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, 14 insertions, 10 deletions

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 4794113ecd59..68e1a9bba027 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -81,7 +81,7 @@ const char *__attribute_const__ ibcm_reject_msg(int reason)
 EXPORT_SYMBOL(ibcm_reject_msg);
 
 struct cm_id_private;
-static void cm_add_one(struct ib_device *device);
+static int cm_add_one(struct ib_device *device);
 static void cm_remove_one(struct ib_device *device, void *client_data);
 static int cm_send_sidr_rep_locked(struct cm_id_private *cm_id_priv,
 				   struct ib_cm_sidr_rep_param *param);
@@ -4382,7 +4382,7 @@ static void cm_remove_port_fs(struct cm_port *port)
 
 }
 
-static void cm_add_one(struct ib_device *ib_device)
+static int cm_add_one(struct ib_device *ib_device)
 {
 	struct cm_device *cm_dev;
 	struct cm_port *port;
@@ -4401,7 +4401,7 @@ static void cm_add_one(struct ib_device *ib_device)
 	cm_dev = kzalloc(struct_size(cm_dev, port, ib_device->phys_port_cnt),
 			 GFP_KERNEL);
 	if (!cm_dev)
-		return;
+		return -ENOMEM;
 
 	cm_dev->ib_device = ib_device;
 	cm_dev->ack_delay = ib_device->attrs.local_ca_ack_delay;
@@ -4413,8 +4413,10 @@ static void cm_add_one(struct ib_device *ib_device)
 			continue;
 
 		port = kzalloc(sizeof *port, GFP_KERNEL);
-		if (!port)
+		if (!port) {
+			ret = -ENOMEM;
 			goto error1;
+		}
 
 		cm_dev->port[i-1] = port;
 		port->cm_dev = cm_dev;
@@ -4435,8 +4437,10 @@ static void cm_add_one(struct ib_device *ib_device)
 							cm_recv_handler,
 							port,
 							0);
-		if (IS_ERR(port->mad_agent))
+		if (IS_ERR(port->mad_agent)) {
+			ret = PTR_ERR(port->mad_agent);
 			goto error2;
+		}
 
 		ret = ib_modify_port(ib_device, i, 0, &port_modify);
 		if (ret)
@@ -4445,15 +4449,17 @@ static void cm_add_one(struct ib_device *ib_device)
 		count++;
 	}
 
-	if (!count)
+	if (!count) {
+		ret = -EOPNOTSUPP;
 		goto free;
+	}
 
 	ib_set_client_data(ib_device, &cm_client, cm_dev);
 
 	write_lock_irqsave(&cm.device_lock, flags);
 	list_add_tail(&cm_dev->list, &cm.device_list);
 	write_unlock_irqrestore(&cm.device_lock, flags);
-	return;
+	return 0;
 
 error3:
 	ib_unregister_mad_agent(port->mad_agent);
@@ -4475,6 +4481,7 @@ error1:
 	}
 free:
 	kfree(cm_dev);
+	return ret;
 }
 
 static void cm_remove_one(struct ib_device *ib_device, void *client_data)
@@ -4489,9 +4496,6 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 	unsigned long flags;
 	int i;
 
-	if (!cm_dev)
-		return;
-
 	write_lock_irqsave(&cm.device_lock, flags);
 	list_del(&cm_dev->list);
 	write_unlock_irqrestore(&cm.device_lock, flags);