			IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
 			IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 
 		if (cur_cm_id_priv) {
@@ -2646,9 +2649,7 @@ static int cm_send_dreq_locked(struct cm_id_private *cm_id_priv,
 		return -EINVAL;
 
 	if (cm_id_priv->id.state != IB_CM_ESTABLISHED) {
-		pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
-			 be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_dreq_skipped(&cm_id_priv->id);
 		return -EINVAL;
 	}
 
@@ -2667,6 +2668,7 @@ static int cm_send_dreq_locked(struct cm_id_private *cm_id_priv,
 	msg->timeout_ms = cm_id_priv->timeout_ms;
 	msg->context[1] = (void *) (unsigned long) IB_CM_DREQ_SENT;
 
+	trace_icm_send_dreq(&cm_id_priv->id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		cm_enter_timewait(cm_id_priv);
@@ -2722,10 +2724,7 @@ static int cm_send_drep_locked(struct cm_id_private *cm_id_priv,
 		return -EINVAL;
 
 	if (cm_id_priv->id.state != IB_CM_DREQ_RCVD) {
-		pr_debug(
-			"%s: local_id %d, cm_idcm_id->state(%d) != IB_CM_DREQ_RCVD\n",
-			__func__, be32_to_cpu(cm_id_priv->id.local_id),
-			cm_id_priv->id.state);
+		trace_icm_send_drep_err(&cm_id_priv->id);
 		kfree(private_data);
 		return -EINVAL;
 	}
@@ -2740,6 +2739,7 @@ static int cm_send_drep_locked(struct cm_id_private *cm_id_priv,
 	cm_format_drep((struct cm_drep_msg *) msg->mad, cm_id_priv,
 		       private_data, private_data_len);
 
+	trace_icm_send_drep(&cm_id_priv->id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		cm_free_msg(msg);
@@ -2789,6 +2789,9 @@ static int cm_issue_drep(struct cm_port *port,
 	IBA_SET(CM_DREP_LOCAL_COMM_ID, drep_msg,
 		IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
 
+	trace_icm_issue_drep(
+		IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
+		IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret)
 		cm_free_msg(msg);
@@ -2810,9 +2813,8 @@ static int cm_dreq_handler(struct cm_work *work)
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_DREQ_COUNTER]);
 		cm_issue_drep(work->port, work->mad_recv_wc);
-		pr_debug(
-			"%s: no cm_id_priv, local_comm_id %d, remote_comm_id %d\n",
-			__func__, IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
+		trace_icm_no_priv_err(
+			IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
 			IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
 		return -EINVAL;
 	}
@@ -2858,9 +2860,7 @@ static int cm_dreq_handler(struct cm_work *work)
 				counter[CM_DREQ_COUNTER]);
 		goto unlock;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_dreq_unknown_err(&cm_id_priv->id);
 		goto unlock;
 	}
 	cm_id_priv->id.state = IB_CM_DREQ_RCVD;
@@ -2945,12 +2945,11 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 			      state);
 		break;
 	default:
-		pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
-			 be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_send_unknown_rej_err(&cm_id_priv->id);
 		return -EINVAL;
 	}
 
+	trace_icm_send_rej(&cm_id_priv->id, reason);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		cm_free_msg(msg);
@@ -3060,9 +3059,7 @@ static int cm_rej_handler(struct cm_work *work)
 		}
 		fallthrough;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_rej_unknown_err(&cm_id_priv->id);
 		spin_unlock_irq(&cm_id_priv->lock);
 		goto out;
 	}
@@ -3118,9 +3115,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 		}
 		fallthrough;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_send_mra_unknown_err(&cm_id_priv->id);
 		ret = -EINVAL;
 		goto error1;
 	}
@@ -3133,6 +3128,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
 			      msg_response, service_timeout,
 			      private_data, private_data_len);
+		trace_icm_send_mra(cm_id);
 		ret = ib_post_send_mad(msg, NULL);
 		if (ret)
 			goto error2;
@@ -3229,9 +3225,7 @@ static int cm_mra_handler(struct cm_work *work)
 				counter[CM_MRA_COUNTER]);
 		fallthrough;
 	default:
-		pr_debug("%s local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_mra_unknown_err(&cm_id_priv->id);
 		goto out;
 	}
 
