net/mlx4_core: Add Crdump FW snapshot support

Crdump allows the driver to create a snapshot of the FW PCI
crspace and health buffer during a critical FW issue.
In case of a FW command timeout, FW getting stuck or a non zero
value on the catastrophic buffer, a snapshot will be taken.

The snapshot is exposed using devlink, cr-space, fw-health
address regions are registered on init and snapshots are attached
once a new snapshot is collected by the driver.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 6 insertions, 0 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e3bfe76aea98..300b944e6e1e 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -852,6 +852,11 @@ struct mlx4_vf_dev {
         u8                      n_ports;
 };
 
+struct mlx4_fw_crdump {
+        struct devlink_region *region_crspace;
+        struct devlink_region *region_fw_health;
+};
+
 enum mlx4_pci_status {
         MLX4_PCI_STATUS_DISABLED,
         MLX4_PCI_STATUS_ENABLED,
@@ -872,6 +877,7 @@ struct mlx4_dev_persistent {
         u8      interface_state;
         struct mutex            pci_status_mutex; /* sync pci state */
         enum mlx4_pci_status    pci_status;
+        struct mlx4_fw_crdump   crdump;
 };
 
 struct mlx4_dev {