RDMA/mlx5: Don't add slave port to unaffiliated list

[ Upstream commit 7ce6095e3bff8e20ce018b050960b527e298f7df ]

The mlx5_ib_bind_slave_port() doesn't remove multiport device from the
unaffiliated list, but mlx5_ib_unbind_slave_port() did it. This unbalanced
flow caused to the situation where mlx5_ib_unaffiliated_port_list was
changed during iteration.

Fixes: 32f69e4be269 ("{net, IB}/mlx5: Manage port association for multiport RoCE")
Link: https://lore.kernel.org/r/2726e6603b1e6ecfe76aa5a12a063af72173bcf7.1622477058.git.leonro@nvidia.com
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index b19506707e45cce91bdf954fee41f33a6c9e897d..60aceb3b47a51d6ed5faaa3a6338fd53cdc4cdcc 100644 (file)
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3440,8 +3440,6 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 
        port->mp.mpi = NULL;
 
-       list_add_tail(&mpi->list, &mlx5_ib_unaffiliated_port_list);
-
        spin_unlock(&port->mp.mpi_lock);
 
        err = mlx5_nic_vport_unaffiliate_multiport(mpi->mdev);
@@ -3595,6 +3593,8 @@ static void mlx5_ib_cleanup_multiport_master(struct mlx5_ib_dev *dev)
                        } else {
                                mlx5_ib_dbg(dev, "unbinding port_num: %d\n", i + 1);
                                mlx5_ib_unbind_slave_port(dev, dev->port[i].mp.mpi);
+                               list_add_tail(&dev->port[i].mp.mpi->list,
+                                             &mlx5_ib_unaffiliated_port_list);
                        }
                }
        }