From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 4 Nov 2020 16:40:07 +0200
Subject: RDMA/cma: Add missing error handling of listen_id
Patch-mainline: v5.11-rc1
Git-commit: c80a0c52d85c49a910d0dc0e342e8d8898677dc0
References: bsc#1181147

Don't silently continue if rdma_listen() fails but destroy previously
created CM_ID and return an error to the caller.

Fixes: d02d1f5359e7 ("RDMA/cma: Fix deadlock destroying listen requests")
Link: https://lore.kernel.org/r/20201104144008.3808124-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/infiniband/core/cma.c |  175 ++++++++++++++++++++++++------------------
 1 file changed, 101 insertions(+), 74 deletions(-)

--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2460,8 +2460,8 @@ static int cma_listen_handler(struct rdm
 	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 *dev_id_priv;
 	struct rdma_cm_id *id;
@@ -2471,12 +2471,12 @@ static void cma_listen_on_dev(struct rdm
 	lockdep_assert_held(&lock);
 
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
-		return;
+		return 0;
 
 	id = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps,
 			      id_priv->id.qp_type, id_priv->res.kern_name);
 	if (IS_ERR(id))
-		return;
+		return PTR_ERR(id);
 
 	dev_id_priv = container_of(id, struct rdma_id_private, id);
 
@@ -2494,19 +2494,34 @@ static void cma_listen_on_dev(struct rdm
 
 	ret = rdma_listen(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;
+	return 0;
+err_listen:
+	list_del(&id_priv->listen_list);
+	dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret);
+	rdma_destroy_id(&dev_id_priv->id);
+	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 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);
+		if (ret)
+			goto err_listen;
+	}
 	mutex_unlock(&lock);
+	return 0;
+
+err_listen:
+	list_del(&id_priv->list);
+	mutex_unlock(&lock);
+	return ret;
 }
 
 void rdma_set_service_type(struct rdma_cm_id *id, int tos)
@@ -3659,8 +3674,11 @@ int rdma_listen(struct rdma_cm_id *id, i
 			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:
@@ -4726,69 +4744,6 @@ 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 };
@@ -4851,6 +4806,78 @@ static void cma_process_remove(struct cm
 	wait_for_completion(&cma_dev->comp);
 }
 
+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) {
+		ret = cma_listen_on_dev(id_priv, cma_dev);
+		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(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;