@@ -3505,10 +3499,12 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
 	msg->context[1] = (void *) (unsigned long) IB_CM_SIDR_REQ_SENT;
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
-	if (cm_id->state == IB_CM_IDLE)
+	if (cm_id->state == IB_CM_IDLE) {
+		trace_icm_send_sidr_req(&cm_id_priv->id);
 		ret = ib_post_send_mad(msg, NULL);
-	else
+	} else {
 		ret = -EINVAL;
+	}
 
 	if (ret) {
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -3670,6 +3666,7 @@ static int cm_send_sidr_rep_locked(struct cm_id_private *cm_id_priv,
 
 	cm_format_sidr_rep((struct cm_sidr_rep_msg *) msg->mad, cm_id_priv,
 			   param);
+	trace_icm_send_sidr_rep(&cm_id_priv->id);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		cm_free_msg(msg);
@@ -3767,8 +3764,7 @@ static void cm_process_send_error(struct ib_mad_send_buf *msg,
 	if (msg != cm_id_priv->msg || state != cm_id_priv->id.state)
 		goto discard;
 
-	pr_debug_ratelimited("CM: failed sending MAD in state %d. (%s)\n",
-			     state, ib_wc_status_msg(wc_status));
+	trace_icm_mad_send_err(state, wc_status);
 	switch (state) {
 	case IB_CM_REQ_SENT:
 	case IB_CM_MRA_REQ_RCVD:
@@ -3891,7 +3887,7 @@ static void cm_work_handler(struct work_struct *_work)
 		ret = cm_timewait_handler(work);
 		break;
 	default:
-		pr_debug("cm_event.event: 0x%x\n", work->cm_event.event);
+		trace_icm_handler_err(work->cm_event.event);
 		ret = -EINVAL;
 		break;
 	}
@@ -3927,8 +3923,7 @@ static int cm_establish(struct ib_cm_id *cm_id)
 		ret = -EISCONN;
 		break;
 	default:
-		pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
-			 be32_to_cpu(cm_id->local_id), cm_id->state);
+		trace_icm_establish_err(cm_id);
 		ret = -EINVAL;
 		break;
 	}
@@ -4125,9 +4120,7 @@ static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
 		ret = 0;
 		break;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_qp_init_err(&cm_id_priv->id);
 		ret = -EINVAL;
 		break;
 	}
@@ -4175,9 +4168,7 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
 		ret = 0;
 		break;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_qp_rtr_err(&cm_id_priv->id);
 		ret = -EINVAL;
 		break;
 	}
@@ -4237,9 +4228,7 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
 		ret = 0;
 		break;
 	default:
-		pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
-			 __func__, be32_to_cpu(cm_id_priv->id.local_id),
-			 cm_id_priv->id.state);
+		trace_icm_qp_rts_err(&cm_id_priv->id);
 		ret = -EINVAL;
 		break;
 	}
@@ -4295,20 +4284,6 @@ static struct kobj_type cm_counter_obj_type = {
 	.default_attrs = cm_counter_default_attrs
 };
 
-static char *cm_devnode(struct device *dev, umode_t *mode)
-{
-	if (mode)
-		*mode = 0666;
-	return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
-}
-
-struct class cm_class = {
-	.owner   = THIS_MODULE,
-	.name    = "infiniband_cm",
-	.devnode = cm_devnode,
-};
-EXPORT_SYMBOL(cm_class);
-
 static int cm_create_port_fs(struct cm_port *port)
 {
 	int i, ret;
@@ -4511,12 +4486,6 @@ static int __init ib_cm_init(void)
 	get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
 	INIT_LIST_HEAD(&cm.timewait_list);
 
-	ret = class_register(&cm_class);
-	if (ret) {
-		ret = -ENOMEM;
-		goto error1;
-	}
-
 	cm.wq = alloc_workqueue("ib_cm", 0, 1);
 	if (!cm.wq) {
 		ret = -ENOMEM;
@@ -4531,8 +4500,6 @@ static int __init ib_cm_init(void)
 error3:
 	destroy_workqueue(cm.wq);
 error2:
-	class_unregister(&cm_class);
-error1:
 	return ret;
 }
 
@@ -4553,7 +4520,6 @@ static void __exit ib_cm_cleanup(void)
 		kfree(timewait_info);
 	}
 
-	class_unregister(&cm_class);
 	WARN_ON(!xa_empty(&cm.local_id_table));
 }
 

drivers/infiniband/core/cm_trace.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Trace points for the IB Connection Manager.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#include <rdma/rdma_cm.h>
+#include "cma_priv.h"
+
+#define CREATE_TRACE_POINTS
+
+#include "cm_trace.h"

