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

Pull rdma updates from Jason Gunthorpe:
 "A smaller set of patches, nothing stands out as being particularly
  major this cycle. The biggest item would be the new HIP09 HW support
  from HNS, otherwise it was pretty quiet for new work here:

   - Driver bug fixes and updates: bnxt_re, cxgb4, rxe, hns, i40iw,
     cxgb4, mlx4 and mlx5

   - Bug fixes and polishing for the new rts ULP

   - Cleanup of uverbs checking for allowed driver operations

   - Use sysfs_emit all over the place

   - Lots of bug fixes and clarity improvements for hns

   - hip09 support for hns

   - NDR and 50/100Gb signaling rates

   - Remove dma_virt_ops and go back to using the IB DMA wrappers

   - mlx5 optimizations for contiguous DMA regions"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (147 commits)
  RDMA/cma: Don't overwrite sgid_attr after device is released
  RDMA/mlx5: Fix MR cache memory leak
  RDMA/rxe: Use acquire/release for memory ordering
  RDMA/hns: Simplify AEQE process for different types of queue
  RDMA/hns: Fix inaccurate prints
  RDMA/hns: Fix incorrect symbol types
  RDMA/hns: Clear redundant variable initialization
  RDMA/hns: Fix coding style issues
  RDMA/hns: Remove unnecessary access right set during INIT2INIT
  RDMA/hns: WARN_ON if get a reserved sl from users
  RDMA/hns: Avoid filling sl in high 3 bits of vlan_id
  RDMA/hns: Do shift on traffic class when using RoCEv2
  RDMA/hns: Normalization the judgment of some features
  RDMA/hns: Limit the length of data copied between kernel and userspace
  RDMA/mlx4: Remove bogus dev_base_lock usage
  RDMA/uverbs: Fix incorrect variable type
  RDMA/core: Do not indicate device ready when device enablement fails
  RDMA/core: Clean up cq pool mechanism
  RDMA/core: Update kernel documentation for ib_create_named_qp()
  MAINTAINERS: SOFT-ROCE: Change Zhu Yanjun's email address
  ...

Author: torvalds

.mailmap

@@ -345,3 +345,4 @@ Wolfram Sang <[email protected]> <[email protected]>
 Wolfram Sang <[email protected]> <[email protected]>
 Yakir Yang <[email protected]> <[email protected]>
 Yusuke Goda <[email protected]>
+Zhu Yanjun <[email protected]> <[email protected]>

MAINTAINERS

@@ -16399,7 +16399,7 @@ F:	drivers/infiniband/sw/siw/
 F:	include/uapi/rdma/siw-abi.h
 
 SOFT-ROCE DRIVER (rxe)
-M:	Zhu Yanjun <yanjunz@nvidia.com>
+M:	Zhu Yanjun <zyjzyj2000@gmail.com>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/sw/rxe/

drivers/infiniband/core/cm.c

@@ -1251,7 +1251,8 @@ int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask)
 EXPORT_SYMBOL(ib_cm_listen);
 
 /**
- * Create a new listening ib_cm_id and listen on the given service ID.
+ * ib_cm_insert_listen - Create a new listening ib_cm_id and listen on
+ *			 the given service ID.
  *
  * If there's an existing ID listening on that same device and service ID,
  * return it.
@@ -1765,7 +1766,7 @@ static u16 cm_get_bth_pkey(struct cm_work *work)
 }
 
 /**
- * Convert OPA SGID to IB SGID
+ * cm_opa_to_ib_sgid - Convert OPA SGID to IB SGID
  * ULPs (such as IPoIB) do not understand OPA GIDs and will
  * reject them as the local_gid will not match the sgid. Therefore,
  * change the pathrec's SGID to an IB SGID.
@@ -4273,8 +4274,8 @@ static ssize_t cm_show_counter(struct kobject *obj, struct attribute *attr,
 	group = container_of(obj, struct cm_counter_group, obj);
 	cm_attr = container_of(attr, struct cm_counter_attribute, attr);
 
