RDMA: Allow ib_client's to fail when add() is called

When a client is added it isn't allowed to fail, but all the client's have
various failure paths within their add routines.

This creates the very fringe condition where the client was added, failed
during add and didn't set the client_data. The core code will then still
call other client_data centric ops like remove(), rename(), get_nl_info(),
and get_net_dev_by_params() with NULL client_data - which is confusing and
unexpected.

If the add() callback fails, then do not call any more client ops for the
device, even remove.

Remove all the now redundant checks for NULL client_data in ops callbacks.

Update all the add() callbacks to return error codes
appropriately. EOPNOTSUPP is used for cases where the ULP does not support
the ib_device - eg because it only works with IB.

Link: https://lore.kernel.org/r/20200421172440.387069-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 12 insertions, 11 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 6406a597dfb6..e8d99b71f44a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -153,7 +153,7 @@ struct rdma_cm_id *rdma_res_to_id(struct rdma_restrack_entry *res)
 }
 EXPORT_SYMBOL(rdma_res_to_id);
 
-static void cma_add_one(struct ib_device *device);
+static int cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device, void *client_data);
 
 static struct ib_client cma_client = {
@@ -4638,29 +4638,34 @@ static struct notifier_block cma_nb = {
 	.notifier_call = cma_netdev_callback
 };
 
-static void cma_add_one(struct ib_device *device)
+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;
+		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)
+	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)
+	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);
@@ -4686,15 +4691,14 @@ static void cma_add_one(struct ib_device *device)
 	mutex_unlock(&lock);
 
 	trace_cm_add_one(device);
-	return;
+	return 0;
 
 free_gid_type:
 	kfree(cma_dev->default_gid_type);
 
 free_cma_dev:
 	kfree(cma_dev);
-
-	return;
+	return ret;
 }
 
 static int cma_remove_id_dev(struct rdma_id_private *id_priv)
@@ -4756,9 +4760,6 @@ static void cma_remove_one(struct ib_device *device, void *client_data)
 
 	trace_cm_remove_one(device);
 
-	if (!cma_dev)
-		return;
-
 	mutex_lock(&lock);
 	list_del(&cma_dev->list);
 	mutex_unlock(&lock);