drivers/infiniband/core/cm_trace.h

@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Trace point definitions for the RDMA Connect Manager.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2020 Oracle and/or its affiliates.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ib_cma
+
+#if !defined(_TRACE_IB_CMA_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_IB_CMA_H
+
+#include <linux/tracepoint.h>
+#include <rdma/ib_cm.h>
+#include <trace/events/rdma.h>
+
+/*
+ * enum ib_cm_state, from include/rdma/ib_cm.h
+ */
+#define IB_CM_STATE_LIST					\
+	ib_cm_state(IDLE)					\
+	ib_cm_state(LISTEN)					\
+	ib_cm_state(REQ_SENT)					\
+	ib_cm_state(REQ_RCVD)					\
+	ib_cm_state(MRA_REQ_SENT)				\
+	ib_cm_state(MRA_REQ_RCVD)				\
+	ib_cm_state(REP_SENT)					\
+	ib_cm_state(REP_RCVD)					\
+	ib_cm_state(MRA_REP_SENT)				\
+	ib_cm_state(MRA_REP_RCVD)				\
+	ib_cm_state(ESTABLISHED)				\
+	ib_cm_state(DREQ_SENT)					\
+	ib_cm_state(DREQ_RCVD)					\
+	ib_cm_state(TIMEWAIT)					\
+	ib_cm_state(SIDR_REQ_SENT)				\
+	ib_cm_state_end(SIDR_REQ_RCVD)
+
+#undef  ib_cm_state
+#undef  ib_cm_state_end
+#define ib_cm_state(x)		TRACE_DEFINE_ENUM(IB_CM_##x);
+#define ib_cm_state_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+
+IB_CM_STATE_LIST
+
+#undef  ib_cm_state
+#undef  ib_cm_state_end
+#define ib_cm_state(x)		{ IB_CM_##x, #x },
+#define ib_cm_state_end(x)	{ IB_CM_##x, #x }
+
+#define show_ib_cm_state(x) \
+		__print_symbolic(x, IB_CM_STATE_LIST)
+
+/*
+ * enum ib_cm_lap_state, from include/rdma/ib_cm.h
+ */
+#define IB_CM_LAP_STATE_LIST					\
+	ib_cm_lap_state(LAP_UNINIT)				\
+	ib_cm_lap_state(LAP_IDLE)				\
+	ib_cm_lap_state(LAP_SENT)				\
+	ib_cm_lap_state(LAP_RCVD)				\
+	ib_cm_lap_state(MRA_LAP_SENT)				\
+	ib_cm_lap_state_end(MRA_LAP_RCVD)
+
+#undef  ib_cm_lap_state
+#undef  ib_cm_lap_state_end
+#define ib_cm_lap_state(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+#define ib_cm_lap_state_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+
+IB_CM_LAP_STATE_LIST
+
+#undef  ib_cm_lap_state
+#undef  ib_cm_lap_state_end
+#define ib_cm_lap_state(x)	{ IB_CM_##x, #x },
+#define ib_cm_lap_state_end(x)	{ IB_CM_##x, #x }
+
+#define show_ib_cm_lap_state(x) \
+		__print_symbolic(x, IB_CM_LAP_STATE_LIST)
+
+/*
+ * enum ib_cm_rej_reason, from include/rdma/ib_cm.h
+ */
+#define IB_CM_REJ_REASON_LIST					\
+	ib_cm_rej_reason(REJ_NO_QP)				\
+	ib_cm_rej_reason(REJ_NO_EEC)				\
+	ib_cm_rej_reason(REJ_NO_RESOURCES)			\
+	ib_cm_rej_reason(REJ_TIMEOUT)				\
+	ib_cm_rej_reason(REJ_UNSUPPORTED)			\
+	ib_cm_rej_reason(REJ_INVALID_COMM_ID)			\
+	ib_cm_rej_reason(REJ_INVALID_COMM_INSTANCE)		\
+	ib_cm_rej_reason(REJ_INVALID_SERVICE_ID)		\
+	ib_cm_rej_reason(REJ_INVALID_TRANSPORT_TYPE)		\
+	ib_cm_rej_reason(REJ_STALE_CONN)			\
+	ib_cm_rej_reason(REJ_RDC_NOT_EXIST)			\
+	ib_cm_rej_reason(REJ_INVALID_GID)			\
+	ib_cm_rej_reason(REJ_INVALID_LID)			\
+	ib_cm_rej_reason(REJ_INVALID_SL)			\
+	ib_cm_rej_reason(REJ_INVALID_TRAFFIC_CLASS)		\
+	ib_cm_rej_reason(REJ_INVALID_HOP_LIMIT)			\
+	ib_cm_rej_reason(REJ_INVALID_PACKET_RATE)		\
+	ib_cm_rej_reason(REJ_INVALID_ALT_GID)			\
+	ib_cm_rej_reason(REJ_INVALID_ALT_LID)			\
+	ib_cm_rej_reason(REJ_INVALID_ALT_SL)			\
+	ib_cm_rej_reason(REJ_INVALID_ALT_TRAFFIC_CLASS)		\
+	ib_cm_rej_reason(REJ_INVALID_ALT_HOP_LIMIT)		\
+	ib_cm_rej_reason(REJ_INVALID_ALT_PACKET_RATE)		\
+	ib_cm_rej_reason(REJ_PORT_CM_REDIRECT)			\
+	ib_cm_rej_reason(REJ_PORT_REDIRECT)			\
+	ib_cm_rej_reason(REJ_INVALID_MTU)			\
