net/mlx4_core: Enhance the catas flow to support device reset

This includes:

- resetting the chip when a fatal error is detected (the current code
  does not do this).

- exposing the ability to enter error state from outside the catas code
  by calling its functionality. (E.g. FW Command timeout, AER error).

- managing a persistent device state. This is needed to sync between
  reset flow cases.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 0 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index da425d2f3708..7d5d317cb7a6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -411,6 +411,11 @@ enum {
         MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK        = 1 << 4,
 };
 
+enum {
+        MLX4_DEVICE_STATE_UP                    = 1 << 0,
+        MLX4_DEVICE_STATE_INTERNAL_ERROR        = 1 << 1,
+};
+
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
                              MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
 
@@ -753,6 +758,8 @@ struct mlx4_dev_persistent {
         enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1];
         struct work_struct      catas_work;
         struct workqueue_struct *catas_wq;
+        struct mutex    device_state_mutex; /* protect HW state */
+        u8              state;
 };
 
 struct mlx4_dev {