{net, IB}/mlx5: Raise fatal IB event when sys error occurs

All other mlx5_events report the port number as 1 based, which is how FW
reports it in the port event EQE. Reporting 0 for this event causes
mlx5_ib to not raise a fatal event notification to registered clients
due to a seemingly invalid port.

All switch cases in mlx5_ib_event that go through the port check are
supposed to set the port now, so just do it once at variable
declaration.

Fixes: 89d44f0a6c73("net/mlx5_core: Add pci error handlers to mlx5_core driver")
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4236c80868200822d30cfc3d8adea4c97ce9afc2..bab38c6647d738233bf322c5ae3ffc43f7f807d8 100644 (file)
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3263,7 +3263,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
        struct mlx5_ib_dev *ibdev;
        struct ib_event ibev;
        bool fatal = false;
-       u8 port = 0;
+       u8 port = (u8)work->param;
 
        if (mlx5_core_is_mp_slave(work->dev)) {
                ibdev = mlx5_ib_get_ibdev_from_mpi(work->context);
@@ -3283,8 +3283,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
        case MLX5_DEV_EVENT_PORT_UP:
        case MLX5_DEV_EVENT_PORT_DOWN:
        case MLX5_DEV_EVENT_PORT_INITIALIZED:
-               port = (u8)work->param;
-
                /* In RoCE, port up/down events are handled in
                 * mlx5_netdev_event().
                 */
@@ -3298,24 +3296,19 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 
        case MLX5_DEV_EVENT_LID_CHANGE:
                ibev.event = IB_EVENT_LID_CHANGE;
-               port = (u8)work->param;
                break;
 
        case MLX5_DEV_EVENT_PKEY_CHANGE:
                ibev.event = IB_EVENT_PKEY_CHANGE;
-               port = (u8)work->param;
-
                schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
                break;
 
        case MLX5_DEV_EVENT_GUID_CHANGE:
                ibev.event = IB_EVENT_GID_CHANGE;
-               port = (u8)work->param;
                break;
 
        case MLX5_DEV_EVENT_CLIENT_REREG:
                ibev.event = IB_EVENT_CLIENT_REREGISTER;
-               port = (u8)work->param;
                break;
        case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
                schedule_work(&ibdev->delay_drop.delay_drop_work);
@@ -3327,7 +3320,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
        ibev.device           = &ibdev->ib_dev;
        ibev.element.port_num = port;
 
-       if (port < 1 || port > ibdev->num_ports) {
+       if (!rdma_is_port_valid(&ibdev->ib_dev, port)) {
                mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
                goto out;
        }

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 21d29f7936f6c5d1e26c6e0d3f10644fd0f096c8..d39b0b7011b2d9cf194180813a5a30d9fe226b6d 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -124,7 +124,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
                trigger_cmd_completions(dev);
        }
 
-       mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0);
+       mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1);
        mlx5_core_err(dev, "end\n");
 
 unlock: