net/mlx5: Only cancel recovery work when cleaning up device

commit 5e44fca5047054f1762813751626b5245e0da022 upstream.

Do not attempt to drain the health workqueue when unloading the device in
the recovery flow, this can cause a deadlock when the recovery work
tries to cancel itself with sync.

Because the work is no longer unconditionally canceled when unloading, it
must be explicitly canceled in the AER flow.

fixes: 689a248df83b ("net/mlx5: Cancel recovery work in remove flow")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 92bd13ddc39d7f0f54e44c1e0247d79940350d79..0c9ef8729ca7b2dfefe2281d777bee8d048b93e1 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1158,7 +1158,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 {
        int err = 0;
 
-       mlx5_drain_health_wq(dev);
+       if (cleanup)
+               mlx5_drain_health_wq(dev);
 
        mutex_lock(&dev->intf_state_mutex);
        if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
@@ -1320,9 +1321,10 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
        mlx5_enter_error_state(dev);
        mlx5_unload_one(dev, priv, false);
-       /* In case of kernel call save the pci state */
+       /* In case of kernel call save the pci state and drain the health wq */
        if (state) {
                pci_save_state(pdev);
+               mlx5_drain_health_wq(dev);
                mlx5_pci_disable_device(dev);
        }