net/mlx5: fw reset, add reset timeout work

Add sync reset timeout to stop poll_sync_reset in case there was no
reset done or abort event within timeout. Otherwise poll sync reset will
just continue and in case of fw fatal error no health reporting will be
done.

Fixes: 38b9f903f22b ("net/mlx5: Handle sync reset request event")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 22995131824a0350ba382d7c2ed7b09d81113830..89e399606877ba2cdefb2d9e40256627707e9972 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -27,6 +27,7 @@ struct mlx5_fw_reset {
        struct work_struct reset_reload_work;
        struct work_struct reset_now_work;
        struct work_struct reset_abort_work;
+       struct delayed_work reset_timeout_work;
        unsigned long reset_flags;
        u8 reset_method;
        struct timer_list timer;
@@ -259,6 +260,8 @@ static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool
                return -EALREADY;
        }
 
+       if (current_work() != &fw_reset->reset_timeout_work.work)
+               cancel_delayed_work(&fw_reset->reset_timeout_work);
        mlx5_stop_sync_reset_poll(dev);
        if (poll_health)
                mlx5_start_health_poll(dev);
@@ -330,6 +333,11 @@ static int mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
        }
        mlx5_stop_health_poll(dev, true);
        mlx5_start_sync_reset_poll(dev);
+
+       if (!test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
+                     &fw_reset->reset_flags))
+               schedule_delayed_work(&fw_reset->reset_timeout_work,
+                       msecs_to_jiffies(mlx5_tout_ms(dev, PCI_SYNC_UPDATE)));
        return 0;
 }
 
@@ -739,6 +747,19 @@ static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct
        }
 }
 
+static void mlx5_sync_reset_timeout_work(struct work_struct *work)
+{
+       struct delayed_work *dwork = container_of(work, struct delayed_work,
+                                                 work);
+       struct mlx5_fw_reset *fw_reset =
+               container_of(dwork, struct mlx5_fw_reset, reset_timeout_work);
+       struct mlx5_core_dev *dev = fw_reset->dev;
+
+       if (mlx5_sync_reset_clear_reset_requested(dev, true))
+               return;
+       mlx5_core_warn(dev, "PCI Sync FW Update Reset Timeout.\n");
+}
+
 static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
        struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb);
@@ -822,6 +843,7 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev)
        cancel_work_sync(&fw_reset->reset_reload_work);
        cancel_work_sync(&fw_reset->reset_now_work);
        cancel_work_sync(&fw_reset->reset_abort_work);
+       cancel_delayed_work(&fw_reset->reset_timeout_work);
 }
 
 static const struct devlink_param mlx5_fw_reset_devlink_params[] = {
@@ -865,6 +887,8 @@ int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
        INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
        INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
        INIT_WORK(&fw_reset->reset_abort_work, mlx5_sync_reset_abort_event);
+       INIT_DELAYED_WORK(&fw_reset->reset_timeout_work,
+                         mlx5_sync_reset_timeout_work);
 
        init_completion(&fw_reset->done);
        return 0;