-	return sprintf(buf, "%ld\n",
-		       atomic_long_read(&group->counter[cm_attr->index]));
+	return sysfs_emit(buf, "%ld\n",
+			  atomic_long_read(&group->counter[cm_attr->index]));
 }
 
 static const struct sysfs_ops cm_counter_ops = {

drivers/infiniband/core/cma.c

@@ -477,6 +477,10 @@ static void cma_release_dev(struct rdma_id_private *id_priv)
 	list_del(&id_priv->list);
 	cma_dev_put(id_priv->cma_dev);
 	id_priv->cma_dev = NULL;
+	if (id_priv->id.route.addr.dev_addr.sgid_attr) {
+		rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr);
+		id_priv->id.route.addr.dev_addr.sgid_attr = NULL;
+	}
 	mutex_unlock(&lock);
 }
 
@@ -1861,9 +1865,6 @@ static void _destroy_id(struct rdma_id_private *id_priv,
 
 	kfree(id_priv->id.route.path_rec);
 
-	if (id_priv->id.route.addr.dev_addr.sgid_attr)
-		rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr);
-
 	put_net(id_priv->id.route.addr.dev_addr.net);
 	rdma_restrack_del(&id_priv->res);
 	kfree(id_priv);
@@ -2495,30 +2496,31 @@ static int cma_listen_handler(struct rdma_cm_id *id,
 	return id_priv->id.event_handler(id, event);
 }
 
-static void cma_listen_on_dev(struct rdma_id_private *id_priv,
-			      struct cma_device *cma_dev)
+static int cma_listen_on_dev(struct rdma_id_private *id_priv,
+			     struct cma_device *cma_dev,
+			     struct rdma_id_private **to_destroy)
 {
 	struct rdma_id_private *dev_id_priv;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
 	lockdep_assert_held(&lock);
 
+	*to_destroy = NULL;
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
-		return;
+		return 0;
 
 	dev_id_priv =
 		__rdma_create_id(net, cma_listen_handler, id_priv,
 				 id_priv->id.ps, id_priv->id.qp_type, id_priv);
 	if (IS_ERR(dev_id_priv))
-		return;
+		return PTR_ERR(dev_id_priv);
 
 	dev_id_priv->state = RDMA_CM_ADDR_BOUND;
 	memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv),
 	       rdma_addr_size(cma_src_addr(id_priv)));
 
 	_cma_attach_to_dev(dev_id_priv, cma_dev);
-	list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
 	cma_id_get(id_priv);
 	dev_id_priv->internal_id = 1;
 	dev_id_priv->afonly = id_priv->afonly;
@@ -2527,19 +2529,42 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 
 	ret = rdma_listen(&dev_id_priv->id, id_priv->backlog);
 	if (ret)
-		dev_warn(&cma_dev->device->dev,
-			 "RDMA CMA: cma_listen_on_dev, error %d\n", ret);
+		goto err_listen;
+	list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
+	return 0;
+err_listen:
+	/* Caller must destroy this after releasing lock */
+	*to_destroy = dev_id_priv;
+	dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret);
+	return ret;
 }
 
-static void cma_listen_on_all(struct rdma_id_private *id_priv)
+static int cma_listen_on_all(struct rdma_id_private *id_priv)
 {
+	struct rdma_id_private *to_destroy;
 	struct cma_device *cma_dev;
+	int ret;
 
 	mutex_lock(&lock);
 	list_add_tail(&id_priv->list, &listen_any_list);
-	list_for_each_entry(cma_dev, &dev_list, list)
-		cma_listen_on_dev(id_priv, cma_dev);
+	list_for_each_entry(cma_dev, &dev_list, list) {
+		ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy);
+		if (ret) {
+			/* Prevent racing with cma_process_remove() */
+			if (to_destroy)
+				list_del_init(&to_destroy->list);
+			goto err_listen;
+		}
+	}
 	mutex_unlock(&lock);
+	return 0;
+
+err_listen:
+	list_del(&id_priv->list);
+	mutex_unlock(&lock);
+	if (to_destroy)
+		rdma_destroy_id(&to_destroy->id);
+	return ret;
 }
 
 void rdma_set_service_type(struct rdma_cm_id *id, int tos)
@@ -3692,8 +3717,11 @@ int rdma_listen(struct rdma_cm_id *id, int backlog)
 			ret = -ENOSYS;
 			goto err;
 		}
-	} else
-		cma_listen_on_all(id_priv);
+	} else {
+		ret = cma_listen_on_all(id_priv);
+		if (ret)
+			goto err;
+	}
 
 	return 0;
 err:
@@ -4773,69 +4801,6 @@ static struct notifier_block cma_nb = {
 	.notifier_call = cma_netdev_callback
 };
 
