net/mlx5: Add support for FW fatal reporter dump

Add support of dump callback for mlx5 FW fatal reporter.
The FW fatal dump uses 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 most FW fatal
errors.

Command example and output:
$ devlink health dump show pci/0000:82:00.0 reporter fw_fatal
 crdump_data:
  00 20 00 01 00 00 00 00 03 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 80
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 ba 82 00 00
  0c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 20
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 fa 00
  a4 0e 00 00 00 00 00 00 80 c7 fe ff 50 0a 00 00
...
...

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 82a6588..4ef62c6 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -565,9 +565,59 @@ mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
        return mlx5_health_try_recover(dev);
 }
 
+#define MLX5_CR_DUMP_CHUNK_SIZE 256
+static int
+mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
+                           struct devlink_fmsg *fmsg, void *priv_ctx)
+{
+       struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+       u32 crdump_size = dev->priv.health.crdump_size;
+       u32 *cr_data;
+       u32 data_size;
+       u32 offset;
+       int err;
+
+       if (!mlx5_core_is_pf(dev))
+               return -EPERM;
+
+       cr_data = kvmalloc(crdump_size, GFP_KERNEL);
+       if (!cr_data)
+               return -ENOMEM;
+       err = mlx5_crdump_collect(dev, cr_data);
+       if (err)
+               return err;
+
+       if (priv_ctx) {
+               struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+
+               err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx);
+               if (err)
+                       goto free_data;
+       }
+
+       err = devlink_fmsg_arr_pair_nest_start(fmsg, "crdump_data");
+       if (err)
+               goto free_data;
+       for (offset = 0; offset < crdump_size; offset += data_size) {
+               if (crdump_size - offset < MLX5_CR_DUMP_CHUNK_SIZE)
+                       data_size = crdump_size - offset;
+               else
+                       data_size = MLX5_CR_DUMP_CHUNK_SIZE;
+               err = devlink_fmsg_binary_put(fmsg, cr_data, data_size);
+               if (err)
+                       goto free_data;
+       }
+       err = devlink_fmsg_arr_pair_nest_end(fmsg);
+
+free_data:
+       kfree(cr_data);
+       return err;
+}
+
 static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
                .name = "fw_fatal",
                .recover = mlx5_fw_fatal_reporter_recover,
+               .dump = mlx5_fw_fatal_reporter_dump,
 };
 
 #define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000