From: Moshe Shemesh <mo...@mellanox.com>
Add support of dump callback for mlx5 FW fatal reporter.
The FW fatal dump use cr-dump functionality to gather cr-space data for
debug. The cr-dump uses vsc interface which is valid even if the FW
command interface is not functional, which is the case in FW fatal errors.
Signed-off-by: Moshe Shemesh <mo...@mellanox.com>
Signed-off-by: Eran Ben Elisha <era...@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 91 +++++++++++++++++++
1 file changed, 91 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index ae08af00b101..406856002dd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -252,9 +252,100 @@ mlx5_fw_fatal_reporter_recover(struct
devlink_health_reporter *reporter,
return 0;
}
+static int
+mlx5_devlink_health_buffer_fill_snapshot(struct devlink_health_buffer
*dh_buffer,
+ char *crdump_region, u32 snapshot_id)
+{
+ int err;
+
+ err = devlink_health_buffer_nest_start(dh_buffer,
+
DEVLINK_ATTR_HEALTH_BUFFER_OBJECT);
+ if (err)
+ return err;
+ err = devlink_health_buffer_nest_start(dh_buffer,
+
DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR);
+ if (err)
+ return err;
+ err = devlink_health_buffer_put_object_name(dh_buffer,
+ "devlink region name");
+ if (err)
+ return err;
+ err = devlink_health_buffer_nest_start(dh_buffer,
+
DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE);
+ if (err)
+ return err;
+ err = devlink_health_buffer_put_value_string(dh_buffer, crdump_region);
+ if (err)
+ return err;
+ devlink_health_buffer_nest_end(dh_buffer);
+ devlink_health_buffer_nest_end(dh_buffer);
+
+ err = devlink_health_buffer_nest_start(dh_buffer,
+
DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR);
+ if (err)
+ return err;
+ err = devlink_health_buffer_put_object_name(dh_buffer, "snapshot id");
+ if (err)
+ return err;
+ err = devlink_health_buffer_nest_start(dh_buffer,
+
DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE);
+ if (err)
+ return err;
+ err = devlink_health_buffer_put_value_u32(dh_buffer, snapshot_id);
+ if (err)
+ return err;
+ devlink_health_buffer_nest_end(dh_buffer);
+ devlink_health_buffer_nest_end(dh_buffer);
+ devlink_health_buffer_nest_end(dh_buffer);
+
+ return 0;
+}
+
+#define MLX5_FW_FATAL_REPORTER_DUMP_SIZE_BYTE 256
+static int
+mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
+ struct devlink_health_buffer **buffers_array,
+ unsigned int buff_size, unsigned int num_buffers,
+ void *priv_ctx)
+{
+ struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+ struct devlink_health_buffer *buffer;
+ char crdump_region[20];
+ u32 snapshot_id;
+ int err;
+
+ if (!mlx5_core_is_pf(dev)) {
+ mlx5_core_err(dev, "Only PF is permitted run FW fatal dump");
+ return -EPERM;
+ }
+
+ if (!buffers_array || num_buffers < 1 ||
+ buff_size < MLX5_FW_FATAL_REPORTER_DUMP_SIZE_BYTE)
+ return -EINVAL;
+
+ err = mlx5_crdump_collect(dev, crdump_region, &snapshot_id);
+ if (err)
+ return err;
+
+ buffer = buffers_array[0];
+ if (priv_ctx) {
+ struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+
+ err = mlx5_devlink_health_buffer_fill_syndrom(buffer,
+
fw_reporter_ctx->err_synd);
+ if (err)
+ return err;
+ }
+
+ return mlx5_devlink_health_buffer_fill_snapshot(buffer, crdump_region,
+ snapshot_id);
+}
+
static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
.name = "FW_fatal",
.recover = mlx5_fw_fatal_reporter_recover,
+ .dump_size = MLX5_FW_FATAL_REPORTER_DUMP_SIZE_BYTE,
+ .dump = mlx5_fw_fatal_reporter_dump,
};
#define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000
--
2.17.1