+	ib_cm_rej_reason(REJ_INSUFFICIENT_RESP_RESOURCES)	\
+	ib_cm_rej_reason(REJ_CONSUMER_DEFINED)			\
+	ib_cm_rej_reason(REJ_INVALID_RNR_RETRY)			\
+	ib_cm_rej_reason(REJ_DUPLICATE_LOCAL_COMM_ID)		\
+	ib_cm_rej_reason(REJ_INVALID_CLASS_VERSION)		\
+	ib_cm_rej_reason(REJ_INVALID_FLOW_LABEL)		\
+	ib_cm_rej_reason(REJ_INVALID_ALT_FLOW_LABEL)		\
+	ib_cm_rej_reason_end(REJ_VENDOR_OPTION_NOT_SUPPORTED)
+
+#undef  ib_cm_rej_reason
+#undef  ib_cm_rej_reason_end
+#define ib_cm_rej_reason(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+#define ib_cm_rej_reason_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+
+IB_CM_REJ_REASON_LIST
+
+#undef  ib_cm_rej_reason
+#undef  ib_cm_rej_reason_end
+#define ib_cm_rej_reason(x)	{ IB_CM_##x, #x },
+#define ib_cm_rej_reason_end(x)	{ IB_CM_##x, #x }
+
+#define show_ib_cm_rej_reason(x) \
+		__print_symbolic(x, IB_CM_REJ_REASON_LIST)
+
+DECLARE_EVENT_CLASS(icm_id_class,
+	TP_PROTO(
+		const struct ib_cm_id *cm_id
+	),
+
+	TP_ARGS(cm_id),
+
+	TP_STRUCT__entry(
+		__field(const void *, cm_id)	/* for eBPF scripts */
+		__field(unsigned int, local_id)
+		__field(unsigned int, remote_id)
+		__field(unsigned long, state)
+		__field(unsigned long, lap_state)
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = cm_id;
+		__entry->local_id = be32_to_cpu(cm_id->local_id);
+		__entry->remote_id = be32_to_cpu(cm_id->remote_id);
+		__entry->state = cm_id->state;
+		__entry->lap_state = cm_id->lap_state;
+	),
+
+	TP_printk("local_id=%u remote_id=%u state=%s lap_state=%s",
+		__entry->local_id, __entry->remote_id,
+		show_ib_cm_state(__entry->state),
+		show_ib_cm_lap_state(__entry->lap_state)
+	)
+);
+
+#define DEFINE_CM_SEND_EVENT(name)					\
+		DEFINE_EVENT(icm_id_class,				\
+				icm_send_##name,				\
+				TP_PROTO(				\
+					const struct ib_cm_id *cm_id	\
+				),					\
+				TP_ARGS(cm_id))
+
+DEFINE_CM_SEND_EVENT(req);
+DEFINE_CM_SEND_EVENT(rep);
+DEFINE_CM_SEND_EVENT(dup_req);
+DEFINE_CM_SEND_EVENT(dup_rep);
+DEFINE_CM_SEND_EVENT(rtu);
+DEFINE_CM_SEND_EVENT(mra);
+DEFINE_CM_SEND_EVENT(sidr_req);
+DEFINE_CM_SEND_EVENT(sidr_rep);
+DEFINE_CM_SEND_EVENT(dreq);
+DEFINE_CM_SEND_EVENT(drep);
+
+TRACE_EVENT(icm_send_rej,
+	TP_PROTO(
+		const struct ib_cm_id *cm_id,
+		enum ib_cm_rej_reason reason
+	),
+
+	TP_ARGS(cm_id, reason),
+
+	TP_STRUCT__entry(
+		__field(const void *, cm_id)
+		__field(u32, local_id)
+		__field(u32, remote_id)
+		__field(unsigned long, state)
+		__field(unsigned long, reason)
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = cm_id;
+		__entry->local_id = be32_to_cpu(cm_id->local_id);
+		__entry->remote_id = be32_to_cpu(cm_id->remote_id);
+		__entry->state = cm_id->state;
+		__entry->reason = reason;
+	),
+
+	TP_printk("local_id=%u remote_id=%u state=%s reason=%s",
+		__entry->local_id, __entry->remote_id,
+		show_ib_cm_state(__entry->state),
+		show_ib_cm_rej_reason(__entry->reason)
+	)
+);
+
+#define DEFINE_CM_ERR_EVENT(name)					\
+		DEFINE_EVENT(icm_id_class,				\
+				icm_##name##_err,			\
+				TP_PROTO(				\
+					const struct ib_cm_id *cm_id	\
+				),					\
+				TP_ARGS(cm_id))
+
+DEFINE_CM_ERR_EVENT(send_cm_rtu);
+DEFINE_CM_ERR_EVENT(establish);
+DEFINE_CM_ERR_EVENT(no_listener);
+DEFINE_CM_ERR_EVENT(send_drep);
+DEFINE_CM_ERR_EVENT(dreq_unknown);
+DEFINE_CM_ERR_EVENT(send_unknown_rej);
+DEFINE_CM_ERR_EVENT(rej_unknown);
+DEFINE_CM_ERR_EVENT(send_mra_unknown);
+DEFINE_CM_ERR_EVENT(mra_unknown);
+DEFINE_CM_ERR_EVENT(qp_init);
+DEFINE_CM_ERR_EVENT(qp_rtr);
+DEFINE_CM_ERR_EVENT(qp_rts);