-static int cma_add_one(struct ib_device *device)
-{
-	struct cma_device *cma_dev;
-	struct rdma_id_private *id_priv;
-	unsigned int i;
-	unsigned long supported_gids = 0;
-	int ret;
-
-	cma_dev = kmalloc(sizeof *cma_dev, GFP_KERNEL);
-	if (!cma_dev)
-		return -ENOMEM;
-
-	cma_dev->device = device;
-	cma_dev->default_gid_type = kcalloc(device->phys_port_cnt,
-					    sizeof(*cma_dev->default_gid_type),
-					    GFP_KERNEL);
-	if (!cma_dev->default_gid_type) {
-		ret = -ENOMEM;
-		goto free_cma_dev;
-	}
-
-	cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt,
-					    sizeof(*cma_dev->default_roce_tos),
-					    GFP_KERNEL);
-	if (!cma_dev->default_roce_tos) {
-		ret = -ENOMEM;
-		goto free_gid_type;
-	}
-
-	rdma_for_each_port (device, i) {
-		supported_gids = roce_gid_type_mask_support(device, i);
-		WARN_ON(!supported_gids);
-		if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE))
-			cma_dev->default_gid_type[i - rdma_start_port(device)] =
-				CMA_PREFERRED_ROCE_GID_TYPE;
-		else
-			cma_dev->default_gid_type[i - rdma_start_port(device)] =
-				find_first_bit(&supported_gids, BITS_PER_LONG);
-		cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0;
-	}
-
-	init_completion(&cma_dev->comp);
-	refcount_set(&cma_dev->refcount, 1);
-	INIT_LIST_HEAD(&cma_dev->id_list);
-	ib_set_client_data(device, &cma_client, cma_dev);
-
-	mutex_lock(&lock);
-	list_add_tail(&cma_dev->list, &dev_list);
-	list_for_each_entry(id_priv, &listen_any_list, list)
-		cma_listen_on_dev(id_priv, cma_dev);
-	mutex_unlock(&lock);
-
-	trace_cm_add_one(device);
-	return 0;
-
-free_gid_type:
-	kfree(cma_dev->default_gid_type);
-
-free_cma_dev:
-	kfree(cma_dev);
-	return ret;
-}
-
 static void cma_send_device_removal_put(struct rdma_id_private *id_priv)
 {
 	struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL };
@@ -4898,6 +4863,80 @@ static void cma_process_remove(struct cma_device *cma_dev)
 	wait_for_completion(&cma_dev->comp);
 }
 
+static int cma_add_one(struct ib_device *device)
+{
+	struct rdma_id_private *to_destroy;
+	struct cma_device *cma_dev;
+	struct rdma_id_private *id_priv;
+	unsigned int i;
+	unsigned long supported_gids = 0;
+	int ret;
+
+	cma_dev = kmalloc(sizeof(*cma_dev), GFP_KERNEL);
+	if (!cma_dev)
+		return -ENOMEM;
+
+	cma_dev->device = device;
+	cma_dev->default_gid_type = kcalloc(device->phys_port_cnt,
+					    sizeof(*cma_dev->default_gid_type),
+					    GFP_KERNEL);
+	if (!cma_dev->default_gid_type) {
+		ret = -ENOMEM;
+		goto free_cma_dev;
+	}
+
+	cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt,
+					    sizeof(*cma_dev->default_roce_tos),
+					    GFP_KERNEL);
+	if (!cma_dev->default_roce_tos) {
+		ret = -ENOMEM;
+		goto free_gid_type;
+	}
+
+	rdma_for_each_port (device, i) {
+		supported_gids = roce_gid_type_mask_support(device, i);
+		WARN_ON(!supported_gids);
+		if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE))
+			cma_dev->default_gid_type[i - rdma_start_port(device)] =
+				CMA_PREFERRED_ROCE_GID_TYPE;
+		else
+			cma_dev->default_gid_type[i - rdma_start_port(device)] =
+				find_first_bit(&supported_gids, BITS_PER_LONG);
+		cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0;
+	}
+
+	init_completion(&cma_dev->comp);
+	refcount_set(&cma_dev->refcount, 1);
+	INIT_LIST_HEAD(&cma_dev->id_list);
+	ib_set_client_data(device, &cma_client, cma_dev);
+
+	mutex_lock(&lock);
+	list_add_tail(&cma_dev->list, &dev_list);
+	list_for_each_entry(id_priv, &listen_any_list, list) {
+		ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy);
+		if (ret)
+			goto free_listen;
+	}
+	mutex_unlock(&lock);
+
+	trace_cm_add_one(device);
+	return 0;
+
+free_listen:
+	list_del(&cma_dev->list);
+	mutex_unlock(&lock);
+
+	/* cma_process_remove() will delete to_destroy */
+	cma_process_remove(cma_dev);
+	kfree(cma_dev->default_roce_tos);
+free_gid_type:
+	kfree(cma_dev->default_gid_type);
+
+free_cma_dev:
+	kfree(cma_dev);
+	return ret;
+}
+
 static void cma_remove_one(struct ib_device *device, void *client_data)
 {
 	struct cma_device *cma_dev = client_data;

