From: Daniel Jurgens <danielj@xxxxxxxxxxxx>
commit 22e3817e6c8301dc0520b855c8a2d764580e719c upstream.
The PCI channel could go offline during reset due to EEH. Don't bug on in
this case, the error is recoverable.
Fixes: f6bc11e42646 ('net/mlx4_core: Enhance the catas flow to support device reset')
Signed-off-by: Daniel Jurgens <danielj@xxxxxxxxxxxx>
Reviewed-by: Yishai Hadas <yishaih@xxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/net/ethernet/mellanox/mlx4/catas.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_
err = mlx4_reset_slave(dev);
else
err = mlx4_reset_master(dev);
- BUG_ON(err != 0);
+ if (!err) {
+ mlx4_err(dev, "device was reset successfully\n");
+ } else {
+ /* EEH could have disabled the PCI channel during reset. That's
+ * recoverable and the PCI error flow will handle it.
+ */
+ if (!pci_channel_offline(dev->persist->pdev))
+ BUG_ON(1);
+ }
dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
- mlx4_err(dev, "device was reset successfully\n");
mutex_unlock(&persist->device_state_mutex);
/* At that step HW was already reset, now notify clients */