+
+DEFINE_EVENT(icm_id_class,						\
+	icm_dreq_skipped,						\
+	TP_PROTO(							\
+		const struct ib_cm_id *cm_id				\
+	),								\
+	TP_ARGS(cm_id)							\
+);
+
+DECLARE_EVENT_CLASS(icm_local_class,
+	TP_PROTO(
+		unsigned int local_id,
+		unsigned int remote_id
+	),
+
+	TP_ARGS(local_id, remote_id),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, local_id)
+		__field(unsigned int, remote_id)
+	),
+
+	TP_fast_assign(
+		__entry->local_id = local_id;
+		__entry->remote_id = remote_id;
+	),
+
+	TP_printk("local_id=%u remote_id=%u",
+		__entry->local_id, __entry->remote_id
+	)
+);
+
+#define DEFINE_CM_LOCAL_EVENT(name)					\
+		DEFINE_EVENT(icm_local_class,				\
+				icm_##name,				\
+				TP_PROTO(				\
+					unsigned int local_id,			\
+					unsigned int remote_id			\
+				),					\
+				TP_ARGS(local_id, remote_id))
+
+DEFINE_CM_LOCAL_EVENT(issue_rej);
+DEFINE_CM_LOCAL_EVENT(issue_drep);
+DEFINE_CM_LOCAL_EVENT(staleconn_err);
+DEFINE_CM_LOCAL_EVENT(no_priv_err);
+
+DECLARE_EVENT_CLASS(icm_remote_class,
+	TP_PROTO(
+		u32 remote_id
+	),
+
+	TP_ARGS(remote_id),
+
+	TP_STRUCT__entry(
+		__field(u32, remote_id)
+	),
+
+	TP_fast_assign(
+		__entry->remote_id = remote_id;
+	),
+
+	TP_printk("remote_id=%u",
+		__entry->remote_id
+	)
+);
+
+#define DEFINE_CM_REMOTE_EVENT(name)					\
+		DEFINE_EVENT(icm_remote_class,				\
+				icm_##name,				\
+				TP_PROTO(				\
+					u32 remote_id			\
+				),					\
+				TP_ARGS(remote_id))
+
+DEFINE_CM_REMOTE_EVENT(remote_no_priv_err);
+DEFINE_CM_REMOTE_EVENT(insert_failed_err);
+
+TRACE_EVENT(icm_send_rep_err,
+	TP_PROTO(
+		__be32 local_id,
+		enum ib_cm_state state
+	),
+
+	TP_ARGS(local_id, state),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, local_id)
+		__field(unsigned long, state)
+	),
+
+	TP_fast_assign(
+		__entry->local_id = be32_to_cpu(local_id);
+		__entry->state = state;
+	),
+
+	TP_printk("local_id=%u state=%s",
+		__entry->local_id, show_ib_cm_state(__entry->state)
+	)
+);
+
+TRACE_EVENT(icm_rep_unknown_err,
+	TP_PROTO(
+		unsigned int local_id,
+		unsigned int remote_id,
+		enum ib_cm_state state
+	),
+
+	TP_ARGS(local_id, remote_id, state),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, local_id)
+		__field(unsigned int, remote_id)
+		__field(unsigned long, state)
+	),
+
+	TP_fast_assign(
+		__entry->local_id = local_id;
+		__entry->remote_id = remote_id;
+		__entry->state = state;
+	),
+
+	TP_printk("local_id=%u remote_id=%u state=%s",
+		__entry->local_id, __entry->remote_id,
+		show_ib_cm_state(__entry->state)
+	)
+);
+
+TRACE_EVENT(icm_handler_err,
+	TP_PROTO(
+		enum ib_cm_event_type event
+	),
+
+	TP_ARGS(event),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, event)
+	),
+
+	TP_fast_assign(
+		__entry->event = event;
+	),
+
+	TP_printk("unhandled event=%s",
+		rdma_show_ib_cm_event(__entry->event)
+	)
+);
+
+TRACE_EVENT(icm_mad_send_err,
+	TP_PROTO(
+		enum ib_cm_state state,
+		enum ib_wc_status wc_status
+	),
+
+	TP_ARGS(state, wc_status),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, state)
+		__field(unsigned long, wc_status)
+	),
+
+	TP_fast_assign(
+		__entry->state = state;
+		__entry->wc_status = wc_status;
+	),
+
+	TP_printk("state=%s completion status=%s",
+		show_ib_cm_state(__entry->state),
+		rdma_show_wc_status(__entry->wc_status)
+	)
+);
+
+#endif /* _TRACE_IB_CMA_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../drivers/infiniband/core
+#define TRACE_INCLUDE_FILE cm_trace
+
+#include <trace/define_trace.h>