drivers/infiniband/core/cma_configfs.c

@@ -115,7 +115,7 @@ static ssize_t default_roce_mode_show(struct config_item *item,
 	if (gid_type < 0)
 		return gid_type;
 
-	return sprintf(buf, "%s\n", ib_cache_gid_type_str(gid_type));
+	return sysfs_emit(buf, "%s\n", ib_cache_gid_type_str(gid_type));
 }
 
 static ssize_t default_roce_mode_store(struct config_item *item,
@@ -157,7 +157,7 @@ static ssize_t default_roce_tos_show(struct config_item *item, char *buf)
 	tos = cma_get_default_roce_tos(cma_dev, group->port_num);
 	cma_configfs_params_put(cma_dev);
 
-	return sprintf(buf, "%u\n", tos);
+	return sysfs_emit(buf, "%u\n", tos);
 }
 
 static ssize_t default_roce_tos_store(struct config_item *item,

drivers/infiniband/core/core_priv.h

@@ -318,15 +318,12 @@ struct ib_device *ib_device_get_by_index(const struct net *net, u32 index);
 void nldev_init(void);
 void nldev_exit(void);
 
-static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
-					  struct ib_pd *pd,
-					  struct ib_qp_init_attr *attr,
-					  struct ib_udata *udata,
-					  struct ib_uqp_object *uobj)
+static inline struct ib_qp *
+_ib_create_qp(struct ib_device *dev, struct ib_pd *pd,
+	      struct ib_qp_init_attr *attr, struct ib_udata *udata,
+	      struct ib_uqp_object *uobj, const char *caller)
 {
-	enum ib_qp_type qp_type = attr->qp_type;
 	struct ib_qp *qp;
-	bool is_xrc;
 
 	if (!dev->ops.create_qp)
 		return ERR_PTR(-EOPNOTSUPP);
@@ -347,23 +344,17 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	qp->srq = attr->srq;
 	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
 	qp->event_handler = attr->event_handler;
+	qp->port = attr->port_num;
 
 	atomic_set(&qp->usecnt, 0);
 	spin_lock_init(&qp->mr_lock);
 	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,
-	 * see mlx5 create_dev_resources() as an example.
-	 */
-	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) {
-		rdma_restrack_parent_name(&qp->res, &pd->res);
-		rdma_restrack_add(&qp->res);
-	}
+	WARN_ONCE(!udata && !caller, "Missing kernel QP owner");
+	rdma_restrack_set_name(&qp->res, udata ? NULL : caller);
+	rdma_restrack_add(&qp->res);
 	return qp;
 }
 
@@ -411,7 +402,6 @@ void rdma_umap_priv_init(struct rdma_umap_priv *priv,
 			 struct vm_area_struct *vma,
 			 struct rdma_user_mmap_entry *entry);
 
-void ib_cq_pool_init(struct ib_device *dev);
-void ib_cq_pool_destroy(struct ib_device *dev);
+void ib_cq_pool_cleanup(struct ib_device *dev);
 
 #endif /* _CORE_PRIV_H */