drivers/infiniband/core/cma_configfs.c

@@ -123,16 +123,17 @@ static ssize_t default_roce_mode_store(struct config_item *item,
 {
 	struct cma_device *cma_dev;
 	struct cma_dev_port_group *group;
-	int gid_type = ib_cache_gid_parse_type_str(buf);
+	int gid_type;
 	ssize_t ret;
 
-	if (gid_type < 0)
-		return -EINVAL;
-
 	ret = cma_configfs_params_get(item, &cma_dev, &group);
 	if (ret)
 		return ret;
 
+	gid_type = ib_cache_gid_parse_type_str(buf);
+	if (gid_type < 0)
+		return -EINVAL;
+
 	ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type);
 
 	cma_configfs_params_put(cma_dev);

drivers/infiniband/core/cma_trace.h

@@ -17,46 +17,6 @@
 #include <linux/tracepoint.h>
 #include <trace/events/rdma.h>
 
-/*
- * enum ib_cm_event_type, from include/rdma/ib_cm.h
- */
-#define IB_CM_EVENT_LIST			\
-	ib_cm_event(REQ_ERROR)			\
-	ib_cm_event(REQ_RECEIVED)		\
-	ib_cm_event(REP_ERROR)			\
-	ib_cm_event(REP_RECEIVED)		\
-	ib_cm_event(RTU_RECEIVED)		\
-	ib_cm_event(USER_ESTABLISHED)		\
-	ib_cm_event(DREQ_ERROR)			\
-	ib_cm_event(DREQ_RECEIVED)		\
-	ib_cm_event(DREP_RECEIVED)		\
-	ib_cm_event(TIMEWAIT_EXIT)		\
-	ib_cm_event(MRA_RECEIVED)		\
-	ib_cm_event(REJ_RECEIVED)		\
-	ib_cm_event(LAP_ERROR)			\
-	ib_cm_event(LAP_RECEIVED)		\
-	ib_cm_event(APR_RECEIVED)		\
-	ib_cm_event(SIDR_REQ_ERROR)		\
-	ib_cm_event(SIDR_REQ_RECEIVED)		\
-	ib_cm_event_end(SIDR_REP_RECEIVED)
-
-#undef ib_cm_event
-#undef ib_cm_event_end
-
-#define ib_cm_event(x)		TRACE_DEFINE_ENUM(IB_CM_##x);
-#define ib_cm_event_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
-
-IB_CM_EVENT_LIST
-
-#undef ib_cm_event
-#undef ib_cm_event_end
-
-#define ib_cm_event(x)		{ IB_CM_##x, #x },
-#define ib_cm_event_end(x)	{ IB_CM_##x, #x }
-
-#define rdma_show_ib_cm_event(x) \
-		__print_symbolic(x, IB_CM_EVENT_LIST)
-
 
 DECLARE_EVENT_CLASS(cma_fsm_class,
 	TP_PROTO(

drivers/infiniband/core/core_priv.h

@@ -44,6 +44,7 @@
 #include <rdma/ib_mad.h>
 #include <rdma/restrack.h>
 #include "mad_priv.h"
+#include "restrack.h"
 
 /* Total number of ports combined across all struct ib_devices's */
 #define RDMA_MAX_PORTS 8192
@@ -352,6 +353,7 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	INIT_LIST_HEAD(&qp->rdma_mrs);
 	INIT_LIST_HEAD(&qp->sig_mrs);
 
+	rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
 	/*
 	 * We don't track XRC QPs for now, because they don't have PD
 	 * and more importantly they are created internaly by driver,
@@ -359,14 +361,9 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	 */
 	is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT;
 	if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) {
-		qp->res.type = RDMA_RESTRACK_QP;
-		if (uobj)
-			rdma_restrack_uadd(&qp->res);
-		else
-			rdma_restrack_kadd(&qp->res);
-	} else
-		qp->res.valid = false;
-
+		rdma_restrack_parent_name(&qp->res, &pd->res);
+		rdma_restrack_add(&qp->res);
+	}
 	return qp;
 }
 

drivers/infiniband/core/counters.c

@@ -80,8 +80,9 @@ static struct rdma_counter *rdma_counter_alloc(struct ib_device *dev, u8 port,
 
 	counter->device    = dev;
 	counter->port      = port;
-	counter->res.type  = RDMA_RESTRACK_COUNTER;
-	counter->stats     = dev->ops.counter_alloc_stats(counter);
+
+	rdma_restrack_new(&counter->res, RDMA_RESTRACK_COUNTER);
+	counter->stats = dev->ops.counter_alloc_stats(counter);
 	if (!counter->stats)
 		goto err_stats;
 
@@ -107,6 +108,7 @@ err_mode:
 	mutex_unlock(&port_counter->lock);
 	kfree(counter->stats);
 err_stats:
+	rdma_restrack_put(&counter->res);
 	kfree(counter);
 	return NULL;
 }
@@ -248,13 +250,8 @@ next:
 static void rdma_counter_res_add(struct rdma_counter *counter,
 				 struct ib_qp *qp)
 {
-	if (rdma_is_kernel_res(&qp->res)) {
-		rdma_restrack_set_task(&counter->res, qp->res.kern_name);
-		rdma_restrack_kadd(&counter->res);
-	} else {
-		rdma_restrack_attach_task(&counter->res, qp->res.task);
-		rdma_restrack_uadd(&counter->res);
-	}
+	rdma_restrack_parent_name(&counter->res, &qp->res);
+	rdma_restrack_add(&counter->res);
 }
 
 static void counter_release(struct kref *kref)

drivers/infiniband/core/cq.c

@@ -197,24 +197,22 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 }
 
 /**
- * __ib_alloc_cq_user - allocate a completion queue
+ * __ib_alloc_cq        allocate a completion queue
  * @dev:		device to allocate the CQ for
  * @private:		driver private data, accessible from cq->cq_context
  * @nr_cqe:		number of CQEs to allocate
  * @comp_vector:	HCA completion vectors for this CQ
  * @poll_ctx:		context to poll the CQ from.
  * @caller:		module owner name.
- * @udata:		Valid user data or NULL for kernel object
  *
  * This is the proper interface to allocate a CQ for in-kernel users. A
  * CQ allocated with this interface will automatically be polled from the
  * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
  * to use this CQ abstraction.
  */
-struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
-				 int nr_cqe, int comp_vector,
-				 enum ib_poll_context poll_ctx,
-				 const char *caller, struct ib_udata *udata)
+struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
+			    int comp_vector, enum ib_poll_context poll_ctx,
+			    const char *caller)
 {
 	struct ib_cq_init_attr cq_attr = {
 		.cqe		= nr_cqe,
@@ -237,15 +235,13 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 	if (!cq->wc)
 		goto out_free_cq;
 
-	cq->res.type = RDMA_RESTRACK_CQ;
-	rdma_restrack_set_task(&cq->res, caller);
+	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
+	rdma_restrack_set_name(&cq->res, caller);
 
 	ret = dev->ops.create_cq(cq, &cq_attr, NULL);
 	if (ret)
 		goto out_free_wc;
 
-	rdma_restrack_kadd(&cq->res);
-
 	rdma_dim_init(cq);
 
 	switch (cq->poll_ctx) {
@@ -271,21 +267,22 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 		goto out_destroy_cq;
 	}
 
+	rdma_restrack_add(&cq->res);
 	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
 out_destroy_cq:
 	rdma_dim_destroy(cq);
-	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, udata);
+	cq->device->ops.destroy_cq(cq, NULL);
 out_free_wc:
+	rdma_restrack_put(&cq->res);
 	kfree(cq->wc);
 out_free_cq:
 	kfree(cq);
 	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(__ib_alloc_cq_user);
+EXPORT_SYMBOL(__ib_alloc_cq);
 
 /**
  * __ib_alloc_cq_any - allocate a completion queue
@@ -310,18 +307,19 @@ struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
 			atomic_inc_return(&counter) %
 			min_t(int, dev->num_comp_vectors, num_online_cpus());
 
-	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
-				  caller, NULL);
+	return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
+			     caller);
 }
 EXPORT_SYMBOL(__ib_alloc_cq_any);
 
 /**
- * ib_free_cq_user - free a completion queue
+ * ib_free_cq - free a completion queue
  * @cq:		completion queue to free.
- * @udata:	User data or NULL for kernel object
  */
-void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
+void ib_free_cq(struct ib_cq *cq)
 {
+	int ret;
+
 	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
 		return;
 	if (WARN_ON_ONCE(cq->cqe_used))
@@ -343,12 +341,13 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 
 	rdma_dim_destroy(cq);
 	trace_cq_free(cq);
+	ret = cq->device->ops.destroy_cq(cq, NULL);
+	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
 	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, udata);
 	kfree(cq->wc);
 	kfree(cq);
 }
-EXPORT_SYMBOL(ib_free_cq_user);
+EXPORT_SYMBOL(ib_free_cq);
 
 void ib_cq_pool_init(struct ib_device *dev)
 {

drivers/infiniband/core/device.c

@@ -1177,58 +1177,23 @@ out:
 	return ret;
 }
 
-static void setup_dma_device(struct ib_device *device)
+static void setup_dma_device(struct ib_device *device,
+			     struct device *dma_device)
 {
-	struct device *parent = device->dev.parent;
-
-	WARN_ON_ONCE(device->dma_device);
-
-#ifdef CONFIG_DMA_OPS
-	if (device->dev.dma_ops) {
-		/*
-		 * The caller provided custom DMA operations. Copy the
-		 * DMA-related fields that are used by e.g. dma_alloc_coherent()
-		 * into device->dev.
-		 */
-		device->dma_device = &device->dev;
-		if (!device->dev.dma_mask) {
-			if (parent)
-				device->dev.dma_mask = parent->dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-		if (!device->dev.coherent_dma_mask) {
-			if (parent)
-				device->dev.coherent_dma_mask =
-					parent->coherent_dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-	} else
-#endif /* CONFIG_DMA_OPS */
-	{
-		/*
-		 * The caller did not provide custom DMA operations. Use the
-		 * DMA mapping operations of the parent device.
-		 */
-		WARN_ON_ONCE(!parent);
-		device->dma_device = parent;
-	}
-
-	if (!device->dev.dma_parms) {
-		if (parent) {
-			/*
-			 * The caller did not provide DMA parameters, so
-			 * 'parent' probably represents a PCI device. The PCI
-			 * core sets the maximum segment size to 64
-			 * KB. Increase this parameter to 2 GB.
-			 */
-			device->dev.dma_parms = parent->dma_parms;
-			dma_set_max_seg_size(device->dma_device, SZ_2G);
-		} else {
-			WARN_ON_ONCE(true);
-		}
+	/*
+	 * If the caller does not provide a DMA capable device then the IB
+	 * device will be used. In this case the caller should fully setup the
+	 * ibdev for DMA. This usually means using dma_virt_ops.
+	 */
+#ifdef CONFIG_DMA_VIRT_OPS
+	if (!dma_device) {
+		device->dev.dma_ops = &dma_virt_ops;
+		dma_device = &device->dev;
 	}
+#endif
+	WARN_ON(!dma_device);
+	device->dma_device = dma_device;
+	WARN_ON(!device->dma_device->dma_parms);
 }
 
 /*
@@ -1241,7 +1206,6 @@ static int setup_device(struct ib_device *device)
 	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
 	int ret;
 
-	setup_dma_device(device);
 	ib_device_check_mandatory(device);
 
 	ret = setup_port_data(device);
@@ -1354,7 +1318,10 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * ib_register_device - Register an IB device with IB core
  * @device: Device to register
  * @name: unique string device name. This may include a '%' which will
- * cause a unique index to be added to the passed device name.
+ * 	  cause a unique index to be added to the passed device name.
+ * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB
+ *	        device will be used. In this case the caller should fully
+ *		setup the ibdev for DMA. This usually means using dma_virt_ops.
  *
  * Low-level drivers use ib_register_device() to register their
  * devices with the IB core.  All registered clients will receive a
@@ -1365,7 +1332,8 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * asynchronously then the device pointer may become freed as soon as this
  * function returns.
  */
-int ib_register_device(struct ib_device *device, const char *name)
+int ib_register_device(struct ib_device *device, const char *name,
+		       struct device *dma_device)
 {
 	int ret;
 
@@ -1373,6 +1341,7 @@ int ib_register_device(struct ib_device *device, const char *name)
 	if (ret)
 		return ret;
 
+	setup_dma_device(device, dma_device);
 	ret = setup_device(device);
 	if (ret)
 		return ret;
@@ -2697,7 +2666,9 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_ah);
 	SET_OBJ_SIZE(dev_ops, ib_counters);
 	SET_OBJ_SIZE(dev_ops, ib_cq);
+	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
+	SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table);
 	SET_OBJ_SIZE(dev_ops, ib_srq);
 	SET_OBJ_SIZE(dev_ops, ib_ucontext);
 	SET_OBJ_SIZE(dev_ops, ib_xrcd);